Example usage for edu.stanford.nlp.ling.tokensregex MatchedExpression getTokenOffsets

Introduction

In this page you can find the example usage for edu.stanford.nlp.ling.tokensregex MatchedExpression getTokenOffsets.

Prototype

public Interval<Integer> getTokenOffsets() 

Source Link

Usage

From source file:edu.cmu.ml.rtw.users.ssrivastava.RegexExtractor.java

@Override
public List<Triple<TokenSpan, String, Double>> annotate(DocumentNLP document) {

    List<Triple<TokenSpan, String, Double>> annotationList = new ArrayList<Triple<TokenSpan, String, Double>>();
    for (int sentIdx = 0; sentIdx < document.getSentenceCount(); sentIdx++) {

        CoreMap sentence = getStanfordSentence(document, sentIdx);
        if (verbose) {
            printSentence(sentence);/*from  w  w w. j a  v  a  2s  .c o m*/
        }

        if (!isGoodToProcess(sentence)) {
            continue;
        }

        //System.out.println("Extracting patterns from sentence with index "+sentIdx);
        List<MatchedExpression> matchedExpressions = extractor.extractExpressions(sentence);
        if (matchedExpressions.size() > 0) {
            if (verbose) {
                System.out.println(matchedExpressions.size());
            }
            for (MatchedExpression expr : matchedExpressions) {
                //Interval<Integer> interv = expr.getCharOffsets();
                Interval<Integer> interv = expr.getTokenOffsets();
                TokenSpan ts = new TokenSpan(document, sentIdx, interv.first(), interv.second() - 1);
                String result = expr.getValue().toString().substring(7,
                        expr.getValue().toString().length() - 1);
                if (verbose) {
                    System.out.println("[ docId:" + ts.getDocument().getName() + " first:" + interv.first()
                            + " end:" + interv.second() + " result:" + result + " ]");
                }
                annotationList.add(new Triple<TokenSpan, String, Double>(ts, result, 0.8));
            }
        }
    }

    return annotationList;
}

---