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
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
|
# Copyright (C) 1998-2006 by the Free Software Foundation, Inc.
#
# 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 2
# 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, write to the Free Software
# Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301,
# USA.
"""Recognizes simple heuristically delimited bounces."""
import re
import email.Iterators
def _c(pattern):
return re.compile(pattern, re.IGNORECASE)
# This is a list of tuples of the form
#
# (start cre, end cre, address cre)
#
# where `cre' means compiled regular expression, start is the line just before
# the bouncing address block, end is the line just after the bouncing address
# block, and address cre is the regexp that will recognize the addresses. It
# must have a group called `addr' which will contain exactly and only the
# address that bounced.
PATTERNS = [
# sdm.de
(_c('here is your list of failed recipients'),
_c('here is your returned mail'),
_c(r'<(?P<addr>[^>]*)>')),
# sz-sb.de, corridor.com, nfg.nl
(_c('the following addresses had'),
_c('transcript of session follows'),
_c(r'<(?P<fulladdr>[^>]*)>|\(expanded from: <?(?P<addr>[^>)]*)>?\)')),
# robanal.demon.co.uk
(_c('this message was created automatically by mail delivery software'),
_c('original message follows'),
_c('rcpt to:\s*<(?P<addr>[^>]*)>')),
# s1.com (InterScan E-Mail VirusWall NT ???)
(_c('message from interscan e-mail viruswall nt'),
_c('end of message'),
_c('rcpt to:\s*<(?P<addr>[^>]*)>')),
# Smail
(_c('failed addresses follow:'),
_c('message text follows:'),
_c(r'\s*(?P<addr>\S+@\S+)')),
# newmail.ru
(_c('This is the machine generated message from mail service.'),
_c('--- Below the next line is a copy of the message.'),
_c('<(?P<addr>[^>]*)>')),
# turbosport.com runs something called `MDaemon 3.5.2' ???
(_c('The following addresses did NOT receive a copy of your message:'),
_c('--- Session Transcript ---'),
_c('[>]\s*(?P<addr>.*)$')),
# usa.net
(_c('Intended recipient:\s*(?P<addr>.*)$'),
_c('--------RETURNED MAIL FOLLOWS--------'),
_c('Intended recipient:\s*(?P<addr>.*)$')),
# hotpop.com
(_c('Undeliverable Address:\s*(?P<addr>.*)$'),
_c('Original message attached'),
_c('Undeliverable Address:\s*(?P<addr>.*)$')),
# Another demon.co.uk format
(_c('This message was created automatically by mail delivery'),
_c('^---- START OF RETURNED MESSAGE ----'),
_c("addressed to '(?P<addr>[^']*)'")),
# Prodigy.net full mailbox
(_c("User's mailbox is full:"),
_c('Unable to deliver mail.'),
_c("User's mailbox is full:\s*<(?P<addr>[^>]*)>")),
# Microsoft SMTPSVC
(_c('The email below could not be delivered to the following user:'),
_c('Old message:'),
_c('<(?P<addr>[^>]*)>')),
# Yahoo on behalf of other domains like sbcglobal.net
(_c('Unable to deliver message to the following address\(es\)\.'),
_c('--- Original message follows\.'),
_c('<(?P<addr>[^>]*)>:')),
# kundenserver.de
(_c('A message that you sent could not be delivered'),
_c('^--- The header of the original'),
_c('<(?P<addr>[^>]*)>')),
# another kundenserver.de
(_c('A message that you sent could not be delivered'),
_c('^--- The header of the original'),
_c('^(?P<addr>[^\s@]+@[^\s@:]+):')),
# thehartford.com
(_c('Delivery to the following recipients failed'),
_c("Bogus - there actually isn't anything"),
_c('^\s*(?P<addr>[^\s@]+@[^\s@]+)\s*$')),
# and another thehartfod.com/hartfordlife.com
(_c('^Your message'),
_c('^because:'),
_c('^\s*(?P<addr>[^\s@]+@[^\s@]+)\s*$')),
# Next one goes here...
]
def process(msg, patterns=None):
if patterns is None:
patterns = PATTERNS
# simple state machine
# 0 = nothing seen yet
# 1 = intro seen
addrs = {}
# MAS: This is a mess. The outer loop used to be over the message
# so we only looped through the message once. Looping through the
# message for each set of patterns is obviously way more work, but
# if we don't do it, problems arise because scre from the wrong
# pattern set matches first and then acre doesn't match. The
# alternative is to split things into separate modules, but then
# we process the message multiple times anyway.
for scre, ecre, acre in patterns:
state = 0
for line in email.Iterators.body_line_iterator(msg):
if state == 0:
if scre.search(line):
state = 1
if state == 1:
mo = acre.search(line)
if mo:
addr = mo.group('addr')
if addr:
addrs[mo.group('addr')] = 1
elif ecre.search(line):
break
if addrs:
break
return addrs.keys()
|
