HangulTextBoundaryDetection.java Source code

Introduction

Here is the source code for HangulTextBoundaryDetection.java

Source

/*
Character Boundaries: 0 3 6 
Word Boundaries:0 6 
*/
import java.text.BreakIterator;
import java.util.Locale;

public class HangulTextBoundaryDetection {
    static void printBoundaries(String source, BreakIterator bi) {
        bi.setText(source);
        int boundary = bi.first();

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

    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);
        System.out.print("\nWord Boundaries:");
        printBoundaries(hangul, wi);
    }
}