Example usage for edu.stanford.nlp.process DocumentPreprocessor DocumentPreprocessor

Introduction

In this page you can find the example usage for edu.stanford.nlp.process DocumentPreprocessor DocumentPreprocessor.

Prototype

DocumentPreprocessor

Source Link

Usage

From source file:es.uniovi.aic.miex.run.Miex.java

License:Open Source License

private static List<List<? extends HasWord>> chopSentences(String text) {
    DocumentPreprocessor documentPreprocessor = new DocumentPreprocessor();

    List<List<? extends HasWord>> sentences = null;

    StringReader theReader = new StringReader(text);

    sentences = documentPreprocessor.getSentencesFromText(theReader, null, null, -1);

    return sentences;
}

---

From source file:reck.corpora.DocumentImpl.java

License:Open Source License

public ArrayList getParseTreeList() {

    // variables needed to process the files to be parsed
    TokenizerFactory tokenizerFactory = null;
    DocumentPreprocessor documentPreprocessor = new DocumentPreprocessor();
    boolean tokenized = false; // whether or not the input file has already been tokenized
    Function<List<HasWord>, List<HasWord>> escaper = null;
    int tagDelimiter = -1;
    String sentenceDelimiter = null;
    String elementDelimiter = null;
    Options op = ParserConstants.lp.getOp();
    PrintWriter pwErr = op.tlpParams.pw(System.err);

    try {//from w w w . j  a  v  a 2s . c om
        if (elementDelimiter != null) {
            document = documentPreprocessor.getSentencesFromXML(textFilename, escaper, elementDelimiter,
                    sentenceDelimiter);
        } else {
            document = documentPreprocessor.getSentencesFromText(textFilename, escaper, sentenceDelimiter,
                    tagDelimiter);
        }
    } catch (IOException e) {
        pwErr.println("ERROR: Couldn't open file: " + textFilename);
    }

    ArrayList treeList = ParserConstants.lp.parseFile(textFilename, noTaggedContent, startSentence, tokenized,
            tokenizerFactory, document, documentPreprocessor, escaper, tagDelimiter);

    return treeList;
}

---