In the original paper they allocate an encoding character for all characters outside the range they actually encode. It isn't obvious to me that you have done this in your code. Any reason? Or am I just not seeing where that is being done?
Sorry for the late reply, haven't actually checked this repo for a long time.
Unknown character is actually set as index "68", which I comment in the code. Special padding is by default "0".
In the original paper they allocate an encoding character for all characters outside the range they actually encode. It isn't obvious to me that you have done this in your code. Any reason? Or am I just not seeing where that is being done?