Gist demonstrating Unicode-awareness in Python's concept of what a digit is

non-latin digits.py

#/usr/bin/env python
# encoding: utf-8
from __future__ import print_function, unicode_literals

import re
import sys

def safe_call(func, *args, **kwargs):
    try:
        return func(*args, **kwargs)
    except ValueError as exc:
        return u"Error calling %s: %s" % (func, str(exc).encode('unicode_escape'))

test_string = u'၁၄၂၈၅'

print("int() literal:")
print("\t", safe_call(int, test_string))

# Python 3 will always match but Python 2 requires re.UNICODE:

print("regex literal")
print("\t", safe_call(re.match, r'\d+', test_string))

print("regex literal, re.UNICODE")
print("\t", safe_call(re.match, r'\d+', test_string, re.UNICODE))