// and everything else is replaced with FFFD.
        assertEscaping(xmlEscaper, "\uFFFD", ch);
      }
    }

    // Test _all_ allowed characters (including surrogate values).
    for (char ch = 0x20; ch <= 0xFFFD; ch++) {
      // There are a small number of cases to consider, so just do it manually.
      if (ch == '&') {
        assertEscaping(xmlEscaper, "&amp;", ch);
      } else if (ch == '<') {

   * 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

     * - Tab (0x9)
     * - Line feed (0xA)
     * - Carriage return (0xD)
     * - Any character between 0x20 and 0xD7FF
     * - Any character between 0xE000 and 0xFFFD
     * - Any character between 0x10000 and 0x10FFFF
     *
     * @param in the input string to be processed
     * @return a new string with invalid XML characters removed, or the original

                + String.valueOf((char) 0x000A) // line feed
                + String.valueOf((char) 0x000D) // carriage return
                + String.valueOf((char) 0xD7FF) + String.valueOf((char) 0xE000) + String.valueOf((char) 0xFFFD);
        String result = XmlUtil.stripInvalidXMLCharacters(input);
        assertNotNull(result);
    }

    public void test_getDataMap_simpleField() throws Exception {
        // Test parsing simple field

	{" ", []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) {

      <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