diff options
author | Mark Sapiro <mark@msapiro.net> | 2016-07-14 19:10:24 -0700 |
---|---|---|
committer | Mark Sapiro <mark@msapiro.net> | 2016-07-14 19:10:24 -0700 |
commit | b17234a23a590d9b27f3f609781596eea27b6974 (patch) | |
tree | 6d065e88b6a68a6fbc989a4b8e425769da00d293 /Mailman/Handlers | |
parent | 6efea059931995de8713f35bccc1116905175cf2 (diff) | |
download | mailman2-b17234a23a590d9b27f3f609781596eea27b6974.tar.gz mailman2-b17234a23a590d9b27f3f609781596eea27b6974.tar.xz mailman2-b17234a23a590d9b27f3f609781596eea27b6974.zip |
Match header_filter_rules as normalized unicodes.
Diffstat (limited to 'Mailman/Handlers')
-rw-r--r-- | Mailman/Handlers/SpamDetect.py | 25 |
1 files changed, 19 insertions, 6 deletions
diff --git a/Mailman/Handlers/SpamDetect.py b/Mailman/Handlers/SpamDetect.py index de19adfc..aaddff5f 100644 --- a/Mailman/Handlers/SpamDetect.py +++ b/Mailman/Handlers/SpamDetect.py @@ -27,6 +27,7 @@ TBD: This needs to be made more configurable and robust. import re +from unicodedata import normalize from email.Errors import HeaderParseError from email.Header import decode_header from email.Utils import parseaddr @@ -36,6 +37,7 @@ from Mailman import Errors from Mailman import i18n from Mailman import Utils from Mailman.Handlers.Hold import hold_for_approval +from Mailman.Logging.Syslog import syslog try: True, False @@ -63,11 +65,11 @@ _ = i18n._ def getDecodedHeaders(msg, cset='utf-8'): - """Returns a string containing all the headers of msg, unfolded and - RFC 2047 decoded and encoded in cset. + """Returns a unicode containing all the headers of msg, unfolded and + RFC 2047 decoded, normalized and separated by new lines. """ - headers = '' + headers = u'' for h, v in msg.items(): uvalue = u'' try: @@ -86,7 +88,8 @@ def getDecodedHeaders(msg, cset='utf-8'): # 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, 'xmlcharrefreplace')) + uhdr = h.decode('us-ascii', 'replace') + headers += u'%s: %s\n' % (h, normalize(mm_cfg.NORMALIZE_FORM, uvalue)) return headers @@ -150,7 +153,7 @@ error, contact the mailing list owner at %(listowner)s.""")) # Now do header_filter_rules # TK: Collect headers in sub-parts because attachment filename # extension may be a clue to possible virus/spam. - headers = '' + headers = u'' # Get the character set of the lists preferred language for headers lcset = Utils.GetCharSet(mlist.preferred_language) for p in msg.walk(): @@ -164,7 +167,17 @@ error, contact the mailing list owner at %(listowner)s.""")) # ignore 'empty' patterns if not pattern.strip(): continue - if re.search(pattern, headers, re.IGNORECASE|re.MULTILINE): + pattern = Utils.xml_to_unicode(pattern, lcset) + pattern = normalize(mm_cfg.NORMALIZE_FORM, pattern) + try: + mo = re.search(pattern, + headers, + re.IGNORECASE|re.MULTILINE|re.UNICODE) + except (re.error, TypeError): + syslog('error', + 'ignoring header_filter_rules invalid pattern: %s', + pattern) + if mo: if action == mm_cfg.DISCARD: raise Errors.DiscardMessage if action == mm_cfg.REJECT: |