Simple script to rename non-BMP Unicode characters out of file and folder names, recursively

strip_emoji.py

#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""Strip emoji and other non-BMP codepoints from paths to make them compatible
with mkisofs/genisoimage"""

# Prevent Python 2.x PyLint from complaining if run on this
from __future__ import (absolute_import, division, print_function,
                        with_statement, unicode_literals)

__author__ = "Stephan Sokolow (deitarion/SSokolow)"
__appname__ = "strip_emoji.py"
__version__ = "0.1"
__license__ = "MIT"

import logging, os, re
log = logging.getLogger(__name__)

NON_BMP_RE = re.compile(r"[\U00010000-\U0010FFFF]")


def process_path(path):
    replaced = NON_BMP_RE.sub('', path)
    if replaced != path:
        os.rename(path, replaced)
    return replaced


def process_arg(path):
    for path, dirs, files in os.walk(path):
        dirs.sort()

        dnew = [process_path(os.path.join(path, x)) for x in dirs]
        dirs[:] = [os.path.basename(x) for x in dnew]

        for fname in files:
            process_path(os.path.join(path, fname))


def main():
    """The main entry point, compatible with setuptools entry points."""
    from argparse import ArgumentParser, RawDescriptionHelpFormatter
    parser = ArgumentParser(formatter_class=RawDescriptionHelpFormatter,
        description=__doc__.replace('\r\n', '\n').split('\n--snip--\n')[0])
    parser.add_argument('--version', action='version',
        version="%%(prog)s v%s" % __version__)
    parser.add_argument('-v', '--verbose', action="count",
        default=2, help="Increase the verbosity. Use twice for extra effect.")
    parser.add_argument('-q', '--quiet', action="count",
        default=0, help="Decrease the verbosity. Use twice for extra effect.")
    parser.add_argument('path', action="store", nargs="+",
        help="Path to operate on")
    # Reminder: %(default)s can be used in help strings.

    args = parser.parse_args()

    # Set up clean logging to stderr
    log_levels = [logging.CRITICAL, logging.ERROR, logging.WARNING,
              logging.INFO, logging.DEBUG]
    args.verbose = min(args.verbose - args.quiet, len(log_levels) - 1)
    args.verbose = max(args.verbose, 0)
    logging.basicConfig(level=log_levels[args.verbose],
                format='%(levelname)s: %(message)s')

    for path in args.path:
        process_arg(path)

if __name__ == '__main__':  # pragma: nocover
    main()

# vim: set sw=4 sts=4 expandtab :