Example usage for java.text BreakIterator getSentenceInstance

Introduction

In this page you can find the example usage for java.text BreakIterator getSentenceInstance.

Prototype

public static BreakIterator getSentenceInstance(Locale locale) 

Source Link

Document

Returns a new BreakIterator instance for sentence breaks for the given locale.

Usage

From source file:Main.java

public static void main(String[] argv) throws Exception {

    BreakIterator iterator = BreakIterator.getSentenceInstance(Locale.CANADA);
    iterator.setText("this is a test.");
    for (int index = iterator.first(); index != BreakIterator.DONE; index = iterator.next()) {
        System.out.println(index);
    }//  www  . j  a va2  s .c o  m
}

---

From source file:Main.java

public TextBoundaryFrame() {
    getContentPane().add(new JScrollPane(outputText));

    Locale currentLocale = Locale.getDefault();
    BreakIterator currentBreakIterator = BreakIterator.getSentenceInstance(currentLocale);

    String text = "The quick, brown fox jump-ed\n" + "over the lazy \"dog.\" And then...what happened?";
    currentBreakIterator.setText(text);/* www.  jav a  2s .  c  o  m*/
    outputText.setText("");

    int from = currentBreakIterator.first();
    int to;
    while ((to = currentBreakIterator.next()) != BreakIterator.DONE) {
        outputText.append(text.substring(from, to) + "|");
        from = to;
    }
    outputText.append(text.substring(from));
}

---

From source file:de.tudarmstadt.lt.lm.service.BreakIteratorStringProvider.java

@Override
public List<String> splitSentences(String text, String language_code) throws Exception {
    LOG.trace(String.format("Splitting sentences from text: %s", StringUtils.abbreviate(text, 200)));
    List<String> sentences = new ArrayList<String>();

    text = de.tudarmstadt.lt.utilities.StringUtils.trim_and_replace_emptyspace(text, " ");

    for (LineIterator iter = new LineIterator(new StringReader(text)); iter.hasNext();) {
        String line = iter.nextLine();
        BreakIterator sentence_bounds = BreakIterator.getSentenceInstance(LocaleUtils.toLocale(language_code));
        sentence_bounds.setText(line);//from  ww  w.j  av  a 2  s. c  o  m
        int begin_s = sentence_bounds.first();
        for (int end_s = sentence_bounds
                .next(); end_s != BreakIterator.DONE; begin_s = end_s, end_s = sentence_bounds.next()) {

            String sentence = de.tudarmstadt.lt.utilities.StringUtils.trim(line.substring(begin_s, end_s));
            if (sentence.isEmpty())
                continue;
            sentences.add(sentence);
            LOG.trace(String.format("Current sentence: %s", StringUtils.abbreviate(sentence, 200)));
        }
    }
    LOG.trace(String.format("Split text '%s' into '%d' sentences.", StringUtils.abbreviate(text, 200),
            sentences.size()));
    return sentences;
}

---

From source file:IteratorTest.java

protected void refreshDisplay() {
    int startIndex, nextIndex;
    Vector items = new Vector();
    String msgText = textArea.getText();
    Locale locale = (Locale) (localeButton.getSelectedItem());
    BreakIterator iterator = null;
    if (charButton.isSelected()) {
        iterator = BreakIterator.getCharacterInstance(locale);
    } else if (wordButton.isSelected()) {
        iterator = BreakIterator.getWordInstance(locale);
    } else if (lineButton.isSelected()) {
        iterator = BreakIterator.getLineInstance(locale);
    } else if (sentButton.isSelected()) {
        iterator = BreakIterator.getSentenceInstance(locale);
    }/*w w w .j a  v a  2s .  c  o  m*/
    iterator.setText(msgText);
    startIndex = iterator.first();
    nextIndex = iterator.next();

    while (nextIndex != BreakIterator.DONE) {
        items.addElement(msgText.substring(startIndex, nextIndex));
        startIndex = nextIndex;
        nextIndex = iterator.next();
    }
    itemList.setListData(items);
}

---

From source file:com.cotrino.knowledgemap.db.Question.java

/**
 * http://stackoverflow.com/questions/2103598/java-simple-sentence-parser
 * @param text//w w  w  . ja  v  a2s  .  c  o  m
 * @param language
 * @param country
 * @return
 */
public static List<String> tokenize(String text, String language, String country) {
    List<String> sentences = new ArrayList<String>();
    Locale currentLocale = new Locale(language, country);
    BreakIterator sentenceIterator = BreakIterator.getSentenceInstance(currentLocale);
    sentenceIterator.setText(text);
    int boundary = sentenceIterator.first();
    int lastBoundary = 0;
    while (boundary != BreakIterator.DONE) {
        boundary = sentenceIterator.next();
        if (boundary != BreakIterator.DONE) {
            sentences.add(text.substring(lastBoundary, boundary));
        }
        lastBoundary = boundary;
    }
    return sentences;
}

---

From source file:graphene.util.StringUtils.java

/**
 * Convert a string to a list of strings broken up by end of sentence
 * tokens.//from w  w w .  ja v  a2s.  c o m
 * 
 * @param input
 * @param locale
 * @return
 */
public static List<String> convertToSentences(final String input, final Locale locale) {
    final BreakIterator iterator = BreakIterator.getSentenceInstance(locale);
    iterator.setText(input);
    final ArrayList<String> sentences = new ArrayList<String>();

    int start = iterator.first();

    for (int end = iterator.next(); end != BreakIterator.DONE; start = end, end = iterator.next()) {
        sentences.add(input.substring(start, end));
    }
    return sentences;
}

---

From source file:org.cloudgraph.examples.test.model.NLPWikiParseTest.java

private void parse(StringBuilder buf) throws IOException {
    BreakIterator iterator = BreakIterator.getSentenceInstance(Locale.US);

    String text = buf.toString();
    int counter = 0;
    iterator.setText(text);/*from  w  w  w  . j  a v  a 2s  .  co m*/

    int lastIndex = iterator.first();
    while (lastIndex != BreakIterator.DONE) {
        int firstIndex = lastIndex;
        lastIndex = iterator.next();

        if (lastIndex != BreakIterator.DONE) {
            String sentence = text.substring(firstIndex, lastIndex);
            long before = System.currentTimeMillis();
            //parse(sentence);
            long after = System.currentTimeMillis();
            log.info("time4: " + String.valueOf(after - before) + ": " + sentence);
            counter++;
        }
    }

}

---

From source file:org.cloudgraph.examples.test.model.StanfordCoreNLPTest.java

private void parse(StringBuilder buf) throws IOException {
    BreakIterator iterator = BreakIterator.getSentenceInstance(Locale.US);

    String text = buf.toString();
    int counter = 0;
    iterator.setText(text);/*  ww  w .  java2  s .  c  om*/

    int lastIndex = iterator.first();
    while (lastIndex != BreakIterator.DONE) {
        int firstIndex = lastIndex;
        lastIndex = iterator.next();

        if (lastIndex != BreakIterator.DONE) {
            String sentence = text.substring(firstIndex, lastIndex);
            long before = System.currentTimeMillis();
            parse(sentence);
            long after = System.currentTimeMillis();
            log.info("time4: " + String.valueOf(after - before) + ": " + sentence);
            counter++;
        }
    }

}

---