} else if (firstIsRandalcat) {
        // 'If a string contains any RandALCat character, the string MUST NOT contain any LCat
        // character.'
        if (codePoint in lcatSet) return null

        // 'If a string contains any RandALCat character, a RandALCat character MUST be the last
        // character of the string.'
        if (validateBuffer.exhausted() && codePoint !in randalcatSet) return null
      } else {

}

/**
 * Returns the index of the first character in this string that is either a control character (like
 * `\u0000` or `\n`) or a non-ASCII character. Returns -1 if this string has no such characters.
 */
internal fun String.indexOfControlOrNonAscii(): Int {
  for (i in 0 until length) {
    val c = this[i]
    if (c <= '\u001f' || c >= '\u007f') {
      return i
    }
  }
  return -1
}

   FFF9; INTERLINEAR ANNOTATION ANCHOR
   FFFA; INTERLINEAR ANNOTATION SEPARATOR
   FFFB; INTERLINEAR ANNOTATION TERMINATOR
   FFFC; OBJECT REPLACEMENT CHARACTER

 *
 *  * In queries, ' ' is encoded to '+' and '+' is encoded to "%2B".
 *
 *  * Characters in `encodeSet` are percent-encoded.
 *
 *  * Control characters and non-ASCII characters are percent-encoded.
 *
 *  * All other characters are copied without transformation.
 *
 * @param alreadyEncoded true to leave '%' as-is; false to convert it to '%25'.

#
&
^
$
@
!
~
:
;
+
/
\
《
》
—
－
，
。
、
：
；
！
·
？
“
”
）
（
【
】
［
］
●
# the line below contains an IDEOGRAPHIC SPACE character (Used as a space in Chinese)
　

# English Stop Words

      if (prefix.exhausted()) {
        break
      }
      val codePoint = prefix.readUtf8CodePoint()
      if (Character.isISOControl(codePoint) && !Character.isWhitespace(codePoint)) {
        return false
      }
    }
    return true
  } catch (_: EOFException) {
    return false // Truncated UTF-8 sequence.
  }

        }
        return percentEncoded.readUtf8()
      }
    },

    /** URLs that contain this character in this component are invalid.  */
    FORBIDDEN,

    /** Hostnames that contain this character are encoded with punycode.  */
    PUNYCODE,

    /** This code point is special and should not be tested.  */
    SKIP,

    ;

    if (size == i + 1L) return null // Dangling escape.
    result.write(this, i)
    // Consume '\'.
    readByte()
    result.write(this, 1L) // The escaped character.
  }
}

/**
 * Consumes and returns a non-empty token, terminating at special characters in
 * [TOKEN_DELIMITERS]. Returns null if the buffer is empty or prefixed with a delimiter.
 */
private fun Buffer.readToken(): String? {

      // character in that label
      return false
    }

    // Optimization: check whether hostname is too short to match the pattern. hostName must be at
    // least as long as the pattern because asterisk must match the whole left-most label and
    // hostname starts with a non-empty label. Thus, asterisk has to match one or more characters.
    if (hostname.length < pattern.length) {

 *
 * This implementation is optimized for readability over efficiency.
 *
 * This implements non-transitional processing by preserving deviation characters.
 *
 * This implementation's STD3 rules are configured to `UseSTD3ASCIIRules=false`. This is
 * permissive and permits the `_` character.
 *
 * [mapping table]: https://www.unicode.org/reports/tr46/#IDNA_Mapping_Table
 * [mapping step]: https://www.unicode.org/reports/tr46/#ProcessingStepMap