aboutsummaryrefslogtreecommitdiffstats
path: root/Mailman/Utils.py
blob: 49121e28e25e2806b12a8a9e5706a6fbd0f1ba35 (plain) (blame)
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
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
# Copyright (C) 1998-2018 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.


"""Miscellaneous essential routines.

This includes actual message transmission routines, address checking and
message and address munging, a handy-dandy routine to map a function on all
the mailing lists, and whatever else doesn't belong elsewhere.

"""

from __future__ import nested_scopes

import os
import sys
import re
import cgi
import time
import errno
import base64
import random
import urllib2
import urlparse
import htmlentitydefs
import email.Header
import email.Iterators
from email.Errors import HeaderParseError
from types import UnicodeType
from string import whitespace, digits
try:
    # Python 2.2
    from string import ascii_letters
except ImportError:
    # Older Pythons
    _lower = 'abcdefghijklmnopqrstuvwxyz'
    ascii_letters = _lower + _lower.upper()

from Mailman import mm_cfg
from Mailman import Errors
from Mailman import Site
from Mailman.SafeDict import SafeDict
from Mailman.Logging.Syslog import syslog

try:
    import hashlib
    md5_new = hashlib.md5
    sha_new = hashlib.sha1
except ImportError:
    import md5
    import sha
    md5_new = md5.new
    sha_new = sha.new

try:
    True, False
except NameError:
    True = 1
    False = 0

try:
    import dns.resolver
    from dns.exception import DNSException
    dns_resolver = True
except ImportError:
    dns_resolver = False

try:
    import ipaddress
    have_ipaddress = True
except ImportError:
    have_ipaddress = False

EMPTYSTRING = ''
UEMPTYSTRING = u''
CR = '\r'
NL = '\n'
DOT = '.'
IDENTCHARS = ascii_letters + digits + '_'

# Search for $(identifier)s strings, except that the trailing s is optional,
# since that's a common mistake
cre = re.compile(r'%\(([_a-z]\w*?)\)s?', re.IGNORECASE)
# Search for $$, $identifier, or ${identifier}
dre = re.compile(r'(\${2})|\$([_a-z]\w*)|\${([_a-z]\w*)}', re.IGNORECASE)



def list_exists(listname):
    """Return true iff list `listname' exists."""
    # The existance of any of the following file proves the list exists
    # <wink>: config.pck, config.pck.last, config.db, config.db.last
    #
    # The former two are for 2.1alpha3 and beyond, while the latter two are
    # for all earlier versions.
    #
    # But first ensure the list name doesn't contain a path traversal
    # attack.
    if len(re.sub(mm_cfg.ACCEPTABLE_LISTNAME_CHARACTERS, '', listname)) > 0:
        remote = os.environ.get('HTTP_FORWARDED_FOR',
                 os.environ.get('HTTP_X_FORWARDED_FOR',
                 os.environ.get('REMOTE_ADDR',
                                'unidentified origin')))
        syslog('mischief',
               'Hostile listname: listname=%s: remote=%s', listname, remote)
        return False
    basepath = Site.get_listpath(listname)
    for ext in ('.pck', '.pck.last', '.db', '.db.last'):
        dbfile = os.path.join(basepath, 'config' + ext)
        if os.path.exists(dbfile):
            return True
    return False


def list_names():
    """Return the names of all lists in default list directory."""
    # We don't currently support separate listings of virtual domains
    return Site.get_listnames()



# a much more naive implementation than say, Emacs's fill-paragraph!
def wrap(text, column=70, honor_leading_ws=True):
    """Wrap and fill the text to the specified column.

    Wrapping is always in effect, although if it is not possible to wrap a
    line (because some word is longer than `column' characters) the line is
    broken at the next available whitespace boundary.  Paragraphs are also
    always filled, unless honor_leading_ws is true and the line begins with
    whitespace.  This is the algorithm that the Python FAQ wizard uses, and
    seems like a good compromise.

    """
    wrapped = ''
    # first split the text into paragraphs, defined as a blank line
    paras = re.split('\n\n', text)
    for para in paras:
        # fill
        lines = []
        fillprev = False
        for line in para.split(NL):
            if not line:
                lines.append(line)
                continue
            if honor_leading_ws and line[0] in whitespace:
                fillthis = False
            else:
                fillthis = True
            if fillprev and fillthis:
                # if the previous line should be filled, then just append a
                # single space, and the rest of the current line
                lines[-1] = lines[-1].rstrip() + ' ' + line
            else:
                # no fill, i.e. retain newline
                lines.append(line)
            fillprev = fillthis
        # wrap each line
        for text in lines:
            while text:
                if len(text) <= column:
                    line = text
                    text = ''
                else:
                    bol = column
                    # find the last whitespace character
                    while bol > 0 and text[bol] not in whitespace:
                        bol -= 1
                    # now find the last non-whitespace character
                    eol = bol
                    while eol > 0 and text[eol] in whitespace:
                        eol -= 1
                    # watch out for text that's longer than the column width
                    if eol == 0:
                        # break on whitespace after column
                        eol = column
                        while eol < len(text) and text[eol] not in whitespace:
                            eol += 1
                        bol = eol
                        while bol < len(text) and text[bol] in whitespace:
                            bol += 1
                        bol -= 1
                    line = text[:eol+1] + '\n'
                    # find the next non-whitespace character
                    bol += 1
                    while bol < len(text) and text[bol] in whitespace:
                        bol += 1
                    text = text[bol:]
                wrapped += line
            wrapped += '\n'
            # end while text
        wrapped += '\n'
        # end for text in lines
    # the last two newlines are bogus
    return wrapped[:-2]



def QuotePeriods(text):
    JOINER = '\n .\n'
    SEP = '\n.\n'
    return JOINER.join(text.split(SEP))


# This takes an email address, and returns a tuple containing (user,host)
def ParseEmail(email):
    user = None
    domain = None
    email = email.lower()
    at_sign = email.find('@')
    if at_sign < 1:
        return email, None
    user = email[:at_sign]
    rest = email[at_sign+1:]
    domain = rest.split('.')
    return user, domain


def LCDomain(addr):
    "returns the address with the domain part lowercased"
    atind = addr.find('@')
    if atind == -1: # no domain part
        return addr
    return addr[:atind] + '@' + addr[atind+1:].lower()


# TBD: what other characters should be disallowed?
_badchars = re.compile(r'[][()<>|:;^,\\"\000-\037\177-\377]')
# Strictly speaking, some of the above are allowed in quoted local parts, but
# this can open the door to certain web exploits so we don't allow them.
# Only characters allowed in domain parts.
_valid_domain = re.compile('[-a-z0-9]', re.IGNORECASE)

def ValidateEmail(s):
    """Verify that an email address isn't grossly evil."""
    # If a user submits a form or URL with post data or query fragments
    # with multiple occurrences of the same variable, we can get a list
    # here.  Be as careful as possible.
    if isinstance(s, list) or isinstance(s, tuple):
        if len(s) == 0:
            s = ''
        else:
            s = s[-1]
    # Pretty minimal, cheesy check.  We could do better...
    if not s or s.count(' ') > 0:
        raise Errors.MMBadEmailError
    if _badchars.search(s):
        raise Errors.MMHostileAddress, s
    user, domain_parts = ParseEmail(s)
    # This means local, unqualified addresses, are not allowed
    if not domain_parts:
        raise Errors.MMBadEmailError, s
    if len(domain_parts) < 2:
        raise Errors.MMBadEmailError, s
    # domain parts may only contain ascii letters, digits and hyphen
    # and must not begin with hyphen.
    for p in domain_parts:
        if len(p) == 0 or p[0] == '-' or len(_valid_domain.sub('', p)) > 0:
            raise Errors.MMHostileAddress, s



# Patterns which may be used to form malicious path to inject a new
# line in the mailman error log. (TK: advisory by Moritz Naumann)
CRNLpat = re.compile(r'[^\x21-\x7e]')

def GetPathPieces(envar='PATH_INFO'):
    path = os.environ.get(envar)
    if path:
        if CRNLpat.search(path):
            path = CRNLpat.split(path)[0]
            remote = os.environ.get('HTTP_FORWARDED_FOR',
                     os.environ.get('HTTP_X_FORWARDED_FOR',
                     os.environ.get('REMOTE_ADDR',
                                    'unidentified origin')))
            syslog('error',
                'Warning: Possible malformed path attack domain=%s remote=%s',
                   get_domain(),
                   remote)
        return [p for p in path.split('/') if p]
    return None



def GetRequestMethod():
    return os.environ.get('REQUEST_METHOD')



def ScriptURL(target, web_page_url=None, absolute=False):
    """target - scriptname only, nothing extra
    web_page_url - the list's configvar of the same name
    absolute - a flag which if set, generates an absolute url
    """
    if web_page_url is None:
        web_page_url = mm_cfg.DEFAULT_URL_PATTERN % get_domain()
        if web_page_url[-1] <> '/':
            web_page_url = web_page_url + '/'
    fullpath = os.environ.get('REQUEST_URI')
    if fullpath is None:
        fullpath = os.environ.get('SCRIPT_NAME', '') + \
                   os.environ.get('PATH_INFO', '')
    baseurl = urlparse.urlparse(web_page_url)[2]
    if not absolute and fullpath.startswith(baseurl):
        # Use relative addressing
        fullpath = fullpath[len(baseurl):]
        i = fullpath.find('?')
        if i > 0:
            count = fullpath.count('/', 0, i)
        else:
            count = fullpath.count('/')
        path = ('../' * count) + target
    else:
        path = web_page_url + target
    return path + mm_cfg.CGIEXT



def GetPossibleMatchingAddrs(name):
    """returns a sorted list of addresses that could possibly match
    a given name.

    For Example, given scott@pobox.com, return ['scott@pobox.com'],
    given scott@blackbox.pobox.com return ['scott@blackbox.pobox.com',
                                           'scott@pobox.com']"""

    name = name.lower()
    user, domain = ParseEmail(name)
    res = [name]
    if domain:
        domain = domain[1:]
        while len(domain) >= 2:
            res.append("%s@%s" % (user, DOT.join(domain)))
            domain = domain[1:]
    return res



def List2Dict(L, foldcase=False):
    """Return a dict keyed by the entries in the list passed to it."""
    d = {}
    if foldcase:
        for i in L:
            d[i.lower()] = True
    else:
        for i in L:
            d[i] = True
    return d



_vowels = ('a', 'e', 'i', 'o', 'u')
_consonants = ('b', 'c', 'd', 'f', 'g', 'h', 'k', 'm', 'n',
               'p', 'r', 's', 't', 'v', 'w', 'x', 'z')
_syllables = []

for v in _vowels:
    for c in _consonants:
        _syllables.append(c+v)
        _syllables.append(v+c)
del c, v

def UserFriendly_MakeRandomPassword(length):
    syls = []
    while len(syls) * 2 < length:
        syls.append(random.choice(_syllables))
    return EMPTYSTRING.join(syls)[:length]


def Secure_MakeRandomPassword(length):
    bytesread = 0
    bytes = []
    fd = None
    try:
        while bytesread < length:
            try:
                # Python 2.4 has this on available systems.
                newbytes = os.urandom(length - bytesread)
            except (AttributeError, NotImplementedError):
                if fd is None:
                    try:
                        fd = os.open('/dev/urandom', os.O_RDONLY)
                    except OSError, e:
                        if e.errno <> errno.ENOENT:
                            raise
                        # We have no available source of cryptographically
                        # secure random characters.  Log an error and fallback
                        # to the user friendly passwords.
                        syslog('error',
                               'urandom not available, passwords not secure')
                        return UserFriendly_MakeRandomPassword(length)
                newbytes = os.read(fd, length - bytesread)
            bytes.append(newbytes)
            bytesread += len(newbytes)
        s = base64.encodestring(EMPTYSTRING.join(bytes))
        # base64 will expand the string by 4/3rds
        return s.replace('\n', '')[:length]
    finally:
        if fd is not None:
            os.close(fd)


def MakeRandomPassword(length=mm_cfg.MEMBER_PASSWORD_LENGTH):
    if mm_cfg.USER_FRIENDLY_PASSWORDS:
        return UserFriendly_MakeRandomPassword(length)
    return Secure_MakeRandomPassword(length)


def GetRandomSeed():
    chr1 = int(random.random() * 52)
    chr2 = int(random.random() * 52)
    def mkletter(c):
        if 0 <= c < 26:
            c += 65
        if 26 <= c < 52:
            #c = c - 26 + 97
            c += 71
        return c
    return "%c%c" % tuple(map(mkletter, (chr1, chr2)))



def set_global_password(pw, siteadmin=True):
    if siteadmin:
        filename = mm_cfg.SITE_PW_FILE
    else:
        filename = mm_cfg.LISTCREATOR_PW_FILE
    # rw-r-----
    omask = os.umask(026)
    try:
        fp = open(filename, 'w')
        fp.write(sha_new(pw).hexdigest() + '\n')
        fp.close()
    finally:
        os.umask(omask)


def get_global_password(siteadmin=True):
    if siteadmin:
        filename = mm_cfg.SITE_PW_FILE
    else:
        filename = mm_cfg.LISTCREATOR_PW_FILE
    try:
        fp = open(filename)
        challenge = fp.read()[:-1]                # strip off trailing nl
        fp.close()
    except IOError, e:
        if e.errno <> errno.ENOENT: raise
        # It's okay not to have a site admin password, just return false
        return None
    return challenge


def check_global_password(response, siteadmin=True):
    challenge = get_global_password(siteadmin)
    if challenge is None:
        return None
    return challenge == sha_new(response).hexdigest()



_ampre = re.compile('&amp;((?:#[0-9]+|[a-z]+);)', re.IGNORECASE)
def websafe(s, doubleescape=False):
    # If a user submits a form or URL with post data or query fragments
    # with multiple occurrences of the same variable, we can get a list
    # here.  Be as careful as possible.
    if isinstance(s, list) or isinstance(s, tuple):
        if len(s) == 0:
            s = ''
        else:
            s = s[-1]
    if mm_cfg.BROKEN_BROWSER_WORKAROUND:
        # Archiver can pass unicode here. Just skip them as the
        # archiver escapes non-ascii anyway.
        if isinstance(s, str):
            for k in mm_cfg.BROKEN_BROWSER_REPLACEMENTS:
                s = s.replace(k, mm_cfg.BROKEN_BROWSER_REPLACEMENTS[k])
    if doubleescape:
        return cgi.escape(s, quote=True)
    else:
        # Don't double escape html entities
        return _ampre.sub(r'&\1', cgi.escape(s, quote=True))


def nntpsplit(s):
    parts = s.split(':', 1)
    if len(parts) == 2:
        try:
            return parts[0], int(parts[1])
        except ValueError:
            pass
    # Use the defaults
    return s, 119



# Just changing these two functions should be enough to control the way
# that email address obscuring is handled.
def ObscureEmail(addr, for_text=False):
    """Make email address unrecognizable to web spiders, but invertable.

    When for_text option is set (not default), make a sentence fragment
    instead of a token."""
    if for_text:
        return addr.replace('@', ' at ')
    else:
        return addr.replace('@', '--at--')

def UnobscureEmail(addr):
    """Invert ObscureEmail() conversion."""
    # Contrived to act as an identity operation on already-unobscured
    # emails, so routines expecting obscured ones will accept both.
    return addr.replace('--at--', '@')



class OuterExit(Exception):
    pass

def findtext(templatefile, dict=None, raw=False, lang=None, mlist=None):
    # Make some text from a template file.  The order of searches depends on
    # whether mlist and lang are provided.  Once the templatefile is found,
    # string substitution is performed by interpolation in `dict'.  If `raw'
    # is false, the resulting text is wrapped/filled by calling wrap().
    #
    # When looking for a template in a specific language, there are 4 places
    # that are searched, in this order:
    #
    # 1. the list-specific language directory
    #    lists/<listname>/<language>
    #
    # 2. the domain-specific language directory
    #    templates/<list.host_name>/<language>
    #
    # 3. the site-wide language directory
    #    templates/site/<language>
    #
    # 4. the global default language directory
    #    templates/<language>
    #
    # The first match found stops the search.  In this way, you can specialize
    # templates at the desired level, or, if you use only the default
    # templates, you don't need to change anything.  You should never modify
    # files in the templates/<language> subdirectory, since Mailman will
    # overwrite these when you upgrade.  That's what the templates/site
    # language directories are for.
    #
    # A further complication is that the language to search for is determined
    # by both the `lang' and `mlist' arguments.  The search order there is
    # that if lang is given, then the 4 locations above are searched,
    # substituting lang for <language>.  If no match is found, and mlist is
    # given, then the 4 locations are searched using the list's preferred
    # language.  After that, the server default language is used for
    # <language>.  If that still doesn't yield a template, then the standard
    # distribution's English language template is used as an ultimate
    # fallback.  If that's missing you've got big problems. ;)
    #
    # A word on backwards compatibility: Mailman versions prior to 2.1 stored
    # templates in templates/*.{html,txt} and lists/<listname>/*.{html,txt}.
    # Those directories are no longer searched so if you've got customizations
    # in those files, you should move them to the appropriate directory based
    # on the above description.  Mailman's upgrade script cannot do this for
    # you.
    #
    # The function has been revised and renamed as it now returns both the
    # template text and the path from which it retrieved the template. The
    # original function is now a wrapper which just returns the template text
    # as before, by calling this renamed function and discarding the second
    # item returned.
    #
    # Calculate the languages to scan
    languages = []
    if lang is not None:
        languages.append(lang)
    if mlist is not None:
        languages.append(mlist.preferred_language)
    languages.append(mm_cfg.DEFAULT_SERVER_LANGUAGE)
    # Calculate the locations to scan
    searchdirs = []
    if mlist is not None:
        searchdirs.append(mlist.fullpath())
        searchdirs.append(os.path.join(mm_cfg.TEMPLATE_DIR, mlist.host_name))
    searchdirs.append(os.path.join(mm_cfg.TEMPLATE_DIR, 'site'))
    searchdirs.append(mm_cfg.TEMPLATE_DIR)
    # Start scanning
    fp = None
    try:
        for lang in languages:
            for dir in searchdirs:
                filename = os.path.join(dir, lang, templatefile)
                try:
                    fp = open(filename)
                    raise OuterExit
                except IOError, e:
                    if e.errno <> errno.ENOENT: raise
                    # Okay, it doesn't exist, keep looping
                    fp = None
    except OuterExit:
        pass
    if fp is None:
        # Try one last time with the distro English template, which, unless
        # you've got a really broken installation, must be there.
        try:
            filename = os.path.join(mm_cfg.TEMPLATE_DIR, 'en', templatefile)
            fp = open(filename)
        except IOError, e:
            if e.errno <> errno.ENOENT: raise
            # We never found the template.  BAD!
            raise IOError(errno.ENOENT, 'No template file found', templatefile)
    template = fp.read()
    fp.close()
    text = template
    if dict is not None:
        try:
            sdict = SafeDict(dict)
            try:
                text = sdict.interpolate(template)
            except UnicodeError:
                # Try again after coercing the template to unicode
                utemplate = unicode(template, GetCharSet(lang), 'replace')
                text = sdict.interpolate(utemplate)
        except (TypeError, ValueError), e:
            # The template is really screwed up
            syslog('error', 'broken template: %s\n%s', filename, e)
            pass
    if raw:
        return text, filename
    return wrap(text), filename


def maketext(templatefile, dict=None, raw=False, lang=None, mlist=None):
    return findtext(templatefile, dict, raw, lang, mlist)[0]



ADMINDATA = {
    # admin keyword: (minimum #args, maximum #args)
    'confirm':     (1, 1),
    'help':        (0, 0),
    'info':        (0, 0),
    'lists':       (0, 0),
    'options':     (0, 0),
    'password':    (2, 2),
    'remove':      (0, 0),
    'set':         (3, 3),
    'subscribe':   (0, 3),
    'unsubscribe': (0, 1),
    'who':         (0, 1),
    }

# Given a Message.Message object, test for administrivia (eg subscribe,
# unsubscribe, etc).  The test must be a good guess -- messages that return
# true get sent to the list admin instead of the entire list.
def is_administrivia(msg):
    linecnt = 0
    lines = []
    for line in email.Iterators.body_line_iterator(msg):
        # Strip out any signatures
        if line == '-- ':
            break
        if line.strip():
            linecnt += 1
        if linecnt > mm_cfg.DEFAULT_MAIL_COMMANDS_MAX_LINES:
            return False
        lines.append(line)
    bodytext = NL.join(lines)
    # See if the body text has only one word, and that word is administrivia
    if ADMINDATA.has_key(bodytext.strip().lower()):
        return True
    # Look at the first N lines and see if there is any administrivia on the
    # line.  BAW: N is currently hardcoded to 5.  str-ify the Subject: header
    # because it may be an email.Header.Header instance rather than a string.
    bodylines = lines[:5]
    subject = str(msg.get('subject', ''))
    bodylines.append(subject)
    for line in bodylines:
        if not line.strip():
            continue
        words = [word.lower() for word in line.split()]
        minargs, maxargs = ADMINDATA.get(words[0], (None, None))
        if minargs is None and maxargs is None:
            continue
        if minargs <= len(words[1:]) <= maxargs:
            # Special case the `set' keyword.  BAW: I don't know why this is
            # here.
            if words[0] == 'set' and words[2] not in ('on', 'off'):
                continue
            return True
    return False



def GetRequestURI(fallback=None, escape=True):
    """Return the full virtual path this CGI script was invoked with.

    Newer web servers seems to supply this info in the REQUEST_URI
    environment variable -- which isn't part of the CGI/1.1 spec.
    Thus, if REQUEST_URI isn't available, we concatenate SCRIPT_NAME
    and PATH_INFO, both of which are part of CGI/1.1.

    Optional argument `fallback' (default `None') is returned if both of
    the above methods fail.

    The url will be cgi escaped to prevent cross-site scripting attacks,
    unless `escape' is set to 0.
    """
    url = fallback
    if os.environ.has_key('REQUEST_URI'):
        url = os.environ['REQUEST_URI']
    elif os.environ.has_key('SCRIPT_NAME') and os.environ.has_key('PATH_INFO'):
        url = os.environ['SCRIPT_NAME'] + os.environ['PATH_INFO']
    if escape:
        return websafe(url)
    return url



# Wait on a dictionary of child pids
def reap(kids, func=None, once=False):
    while kids:
        if func:
            func()
        try:
            pid, status = os.waitpid(-1, os.WNOHANG)
        except OSError, e:
            # If the child procs had a bug we might have no children
            if e.errno <> errno.ECHILD:
                raise
            kids.clear()
            break
        if pid <> 0:
            try:
                del kids[pid]
            except KeyError:
                # Huh?  How can this happen?
                pass
        if once:
            break


def GetLanguageDescr(lang):
    return mm_cfg.LC_DESCRIPTIONS[lang][0]


def GetCharSet(lang):
    return mm_cfg.LC_DESCRIPTIONS[lang][1]

def GetDirection(lang):
    return mm_cfg.LC_DESCRIPTIONS[lang][2]

def IsLanguage(lang):
    return mm_cfg.LC_DESCRIPTIONS.has_key(lang)



def get_domain():
    host = os.environ.get('HTTP_HOST', os.environ.get('SERVER_NAME'))
    port = os.environ.get('SERVER_PORT')
    # Strip off the port if there is one
    if port and host.endswith(':' + port):
        host = host[:-len(port)-1]
    if mm_cfg.VIRTUAL_HOST_OVERVIEW and host:
        return websafe(host.lower())
    else:
        # See the note in Defaults.py concerning DEFAULT_URL
        # vs. DEFAULT_URL_HOST.
        hostname = ((mm_cfg.DEFAULT_URL
                     and urlparse.urlparse(mm_cfg.DEFAULT_URL)[1])
                     or mm_cfg.DEFAULT_URL_HOST)
        return hostname.lower()


def get_site_email(hostname=None, extra=None):
    if hostname is None:
        hostname = mm_cfg.VIRTUAL_HOSTS.get(get_domain(), get_domain())
    if extra is None:
        return '%s@%s' % (mm_cfg.MAILMAN_SITE_LIST, hostname)
    return '%s-%s@%s' % (mm_cfg.MAILMAN_SITE_LIST, extra, hostname)



# This algorithm crafts a guaranteed unique message-id.  The theory here is
# that pid+listname+host will distinguish the message-id for every process on
# the system, except when process ids wrap around.  To further distinguish
# message-ids, we prepend the integral time in seconds since the epoch.  It's
# still possible that we'll vend out more than one such message-id per second,
# so we prepend a monotonically incrementing serial number.  It's highly
# unlikely that within a single second, there'll be a pid wraparound.
_serial = 0
def unique_message_id(mlist):
    global _serial
    msgid = '<mailman.%d.%d.%d.%s@%s>' % (
        _serial, time.time(), os.getpid(),
        mlist.internal_name(), mlist.host_name)
    _serial += 1
    return msgid


# Figure out epoch seconds of midnight at the start of today (or the given
# 3-tuple date of (year, month, day).
def midnight(date=None):
    if date is None:
        date = time.localtime()[:3]
    # -1 for dst flag tells the library to figure it out
    return time.mktime(date + (0,)*5 + (-1,))



# Utilities to convert from simplified $identifier substitutions to/from
# standard Python $(identifier)s substititions.  The "Guido rules" for the
# former are:
#    $$ -> $
#    $identifier -> $(identifier)s
#    ${identifier} -> $(identifier)s

def to_dollar(s):
    """Convert from %-strings to $-strings."""
    s = s.replace('$', '$$').replace('%%', '%')
    parts = cre.split(s)
    for i in range(1, len(parts), 2):
        if parts[i+1] and parts[i+1][0] in IDENTCHARS:
            parts[i] = '${' + parts[i] + '}'
        else:
            parts[i] = '$' + parts[i]
    return EMPTYSTRING.join(parts)


def to_percent(s):
    """Convert from $-strings to %-strings."""
    s = s.replace('%', '%%').replace('$$', '$')
    parts = dre.split(s)
    for i in range(1, len(parts), 4):
        if parts[i] is not None:
            parts[i] = '$'
        elif parts[i+1] is not None:
            parts[i+1] = '%(' + parts[i+1] + ')s'
        else:
            parts[i+2] = '%(' + parts[i+2] + ')s'
    return EMPTYSTRING.join(filter(None, parts))


def dollar_identifiers(s):
    """Return the set (dictionary) of identifiers found in a $-string."""
    d = {}
    for name in filter(None, [b or c or None for a, b, c in dre.findall(s)]):
        d[name] = True
    return d


def percent_identifiers(s):
    """Return the set (dictionary) of identifiers found in a %-string."""
    d = {}
    for name in cre.findall(s):
        d[name] = True
    return d



# Utilities to canonicalize a string, which means un-HTML-ifying the string to
# produce a Unicode string or an 8-bit string if all the characters are ASCII.
def canonstr(s, lang=None):
    newparts = []
    parts = re.split(r'&(?P<ref>[^;]+);', s)
    def appchr(i):
        # do everything in unicode
        newparts.append(unichr(i))
    def tounicode(s):
        # We want the default fallback to be iso-8859-1 even if the language
        # is English (us-ascii).  This seems like a practical compromise so
        # that non-ASCII characters in names can be used in English lists w/o
        # having to change the global charset for English from us-ascii (which
        # I superstitiously think may have unintended consequences).
        if isinstance(s, unicode):
            return s
        if lang is None:
            charset = 'iso-8859-1'
        else:
            charset = GetCharSet(lang)
            if charset == 'us-ascii':
                charset = 'iso-8859-1'
        return unicode(s, charset, 'replace')
    while True:
        newparts.append(tounicode(parts.pop(0)))
        if not parts:
            break
        ref = parts.pop(0)
        if ref.startswith('#'):
            try:
                appchr(int(ref[1:]))
            except ValueError:
                # Non-convertable, stick with what we got
                newparts.append(tounicode('&'+ref+';'))
        else:
            c = htmlentitydefs.entitydefs.get(ref, '?')
            if c.startswith('#') and c.endswith(';'):
                appchr(int(ref[1:-1]))
            else:
                newparts.append(tounicode(c))
    newstr = EMPTYSTRING.join(newparts)
    # newstr is unicode
    return newstr


# The opposite of canonstr() -- sorta.  I.e. it attempts to encode s in the
# charset of the given language, which is the character set that the page will
# be rendered in, and failing that, replaces non-ASCII characters with their
# html references.  It always returns a byte string.
def uncanonstr(s, lang=None):
    if s is None:
        s = u''
    if lang is None:
        charset = 'us-ascii'
    else:
        charset = GetCharSet(lang)
    # See if the string contains characters only in the desired character
    # set.  If so, return it unchanged, except for coercing it to a byte
    # string.
    try:
        if isinstance(s, UnicodeType):
            return s.encode(charset)
        else:
            u = unicode(s, charset)
            return s
    except UnicodeError:
        # Nope, it contains funny characters, so html-ref it
        return uquote(s)


def uquote(s):
    a = []
    for c in s:
        o = ord(c)
        if o > 127:
            a.append('&#%3d;' % o)
        else:
            a.append(c)
    # Join characters together and coerce to byte string
    return str(EMPTYSTRING.join(a))


def oneline(s, cset):
    # Decode header string in one line and convert into specified charset
    try:
        h = email.Header.make_header(email.Header.decode_header(s))
        ustr = h.__unicode__()
        line = UEMPTYSTRING.join(ustr.splitlines())
        return line.encode(cset, 'replace')
    except (LookupError, UnicodeError, ValueError, HeaderParseError):
        # possibly charset problem. return with undecoded string in one line.
        return EMPTYSTRING.join(s.splitlines())


def strip_verbose_pattern(pattern):
    # Remove white space and comments from a verbose pattern and return a
    # non-verbose, equivalent pattern.  Replace CR and NL in the result
    # with '\\r' and '\\n' respectively to avoid multi-line results.
    if not isinstance(pattern, str):
        return pattern
    newpattern = ''
    i = 0
    inclass = False
    skiptoeol = False
    copynext = False
    while i < len(pattern):
        c = pattern[i]
        if copynext:
            if c == NL:
                newpattern += '\\n'
            elif c == CR:
                newpattern += '\\r'
            else:
                newpattern += c
            copynext = False
        elif skiptoeol:
            if c == NL:
                skiptoeol = False
        elif c == '#' and not inclass:
            skiptoeol = True
        elif c == '[' and not inclass:
            inclass = True
            newpattern += c
            copynext = True
        elif c == ']' and inclass:
            inclass = False
            newpattern += c
        elif re.search('\s', c):
            if inclass:
                if c == NL:
                    newpattern += '\\n'
                elif c == CR:
                    newpattern += '\\r'
                else:
                    newpattern += c
        elif c == '\\' and not inclass:
            newpattern += c
            copynext = True
        else:
            if c == NL:
                newpattern += '\\n'
            elif c == CR:
                newpattern += '\\r'
            else:
                newpattern += c
        i += 1
    return newpattern


# Patterns and functions to flag possible XSS attacks in HTML.
# This list is compiled from information at http://ha.ckers.org/xss.html,
# http://www.quirksmode.org/js/events_compinfo.html,
# http://www.htmlref.com/reference/appa/events1.htm,
# http://lxr.mozilla.org/mozilla/source/content/events/src/nsDOMEvent.cpp#59,
# http://www.w3.org/TR/DOM-Level-2-Events/events.html and
# http://www.xulplanet.com/references/elemref/ref_EventHandlers.html
# Many thanks are due to Moritz Naumann for his assistance with this.
_badwords = [
    '<i?frame',
    # Kludge to allow the specific tag that's in the options.html template.
    '<link(?! rel="SHORTCUT ICON" href="<mm-favicon>">)',
    '<meta',
    '<object',
    '<script',
    '@keyframes',
    r'\bj(?:ava)?script\b',
    r'\bvbs(?:cript)?\b',
    r'\bdomactivate\b',
    r'\bdomattrmodified\b',
    r'\bdomcharacterdatamodified\b',
    r'\bdomfocus(?:in|out)\b',
    r'\bdommenuitem(?:in)?active\b',
    r'\bdommousescroll\b',
    r'\bdomnodeinserted(?:intodocument)?\b',
    r'\bdomnoderemoved(?:fromdocument)?\b',
    r'\bdomsubtreemodified\b',
    r'\bfscommand\b',
    r'\bonabort\b',
    r'\bon(?:de)?activate\b',
    r'\bon(?:after|before)print\b',
    r'\bon(?:after|before)update\b',
    r'\b(?:on)?animation(?:end|iteration|start)\b',
    r'\bonbefore(?:(?:de)?activate|copy|cut|editfocus|paste)\b',
    r'\bonbeforeunload\b',
    r'\bonbegin\b',
    r'\bonblur\b',
    r'\bonbounce\b',
    r'\bonbroadcast\b',
    r'\boncanplay(?:through)?\b',
    r'\bon(?:cell)?change\b',
    r'\boncheckboxstatechange\b',
    r'\bon(?:dbl)?click\b',
    r'\bonclose\b',
    r'\boncommand(?:update)?\b',
    r'\boncomposition(?:end|start)\b',
    r'\boncontextmenu\b',
    r'\boncontrolselect\b',
    r'\boncopy\b',
    r'\boncut\b',
    r'\bondataavailable\b',
    r'\bondataset(?:changed|complete)\b',
    r'\bondrag(?:drop|end|enter|exit|gesture|leave|over)?\b',
    r'\bondragstart\b',
    r'\bondrop\b',
    r'\bondurationchange\b',
    r'\bonemptied\b',
    r'\bonend(?:ed)?\b',
    r'\bonerror(?:update)?\b',
    r'\bonfilterchange\b',
    r'\bonfinish\b',
    r'\bonfocus(?:in|out)?\b',
    r'\bonhelp\b',
    r'\boninput\b',
    r'\bonkey(?:up|down|press)\b',
    r'\bonlayoutcomplete\b',
    r'\bon(?:un)?load\b',
    r'\bonloaded(?:meta)?data\b',
    r'\bonloadstart\b',
    r'\bonlosecapture\b',
    r'\bonmedia(?:complete|error)\b',
    r'\bonmessage\b',
    r'\bonmouse(?:down|enter|leave|move|out|over|up|wheel)\b',
    r'\bonmove(?:end|start)?\b',
    r'\bon(?:off|on)line\b',
    r'\bonopen\b',
    r'\bonoutofsync\b',
    r'\bonoverflow(?:changed)?\b',
    r'\bonpage(?:hide|show)\b',
    r'\bonpaint\b',
    r'\bonpaste\b',
    r'\bonpause\b',
    r'\bonplay(?:ing)?\b',
    r'\bonpopstate\b',
    r'\bonpopup(?:hidden|hiding|showing|shown)\b',
    r'\bonprogress\b',
    r'\bonpropertychange\b',
    r'\bonradiostatechange\b',
    r'\bonratechange\b',
    r'\bonreadystatechange\b',
    r'\bonrepeat\b',
    r'\bonreset\b',
    r'\bonresize(?:end|start)?\b',
    r'\bonresume\b',
    r'\bonreverse\b',
    r'\bonrow(?:delete|enter|exit|inserted)\b',
    r'\bonrows(?:delete|enter|inserted)\b',
    r'\bonscroll\b',
    r'\bonsearch\b',
    r'\bonseek(?:ed|ing)?\b',
    r'\bonselect(?:start)?\b',
    r'\bonselectionchange\b',
    r'\bonshow\b',
    r'\bonstart\b',
    r'\bonstalled\b',
    r'\bonstop\b',
    r'\bonstorage\b',
    r'\bonsubmit\b',
    r'\bonsuspend\b',
    r'\bonsync(?:from|to)preference\b',
    r'\bonsyncrestored\b',
    r'\bontext\b',
    r'\bontime(?:error|update)\b',
    r'\bontoggle\b',
    r'\bontouch(?:cancel|end|move|start)\b',
    r'\bontrackchange\b',
    r'\b(?:on)?transitionend\b',
    r'\bonunderflow\b',
    r'\bonurlflip\b',
    r'\bonvolumechange\b',
    r'\bonwaiting\b',
    r'\bonwheel\b',
    r'\bseeksegmenttime\b',
    r'\bsvgabort\b',
    r'\bsvgerror\b',
    r'\bsvgload\b',
    r'\bsvgresize\b',
    r'\bsvgscroll\b',
    r'\bsvgunload\b',
    r'\bsvgzoom\b',
    ]


# This is the actual re to look for the above patterns
_badhtml = re.compile('|'.join(_badwords), re.IGNORECASE)
# This is used to filter non-printable us-ascii characters, some of which
# can be used to break words to avoid recognition.
_filterchars = re.compile('[\000-\011\013\014\016-\037\177-\237]')
# This is used to recognize '&#' and '%xx' strings for _translate which
# translates them to characters
_encodedchars = re.compile('(&#[0-9]+;?)|(&#x[0-9a-f]+;?)|(%[0-9a-f]{2})',
                           re.IGNORECASE)


def _translate(mo):
    """Translate &#... and %xx encodings into the encoded character."""
    match = mo.group().lower().strip('&#;')
    try:
        if match.startswith('x') or match.startswith('%'):
            val = int(match[1:], 16)
        else:
            val = int(match, 10)
    except ValueError:
        return ''
    if val < 256:
        return chr(val)
    else:
        return ''


def suspiciousHTML(html):
    """Check HTML string for various tags, script language names and
    'onxxx' actions that can be used in XSS attacks.
    Currently, this a very simple minded test.  It just looks for
    patterns without analyzing context.  Thus, it potentially flags lots
    of benign stuff.
    Returns True if anything suspicious found, False otherwise.
    """

    if _badhtml.search(_filterchars.sub(
                       '', _encodedchars.sub(_translate, html))):
        return True
    else:
        return False


# The next functions read data from
# https://publicsuffix.org/list/public_suffix_list.dat and implement the
# algorithm at https://publicsuffix.org/list/ to find the "Organizational
# Domain corresponding to a From: domain.

s_dict = {}

def get_suffixes(url):
    """This loads and parses the data from the url argument into s_dict for
    use by get_org_dom."""
    global s_dict
    if s_dict:
        return
    if not url:
        return
    try:
        d = urllib2.urlopen(url)
    except urllib2.URLError, e:
        syslog('error',
               'Unable to retrieve data from %s: %s',
               url, e)
        return
    for line in d.readlines():
        if not line.strip() or line.startswith(' ') or line.startswith('//'):
            continue
        line = re.sub(' .*', '', line.strip())
        if not line:
            continue
        parts = line.lower().split('.')
        if parts[0].startswith('!'):
            exc = True
            parts = [parts[0][1:]] + parts[1:]
        else:
            exc = False
        parts.reverse()
        k = '.'.join(parts)
        s_dict[k] = exc

def _get_dom(d, l):
    """A helper to get a domain name consisting of the first l+1 labels
    in d."""
    dom = d[:min(l+1, len(d))]
    dom.reverse()
    return '.'.join(dom)

def get_org_dom(domain):
    """Given a domain name, this returns the corresponding Organizational
    Domain which may be the same as the input."""
    global s_dict
    if not s_dict:
        get_suffixes(mm_cfg.DMARC_ORGANIZATIONAL_DOMAIN_DATA_URL)
    hits = []
    d = domain.lower().split('.')
    d.reverse()
    for k in s_dict.keys():
        ks = k.split('.')
        if len(d) >= len(ks):
            for i in range(len(ks)-1):
                if d[i] != ks[i] and ks[i] != '*':
                    break
            else:
                if d[len(ks)-1] == ks[-1] or ks[-1] == '*':
                    hits.append(k)
    if not hits:
        return _get_dom(d, 1)
    l = 0
    for k in hits:
        if s_dict[k]:
            # It's an exception
            return _get_dom(d, len(k.split('.'))-1)
        if len(k.split('.')) > l:
            l = len(k.split('.'))
    return _get_dom(d, l)


# This takes an email address, and returns True if DMARC policy is p=reject
# or possibly quarantine.
def IsDMARCProhibited(mlist, email):
    if not dns_resolver:
        # This is a problem; log it.
        syslog('error',
            'DNS lookup for dmarc_moderation_action for list %s not available',
            mlist.real_name)
        return False

    email = email.lower()
    # Scan from the right in case quoted local part has an '@'.
    at_sign = email.rfind('@')
    if at_sign < 1:
        return False
    f_dom = email[at_sign+1:]
    x = _DMARCProhibited(mlist, email, '_dmarc.' + f_dom)
    if x != 'continue':
        return x
    o_dom = get_org_dom(f_dom)
    if o_dom != f_dom:
        x = _DMARCProhibited(mlist, email, '_dmarc.' + o_dom, org=True)
        if x != 'continue':
            return x
    return False

def _DMARCProhibited(mlist, email, dmarc_domain, org=False):

    try:
        resolver = dns.resolver.Resolver()
        resolver.timeout = float(mm_cfg.DMARC_RESOLVER_TIMEOUT)
        resolver.lifetime = float(mm_cfg.DMARC_RESOLVER_LIFETIME)
        txt_recs = resolver.query(dmarc_domain, dns.rdatatype.TXT)
    except (dns.resolver.NXDOMAIN, dns.resolver.NoAnswer):
        return 'continue'
    except (dns.resolver.NoNameservers):
        syslog('error',
               'DNSException: No Nameservers available for %s (%s)',
               email, dmarc_domain)
        # Typically this means a dnssec validation error.  Clients that don't
        # perform validation *may* successfully see a _dmarc RR whereas a
        # validating mailman server won't see the _dmarc RR.  We should
        # mitigate this email to be safe.
        return True
    except DNSException, e:
        syslog('error',
               'DNSException: Unable to query DMARC policy for %s (%s). %s',
               email, dmarc_domain, e.__doc__)
        # While we can't be sure what caused the error, there is potentially
        # a DMARC policy record that we missed and that a receiver of the mail
        # might see.  Thus, we should err on the side of caution and mitigate.
        return True
    else:
        # Be as robust as possible in parsing the result.
        results_by_name = {}
        cnames = {}
        want_names = set([dmarc_domain + '.'])
        for txt_rec in txt_recs.response.answer:
            if txt_rec.rdtype == dns.rdatatype.CNAME:
                cnames[txt_rec.name.to_text()] = (
                    txt_rec.items[0].target.to_text())
            if txt_rec.rdtype != dns.rdatatype.TXT:
                continue
            results_by_name.setdefault(txt_rec.name.to_text(), []).append(
                "".join(txt_rec.items[0].strings))
        expands = list(want_names)
        seen = set(expands)
        while expands:
            item = expands.pop(0)
            if item in cnames:
                if cnames[item] in seen:
                    continue # cname loop
                expands.append(cnames[item])
                seen.add(cnames[item])
                want_names.add(cnames[item])
                want_names.discard(item)

        if len(want_names) != 1:
            syslog('error',
                   """multiple DMARC entries in results for %s,
                   processing each to be strict""",
                   dmarc_domain)
        for name in want_names:
            if name not in results_by_name:
                continue
            dmarcs = filter(lambda n: n.startswith('v=DMARC1;'),
                            results_by_name[name])
            if len(dmarcs) == 0:
                return 'continue'
            if len(dmarcs) > 1:
                syslog('error',
                       """RRset of TXT records for %s has %d v=DMARC1 entries;
                       testing them all""",
                        dmarc_domain, len(dmarcs))
            for entry in dmarcs:
                mo = re.search(r'\bsp=(\w*)\b', entry, re.IGNORECASE)
                if org and mo:
                    policy = mo.group(1).lower()
                else:
                    mo = re.search(r'\bp=(\w*)\b', entry, re.IGNORECASE)
                    if mo:
                        policy = mo.group(1).lower()
                    else:
                        continue
                if policy == 'reject':
                    syslog('vette',
                      '%s: DMARC lookup for %s (%s) found p=reject in %s = %s',
                      mlist.real_name,  email, dmarc_domain, name, entry)
                    return True

                if (mlist.dmarc_quarantine_moderation_action and
                    policy == 'quarantine'):
                    syslog('vette',
                  '%s: DMARC lookup for %s (%s) found p=quarantine in %s = %s',
                          mlist.real_name,  email, dmarc_domain, name, entry)
                    return True

                if (mlist.dmarc_none_moderation_action and
                    mlist.dmarc_quarantine_moderation_action and
                    mlist.dmarc_moderation_action in (1, 2) and
                    policy == 'none'):
                    syslog('vette',
                  '%s: DMARC lookup for %s (%s) found p=none in %s = %s',
                          mlist.real_name,  email, dmarc_domain, name, entry)
                    return True

    return False


# Check a known list in order to auto-moderate verbose members
# dictionary to remember recent posts.
recentMemberPostings = {}
# counter of times through
clean_count = 0
def IsVerboseMember(mlist, email):
    """For lists that request it, we keep track of recent posts by address.
A message from an address to a list, if the list requests it, is remembered
for a specified time whether or not the address is a list member, and if the
address is a member and the member is over the threshold for the list, that
fact is returned."""

    global clean_count

    if mlist.member_verbosity_threshold == 0:
        return False

    email = email.lower()

    now = time.time()
    recentMemberPostings.setdefault(email,[]).append(now +
                                       float(mlist.member_verbosity_interval)
                                   )
    x = range(len(recentMemberPostings[email]))
    x.reverse()
    for i in x:
        if recentMemberPostings[email][i] < now:
            del recentMemberPostings[email][i]

    clean_count += 1
    if clean_count >= mm_cfg.VERBOSE_CLEAN_LIMIT:
        clean_count = 0
        for addr in recentMemberPostings.keys():
            x = range(len(recentMemberPostings[addr]))
            x.reverse()
            for i in x:
                if recentMemberPostings[addr][i] < now:
                    del recentMemberPostings[addr][i]
            if not recentMemberPostings[addr]:
                del recentMemberPostings[addr]
    if not mlist.isMember(email):
        return False
    return (len(recentMemberPostings.get(email, [])) >
                mlist.member_verbosity_threshold
           )


def check_eq_domains(email, domains_list):
    """The arguments are an email address and a string representing a
    list of lists in a form like 'a,b,c;1,2' representing [['a', 'b',
    'c'],['1', '2']].  The inner lists are domains which are
    equivalent in some sense.  The return is an empty list or a list
    of email addresses equivalent to the first argument.
    For example, given

    email = 'user@me.com'
    domains_list = '''domain1, domain2; mac.com, me.com, icloud.com;
                   domaina, domainb
                   '''

    check_eq_domains(email, domains_list) will return
    ['user@mac.com', 'user@icloud.com']
    """
    if not domains_list:
        return []
    try:
        local, domain = email.rsplit('@', 1)
    except ValueError:
        return []
    domain = domain.lower()
    domains_list = re.sub('\s', '', domains_list).lower()
    domains = domains_list.split(';')
    domains_list = []
    for d in domains:
        domains_list.append(d.split(','))
    for domains in domains_list:
        if domain in domains:
            return [local + '@' + x for x in domains if x != domain]
    return []


def _invert_xml(mo):
    # This is used with re.sub below to convert XML char refs and textual \u
    # escapes to unicodes.
    try:
        if mo.group(1)[:1] == '#':
            return unichr(int(mo.group(1)[1:]))
        elif mo.group(1)[:1].lower() == 'u':
            return unichr(int(mo.group(1)[1:], 16))
        else:
            return(u'\ufffd')
    except ValueError:
        # Value is out of range.  Return the unicode replace character.
        return(u'\ufffd')


def xml_to_unicode(s, cset):
    """This converts a string s, encoded in cset to a unicode with translation
    of XML character references and textual \uxxxx escapes.  It is more or less
    the inverse of unicode.decode(cset, errors='xmlcharrefreplace').  It is
    similar to canonstr above except for replacing invalid refs with the
    unicode replace character and recognizing \u escapes.
    """
    if isinstance(s, str):
        us = s.decode(cset, 'replace')
        us = re.sub(u'&(#[0-9]+);', _invert_xml, us)
        us = re.sub(u'(?i)\\\\(u[a-f0-9]{4})', _invert_xml, us)
        return us
    else:
        return s

def banned_ip(ip):
    if not dns_resolver:
        return False
    if have_ipaddress:
        try:
            uip = unicode(ip, encoding='us-ascii', errors='replace')
            ptr = ipaddress.ip_address(uip).reverse_pointer
        except ValueError:
            return False
	lookup = '{0}.zen.spamhaus.org'.format('.'.join(ptr.split('.')[:-2]))
    else:
        parts = ip.split('.')
        if len(parts) != 4:
            return False
        lookup = '{0}.{1}.{2}.{3}.zen.spamhaus.org'.format(parts[3],
                                                           parts[2],
                                                           parts[1],
                                                           parts[0])
    resolver = dns.resolver.Resolver()
    try:
        ans = resolver.query(lookup, dns.rdatatype.A)
    except DNSException:
        return False
    if not ans:
        return False
    text = ans.rrset.to_text()
    if re.search(r'127\.0\.0\.[2-7]$', text, re.MULTILINE):
        return True
    return False

def banned_domain(email):
    if not dns_resolver:
        return False

    email = email.lower()
    user, domain = ParseEmail(email)

    lookup = '%s.dbl.spamhaus.org' % (domain)

    resolver = dns.resolver.Resolver()
    try:
        ans = resolver.query(lookup, dns.rdatatype.A)
    except DNSException:
        return False
    if not ans:
        return False
    text = ans.rrset.to_text()
    if re.search(r'127\.0\.1\.\d{1,3}$', text, re.MULTILINE):
        if not re.search(r'127\.0\.1\.255$', text, re.MULTILINE):
            return True
    return False