Find strings with non-latin characters in files

gistfile1.py

import sys
import os
import codecs
import unicodedata as ud

# from http://stackoverflow.com/questions/3094498/how-can-i-check-if-a-python-unicode-string-contains-non-western-letters

latin_letters = {}


def is_latin(uchr):
    try:
        return latin_letters[uchr]
    except KeyError:
        return latin_letters.setdefault(uchr, 'LATIN' in ud.name(uchr))


def only_roman_chars(unistr):
    return all(is_latin(uchr)
               for uchr in unistr
               if uchr.isalpha())  # isalpha suggested by John Machin


path = sys.argv[1]

for dirpath, dirnames, filenames in os.walk(path):
    for fn in filenames:
        full_path = os.path.join(dirpath, fn)
        try:
            with codecs.open(full_path, encoding='utf-8') as f:
                for line in f:
                    if not only_roman_chars(line):
                        print full_path, ':'
                        print line
        except UnicodeDecodeError:
            continue
        except:
            print 'Error while reading', full_path
            raise