Test.java

  @Test
  public void canSplitIntoCharacterWithCombiningCharacters() throws UnsupportedEncodingException {
    assert DataImageWriter.stringToCharacterWithCombiningChars("a").equals(Arrays.asList("a"));
    assert DataImageWriter.stringToCharacterWithCombiningChars("ab").equals(Arrays.asList("a", "b"));
    String umlautMark = new String(new byte[]{(byte)0xCC, (byte) 0x88}, "UTF-8");
    String marksFirst = umlautMark + umlautMark + "a";
    assert DataImageWriter.stringToCharacterWithCombiningChars(marksFirst).equals(Arrays.asList(umlautMark + umlautMark, "a"));
    String charsThenMarks = "a" + umlautMark + "b";
    assert DataImageWriter.stringToCharacterWithCombiningChars(charsThenMarks).equals(Arrays.asList("a" + umlautMark, "b"));
    String khmerCombiningWithWidth = new String(new byte[]{(byte) 0xe1, (byte) 0x9f, (byte) 0x80}, "UTF-8");
    String charsThenWeirdMarks = "a" + khmerCombiningWithWidth + "b";
    assert DataImageWriter.stringToCharacterWithCombiningChars(charsThenWeirdMarks).equals(Arrays.asList("a" + khmerCombiningWithWidth, "b"));
    // and lots of stuff together:
    assert DataImageWriter.stringToCharacterWithCombiningChars(umlautMark + "ab" + umlautMark + " c" + khmerCombiningWithWidth).equals(Arrays.asList(umlautMark, "a", "b" + umlautMark, " ", "c" + khmerCombiningWithWidth));
  }