private static Optional validateUTF8Internal()

in vector/src/main/java/org/apache/arrow/vector/util/Text.java [434:508]
69 lines of code
23 McCabe index (conditional complexity)

  private static Optional<Integer> validateUTF8Internal(byte[] utf8, int start, int len) {
    int count = start;
    int leadByte = 0;
    int length = 0;
    int state = LEAD_BYTE;
    while (count < start + len) {
      int aByte = utf8[count] & 0xFF;

      switch (state) {
        case LEAD_BYTE:
          leadByte = aByte;
          length = bytesFromUTF8[aByte];

          switch (length) {
            case 0: // check for ASCII
              if (leadByte > 0x7F) {
                return Optional.of(count);
              }
              break;
            case 1:
              if (leadByte < 0xC2 || leadByte > 0xDF) {
                return Optional.of(count);
              }
              state = TRAIL_BYTE_1;
              break;
            case 2:
              if (leadByte < 0xE0 || leadByte > 0xEF) {
                return Optional.of(count);
              }
              state = TRAIL_BYTE_1;
              break;
            case 3:
              if (leadByte < 0xF0 || leadByte > 0xF4) {
                return Optional.of(count);
              }
              state = TRAIL_BYTE_1;
              break;
            default:
              // too long! Longest valid UTF-8 is 4 bytes (lead + three)
              // or if < 0 we got a trail byte in the lead byte position
              return Optional.of(count);
          } // switch (length)
          break;

        case TRAIL_BYTE_1:
          if (leadByte == 0xF0 && aByte < 0x90) {
            return Optional.of(count);
          }
          if (leadByte == 0xF4 && aByte > 0x8F) {
            return Optional.of(count);
          }
          if (leadByte == 0xE0 && aByte < 0xA0) {
            return Optional.of(count);
          }
          if (leadByte == 0xED && aByte > 0x9F) {
            return Optional.of(count);
          }
          // falls through to regular trail-byte test!!
        case TRAIL_BYTE:
          if (aByte < 0x80 || aByte > 0xBF) {
            return Optional.of(count);
          }
          if (--length == 0) {
            state = LEAD_BYTE;
          } else {
            state = TRAIL_BYTE;
          }
          break;
        default:
          break;
      } // switch (state)
      count++;
    }
    return Optional.empty();
  }