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
88
89
90
91
92
93
94
95
96
|
# Copyright (C) 1998-2011 by the Free Software Foundation, Inc.
#
# This file is part of GNU Mailman.
#
# GNU Mailman 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.
#
# GNU Mailman 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
# GNU Mailman. If not, see <http://www.gnu.org/licenses/>.
"""Parse bounce messages generated by qmail.
Qmail actually has a standard, called QSBMF (qmail-send bounce message
format), as described in
http://cr.yp.to/proto/qsbmf.txt
This module should be conformant.
"""
from __future__ import absolute_import, unicode_literals
__metaclass__ = type
__all__ = [
'Qmail',
]
import re
from email.iterators import body_line_iterator
from flufl.enum import Enum
from zope.interface import implements
from mailman.interfaces.bounce import IBounceDetector
# Other (non-standard?) intros have been observed in the wild.
introtags = [
'Hi. This is the',
"We're sorry. There's a problem",
'Check your send e-mail address.',
'This is the mail delivery agent at',
'Unfortunately, your mail was not delivered'
]
acre = re.compile(r'<(?P<addr>[^>]*)>:')
class ParseState(Enum):
start = 0
intro_paragraph_seen = 1
recip_paragraph_seen = 2
class Qmail:
"""Parse QSBMF format bounces."""
implements(IBounceDetector)
def process(self, msg):
"""See `IBounceDetector`."""
addresses = set()
state = ParseState.start
for line in body_line_iterator(msg):
line = line.strip()
if state is ParseState.start:
for introtag in introtags:
if line.startswith(introtag):
state = ParseState.intro_paragraph_seen
break
elif state is ParseState.intro_paragraph_seen and not line:
# Looking for the end of the intro paragraph.
state = ParseState.recip_paragraph_seen
elif state is ParseState.recip_paragraph_seen:
if line.startswith('-'):
# We're looking at the break paragraph, so we're done.
break
# At this point we know we must be looking at a recipient
# paragraph.
mo = acre.match(line)
if mo:
addresses.add(mo.group('addr'))
# Otherwise, it must be a continuation line, so just ignore it.
else:
# We're not looking at anything in particular.
pass
return list(addresses)
|
