* escaper to escape attribute values. Use {@link #xmlContentEscaper} if the output can appear in
   * element content or {@link #xmlAttributeEscaper} in attribute values.
   *
   * <p>This escaper substitutes {@code 0xFFFD} for non-whitespace control characters and the
   * character values {@code 0xFFFE} and {@code 0xFFFF} which are not permitted in XML. For more

        char c;
        for (int i = 0; i < in.length(); i++) {
            c = in.charAt(i);
            if (c == 0x9 || c == 0xA || c == 0xD || c >= 0x20 && c <= 0xD7FF || c >= 0xE000 && c <= 0xFFFD
                    || c >= 0x10000 && c <= 0x10FFFF) {
                buf.append(c);
            }
        }
        return buf.toString().trim();
    }

	{" ", []rune{32}, false},
	{"ABC", []rune{65, 66, 67}, false},
	{"abc", []rune{97, 98, 99}, false},
	{"\u65e5\u672c\u8a9e", []rune{26085, 26412, 35486}, false},
	{"ab\x80c", []rune{97, 98, 0xFFFD, 99}, true},
	{"ab\xc0c", []rune{97, 98, 0xFFFD, 99}, true},
}

func TestRunes(t *testing.T) {
	for _, tt := range RunesTests {
		tin := []byte(tt.in)
		a := Runes(tin)
		if !slices.Equal(a, tt.out) {

and the second value, of type <code>rune</code>, will be the value of
the corresponding code point.  If the iteration encounters an invalid
UTF-8 sequence, the second value will be <code>0xFFFD</code>,
the Unicode replacement character, and the next iteration will advance
a single byte in the string.
</li>

<li>
The iteration order over maps is not specified

      <match value="0xfffb" type="string" offset="0"/> <!-- V1, L3      -->
      <match value="0xfffc" type="string" offset="0"/> <!-- V1, L2, CRC -->
      <match value="0xfffd" type="string" offset="0"/> <!-- V1, L2      -->
      <match value="0xffe3" type="string" offset="0"/> <!-- MP3 2.5 from pronom     -->
      <!-- TIKA-417: This is the UTF-16 LE byte order mark! -->

and the second value, of type <code>rune</code>, will be the value of
the corresponding code point. If the iteration encounters an invalid
UTF-8 sequence, the second value will be <code>0xFFFD</code>,
the Unicode replacement character, and the next iteration will advance
a single byte in the string.
</li>

<li>
The iteration order over maps is not specified