import string
import unicodedata

# We can use "_" to represent an out-of-vocabulary character, that is, any character we are not handling in our model
allowed_characters = string.ascii_letters + " .,;'" + "_"
n_letters = len(allowed_characters)

# Turn a Unicode string to plain ASCII, thanks to https://stackoverflow.com/a/518232/2809427
def unicodeToAscii(s):
    return ''.join(
        c for c in unicodedata.normalize('NFD', s)
        if unicodedata.category(c) != 'Mn'
        and c in allowed_characters
    )