Name: gm110360 Date: 01/25/2002


java version "1.4.0-beta3"
Java(TM) 2 Runtime Environment, Standard Edition (build 1.4.0-
Java HotSpot(TM) Client VM (build 1.4.0-beta3-b84, mixed mode)


When converting a String to bytes in UTF-8 format and back, the translation
fails for certain character strings. See code below.

import java.io.ByteArrayInputStream;
import java.io.ByteArrayOutputStream;
import java.io.DataInputStream;
import java.io.DataOutputStream;

/*
 * Copyright (c) 2001 Kenamea, Inc.
 */

/**
 * Test program that seems to show a problem with the UTF-8 encoding
 * for Strings.
 */
public class UTFTest {

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

    checkConversions("hello, world");
    checkConversions(new String(new char[] { 0xd800 - 1 }));
    checkConversions(new String(new char[] { 0xd800 }));
    checkConversions(new String(new char[] { 0xd900 }));
    checkConversions(new String(new char[] { 0xda00 }));
    checkConversions(new String(new char[] { 0xdb00 }));
    checkConversions(new String(new char[] { 0xdc00 - 1 }));
    checkConversions(new String(new char[] { 0xdc00 }));
    checkConversions(new String(new char[] { 0xffff }));
  }

  private static void checkConversions(String in)
    throws Exception
  {
    checkStringConversion(in);
    checkDataInputOutputStream(in);
  }

  private static void checkStringConversion(String in)
    throws Exception
  {
    
    byte[] bytes = in.getBytes("UTF-8");
    String out = new String(bytes, 0, bytes.length, "UTF-8");

    checkStrings("string", in, out);
  }

  private static void checkDataInputOutputStream(String in)
    throws Exception
  {
    ByteArrayOutputStream baos = new ByteArrayOutputStream();
    DataOutputStream dos = new DataOutputStream(baos);
    dos.writeUTF(in);
    ByteArrayInputStream bais = new ByteArrayInputStream(baos.toByteArray());
    DataInputStream dis = new DataInputStream(bais);

    String out = dis.readUTF();
  
    checkStrings("data io", in, out);
  }


  private static void checkStrings(String label, String in, String out) {
    String fullLabel = label + " '" + hexString(in) + "': ";
    if (in.equals(out)) {
      say(fullLabel + "ok");
    } else {
      say(fullLabel + "bad; got '" + hexString(out) + "'");
    }
  }

  private static String hexString(String s) {
    StringBuffer buf = new StringBuffer();
    char[] chars = s.toCharArray();
    for (int i = 0; i < chars.length; i++) {
      String hex = Integer.toHexString(chars[i] & 0xffff);
      for (int j = 0; j < (4 - hex.length()); j++) {
buf.append("0");
      }
      buf.append(hex);
      if (i <= chars.length) buf.append(" ");
    }
    return buf.toString();
  }

  private static void say(String s) { System.out.println(s); }
}
(Review ID: 137295)
======================================================================