public ObjectStream<POSSample> create(String[] args) { Parameters params = ArgumentParser.parse(args, Parameters.class); InputStreamFactory inFactory = CmdLineUtil.createInputStreamFactory(params.getData()); try { System.setOut(new PrintStream(System.out, true, "UTF-8")); return new ConllXPOSSampleStream(inFactory, StandardCharsets.UTF_8); } catch (UnsupportedEncodingException e) { // this shouldn't happen throw new TerminateToolException(-1, "UTF-8 encoding is not supported: " + e.getMessage(), e); } catch (IOException e) { // That will throw an exception CmdLineUtil.handleCreateObjectStreamError(e); return null; } } }
@Override public ObjectStream<SentenceSample> create(String[] args) { Parameters params = ArgumentParser.parse(args, Parameters.class); InputStreamFactory inFactory = CmdLineUtil.createInputStreamFactory(params.getData()); try { return new ConlluSentenceSampleStream(new ConlluStream(inFactory), Integer.parseInt(params.getSentencesPerSample())); } catch (IOException e) { // That will throw an exception CmdLineUtil.handleCreateObjectStreamError(e); } return null; } }
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 ObjectStream<TokenSample> create(String[] args) { Parameters params = ArgumentParser.parse(args, Parameters.class); InputStreamFactory inFactory = CmdLineUtil.createInputStreamFactory(params.getData()); try { return new ConlluTokenSampleStream(new ConlluStream(inFactory)); } catch (IOException e) { // That will throw an exception CmdLineUtil.handleCreateObjectStreamError(e); } return null; } }
public ObjectStream<ChunkSample> create(String[] args) { Parameters params = ArgumentParser.parse(args, Parameters.class); CmdLineUtil.checkInputFile("Data", params.getData()); InputStreamFactory sampleDataIn = CmdLineUtil.createInputStreamFactory(params.getData()); ObjectStream<String> lineStream = null; try { lineStream = new PlainTextByLineStream(sampleDataIn, params.getEncoding()); } catch (IOException ex) { CmdLineUtil.handleCreateObjectStreamError(ex); } return new ChunkSampleStream(lineStream); } }
public ObjectStream<LemmaSample> create(String[] args) { Parameters params = ArgumentParser.parse(args, Parameters.class); CmdLineUtil.checkInputFile("Data", params.getData()); InputStreamFactory sampleDataIn = CmdLineUtil.createInputStreamFactory(params.getData()); ObjectStream<String> lineStream = null; try { lineStream = new PlainTextByLineStream(sampleDataIn, params.getEncoding()); } catch (IOException ex) { CmdLineUtil.handleCreateObjectStreamError(ex); } return new LemmaSampleStream(lineStream); } }
public ObjectStream<NameSample> create(String[] args) { Parameters params = ArgumentParser.parse(args, Parameters.class); language = params.getLang(); InputStreamFactory sampleDataIn = CmdLineUtil.createInputStreamFactory(params.getData()); ObjectStream<String> lineStream = null; try { lineStream = new PlainTextByLineStream(sampleDataIn, params.getEncoding()); } catch (IOException ex) { CmdLineUtil.handleCreateObjectStreamError(ex); } return new ADNameSampleStream(lineStream, params.getSplitHyphenatedTokens()); } }
public ObjectStream<NameSample> create(String[] args) { Parameters params = ArgumentParser.parse(args, Parameters.class); CmdLineUtil.checkInputFile("Data", params.getData()); InputStreamFactory sampleDataIn = CmdLineUtil.createInputStreamFactory(params.getData()); ObjectStream<String> lineStream = null; try { lineStream = new PlainTextByLineStream(sampleDataIn, params.getEncoding()); } catch (IOException ex) { CmdLineUtil.handleCreateObjectStreamError(ex); } return new NameSampleDataStream(lineStream); } }
public ObjectStream<POSSample> create(String[] args) { Parameters params = ArgumentParser.parse(args, Parameters.class); CmdLineUtil.checkInputFile("Data", params.getData()); InputStreamFactory sampleDataIn = CmdLineUtil.createInputStreamFactory(params.getData()); ObjectStream<String> lineStream = null; try { lineStream = new PlainTextByLineStream(sampleDataIn, params.getEncoding()); } catch (IOException ex) { CmdLineUtil.handleCreateObjectStreamError(ex); } return new WordTagSampleStream(lineStream); } }
public ObjectStream<LanguageSample> create(String[] args) { Parameters params = ArgumentParser.parse(args, Parameters.class); CmdLineUtil.checkInputFile("Data", params.getData()); InputStreamFactory sampleDataIn = CmdLineUtil.createInputStreamFactory(params.getData()); ObjectStream<String> lineStream = null; try { lineStream = new PlainTextByLineStream(sampleDataIn, params.getEncoding()); } catch (IOException ex) { CmdLineUtil.handleCreateObjectStreamError(ex); } return new LanguageDetectorSampleStream(lineStream); } }
public ObjectStream<SentenceSample> create(String[] args) { Parameters params = ArgumentParser.parse(args, Parameters.class); CmdLineUtil.checkInputFile("Data", params.getData()); InputStreamFactory sampleDataIn = CmdLineUtil.createInputStreamFactory(params.getData()); ObjectStream<String> lineStream = null; try { lineStream = new PlainTextByLineStream(sampleDataIn, params.getEncoding()); } catch (IOException ex) { CmdLineUtil.handleCreateObjectStreamError(ex); } return new MosesSentenceSampleStream(lineStream); } }
public ObjectStream<TokenSample> create(String[] args) { Parameters params = ArgumentParser.parse(args, Parameters.class); CmdLineUtil.checkInputFile("Data", params.getData()); InputStreamFactory sampleDataIn = CmdLineUtil.createInputStreamFactory(params.getData()); ObjectStream<String> lineStream = null; try { lineStream = new PlainTextByLineStream(sampleDataIn, params.getEncoding()); } catch (IOException ex) { CmdLineUtil.handleCreateObjectStreamError(ex); } return new TokenSampleStream(lineStream); } }
public ObjectStream<DocumentSample> create(String[] args) { Parameters params = ArgumentParser.parse(args, Parameters.class); CmdLineUtil.checkInputFile("Data", params.getData()); InputStreamFactory sampleDataIn = CmdLineUtil.createInputStreamFactory(params.getData()); ObjectStream<String> lineStream = null; try { lineStream = new PlainTextByLineStream(sampleDataIn, params.getEncoding()); } catch (IOException ex) { CmdLineUtil.handleCreateObjectStreamError(ex); } return new DocumentSampleStream(lineStream); } }
public ObjectStream<SentenceSample> create(String[] args) { Parameters params = ArgumentParser.parse(args, Parameters.class); CmdLineUtil.checkInputFile("Data", params.getData()); InputStreamFactory sampleDataIn = CmdLineUtil.createInputStreamFactory(params.getData()); ObjectStream<String> lineStream = null; try { lineStream = new PlainTextByLineStream(sampleDataIn, params.getEncoding()); } catch (IOException ex) { CmdLineUtil.handleCreateObjectStreamError(ex); } return new SentenceSampleStream(lineStream); } }
public ObjectStream<Parse> create(String[] args) { Parameters params = ArgumentParser.parse(args, Parameters.class); CmdLineUtil.checkInputFile("Data", params.getData()); InputStreamFactory sampleDataIn = CmdLineUtil.createInputStreamFactory(params.getData()); ObjectStream<String> lineStream = null; try { lineStream = new PlainTextByLineStream(sampleDataIn, params.getEncoding()); } catch (IOException ex) { CmdLineUtil.handleCreateObjectStreamError(ex); } return new ParseSampleStream(lineStream); } }
public ObjectStream<SentenceSample> create(String[] args) { Parameters params = ArgumentParser.parse(args, Parameters.class); language = params.getLang(); boolean includeTitle = params.getIncludeTitles(); InputStreamFactory sampleDataIn = CmdLineUtil.createInputStreamFactory(params.getData()); ObjectStream<String> lineStream = null; try { lineStream = new PlainTextByLineStream(sampleDataIn, params.getEncoding()); } catch (IOException ex) { CmdLineUtil.handleCreateObjectStreamError(ex); } return new ADSentenceSampleStream(lineStream, includeTitle); } }
public ObjectStream<POSSample> create(String[] args) { Parameters params = ArgumentParser.parse(args, Parameters.class); language = params.getLang(); InputStreamFactory sampleDataIn = CmdLineUtil.createInputStreamFactory(params.getData()); ObjectStream<String> lineStream = null; try { lineStream = new PlainTextByLineStream(sampleDataIn, params.getEncoding()); } catch (IOException ex) { CmdLineUtil.handleCreateObjectStreamError(ex); } return new ADPOSSampleStream(lineStream, params.getExpandME(), params.getIncludeFeatures()); }
@Override public ObjectStream<SentenceSample> create(String[] args) { Parameters params = ArgumentParser.parse(args, Parameters.class); CmdLineUtil.checkInputFile("Data", params.getData()); CmdLineUtil.checkInputFile("Text", params.getTextFile()); NKJPSegmentationDocument segDoc = null; NKJPTextDocument textDoc = null; try { segDoc = NKJPSegmentationDocument.parse(params.getData()); textDoc = NKJPTextDocument.parse(params.getTextFile()); } catch (IOException ex) { CmdLineUtil.handleCreateObjectStreamError(ex); } return new NKJPSentenceSampleStream(segDoc, textDoc); } }
public ObjectStream<ChunkSample> create(String[] args) { Parameters params = ArgumentParser.parse(args, Parameters.class); language = params.getLang(); InputStreamFactory sampleDataIn = CmdLineUtil.createInputStreamFactory(params.getData()); ObjectStream<String> lineStream = null; try { lineStream = new PlainTextByLineStream(sampleDataIn, params.getEncoding()); } catch (IOException ex) { CmdLineUtil.handleCreateObjectStreamError(ex); } ADChunkSampleStream sampleStream = new ADChunkSampleStream(lineStream); if (params.getStart() != null && params.getStart() > -1) { sampleStream.setStart(params.getStart()); } if (params.getEnd() != null && params.getEnd() > -1) { sampleStream.setEnd(params.getEnd()); } return sampleStream; } }