summaryrefslogtreecommitdiff
path: root/email-print-mime-structure
blob: 185173f4266e25eab4fc79b1f48ccaf0ce9e443d (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
#!/usr/bin/env python3
# -*- coding: utf-8 -*-

# Copyright (C) 2019 Daniel Kahn Gillmor
#
# This program is free software: you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation, either version 3 of the License, or (at
# your option) any later version.
#
# This program is distributed in the hope that it will be useful, but
# WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
# General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with this program.  If not, see <https://www.gnu.org/licenses/>.
'''
This script reads a MIME message from stdin and produces a treelike
representation on it stdout.

Example:
0 dkg@alice:~$ printmimestructure < 'Maildir/cur/1269025522.M338697P12023.monkey,S=6459,W=6963:2,Sa'
└┬╴multipart/signed 6546 bytes
 ├─╴text/plain inline 895 bytes
 └─╴application/pgp-signature inline [signature.asc] 836 bytes
0 dkg@alice:~$

If you want to number the parts, i suggest piping the output through
something like "cat -n"
'''
import sys
import email
import logging

from typing import Optional, Union, List, Tuple, Any
from email.charset import Charset
from email.message import Message

def print_part(z:Message, prefix:str) -> None:
    ofname:Optional[str] = z.get_filename()
    fname:str = '' if ofname is None else f' [{ofname}]'
    ocharset:Union[Charset, str, None] = z.get_charset()
    cset:str = '' if ocharset is None else f' ({ocharset})'
    disp:Union[List[Tuple[str,str]], List[str], None] = z.get_params(None, header='Content-Disposition')
    disposition:str = ''
    if (disp is not None):
        for d in disp:
            if d[0] in [ 'attachment', 'inline' ]:
                disposition = ' ' + d[0]
    nbytes:int
    if z.is_multipart():
        # FIXME: it looks like we are counting chars here, not bytes:
        nbytes = len(z.as_string())
    else:
        payload:Union[List[Message], str, bytes, None] = z.get_payload()
        if not isinstance(payload, (str,bytes)):
            raise TypeError(f'expected payload to be either str or bytes, got {type(payload)}')
        nbytes = len(payload)

    print(f'{prefix}{z.get_content_type()}{cset}{disposition}{fname} {nbytes} bytes')

def test(z:Message, prefix:str='') -> None:
    if (z.is_multipart()):
        print_part(z, prefix+'┬╴')
        if prefix.endswith('└'):
            prefix = prefix.rpartition('└')[0] + ' '
        if prefix.endswith('├'):
            prefix = prefix.rpartition('├')[0] + '│'
        parts:Union[List[Message], str, bytes, None] = z.get_payload()
        if not isinstance(parts, list):
            raise TypeError(f'parts was {type(parts)}, expected List[Message]')
        i = 0
        while (i < len(parts)-1):
            test(parts[i], prefix + '├')
            i += 1
        test(parts[i], prefix + '└')
        # FIXME: show epilogue?
    else:
        print_part(z, prefix+'─╴')

msg:Union[Message, str, int, Any] = email.message_from_file(sys.stdin)

if isinstance(msg, Message):
    test(msg, '└')
else:
    logging.error('Input was not an e-mail message')