Example usage for java.text BreakIterator getWordInstance

Introduction

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

Prototype

public static BreakIterator getWordInstance(Locale locale) 

Source Link

Document

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

Usage

From source file:Main.java

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

    BreakIterator iterator = BreakIterator.getWordInstance(Locale.CANADA);
    iterator.setText("a sentence");
    for (int index = iterator.first(); index != BreakIterator.DONE; index = iterator.next()) {
        System.out.println(index);
    }//  ww w .  jav a  2 s  . c o  m
}

---

From source file:Main.java

public static void main(String[] args) {
    String text = "this is a test(this is a test).";
    BreakIterator wordIterator = BreakIterator.getWordInstance(Locale.getDefault());
    extractWords(text, wordIterator);//w ww  .j a va  2  s .  com
}

---

From source file:HangulTextBoundaryDetection.java

public static void main(String s[]) {
    String hangul = "\u1112\u1161\u11ab\u1100\u1173\u11af";
    BreakIterator ci = BreakIterator.getCharacterInstance(Locale.KOREAN);
    BreakIterator wi = BreakIterator.getWordInstance(Locale.KOREAN);

    System.out.print("Character Boundaries: ");
    printBoundaries(hangul, ci);//from   w  w w .jav a 2s. c om
    System.out.print("\nWord Boundaries:");
    printBoundaries(hangul, wi);
}

---

From source file:Main.java

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

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

    String text = "The quick, brown fox jump-ed\n" + "over the lazy \"dog.\" And then...what happened?";
    currentBreakIterator.setText(text);//from  ww w .  j a v a  2  s  .  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:pt.ua.ri.tokenizer.WordTokenizer.java

private WordTokenizer(String locale) {
    checkNotNull(locale);/*from  w  w  w  .j  a va  2 s .  c om*/
    bi = BreakIterator.getWordInstance(Locale.forLanguageTag(locale));
    tokens = new PatriciaTrie<>();
    bf = new StringBuilder();
}

---

From source file:nl.gridline.free.taalserver.TokenizeMap.java

@Override
protected void setup(Context context) throws IOException, InterruptedException {

    String loc = context.getConfiguration().get(TaskConfig.TEXT_LANGUAGE);
    if (loc == null) {
        splitter = BreakIterator.getWordInstance(new Locale("nl_NL"));
    } else {//from  ww  w  .ja  v a  2  s . co  m
        splitter = BreakIterator.getWordInstance(new Locale(loc));
    }

    String useDescStr = context.getConfiguration().get(TaskConfig.TEXT_ANALYSIS_USE_DESCRIPTION);
    if (useDescStr != null && !useDescStr.isEmpty()) {
        useDescription = Boolean.parseBoolean(useDescStr);
    } else {
        LOG.warn("parameter missing <" + TaskConfig.TEXT_ANALYSIS_USE_DESCRIPTION + "> defaulting to: true");
        useDescription = true;
    }

    String useTitleStr = context.getConfiguration().get(TaskConfig.TEXT_ANALYSIS_USE_TITLE);
    if (useTitleStr != null && !useTitleStr.isEmpty()) {
        useTitle = Boolean.parseBoolean(useTitleStr);

    } else {
        LOG.warn("parameter missing <" + TaskConfig.TEXT_ANALYSIS_USE_TITLE + "> defaulting to: true");
        useTitle = true;
    }

    String useKeyWordsStr = context.getConfiguration().get(TaskConfig.TEXT_ANALYSIS_USE_KEYWORDS);
    if (useKeyWordsStr != null && !useKeyWordsStr.isEmpty()) {
        useKeywords = Boolean.parseBoolean(useKeyWordsStr);
    }

}

---

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);
    }//from   ww  w  .  j av a 2 s . co 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:forge.view.arcane.util.OutlinedLabel.java

/** {@inheritDoc} */
@Override//from   w ww .  java2s .c o  m
public final void paint(final Graphics g) {
    if (getText().length() == 0) {
        return;
    }

    Dimension size = getSize();
    //
    //        if( size.width < 50 ) {
    //            g.setColor(Color.cyan);
    //            g.drawRect(0, 0, size.width-1, size.height-1);
    //        }

    Graphics2D g2d = (Graphics2D) g;

    g2d.setRenderingHint(RenderingHints.KEY_ANTIALIASING, RenderingHints.VALUE_ANTIALIAS_ON);
    g2d.setRenderingHint(RenderingHints.KEY_TEXT_ANTIALIASING, RenderingHints.VALUE_TEXT_ANTIALIAS_ON);

    int textX = outlineSize, textY = 0;
    int wrapWidth = Math.max(0, wrap ? size.width - outlineSize * 2 : Integer.MAX_VALUE);

    final String text = getText();
    AttributedString attributedString = new AttributedString(text);
    if (!StringUtils.isEmpty(text)) {
        attributedString.addAttribute(TextAttribute.FONT, getFont());
    }
    AttributedCharacterIterator charIterator = attributedString.getIterator();
    FontRenderContext fontContext = g2d.getFontRenderContext();

    LineBreakMeasurer measurer = new LineBreakMeasurer(charIterator,
            BreakIterator.getWordInstance(Locale.ENGLISH), fontContext);
    int lineCount = 0;
    while (measurer.getPosition() < charIterator.getEndIndex()) {
        measurer.nextLayout(wrapWidth);
        lineCount++;
        if (lineCount > 2) {
            break;
        }
    }
    charIterator.first();
    // Use char wrap if word wrap would cause more than two lines of text.
    if (lineCount > 2) {
        measurer = new LineBreakMeasurer(charIterator, BreakIterator.getCharacterInstance(Locale.ENGLISH),
                fontContext);
    } else {
        measurer.setPosition(0);
    }
    while (measurer.getPosition() < charIterator.getEndIndex()) {
        TextLayout textLayout = measurer.nextLayout(wrapWidth);
        float ascent = textLayout.getAscent();
        textY += ascent; // Move down to baseline.

        g2d.setColor(outlineColor);
        g2d.setComposite(AlphaComposite.getInstance(AlphaComposite.SRC_OVER, 0.8f));

        textLayout.draw(g2d, textX + outlineSize, textY - outlineSize);
        textLayout.draw(g2d, textX + outlineSize, textY + outlineSize);
        textLayout.draw(g2d, textX - outlineSize, textY - outlineSize);
        textLayout.draw(g2d, textX - outlineSize, textY + outlineSize);

        g2d.setColor(getForeground());
        g2d.setComposite(AlphaComposite.getInstance(AlphaComposite.SRC_OVER, 1.0f));
        textLayout.draw(g2d, textX, textY);

        // Move down to top of next line.
        textY += textLayout.getDescent() + textLayout.getLeading();
    }
}

---

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

@Override
public List<String> tokenizeSentence_intern(String sentence, String language_code) {
    ArrayList<String> tokens = new ArrayList<String>();
    BreakIterator token_bounds = BreakIterator.getWordInstance(LocaleUtils.toLocale(language_code));
    token_bounds.setText(sentence.trim());
    int begin_t = token_bounds.first();
    for (int end_t = token_bounds.next(); end_t != BreakIterator.DONE; begin_t = end_t, end_t = token_bounds
            .next()) {/*from w  w w . j  ava2s  . c  o  m*/
        String token = de.tudarmstadt.lt.utilities.StringUtils
                .trim_and_replace_emptyspace(sentence.substring(begin_t, end_t), "_");
        if (!token.isEmpty()) { // add token iff token is not empty
            tokens.add(token);
        }
    }
    return tokens;
}

---