How to safely work with unicode strings in Java: Inspired by http://mortoray.com/2013/11/27/the-string-type-is-broken/

gistfile1.java

import java.text.BreakIterator;

public class UnicodeTest {

	public static void main(String[] args) {
		String noel = "noe\u0308l";
		System.out.println("noel=" + noel);
		System.out.println("Broken (java.lang.String methods):");
		System.out.println("noel.length=" + noel.length());
		System.out.println("noel.substring(0,3)=" + noel.substring(0, 3));
		System.out.println("noel.reverse="
				+ new StringBuilder(noel).reverse().toString());
		
		System.out.println();
		System.out.println("Works (java.text.BreakIterator methods):");
		System.out.println("noel.breakIteratorLength=" + breakIteratorLength(noel));
		System.out.println("noel.breakIteratorSubstring(0,3)=" + breakIteratorSubstring(noel, 0, 3));
		System.out.println("noel.breakIteraorReverse=" + breakIteratorReverse(noel));
		
		// Output:
		// noel=noël
		// Broken (java.lang.String methods):
		// noel.length=5
		// noel.substring(0,3)=noe
		// noel.reverse=l̈eon
		// 
		// Works (java.text.BreakIterator methods):
		// noel.breakIteratorLength=4
		// noel.breakIteratorSubstring(0,3)=noë
		// noel.breakIteraorReverse=lëon
	}

	private static int breakIteratorLength(String s) {
		if (s.length() == 0) {
			return 0;
		} else {
			BreakIterator characterBreakIterator = BreakIterator
					.getCharacterInstance();
			characterBreakIterator.setText(s);
			int breakIteratorLength = -1;
			for (int boundary = characterBreakIterator.first(); boundary != BreakIterator.DONE; boundary = characterBreakIterator
					.next()) {
				breakIteratorLength++;
			}
			return breakIteratorLength;
		}
	}
	
	private static String breakIteratorReverse(String s) {
		if (s.length() == 0) {
			return "";
		} else {
			BreakIterator characterBreakIterator = BreakIterator.getCharacterInstance();
			characterBreakIterator.setText(s);
			StringBuilder reverseStringBuilder = new StringBuilder(s.length());
			int closerToEndBoundary = characterBreakIterator.last();
			int boundary = characterBreakIterator.previous();
			while (boundary != BreakIterator.DONE) {
				reverseStringBuilder.append(s.substring(boundary, closerToEndBoundary));
				
				closerToEndBoundary = boundary;
				boundary = characterBreakIterator.previous();
			}
			return reverseStringBuilder.toString();
		}
	}
	
	private static String breakIteratorSubstring(String s, int begin, int end) {
		if (s.length() == 0) {
			return "";
		} else {
			BreakIterator characterBreakIterator = BreakIterator.getCharacterInstance();
			characterBreakIterator.setText(s);
			characterBreakIterator.first();
			int beginBoundary = characterBreakIterator.next(begin);
			int endBoundary = characterBreakIterator.next(end-begin);
			return s.substring(beginBoundary, endBoundary);
		}
	}
}