IrishSentenceBankSentenceStream(IrishSentenceBankDocument source) { this.source = source; reset(); }
IrishSentenceBankTokenSampleStream(IrishSentenceBankDocument source) { this.source = source; reset(); }
@Override public void reset() { sentenceIt = source.getSentences().iterator(); } }
IrishSentenceBankDocumentTest.class.getResourceAsStream("irishsentencebank-sample.xml")) { IrishSentenceBankDocument doc = IrishSentenceBankDocument.parse(irishSBXmlIn); List<IrishSentenceBankDocument.IrishSentenceBankSentence> sents = doc.getSentences(); IrishSentenceBankDocument.IrishSentenceBankSentence sent2 = sents.get(1); Assert.assertEquals("A Dhia, tá mé ag iompar clainne!", sent1.getOriginal()); IrishSentenceBankDocument.IrishSentenceBankFlex[] flex = sent1.getFlex(); Assert.assertEquals(7, flex.length); Assert.assertEquals("A", flex[0].getSurface()); Assert.assertArrayEquals(new String[]{"a"}, flex[0].getFlex()); IrishSentenceBankDocument.IrishSentenceBankFlex[] flex2 = sent2.getFlex(); Assert.assertEquals("ón", flex2[4].getSurface()); Assert.assertArrayEquals(new String[]{"ó", "an"}, flex2[4].getFlex()); Assert.assertEquals("Excuse me, are you from the stone age?", sent2.getTranslation()); TokenSample ts = sent1.getTokenSample(); Span[] spans = ts.getTokenSpans(); Assert.assertEquals(9, spans.length);
public static IrishSentenceBankDocument parse(InputStream is) throws IOException { IrishSentenceBankDocument document = new IrishSentenceBankDocument(); spans.add(new Span(advanceLeft(tmptxt, last), advanceRight(tmptxt, last))); String[] right = new String[rsize]; right = flx.get(flexidx).toArray(right); flexa[flexidx - 1] = new IrishSentenceBankFlex(left, right); document.add(new IrishSentenceBankSentence(src, trans, orig.toString(), spanout, flexa)); } else if (!sentnode.getNodeName().equals("#text") && !sentnode.getNodeName().equals("#comment")) { throw new IOException("Unexpected node: " + sentnode.getNodeName());
public ObjectStream<TokenSample> create(String[] args) { Parameters params = ArgumentParser.parse(args, Parameters.class); CmdLineUtil.checkInputFile("Data", params.getData()); IrishSentenceBankDocument isbDoc = null; try { isbDoc = IrishSentenceBankDocument.parse(params.getData()); } catch (IOException ex) { CmdLineUtil.handleCreateObjectStreamError(ex); } return new IrishSentenceBankTokenSampleStream(isbDoc); } }
@Override public ObjectStream<SentenceSample> create(String[] args) { Parameters params = ArgumentParser.parse(args, Parameters.class); CmdLineUtil.checkInputFile("Data", params.getData()); IrishSentenceBankDocument isbDoc = null; try { isbDoc = IrishSentenceBankDocument.parse(params.getData()); } catch (IOException ex) { CmdLineUtil.handleCreateObjectStreamError(ex); } return new IrishSentenceBankSentenceStream(isbDoc); } }
static IrishSentenceBankDocument parse(File file) throws IOException { try (InputStream in = new FileInputStream(file)) { return parse(in); } } }
@Override public TokenSample read() throws IOException { if (sentenceIt.hasNext()) { IrishSentenceBankDocument.IrishSentenceBankSentence sentence = sentenceIt.next(); return sentence.getTokenSample(); } else { return null; } }
@Override public SentenceSample read() throws IOException { StringBuilder sentencesString = new StringBuilder(); List<Span> sentenceSpans = new LinkedList<>(); while (sentenceIt.hasNext()) { IrishSentenceBankDocument.IrishSentenceBankSentence sentence = sentenceIt.next(); int begin = sentencesString.length(); if (sentence.getOriginal() != null) { sentencesString.append(sentence.getOriginal()); } sentenceSpans.add(new Span(begin, sentencesString.length())); sentencesString.append(' '); } // end of stream is reached, indicate that with null return value if (sentenceSpans.size() == 0) { return null; } return new SentenceSample(sentencesString.toString(), sentenceSpans.toArray(new Span[sentenceSpans.size()])); }
public static void registerFactory() { StreamFactoryRegistry.registerFactory(TokenSample.class, "irishsentencebank", new IrishSentenceBankTokenSampleStreamFactory( IrishSentenceBankTokenSampleStreamFactory.Parameters.class)); }
public static void registerFactory() { StreamFactoryRegistry.registerFactory(SentenceSample.class, "irishsentencebank", new IrishSentenceBankSentenceStreamFactory( IrishSentenceBankSentenceStreamFactory.Parameters.class)); }
public ObjectStream<TokenSample> create(String[] args) { Parameters params = ArgumentParser.parse(args, Parameters.class); CmdLineUtil.checkInputFile("Data", params.getData()); IrishSentenceBankDocument isbDoc = null; try { isbDoc = IrishSentenceBankDocument.parse(params.getData()); } catch (IOException ex) { CmdLineUtil.handleCreateObjectStreamError(ex); } return new IrishSentenceBankTokenSampleStream(isbDoc); } }
@Override public ObjectStream<SentenceSample> create(String[] args) { Parameters params = ArgumentParser.parse(args, Parameters.class); CmdLineUtil.checkInputFile("Data", params.getData()); IrishSentenceBankDocument isbDoc = null; try { isbDoc = IrishSentenceBankDocument.parse(params.getData()); } catch (IOException ex) { CmdLineUtil.handleCreateObjectStreamError(ex); } return new IrishSentenceBankSentenceStream(isbDoc); } }
@Override public void reset() { sentenceIt = source.getSentences().iterator(); } }
IrishSentenceBankSentenceStream(IrishSentenceBankDocument source) { this.source = source; reset(); }
IrishSentenceBankTokenSampleStream(IrishSentenceBankDocument source) { this.source = source; reset(); }
public ObjectStream<TokenSample> create(String[] args) { Parameters params = ArgumentParser.parse(args, Parameters.class); CmdLineUtil.checkInputFile("Data", params.getData()); IrishSentenceBankDocument isbDoc = null; try { isbDoc = IrishSentenceBankDocument.parse(params.getData()); } catch (IOException ex) { CmdLineUtil.handleCreateObjectStreamError(ex); } return new IrishSentenceBankTokenSampleStream(isbDoc); } }
IrishSentenceBankSentenceStream(IrishSentenceBankDocument source) { this.source = source; reset(); }
IrishSentenceBankTokenSampleStream(IrishSentenceBankDocument source) { this.source = source; reset(); }