A script to find and rename filenames containing unicode characters

find_unicode_files.py

#!/usr/bin/python3
import sys, os, unicodedata

def main(argv):
    if len(argv) != 2:
        raise Exception('Syntax: FindUnicodeFiles.py <directory>')

    startdir = argv[1]
    if not os.path.isdir(startdir):
        raise Exception('"%s" is not a directory' % startdir)

    for r in recurse_breadth_first(startdir, is_unicode_filename):
        print(r.encode('unicode-escape').decode('ascii'))
        nn = unicodedata.normalize('NFKD',r).encode('ASCII','ignore').decode()
        print('-->',nn)
        if(yesno("Rename File")):
            os.rename(r, nn)

def yesno(question):
    """Simple Yes/No Function."""
    prompt = f'{question} ? (y/n): '
    ans = input(prompt).strip().lower()
    if ans not in ['y', 'n']:
        print(f'{ans} is invalid, please try again...')
        return yesno(question)
    if ans == 'y':
        return True
    return False

def recurse_breadth_first(dirpath, test_func):
    namesandpaths = [(f, os.path.join(dirpath, f)) for f in os.listdir(dirpath)]

    for (name, path) in namesandpaths:
        if test_func(name):
            yield path

    for (_, path) in namesandpaths:
        if os.path.isdir(path):
            for r in recurse_breadth_first(path, test_func):
                yield r


def is_unicode_filename(filename):
    return any(ord(c) >= 0x7F for c in filename)


if __name__ == '__main__':
    main(sys.argv)