public DataBag exec(Tuple input) throws IOException {
if (input == null || input.size() < 1 || input.isNull(0)) return null;
// Output bag
DataBag bagOfTokens = bagFactory.newDefaultBag();
StringReader textInput = new StringReader(input.get(0).toString());
PTBTokenizer ptbt = new PTBTokenizer(textInput, new CoreLabelTokenFactory(), "");
for (CoreLabel label; ptbt.hasNext(); ) {
label = (CoreLabel) ptbt.next();
if (label.value().length() > 2) {
System.err.println(label.toString());
Tuple termText = tupleFactory.newTuple(label.word());
bagOfTokens.add(termText);
}
}
return bagOfTokens;
}
public static void main(String[] args) throws IOException {
PrintWriter pw = new PrintWriter(filename + ".tokenized.SPL");
@SuppressWarnings({"unchecked", "rawtypes"})
PTBTokenizer tokenizer =
new PTBTokenizer(new FileReader(filename), new CoreLabelTokenFactory(), "");
Sentence s = new Sentence();
for (CoreLabel label; tokenizer.hasNext(); ) {
label = (CoreLabel) tokenizer.next();
String token = label.toString("value");
if (token.equals("-LRB-")) {
token = "(";
}
if (token.equals("-RRB-")) {
token = ")";
}
if (token.equals("-LSB-")) {
token = "[";
}
if (token.equals("-RSB-")) {
token = "]";
}
if (token.equals("-LCB-")) {
token = "{";
}
if (token.equals("-RCB-")) {
token = "}";
}
s.words.add(token);
// is it sentence splitter?
if (token.equals(".") || token.equals("?") || token.equals("!")) {
if (s.isCleanSentence()) {
pw.println(s.toString());
}
s = new Sentence();
}
}
pw.close();
}
