Last active
June 14, 2019 09:52
-
-
Save bodqhrohro/3bd9183e59c483c9186a90bc1dd21ad0 to your computer and use it in GitHub Desktop.
Decode the filenames of attachments exported with munpack
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env python | |
# -*- coding: utf-8 -*- | |
from email.header import decode_header, HeaderParseError | |
import os | |
import re | |
import itertools | |
from pprint import pprint | |
encodings = ( 'UTF-8', 'utf-8', 'koi8-r', 'KOI8-R' ) | |
formats = ( 'B', 'Q' ) | |
patterns = list(("=?%s?%s?" % (enc, f) for enc, f in itertools.product(encodings, formats))) | |
spoiled_patterns = list((s.replace('?', 'X') for s in patterns)) | |
for root, dirs, files in os.walk('.', topdown=False): | |
for filename in files: | |
full_name = root + '/' + filename | |
orig_name = full_name[2:] | |
for pattern, spoiled_pattern in zip(patterns, spoiled_patterns): | |
if (orig_name.startswith(spoiled_pattern)): | |
# cutout the suffices of duplicates | |
parts = re.match(r'(.*)(\.\d+)$', orig_name) | |
if (parts is None): | |
f = orig_name | |
suffix = None | |
else: | |
f = parts.group(1) | |
suffix = parts.group(2) | |
# cutout possible extensions out of the encoded part | |
while True: | |
parts = re.match(r'(.*)(\.[^\.]+)$', f) | |
if (parts is not None and 'X=' not in parts.group(2)): | |
f = parts.group(1) | |
suffix = parts.group(2) + ("" if suffix is None else suffix) | |
else: | |
break | |
# munpack spoils special characters, restoring them | |
f = re.sub(r'X=X?X?' + spoiled_pattern, "?=\r\n" + pattern, f) | |
f = re.sub(r'^' + spoiled_pattern, pattern, f) | |
f = re.sub(r'X=$', "?=", f) | |
if (not f.endswith('?=')): | |
f += '?=' | |
try: | |
# decoding | |
h = decode_header(f) | |
if (len(h) <> 1 or h[0][1] is None or h[0][1] not in pattern.lower()): | |
print("Parsing error: %s" % f) | |
pprint(h) | |
continue | |
f = h[0][0] | |
enc = h[0][1] | |
try: | |
f = f.decode(enc) | |
# append the suffix back | |
if (suffix): | |
f += suffix | |
# clean the name from unwanted symbols | |
f = re.sub(r'[/\\\?\*]', '_', f) | |
# make sure the name would fit in a *NIX filesystem | |
if (len(f.encode('utf-8')) > 200): | |
f = u"%s…%s" % (f[:50], f[-50:]) | |
try: | |
os.rename(full_name, f) | |
except OSError: | |
print("Rename error: `%s` to `%s`" % (full_name, f)) | |
except UnicodeError,e: | |
print("Malformed string (%s): %s" % (e.reason, orig_name)) | |
pprint(h) | |
pprint(e.object) | |
except HeaderParseError: | |
print("Couldn't parse: %s" % f) | |
# cleanup the emptied directories | |
if (root <> "." and len(os.listdir(root)) == 0): | |
os.rmdir(root) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment