Example usage for java.text BreakIterator first

List of usage examples for java.text BreakIterator first

Introduction

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

Prototype

public abstract int first();

Source Link

Document

Returns the first boundary.

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);
    }/*  w w w  . j a va 2  s. c o  m*/
}

From source file:Main.java

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

    BreakIterator iterator = BreakIterator.getCharacterInstance(Locale.CANADA);
    iterator.setText("aString");
    for (int index = iterator.first(); index != BreakIterator.DONE; index = iterator.next()) {
        System.out.println(index);
    }/*from   ww  w  .  j  a v a2s .  co m*/
}

From source file:Main.java

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

    BreakIterator iterator = BreakIterator.getLineInstance(Locale.CANADA);
    iterator.setText("line1\nline2");
    for (int index = iterator.first(); index != BreakIterator.DONE; index = iterator.next()) {
        System.out.println(index);
    }/*from   w  w w . j ava  2 s  .  co m*/
}

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  .  jav  a2  s.  c  o  m*/
}

From source file:HangulTextBoundaryDetection.java

static void printBoundaries(String source, BreakIterator bi) {
    bi.setText(source);/*  w w  w.  j  a  v a 2 s  .c o m*/
    int boundary = bi.first();

    while (boundary != BreakIterator.DONE) {
        System.out.print(boundary + " ");
        boundary = bi.next();
    }
}

From source file:Main.java

static void extractWords(String target, BreakIterator wordIterator) {
    wordIterator.setText(target);/*from  w  w  w.  j  av  a 2 s . co  m*/
    int start = wordIterator.first();
    int end = wordIterator.next();

    while (end != BreakIterator.DONE) {
        String word = target.substring(start, end);
        if (Character.isLetterOrDigit(word.charAt(0))) {
            System.out.println(word);
        }
        start = end;
        end = wordIterator.next();
    }
}

From source file:Main.java

public static String wordSpace(String source) {
    BreakIterator boundary = BreakIterator.getLineInstance(new Locale("th"));
    boundary.setText(source);//w ww . ja  va2s  . c om
    int start = boundary.first();
    StringBuffer wordbuffer = new StringBuffer("");
    for (int end = boundary.next(); end != BreakIterator.DONE; start = end, end = boundary.next()) {
        wordbuffer.append(source.substring(start, end) + "\u200b");
        //           wordbuffer.append(source.substring(start, end)+"\ufeff");
    }
    return wordbuffer.toString();
}

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

/**
 * http://stackoverflow.com/questions/2103598/java-simple-sentence-parser
 * @param text/*from  w w w .ja  va 2s  .  co  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:com.conversantmedia.mapreduce.tool.RunJob.java

private static void splitLine(List<String> lines, String text, int maxLength) {
    BreakIterator boundary = BreakIterator.getLineInstance();
    boundary.setText(text);/*from ww  w  .  j a  va  2s.  c om*/
    int start = boundary.first();
    int end = boundary.next();
    int lineLength = 0;
    StringBuilder buffer = new StringBuilder();
    while (end != BreakIterator.DONE) {
        String word = text.substring(start, end);
        lineLength = lineLength + word.length();
        if (lineLength > maxLength) {
            lineLength = word.length();
            lines.add(buffer.toString());
            buffer.setLength(0);
        }
        buffer.append(word);
        start = end;
        end = boundary.next();
    }
    lines.add(buffer.toString());
}

From source file:eu.fbk.utils.lsa.util.Anvur.java

static String tokenize(String in) {

    //print each word in order
    BreakIterator boundary = BreakIterator.getWordInstance();
    boundary.setText(in);/*from  w ww .ja  va2  s .c  o m*/
    StringBuilder out = new StringBuilder();
    int start = boundary.first();

    for (int end = boundary.next(); end != BreakIterator.DONE; start = end, end = boundary.next()) {
        out.append(" ");
        out.append(in.substring(start, end));
    }
    return out.toString();
}