Example usage for org.apache.commons.lang3.text StrMatcher stringMatcher

Introduction

In this page you can find the example usage for org.apache.commons.lang3.text StrMatcher stringMatcher.

Prototype

public static StrMatcher stringMatcher(final String str) 

Source Link

Document

Constructor that creates a matcher from a string.

Usage

From source file:edu.sabanciuniv.sentilab.sare.controllers.opinion.OpinionCorpusFactory.java

@Override
protected OpinionCorpusFactory addTextPacket(OpinionCorpus corpus, InputStream input, String delimiter)
        throws IOException {

    Validate.notNull(corpus, CannedMessages.NULL_ARGUMENT, "corpus");
    Validate.notNull(input, CannedMessages.NULL_ARGUMENT, "input");

    OpinionDocumentFactory opinionFactory = null;
    BufferedReader reader = new BufferedReader(new InputStreamReader(input));
    String line;//  w  w w.  j a  v a 2  s . c  o m

    while ((line = reader.readLine()) != null) {
        StrTokenizer tokenizer = new StrTokenizer(line, StrMatcher.stringMatcher(delimiter),
                StrMatcher.quoteMatcher());
        List<String> columns = tokenizer.getTokenList();
        if (columns.size() < 1) {
            continue;
        }

        opinionFactory = new OpinionDocumentFactory().setCorpus(corpus).setContent(columns.get(0));

        if (columns.size() > 1) {
            try {
                opinionFactory.setPolarity(Double.parseDouble(columns.get(1)));
            } catch (NumberFormatException e) {
                opinionFactory.setPolarity(null);
            }
        }

        corpus.addDocument(opinionFactory.create());
    }

    return this;
}

---

From source file:edu.sabanciuniv.sentilab.sare.controllers.aspect.AspectLexiconFactory.java

@Override
protected AspectLexiconFactory addTextPacket(AspectLexicon lexicon, InputStream input, String delimiter)
        throws IOException {
    Validate.notNull(lexicon, CannedMessages.NULL_ARGUMENT, "lexicon");
    Validate.notNull(input, CannedMessages.NULL_ARGUMENT, "input");

    delimiter = StringUtils.defaultString(delimiter, "\t");

    BufferedReader reader = new BufferedReader(new InputStreamReader(input));
    String line;/*from   www  .j a v a2 s  .  com*/

    while ((line = reader.readLine()) != null) {
        StrTokenizer tokenizer = new StrTokenizer(line, StrMatcher.stringMatcher(delimiter),
                StrMatcher.quoteMatcher());
        List<String> columns = tokenizer.getTokenList();
        if (columns.size() < 1) {
            continue;
        }

        String aspectStr = columns.get(0);
        Matcher matcher = Pattern.compile("^<(.*)>$").matcher(aspectStr);
        if (matcher.matches()) {
            aspectStr = matcher.group(1);
        } else {
            continue;
        }

        AspectLexicon aspect = lexicon.addAspect(aspectStr);
        for (int i = 1; i < columns.size(); i++) {
            aspect.addExpression(columns.get(i));
        }
    }

    return this;
}

---