*
 * 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

    val c = this[i]
    // The WHATWG Host parsing rules accepts some character codes which are invalid by
    // definition for OkHttp's host header checks (and the WHATWG Host syntax definition). Here
    // we rule out characters that would cause problems in host headers.
    if (c <= '\u001f' || c >= '\u007f') {
      return true
    }
    // Check for the characters mentioned in the WHATWG Host parsing spec:

      } 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

    // Host names are special:
    //
    //  * Several characters are forbidden and must throw exceptions if used.
    //  * They don't use percent escaping at all.
    //  * They use punycode for internationalization.
    //  * URI is much more strict than HttpUrl or URL on what's accepted.
    //
    // HttpUrl is quite lenient with what characters it accepts. In particular, characters like '{'

    "output": null
  },
  {
    "input": "xn--a.ß",
    "output": null
  },
  {
    "input": "xn--ls8h=",
    "output": null
  },
  {
    "comment": "Invalid Punycode (contains non-ASCII character)",
    "input": "xn--tešla",
    "output": null
  },
  {
    "comment": "Valid Punycode",
    "input": "xn--zca.xn--zca",
    "output": "xn--zca.xn--zca"
  },
  {
    "comment": "Mixed",

 *
 *  * 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'.

            't'.code -> append('\t')
            'f'.code -> append('\u000c')
            'u'.code -> append(buffer.readUtf8(4).toInt(16).toChar())
            else -> throw IllegalArgumentException("unexpected escape character in $s")
          }
        }
      }
    }
  }

 *
 * Percent encoding replaces a character (like `\ud83c\udf69`) with its UTF-8 hex bytes (like
 * `%F0%9F%8D%A9`). This approach works for whitespace characters, control characters, non-ASCII
 * characters, and characters that already have another meaning in a particular context.
 *
 * Percent encoding is used in every URL component except for the hostname. But the set of