finding non-ascii characters

find_non_ascii_chars.py

#!/usr/bin/env python
# -*- coding: utf-8 -*-

# Here's a program that will find non-ascii characters that might
# break your program, especially if the non-ascii characters are 
# in a json config file.

# The offending characters below should be smart quotes
# from M$ Word on the first line of the cfg.

cfg = u"""
Some Offending "ascii text".

Lorem ipsum dolor sit amet, consectetur adipisicing elit, sed 
do eiusmod tempor incididunt ut labore et dolore magna aliqua. 
Ut enim ad minim veniam, quis nostrud exercitation ullamco 
laboris nisi ut aliquip ex ea commodo consequat. Duis aute 
irure dolor in reprehenderit in voluptate velit esse cillum 
dolore eu fugiat nulla pariatur. Excepteur sint occaecat 
cupidatat non proident, sunt in culpa qui officia deserunt 
mollit anim id est laborum.
"""

LINE_BREAK = 10
CARRIAGE_RETURN = 13

lines = 1
for idx, c in enumerate(list(cfg)):
    if ord(c) in [LINE_BREAK, CARRIAGE_RETURN]:
        lines += 1
    if ord(c) > 127:
        print "line # ", lines, ", ascii code: ", ord(c), ", actual character:  ", c