Normalize and remove illegal characters in filenames in Python.

secure_filename.py

import string
import unicodedata

INVALID_FILE_CHARS = '/\\?%*:|"<>' # https://en.wikipedia.org/wiki/Filename#Reserved_characters_and_words

def secure_filename(filename):
    # keep only valid ascii chars
    output = list(unicodedata.normalize("NFKD", filename))

    # special case characters that don't get stripped by the above technique
    for pos, char in enumerate(output):
        if char == '\u0141':
            output[pos] = 'L'
        elif char == '\u0142':
            output[pos] = 'l'

    # remove unallowed characters
    output = [c if c not in INVALID_FILE_CHARS else '_' for c in output]
    return "".join(output).encode("ASCII", "ignore").decode()