Example usage for edu.stanford.nlp.util StringUtils split

Introduction

In this page you can find the example usage for edu.stanford.nlp.util StringUtils split.

Prototype

public static List<String> split(String str, String regex) 

Source Link

Document

Splits the given string using the given regex as delimiters.

Usage

From source file:org.voyanttools.trombone.storage.file.FileStorage.java

License:Open Source License

@Override
public List<String> retrieveStrings(String id) throws IOException {
    String string = retrieveString(id);
    return StringUtils.split(string, "\n");
}

---

From source file:semRewrite.datesandnumber.StanfordDateTimeExtractor.java

License:Open Source License

/** ***************************************************************
   * Calls the stanford parser and extracts the necessary information about the words in the string 
   * and stores them in Token object for further usage. 
   * @param input: The natural language string.
* @return List of Tokens./*from   w w w . ja va2s . co  m*/
   */
public List<Tokens> populateParserInfo(String inputSentence) {

    Properties props = new Properties();
    // props.setProperty("annotators", "tokenize, ssplit, pos, lemma, ner, parse, dcoref");
    props.setProperty("annotators", "tokenize, ssplit, pos, lemma, ner, parse");
    StanfordCoreNLP pipeline = new StanfordCoreNLP(props);
    Annotation annotation;
    annotation = new Annotation(inputSentence);

    pipeline.annotate(annotation);
    List<CoreMap> sentences = annotation.get(CoreAnnotations.SentencesAnnotation.class);
    int sentenceCount = 0;
    List<Tokens> tokenList = new ArrayList<Tokens>();
    for (CoreMap sentence : sentences) {
        tokenCount = 1;
        for (CoreLabel token : sentence.get(TokensAnnotation.class)) {
            String namedEntity = token.get(NamedEntityTagAnnotation.class);
            if ((DATE_ENTITIES.contains(namedEntity))
                    || ((MEASURE_ENTITIES.contains(namedEntity))
                            && (token.get(PartOfSpeechAnnotation.class).equals("CD")
                                    || token.get(PartOfSpeechAnnotation.class).equals("JJ")))
                    || (namedEntity.equals("DURATION")
                            && token.get(PartOfSpeechAnnotation.class).equals("CD"))) {
                Tokens tokens = new Tokens();
                tokens.setId(tokenCount);
                tokens.setWord(token.get(TextAnnotation.class));
                tokens.setNer(token.get(NamedEntityTagAnnotation.class));
                tokens.setNormalizedNer(token.get(NormalizedNamedEntityTagAnnotation.class));
                tokens.setCharBegin(token.get(BeginIndexAnnotation.class));
                tokens.setCharEnd(token.get(EndIndexAnnotation.class));
                tokens.setPos(token.get(PartOfSpeechAnnotation.class));
                tokens.setLemma(token.get(LemmaAnnotation.class));
                tokenList.add(tokens);
            }
            tokenCount++;
        }
        dependencies = (sentence.get(CollapsedDependenciesAnnotation.class));
        dependencyList = (StringUtils.split(dependencies.toList(), "\n"));
    }
    return tokenList;
}

---