public static void main(String[] args) { try { NagelSentenceSplitter nss = new NagelSentenceSplitter(); nss.setDocument("I am nice. I am very nice.\n\n This is what you can see here. Bye!!!"); nss.split(); for (String sentence : nss.getSentences()) { System.out.println(sentence); } } catch(Exception e) { e.printStackTrace(); } } }
protected void setDocumentImpl(InputStream documentStream) throws SentenceSplitterException { clean(); this.readers = new LinkedList<Reader>(); this.readers.add(new InputStreamReader(documentStream)); documentSet = true; }
@Override protected NagelSentenceSplitter buildInnerTool() throws Exception { NagelSentenceSplitter sentenceSplitter = new NagelSentenceSplitter(); return sentenceSplitter; }
LinkedList<String> ret = executeCommandWithReader(command, reader); ret.addAll(0, executeCommandWithReader(command, demarcationReader));
public AbstractSentenceSplitter getSplitter() { return new NagelSentenceSplitter(); }
public SentenceSplitter getDefaultSentenceSplitter() { return new NagelSentenceSplitter(); }
protected void setDocumentImpl(File textFile) throws SentenceSplitterException { clean(); try { this.readers = new LinkedList<Reader>(); this.readers.add( new FileReader(textFile)); } catch (FileNotFoundException e) { throw new SentenceSplitterException("invalid input File:"+textFile.toString(),e); } documentSet = true; }
SentenceSplitter sentenceSplitter = new NagelSentenceSplitter(); File ReutersCorpusDir = new File(args[argsIndex++]); ReutersCorpusReader reader = new ReutersCorpusReader(ReutersCorpusDir);
protected void setDocumentImpl(String documentContents) throws SentenceSplitterException { clean(); this.readers = new LinkedList<Reader>(); // Amnon 8.9.10: fragment documentContents into digestible chunks int length = documentContents.length(); int right = 0; int left = 0; while (right < length) { right = Math.min(length, right + MAX_EXEC_PARAM_SZ); this.readers.add(new StringReader(documentContents.substring(left, right))); left = right; } documentSet = true; }
this.sentenceSplitter = new NagelSentenceSplitter(); break; case MORPH_ADORNER: