apply {
      for (i in 0..127) {
        encodings[i] = encoding
      }
    }

  fun override(
    encoding: Encoding,
    vararg codePoints: Int,
  ) = apply {
    for (codePoint in codePoints) {
      encodings[codePoint] = encoding
    }
  }

  fun nonPrintableAscii(encoding: Encoding) =
    apply {
      encodings[ 0x0] = encoding // Null character

    utf8Lengths.put(MAX_CODE_POINT, 4);

    Integer[] codePoints = utf8Lengths.keySet().toArray(new Integer[] {});
    StringBuilder sb = new StringBuilder();
    Random rnd = new Random();
    for (int trial = 0; trial < 100; trial++) {
      sb.setLength(0);
      int utf8Length = 0;
      for (int i = 0; i < 6; i++) {
        Integer randomCodePoint = codePoints[rnd.nextInt(codePoints.length)];
        sb.appendCodePoint(randomCodePoint);

  private static long codePointToFourUtf8Bytes(int codePoint) {
    // codePoint has at most 21 bits
    return ((0xFL << 4) | (codePoint >>> 18))
        | ((0x80L | (0x3F & (codePoint >>> 12))) << 8)
        | ((0x80L | (0x3F & (codePoint >>> 6))) << 16)
        | ((0x80L | (0x3F & codePoint)) << 24);
  }

  private static long charToThreeUtf8Bytes(char c) {
    return ((0x7L << 5) | (c >>> 12))

  private static long codePointToFourUtf8Bytes(int codePoint) {
    // codePoint has at most 21 bits
    return ((0xFL << 4) | (codePoint >>> 18))
        | ((0x80L | (0x3F & (codePoint >>> 12))) << 8)
        | ((0x80L | (0x3F & (codePoint >>> 6))) << 16)
        | ((0x80L | (0x3F & codePoint)) << 24);
  }

  private static long charToThreeUtf8Bytes(char c) {
    return ((0x7L << 5) | (c >>> 12))

        BytesRef matchOutput = null;

        int index = 0;
        while (start + index < src.length) {
            final int codePoint = Character.codePointAt(src, start + index, src.length);
            if (fst.findTargetArc(ignoreCase ? Character.toLowerCase(codePoint) : codePoint, scratchArc, scratchArc, fstReader) == null) {
                return matchOutput;
            }

    }
    return new String(dest, 0, destIndex);
  }

  /**
   * Returns the Unicode code point of the character at the given index.
   *
   * <p>Unlike {@link Character#codePointAt(CharSequence, int)} or {@link String#codePointAt(int)}
   * this method will never fail silently when encountering an invalid surrogate pair.
   *
   * <p>The behaviour of this method is as follows:
   *
   * <ol>

    }
    return new String(dest, 0, destIndex);
  }

  /**
   * Returns the Unicode code point of the character at the given index.
   *
   * <p>Unlike {@link Character#codePointAt(CharSequence, int)} or {@link String#codePointAt(int)}
   * this method will never fail silently when encountering an invalid surrogate pair.
   *
   * <p>The behaviour of this method is as follows:
   *
   * <ol>

  val bufferA = Buffer().writeUtf8(host)
  val bufferB = Buffer()

  // 1. Map, from bufferA to bufferB.
  while (!bufferA.exhausted()) {
    val codePoint = bufferA.readUtf8CodePoint()
    if (!IDNA_MAPPING_TABLE.map(codePoint, bufferB)) return null
  }

  // 2. Normalize, from bufferB to bufferA.
  val normalized = normalizeNfc(bufferB.readUtf8())
  bufferA.writeUtf8(normalized)

                try {
                    char low = version.charAt(i + 1);
                    char[] both = {character, low};
                    c = Character.codePointAt(both, 0);
                    i++;
                } catch (IndexOutOfBoundsException ex) {
                    // high surrogate without low surrogate. Not a lot we can do here except treat it as a regular