writeByte((d1 shl 4) + d2)
        i += 2
        i += Character.charCount(codePoint)
        continue
      }
    } else if (codePoint == '+'.code && plusIsSpace) {
      writeByte(' '.code)
      i++
      continue
    }
    writeUtf8CodePoint(codePoint)
    i += Character.charCount(codePoint)
  }
}

internal fun String.canonicalize(
  pos: Int = 0,

   * kinds of common human text.
   *
   * @see MaxCodePoint#decode
   */
  @Param({"0x80", "0x90", "0x100", "0x800", "0x10000", "0x10ffff"})
  MaxCodePoint maxCodePoint;

  @Param({"16384"})
  int charCount;

  @Param({"MURMUR3_32", "MURMUR3_128", "SHA1"})
  HashFunctionEnum hashFunctionEnum;

  private String[] strings;

  static final int SAMPLES = 0x100;
  static final int SAMPLE_MASK = 0xFF;

  /**

    assertHash(expected, murmur3_32_fixed().newHasher().putBytes(string.getBytes(charset)).hash());
  }

  private boolean allBmp(String string) {
    // Ordinarily we'd use something like i += Character.charCount(string.codePointAt(i)) here. But
    // we can get away with i++ because the whole point of this method is to return false if we find
    // a code point that doesn't fit in a char.
    for (int i = 0; i < string.length(); i++) {