diff options
Diffstat (limited to 'Mailman/Handlers/SpamDetect.py')
| -rw-r--r-- | Mailman/Handlers/SpamDetect.py | 53 |
1 files changed, 48 insertions, 5 deletions
diff --git a/Mailman/Handlers/SpamDetect.py b/Mailman/Handlers/SpamDetect.py index 8d26da03..d85cc6a6 100644 --- a/Mailman/Handlers/SpamDetect.py +++ b/Mailman/Handlers/SpamDetect.py @@ -1,4 +1,4 @@ -# Copyright (C) 1998-2012 by the Free Software Foundation, Inc. +# Copyright (C) 1998-2015 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 @@ -27,12 +27,14 @@ TBD: This needs to be made more configurable and robust. import re +from email.Errors import HeaderParseError from email.Header import decode_header +from email.Utils import parseaddr from Mailman import mm_cfg from Mailman import Errors from Mailman import i18n -from Mailman.Utils import GetCharSet +from Mailman import Utils from Mailman.Handlers.Hold import hold_for_approval try: @@ -68,17 +70,58 @@ def getDecodedHeaders(msg, cset='utf-8'): headers = '' for h, v in msg.items(): uvalue = u'' - v = decode_header(re.sub('\n\s', ' ', v)) + try: + v = decode_header(re.sub('\n\s', ' ', v)) + except HeaderParseError: + v = [(v, 'us-ascii')] for frag, cs in v: if not cs: cs = 'us-ascii' - uvalue += unicode(frag, cs, 'replace') + try: + uvalue += unicode(frag, cs, 'replace') + except LookupError: + # The encoding charset is unknown. At this point, frag + # has been QP or base64 decoded into a byte string whose + # charset we don't know how to handle. We will try to + # unicode it as iso-8859-1 which may result in a garbled + # mess, but we have to do something. + uvalue += unicode(frag, 'iso-8859-1', 'replace') headers += '%s: %s\n' % (h, uvalue.encode(cset, 'replace')) return headers def process(mlist, msg, msgdata): + # Before anything else, check DMARC if necessary. We do this as early + # as possible so reject/discard actions trump other holds/approvals and + # wrap/munge actions get flagged even for approved messages. + # But not for owner mail which should not be subject to DMARC reject or + # discard actions. + if not msgdata.get('toowner'): + msgdata['from_is_list'] = 0 + dn, addr = parseaddr(msg.get('from')) + if addr and mlist.dmarc_moderation_action > 0: + if Utils.IsDMARCProhibited(mlist, addr): + # Note that for dmarc_moderation_action, 0 = Accept, + # 1 = Munge, 2 = Wrap, 3 = Reject, 4 = Discard + if mlist.dmarc_moderation_action == 1: + msgdata['from_is_list'] = 1 + elif mlist.dmarc_moderation_action == 2: + msgdata['from_is_list'] = 2 + elif mlist.dmarc_moderation_action == 3: + # Reject + text = mlist.dmarc_moderation_notice + if text: + text = Utils.wrap(text) + else: + text = Utils.wrap(_( +"""You are not allowed to post to this mailing list From: a domain which +publishes a DMARC policy of reject or quarantine, and your message has been +automatically rejected. If you think that your messages are being rejected in +error, contact the mailing list owner at %(listowner)s.""")) + raise Errors.RejectMessage, text + elif mlist.dmarc_moderation_action == 4: + raise Errors.DiscardMessage if msgdata.get('approved'): return # First do site hard coded header spam checks @@ -94,7 +137,7 @@ def process(mlist, msg, msgdata): # extension may be a clue to possible virus/spam. headers = '' # Get the character set of the lists preferred language for headers - lcset = GetCharSet(mlist.preferred_language) + lcset = Utils.GetCharSet(mlist.preferred_language) for p in msg.walk(): headers += getDecodedHeaders(p, lcset) for patterns, action, empty in mlist.header_filter_rules: |