alnum encoding scheme

README.md

alnum encoding scheme

The goal is to be able to take any Python string and reversibly convert it into a string that consists only of a-zA-Z9-0_ characters.

>>> alnum_encode("hello.csv")
'hello_2e_csv'
>>> alnum_encode("this é has ü accents")
'this_20__e9__20_has_20__fc__20_accents'

alnum.py

import re

ALLOWED = "abcdefghijklmnopqrstuvwxyz" "ABCDEFGHIJKLMNOPQRSTUVWXYZ" "0123456789"
split_re = re.compile("(_[0-9a-f]+_)")


def alnum_encode(s):
    encoded = []
    for char in s:
        if char in ALLOWED:
            encoded.append(char)
        else:
            encoded.append("_" + hex(ord(char))[2:] + "_")
    return "".join(encoded)


split_re = re.compile("(_[0-9a-f]+_)")


def alnum_decode(s):
    decoded = []
    for bit in split_re.split(s):
        if bit.startswith("_"):
            hexbit = bit[1:-1]
            decoded.append(chr(int(hexbit, 16)))
        else:
            decoded.append(bit)
    return "".join(decoded)