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
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
|
--[[
Copyright (c) 2015, Vsevolod Stakhov <vsevolod@highsecure.ru>
Licensed under the Apache License, Version 2.0 (the "License");
you may not use this file except in compliance with the License.
You may obtain a copy of the License at
http://www.apache.org/licenses/LICENSE-2.0
Unless required by applicable law or agreed to in writing, software
distributed under the License is distributed on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
See the License for the specific language governing permissions and
limitations under the License.
]]--
-- This plugin is intended to read and parse spamassassin rules with regexp
-- rules. SA plugins or statistics are not supported
local rspamd_logger = require "rspamd_logger"
local rspamd_regexp = require "rspamd_regexp"
local rspamd_expression = require "rspamd_expression"
local rspamd_mempool = require "rspamd_mempool"
local rspamd_trie = require "rspamd_trie"
local util = require "rspamd_util"
require "fun" ()
-- Known plugins
local known_plugins = {
'Mail::SpamAssassin::Plugin::FreeMail',
'Mail::SpamAssassin::Plugin::HeaderEval',
'Mail::SpamAssassin::Plugin::ReplaceTags',
'Mail::SpamAssassin::Plugin::RelayEval',
'Mail::SpamAssassin::Plugin::MIMEEval',
'Mail::SpamAssassin::Plugin::BodyEval',
'Mail::SpamAssassin::Plugin::MIMEHeader',
'Mail::SpamAssassin::Plugin::WLBLEval',
}
-- Table that replaces SA symbol with rspamd equialent
-- Used for dependency resolution
local symbols_replacements = {
-- SPF replacements
USER_IN_SPF_WHITELIST = 'WHITELIST_SPF',
USER_IN_DEF_SPF_WL = 'WHITELIST_SPF',
SPF_PASS = 'R_SPF_ALLOW',
SPF_FAIL = 'R_SPF_FAIL',
SPF_SOFTFAIL = 'R_SPF_SOFTFAIL',
SPF_HELO_PASS = 'R_SPF_ALLOW',
SPF_HELLO_FAIL = 'R_SPF_FAIL',
SPF_HELLO_SOFTFAIL = 'R_SPF_SOFTFAIL',
-- DKIM replacements
USER_IN_DKIM_WHITELIST = 'WHITELIST_DKIM',
USER_IN_DEF_DKIM_WL = 'WHITELIST_DKIM',
DKIM_VALID = 'R_DKIM_ALLOW',
-- SURBL replacements
URIBL_SBL_A = 'URIBL_SBL',
URIBL_DBL_SPAM = 'DBL_SPAM',
URIBL_DBL_PHISH = 'DBL_PHISH',
URIBL_DBL_MALWARE = 'DBL_MALWARE',
URIBL_DBL_BOTNETCC = 'DBL_BOTNET',
URIBL_DBL_ABUSE_SPAM = 'DBL_ABUSE',
URIBL_DBL_ABUSE_REDIR = 'DBL_ABUSE_REDIR',
URIBL_DBL_ABUSE_MALW = 'DBL_ABUSE_MALWARE',
URIBL_DBL_ABUSE_BOTCC = 'DBL_ABUSE_BOTNET',
URIBL_WS_SURBL = 'WS_SURBL_MULTI',
URIBL_PH_SURBL = 'PH_SURBL_MULTI',
URIBL_MW_SURBL = 'MW_SURBL_MULTI',
URIBL_CR_SURBL = 'CRACKED_SURBL',
URIBL_ABUSE_SURBL = 'ABUSE_SURBL',
-- Misc rules
BODY_URI_ONLY = 'R_EMPTY_IMAGE',
HTML_IMAGE_ONLY_04 = 'HTML_SHORT_LINK_IMG_1',
HTML_IMAGE_ONLY_08 = 'HTML_SHORT_LINK_IMG_1',
HTML_IMAGE_ONLY_12 = 'HTML_SHORT_LINK_IMG_1',
HTML_IMAGE_ONLY_16 = 'HTML_SHORT_LINK_IMG_2',
HTML_IMAGE_ONLY_20 = 'HTML_SHORT_LINK_IMG_2',
HTML_IMAGE_ONLY_24 = 'HTML_SHORT_LINK_IMG_3',
HTML_IMAGE_ONLY_28 = 'HTML_SHORT_LINK_IMG_3',
HTML_IMAGE_ONLY_32 = 'HTML_SHORT_LINK_IMG_3',
}
-- Internal variables
local rules = {}
local atoms = {}
local metas = {}
local scores = {}
local scores_added = {}
local external_deps = {}
local freemail_domains = {}
local pcre_only_regexps = {}
local freemail_trie
local sa_mempool = rspamd_mempool.create()
local replace = {
tags = {},
pre = {},
inter = {},
post = {},
rules = {},
}
local internal_regexp = {
date_shift = rspamd_regexp.create("^\\(\\s*'((?:-?\\d+)|(?:undef))'\\s*,\\s*'((?:-?\\d+)|(?:undef))'\\s*\\)$")
}
-- Mail::SpamAssassin::Plugin::WLBLEval plugin
local sa_lists = {
from_blacklist = {},
from_whitelist = {},
from_def_whitelist = {},
to_blacklist = {},
to_whitelist = {},
elts = 0,
}
local func_cache = {}
local section = rspamd_config:get_all_opt("spamassassin")
if not (section and type(section) == 'table') then
rspamd_logger.info('Module is unconfigured')
elseif section['enabled'] == false then
rspamd_logger.info('Module is disabled')
return
end
-- Minimum score to treat symbols as meta
local meta_score_alpha = 0.5
-- Maximum size of regexp checked
local match_limit = 0
local function split(str, delim)
local result = {}
if not delim then
delim = '[^%s]+'
end
for token in string.gmatch(str, delim) do
table.insert(result, token)
end
return result
end
local function replace_symbol(s)
local rspamd_symbol = symbols_replacements[s]
if not rspamd_symbol then
return s, false
end
return rspamd_symbol, true
end
local function trim(s)
return s:match "^%s*(.-)%s*$"
end
local function is_pcre_only(name)
if pcre_only_regexps[name] then
return true
end
return false
end
local function handle_header_def(hline, cur_rule)
--Now check for modifiers inside header's name
local hdrs = split(hline, '[^|]+')
local hdr_params = {}
local cur_param = {}
-- Check if an re is an ordinary re
local ordinary = true
for i,h in ipairs(hdrs) do
if h == 'ALL' or h == 'ALL:raw' then
ordinary = false
cur_rule['type'] = 'function'
-- Pack closure
local re = cur_rule['re']
local not_f = cur_rule['not']
local sym = cur_rule['symbol']
-- Rule to match all headers
rspamd_config:register_regexp({
re = re,
type = 'allheader',
pcre_only = is_pcre_only(cur_rule['symbol']),
})
cur_rule['function'] = function(task)
if not re then
rspamd_logger.errx(task, 're is missing for rule %1', h)
return 0
end
return task:process_regexp(re, 'allheader')
end
else
local args = split(h, '[^:]+')
cur_param['strong'] = false
cur_param['raw'] = false
cur_param['header'] = args[1]
if args[2] then
-- We have some ops that are required for the header, so it's not ordinary
ordinary = false
end
each(function(func)
if func == 'addr' then
cur_param['function'] = function(str)
local addr_parsed = util.parse_addr(str)
local ret = {}
if addr_parsed then
for i,elt in ipairs(addr_parsed) do
if elt['addr'] then
table.insert(ret, elt['addr'])
end
end
end
return ret
end
elseif func == 'name' then
cur_param['function'] = function(str)
local addr_parsed = util.parse_addr(str)
local ret = {}
if addr_parsed then
for i,elt in ipairs(addr_parsed) do
if elt['name'] then
table.insert(ret, elt['name'])
end
end
end
return ret
end
elseif func == 'raw' then
cur_param['raw'] = true
elseif func == 'case' then
cur_param['strong'] = true
else
rspamd_logger.warnx(rspamd_config, 'Function %1 is not supported in %2',
func, cur_rule['symbol'])
end
end, tail(args))
local function split_hdr_param(param, headers)
for i,h in ipairs(headers) do
local nparam = {}
for k,v in pairs(param) do
if k ~= 'header' then
nparam[k] = v
end
end
nparam['header'] = h
table.insert(hdr_params, nparam)
end
end
-- Some header rules require splitting to check of multiple headers
if cur_param['header'] == 'MESSAGEID' then
-- Special case for spamassassin
ordinary = false
split_hdr_param(cur_param, {
'Message-ID',
'X-Message-ID',
'Resent-Message-ID'})
elseif cur_param['header'] == 'ToCc' then
ordinary = false
split_hdr_param(cur_param, { 'To', 'Cc', 'Bcc' })
else
table.insert(hdr_params, cur_param)
end
end
cur_rule['ordinary'] = ordinary
cur_rule['header'] = hdr_params
end
end
local function freemail_search(input)
local res = 0
local function trie_callback(number, pos)
rspamd_logger.debugx('Matched pattern %1 at pos %2', freemail_domains[number], pos)
res = res + 1
end
if input then
freemail_trie:match(input, trie_callback, true)
end
return res
end
local function gen_eval_rule(arg)
local eval_funcs = {
{'check_freemail_from', function(task, remain)
local from = task:get_from('mime')
if from and from[1] then
return freemail_search(string.lower(from[1]['addr']))
end
return 0
end},
{'check_freemail_replyto',
function(task, remain)
return freemail_search(task:get_header('Reply-To'))
end
},
{'check_freemail_header',
function(task, remain)
-- Remain here contains one or two args: header and regexp to match
local arg = string.match(remain, "^%(%s*['\"]([^%s]+)['\"]%s*%)$")
local re = nil
if not arg then
arg, re = string.match(remain, "^%(%s*['\"]([^%s]+)['\"]%s*,%s*['\"]([^%s]+)['\"]%s*%)$")
end
if arg then
local h
if arg == 'EnvelopeFrom' then
h = task:get_from('smtp')
if h then h = h[1]['addr'] end
else
h = task:get_header(arg)
end
if h then
local hdr_freemail = freemail_search(string.lower(h))
if hdr_freemail > 0 and re then
local r = rspamd_regexp.create_cached(re)
if r then
if r:match(h) then
return 1
end
else
rspamd_logger.infox(rspamd_config, 'cannot create regexp %1', re)
return 0
end
end
return hdr_freemail
end
end
return 0
end
},
{
'check_for_missing_to_header',
function (task, remain)
local th = task:get_recipients('mime')
if not th or #th == 0 then
return 1
end
return 0
end
},
{
'check_relays_unparseable',
function(task, remain)
local rh_mime = task:get_header_full('Received')
local rh_parsed = task:get_received_headers()
local rh_cnt = 0
if rh_mime then rh_cnt = #rh_mime end
local parsed_cnt = 0
if rh_parsed then parsed_cnt = #rh_parsed end
return rh_cnt - parsed_cnt
end
},
{
'check_for_shifted_date',
function (task, remain)
-- Remain here contains two args: start and end hours shift
local matches = internal_regexp['date_shift']:search(remain, true, true)
if matches and matches[1] then
local min_diff = matches[1][2]
local max_diff = matches[1][3]
if min_diff == 'undef' then
min_diff = 0
else
min_diff = tonumber(min_diff) * 3600
end
if max_diff == 'undef' then
max_diff = 0
else
max_diff = tonumber(max_diff) * 3600
end
-- Now get the difference between Date and message received date
local dm = task:get_date { format = 'message', gmt = true}
local dt = task:get_date { format = 'connect', gmt = true}
local diff = dm - dt
if (max_diff == 0 and diff >= min_diff) or
(min_diff == 0 and diff <= max_diff) or
(diff >= min_diff and diff <= max_diff) then
return 1
end
end
return 0
end
},
{
'check_for_mime',
function(task, remain)
local arg = string.match(remain, "^%(%s*['\"]([^%s]+)['\"]%s*%)$")
if arg then
if arg == 'mime_attachment' then
local parts = task:get_parts()
if parts then
for i,p in ipairs(parts) do
if p:get_filename() then
return 1
end
end
end
else
rspamd_logger.infox(task, 'unimplemented mime check %1', arg)
end
end
return 0
end
},
{
'check_from_in_blacklist',
function(task, remain)
local from = task:get_from('mime')
if from and from[1] and from[1]['addr'] then
if sa_lists['from_blacklist'][string.lower(from[1]['addr'])] then
return 1
end
end
return 0
end
},
{
'check_from_in_whitelist',
function(task, remain)
local from = task:get_from('mime')
if from and from[1] and from[1]['addr'] then
if sa_lists['from_whitelist'][string.lower(from[1]['addr'])] then
return 1
end
end
return 0
end
},
{
'check_from_in_default_whitelist',
function(task, remain)
local from = task:get_from('mime')
if from and from[1] and from[1]['addr'] then
if sa_lists['from_def_whitelist'][string.lower(from[1]['addr'])] then
return 1
end
end
return 0
end
},
{
'check_to_in_blacklist',
function(task, remain)
local rcpt = task:get_recipients('mime')
if rcpt then
for i,r in ipairs(rcpt) do
if sa_lists['to_blacklist'][string.lower(r['addr'])] then
return 1
end
end
end
return 0
end
},
{
'check_to_in_whitelist',
function(task, remain)
local rcpt = task:get_recipients('mime')
if rcpt then
for i,r in ipairs(rcpt) do
if sa_lists['to_whitelist'][string.lower(r['addr'])] then
return 1
end
end
end
return 0
end
},
}
for k,f in ipairs(eval_funcs) do
local pat = string.format('^%s', f[1])
local first,last = string.find(arg, pat)
if first then
local func_arg = string.sub(arg, last + 1)
return function(task)
return f[2](task, func_arg)
end
end
end
end
-- Returns parser function or nil
local function maybe_parse_sa_function(line)
local arg
local elts = split(line, '[^:]+')
arg = elts[2]
rspamd_logger.debugx(rspamd_config, 'trying to parse SA function %1 with args %2',
elts[1], elts[2])
local substitutions = {
{'^exists:',
function(task) -- filter
local hdrs_check = {}
if arg == 'MESSAGEID' then
hdrs_check = {
'Message-ID',
'X-Message-ID',
'Resent-Message-ID'
}
elseif arg == 'ToCc' then
hdrs_check = { 'To', 'Cc', 'Bcc' }
else
hdrs_check = {arg}
end
for i,h in ipairs(hdrs_check) do
if task:get_header(h) then
return 1
end
end
return 0
end,
},
{'^eval:',
function(task)
local func = func_cache[arg]
if not func then
func = gen_eval_rule(arg)
func_cache[arg] = func
end
if not func then
rspamd_logger.errx(task, 'cannot find appropriate eval rule for function %1',
arg)
else
return func(task)
end
return 0
end
},
}
for k,s in ipairs(substitutions) do
if string.find(line, s[1]) then
return s[2]
end
end
return nil
end
local function words_to_re(words, start)
return table.concat(totable(drop_n(start, words)), " ");
end
local function process_tflags(rule, flags)
each(function(flag)
if flag == 'publish' then
rule['publish'] = true
elseif flag == 'multiple' then
rule['multiple'] = true
elseif string.match(flag, '^maxhits=(%d+)$') then
rule['maxhits'] = tonumber(string.match(flag, '^maxhits=(%d+)$'))
elseif flag == 'nice' then
rule['nice'] = true
end
end, drop_n(1, flags))
if rule['re'] then
if rule['maxhits'] then
rule['re']:set_max_hits(rule['maxhits'])
elseif rule['multiple'] then
rule['re']:set_max_hits(0)
else
rule['re']:set_max_hits(1)
end
end
end
local function process_replace(words, tbl)
local re = words_to_re(words, 2)
tbl[words[2]] = re
end
local function process_sa_conf(f)
local cur_rule = {}
local valid_rule = false
local function insert_cur_rule()
if cur_rule['type'] ~= 'meta' and cur_rule['publish'] then
-- Create meta rule from this rule
local nsym = '__fake' .. cur_rule['symbol']
local nrule = {
type = 'meta',
symbol = cur_rule['symbol'],
score = cur_rule['score'],
meta = nsym,
description = cur_rule['description'],
}
rules[nrule['symbol']] = nrule
cur_rule['symbol'] = nsym
end
-- We have previous rule valid
if not cur_rule['symbol'] then
rspamd_logger.errx(rspamd_config, 'bad rule definition: %1', cur_rule)
end
rules[cur_rule['symbol']] = cur_rule
cur_rule = {}
valid_rule = false
end
local function parse_score(words)
if #words == 3 then
-- score rule <x>
rspamd_logger.debugx(rspamd_config, 'found score for %1: %2', words[2], words[3])
return tonumber(words[3])
elseif #words == 6 then
-- score rule <x1> <x2> <x3> <x4>
-- we assume here that bayes and network are enabled and select <x4>
rspamd_logger.debugx(rspamd_config, 'found score for %1: %2', words[2], words[6])
return tonumber(words[6])
else
rspamd_logger.errx(rspamd_config, 'invalid score for %1', words[2])
end
return 0
end
local skip_to_endif = false
local if_nested = 0
for l in f:lines() do
(function ()
l = trim(l)
if string.len(l) == 0 or string.sub(l, 1, 1) == '#' then
return
end
if skip_to_endif then
if string.match(l, '^endif') then
if_nested = if_nested - 1
if if_nested == 0 then
skip_to_endif = false
end
elseif string.match(l, '^if') then
if_nested = if_nested + 1
end
return
else
if string.match(l, '^ifplugin') then
local ls = split(l)
if not any(function(pl)
if pl == ls[2] then return true end
return false
end, known_plugins) then
skip_to_endif = true
if_nested = 1
end
elseif string.match(l, '^if !plugin%(') then
local pname = string.match(l, '^if !plugin%(([A-Za-z:]+)%)')
if any(function(pl)
if pl == pname then return true end
return false
end, known_plugins) then
skip_to_endif = true
if_nested = 1
end
elseif string.match(l, '^if') then
-- Unknown if
skip_to_endif = true
if_nested = 1
end
end
local slash = string.find(l, '/')
-- Skip comments
words = totable(take_while(
function(w) return string.sub(w, 1, 1) ~= '#' end,
filter(function(w)
return w ~= "" end,
iter(split(l)))))
if words[1] == "header" or words[1] == 'mimeheader' then
-- header SYMBOL Header ~= /regexp/
if valid_rule then
insert_cur_rule()
end
if words[4] and (words[4] == '=~' or words[4] == '!~') then
cur_rule['type'] = 'header'
cur_rule['symbol'] = words[2]
if words[4] == '!~' then
cur_rule['not'] = true
end
cur_rule['re_expr'] = words_to_re(words, 4)
local unset_comp = string.find(cur_rule['re_expr'], '%s+%[if%-unset:')
if unset_comp then
-- We have optional part that needs to be processed
unset = string.match(string.sub(cur_rule['re_expr'], unset_comp),
'%[if%-unset:%s*([^%]%s]+)]')
cur_rule['unset'] = unset
-- Cut it down
cur_rule['re_expr'] = string.sub(cur_rule['re_expr'], 1, unset_comp - 1)
end
cur_rule['re'] = rspamd_regexp.create(cur_rule['re_expr'])
if not cur_rule['re'] then
rspamd_logger.warnx(rspamd_config, "Cannot parse regexp '%1' for %2",
cur_rule['re_expr'], cur_rule['symbol'])
else
cur_rule['re']:set_max_hits(1)
handle_header_def(words[3], cur_rule)
end
if words[1] == 'mimeheader' then
cur_rule['mime'] = true
else
cur_rule['mime'] = false
end
if cur_rule['re'] and cur_rule['symbol'] and
(cur_rule['header'] or cur_rule['function']) then
valid_rule = true
cur_rule['re']:set_max_hits(1)
if cur_rule['header'] and cur_rule['ordinary'] then
for i,h in ipairs(cur_rule['header']) do
if type(h) == 'string' then
if cur_rule['mime'] then
rspamd_config:register_regexp({
re = cur_rule['re'],
type = 'mimeheader',
header = h,
pcre_only = is_pcre_only(cur_rule['symbol']),
})
else
rspamd_config:register_regexp({
re = cur_rule['re'],
type = 'header',
header = h,
pcre_only = is_pcre_only(cur_rule['symbol']),
})
end
else
h['mime'] = cur_rule[mime]
if cur_rule['mime'] then
rspamd_config:register_regexp({
re = cur_rule['re'],
type = 'mimeheader',
header = h['header'],
pcre_only = is_pcre_only(cur_rule['symbol']),
})
else
if h['raw'] then
rspamd_config:register_regexp({
re = cur_rule['re'],
type = 'rawheader',
header = h['header'],
pcre_only = is_pcre_only(cur_rule['symbol']),
})
else
rspamd_config:register_regexp({
re = cur_rule['re'],
type = 'header',
header = h['header'],
pcre_only = is_pcre_only(cur_rule['symbol']),
})
end
end
end
end
cur_rule['re']:set_limit(match_limit)
cur_rule['re']:set_max_hits(1)
end
end
else
-- Maybe we know the function and can convert it
local args = words_to_re(words, 2)
local func = maybe_parse_sa_function(args)
if func then
cur_rule['type'] = 'function'
cur_rule['symbol'] = words[2]
cur_rule['function'] = func
valid_rule = true
else
rspamd_logger.infox(rspamd_config, 'unknown function %1', args)
end
end
elseif words[1] == "body" then
-- body SYMBOL /regexp/
if valid_rule then
insert_cur_rule()
end
cur_rule['symbol'] = words[2]
if words[3] and (string.sub(words[3], 1, 1) == '/'
or string.sub(words[3], 1, 1) == 'm') then
cur_rule['type'] = 'sabody'
cur_rule['re_expr'] = words_to_re(words, 2)
cur_rule['re'] = rspamd_regexp.create(cur_rule['re_expr'])
if cur_rule['re'] then
rspamd_config:register_regexp({
re = cur_rule['re'],
type = 'sabody',
pcre_only = is_pcre_only(cur_rule['symbol']),
})
valid_rule = true
cur_rule['re']:set_limit(match_limit)
cur_rule['re']:set_max_hits(1)
end
else
-- might be function
local args = words_to_re(words, 2)
local func = maybe_parse_sa_function(args)
if func then
cur_rule['type'] = 'function'
cur_rule['symbol'] = words[2]
cur_rule['function'] = func
valid_rule = true
else
rspamd_logger.infox(rspamd_config, 'unknown function %1', args)
end
end
elseif words[1] == "rawbody" then
-- body SYMBOL /regexp/
if valid_rule then
insert_cur_rule()
end
cur_rule['symbol'] = words[2]
if words[3] and (string.sub(words[3], 1, 1) == '/'
or string.sub(words[3], 1, 1) == 'm') then
cur_rule['type'] = 'sarawbody'
cur_rule['re_expr'] = words_to_re(words, 2)
cur_rule['re'] = rspamd_regexp.create(cur_rule['re_expr'])
if cur_rule['re'] then
rspamd_config:register_regexp({
re = cur_rule['re'],
type = 'sarawbody',
pcre_only = is_pcre_only(cur_rule['symbol']),
})
valid_rule = true
cur_rule['re']:set_limit(match_limit)
cur_rule['re']:set_max_hits(1)
end
else
-- might be function
local args = words_to_re(words, 2)
local func = maybe_parse_sa_function(args)
if func then
cur_rule['type'] = 'function'
cur_rule['symbol'] = words[2]
cur_rule['function'] = func
valid_rule = true
else
rspamd_logger.infox(rspamd_config, 'unknown function %1', args)
end
end
elseif words[1] == "full" then
-- body SYMBOL /regexp/
if valid_rule then
insert_cur_rule()
end
cur_rule['symbol'] = words[2]
if words[3] and (string.sub(words[3], 1, 1) == '/'
or string.sub(words[3], 1, 1) == 'm') then
cur_rule['type'] = 'message'
cur_rule['re_expr'] = words_to_re(words, 2)
cur_rule['re'] = rspamd_regexp.create(cur_rule['re_expr'])
cur_rule['raw'] = true
if cur_rule['re'] then
valid_rule = true
rspamd_config:register_regexp({
re = cur_rule['re'],
type = 'body',
pcre_only = is_pcre_only(cur_rule['symbol']),
})
cur_rule['re']:set_limit(match_limit)
cur_rule['re']:set_max_hits(1)
end
else
-- might be function
local args = words_to_re(words, 2)
local func = maybe_parse_sa_function(args)
if func then
cur_rule['type'] = 'function'
cur_rule['symbol'] = words[2]
cur_rule['function'] = func
valid_rule = true
else
rspamd_logger.infox(rspamd_config, 'unknown function %1', args)
end
end
elseif words[1] == "uri" then
-- uri SYMBOL /regexp/
if valid_rule then
insert_cur_rule()
end
cur_rule['type'] = 'uri'
cur_rule['symbol'] = words[2]
cur_rule['re_expr'] = words_to_re(words, 2)
cur_rule['re'] = rspamd_regexp.create(cur_rule['re_expr'])
if cur_rule['re'] and cur_rule['symbol'] then
valid_rule = true
rspamd_config:register_regexp({
re = cur_rule['re'],
type = 'url',
pcre_only = is_pcre_only(cur_rule['symbol']),
})
cur_rule['re']:set_limit(match_limit)
cur_rule['re']:set_max_hits(1)
end
elseif words[1] == "meta" then
-- meta SYMBOL expression
if valid_rule then
insert_cur_rule()
end
cur_rule['type'] = 'meta'
cur_rule['symbol'] = words[2]
cur_rule['meta'] = words_to_re(words, 2)
if cur_rule['meta'] and cur_rule['symbol'] then valid_rule = true end
elseif words[1] == "describe" and valid_rule then
cur_rule['description'] = words_to_re(words, 2)
elseif words[1] == "score" then
scores[words[2]] = parse_score(words)
elseif words[1] == 'freemail_domains' then
each(function(dom)
table.insert(freemail_domains, '@' .. dom)
end, drop_n(1, words))
elseif words[1] == 'blacklist_from' then
sa_lists['from_blacklist'][words[2]] = 1
sa_lists['elts'] = sa_lists['elts'] + 1
elseif words[1] == 'whitelist_from' then
sa_lists['from_whitelist'][words[2]] = 1
sa_lists['elts'] = sa_lists['elts'] + 1
elseif words[1] == 'whitelist_to' then
sa_lists['to_whitelist'][words[2]] = 1
sa_lists['elts'] = sa_lists['elts'] + 1
elseif words[1] == 'blacklist_to' then
sa_lists['to_blacklist'][words[2]] = 1
sa_lists['elts'] = sa_lists['elts'] + 1
elseif words[1] == 'tflags' then
process_tflags(cur_rule, words)
elseif words[1] == 'replace_tag' then
process_replace(words, replace['tags'])
elseif words[1] == 'replace_pre' then
process_replace(words, replace['pre'])
elseif words[1] == 'replace_inter' then
process_replace(words, replace['inter'])
elseif words[1] == 'replace_post' then
process_replace(words, replace['post'])
elseif words[1] == 'replace_rules' then
each(function(r) table.insert(replace['rules'], r) end,
drop_n(1, words))
end
end)()
end
if valid_rule then
insert_cur_rule()
end
end
-- Now check all valid rules and add the according rspamd rules
local function calculate_score(sym, rule)
if all(function(c) return c == '_' end, take_n(2, iter(sym))) then
return 0.0
end
if rule['nice'] or (rule['score'] and rule['score'] < 0.0) then
return -1.0
end
return 1.0
end
local function add_sole_meta(sym, rule)
local r = {
type = 'meta',
meta = rule['symbol'],
score = rule['score'],
description = rule['description']
}
rules[sym] = r
end
local function sa_regexp_match(data, re, raw, rule)
local res = 0
if not re then
return 0
end
if rule['multiple'] then
local lim = -1
if rule['maxhits'] then
lim = rule['maxhits']
end
res = res + re:matchn(data, lim, raw)
else
if re:match(data, raw) then res = 1 end
end
return res
end
local function apply_replacements(str)
local pre = ""
local post = ""
local inter = ""
local function check_specific_tag(prefix, s, tbl)
local replacement = nil
local ret = s
each(function(n, t)
local ns,matches = string.gsub(s, string.format("<%s%s>", prefix, n), "")
if matches > 0 then
replacement = t
ret = ns
end
end, tbl)
return ret,replacement
end
local repl
str,repl = check_specific_tag("pre ", str, replace['pre'])
if repl then
pre = repl
end
str,repl = check_specific_tag("inter ", str, replace['inter'])
if repl then
inter = repl
end
str,repl = check_specific_tag("post ", str, replace['post'])
if repl then
post = repl
end
-- XXX: ugly hack
if inter then
str = string.gsub(str, "><", string.format(">%s<", inter))
end
local function replace_all_tags(s)
local str, matches
str = s
each(function(n, t)
str,matches = string.gsub(str, string.format("<%s>", n),
string.format("%s%s%s", pre, t, post))
end, replace['tags'])
return str
end
local s = replace_all_tags(str)
if str ~= s then
return true,s
end
return false,str
end
local function parse_atom(str)
local atom = table.concat(totable(take_while(function(c)
if string.find(', \t()><+!|&\n', c) then
return false
end
return true
end, iter(str))), '')
return atom
end
local function process_atom(atom, task)
local atom_cb = atoms[atom]
if atom_cb then
local res = atom_cb(task)
if not res then
rspamd_logger.debugx(task, 'atom: %1, NULL result', atom)
elseif res > 0 then
rspamd_logger.debugx(task, 'atom: %1, result: %2', atom, res)
end
return res
else
local ext_dep = external_deps[atom]
if ext_dep then
local res = 0
if type(ext_dep) == 'number' then
if task:has_symbol(atom) then
res = 1
end
elseif type(ext_dep) == 'string' then
-- Apply replacement
if task:has_symbol(ext_dep) then
res = 1
end
end
rspamd_logger.debugx(task, 'external atom: %1, result: %2', atom, res)
return res
else
rspamd_logger.debugx(task, 'Cannot find atom ' .. atom)
end
end
return 0
end
local function post_process()
-- Replace rule tags
local ntags = {}
local function rec_replace_tags(tag, tagv)
if ntags[tag] then return ntags[tag] end
each(function(n, t)
if n ~= tag then
local s, matches = string.gsub(tagv, string.format("<%s>", n), t)
if matches > 0 then
ntags[tag] = rec_replace_tags(tag, s)
end
end
end, replace['tags'])
if not ntags[tag] then ntags[tag] = tagv end
return ntags[tag]
end
each(function(n, t)
rec_replace_tags(n, t)
end, replace['tags'])
each(function(n, t)
replace['tags'][n] = t
end, ntags)
each(function(r)
local rule = rules[r]
if rule['re_expr'] and rule['re'] then
local res, nexpr = apply_replacements(rule['re_expr'])
if res then
local nre = rspamd_regexp.create(nexpr)
if not nre then
rspamd_logger.errx(rspamd_config, 'cannot apply replacement for rule %1', r)
--rule['re'] = nil
else
local old_max_hits = rule['re']:get_max_hits()
rspamd_logger.debugx(rspamd_config, 'replace %1 -> %2', r, nexpr)
rspamd_config:replace_regexp({
old_re = rule['re'],
new_re = nre
})
rule['re'] = nre
rule['re_expr'] = nexpr
nre:set_limit(match_limit)
nre:set_max_hits(old_max_hits)
end
end
end
end, replace['rules'])
each(function(key, score)
if rules[key] then
rules[key]['score'] = score
end
end, scores)
-- Header rules
each(function(k, r)
local f = function(task)
local raw = false
local check = {}
-- Cached path for ordinary expressions
if r['ordinary'] then
local h = r['header'][1]
local t = 'header'
if h['raw'] then
t = 'rawheader'
end
if not r['re'] then
rspamd_logger.errx(task, 're is missing for rule %1 (%2 header)', k,
h['header'])
return 0
end
local ret = task:process_regexp(r['re'], t, h['header'], h['strong'])
if r['not'] then
if ret ~= 0 then
ret = 0
else
ret = 1
end
end
return ret
end
-- Slow path
each(function(h)
local headers = {}
local hname = h['header']
local hdr
if h['mime'] then
local parts = task:get_parts()
for i, p in ipairs(parts) do
local m_hdr = p:get_header_full(hname, h['strong'])
if m_hdr then
if not hdr then
hdr = {}
end
for k, mh in ipairs(m_hdr) do
table.insert(hdr, mh)
end
end
end
else
hdr = task:get_header_full(hname, h['strong'])
end
if hdr then
for n, rh in ipairs(hdr) do
-- Subject for optimization
local str
if h['raw'] then
str = rh['value']
raw = true
else
str = rh['decoded']
end
if not str then return 0 end
if h['function'] then
str = h['function'](str)
end
if type(str) == 'string' then
table.insert(check, str)
else
for ii, c in ipairs(str) do
table.insert(check, c)
end
end
end
elseif r['unset'] then
table.insert(check, r['unset'])
end
end, r['header'])
if #check == 0 then
if r['not'] then return 1 end
return 0
end
local ret = 0
for i, c in ipairs(check) do
local match = sa_regexp_match(c, r['re'], raw, r)
if (match > 0 and not r['not']) or (match == 0 and r['not']) then
ret = 1
end
end
return ret
end
if r['score'] then
local real_score = r['score'] * calculate_score(k, r)
if math.abs(real_score) > meta_score_alpha then
add_sole_meta(k, r)
end
end
atoms[k] = f
end,
filter(function(k, r)
return r['type'] == 'header' and r['header']
end,
rules))
-- Custom function rules
each(function(k, r)
local f = function(task)
local res = r['function'](task)
if res and res > 0 then
return res
end
return 0
end
if r['score'] then
local real_score = r['score'] * calculate_score(k, r)
if math.abs(real_score) > meta_score_alpha then
add_sole_meta(k, r)
end
end
atoms[k] = f
end,
filter(function(k, r)
return r['type'] == 'function' and r['function']
end,
rules))
-- Parts rules
each(function(k, r)
local f = function(task)
if not r['re'] then
rspamd_logger.errx(task, 're is missing for rule %1', k)
return 0
end
local t = 'mime'
if r['raw'] then t = 'rawmime' end
return task:process_regexp(r['re'], t)
end
if r['score'] then
local real_score = r['score'] * calculate_score(k, r)
if math.abs(real_score) > meta_score_alpha then
add_sole_meta(k, r)
end
end
atoms[k] = f
end,
filter(function(k, r)
return r['type'] == 'part'
end, rules))
-- SA body rules
each(function(k, r)
local f = function(task)
if not r['re'] then
rspamd_logger.errx(task, 're is missing for rule %1', k)
return 0
end
local t = r['type']
local ret = task:process_regexp(r['re'], t)
return ret
end
if r['score'] then
local real_score = r['score'] * calculate_score(k, r)
if math.abs(real_score) > meta_score_alpha then
add_sole_meta(k, r)
end
end
atoms[k] = f
end,
filter(function(k, r)
return r['type'] == 'sabody' or r['type'] == 'message' or r['type'] == 'sarawbody'
end, rules))
-- URL rules
each(function(k, r)
local f = function(task)
if not r['re'] then
rspamd_logger.errx(task, 're is missing for rule %1', k)
return 0
end
return task:process_regexp(r['re'], 'url')
end
if r['score'] then
local real_score = r['score'] * calculate_score(k, r)
if math.abs(real_score) > meta_score_alpha then
add_sole_meta(k, r)
end
end
atoms[k] = f
end,
filter(function(k, r)
return r['type'] == 'uri'
end,
rules))
-- Meta rules
each(function(k, r)
local expression = nil
-- Meta function callback
local meta_cb = function(task)
local res = 0
local trace = {}
-- XXX: need to memoize result for better performance
local sym = task:has_symbol(k)
if not sym then
if expression then
res,trace = expression:process_traced(task)
end
if res > 0 then
-- Symbol should be one shot to make it working properly
task:insert_result(k, res, trace)
end
else
res = 1
end
return res
end
expression = rspamd_expression.create(r['meta'],
{parse_atom, process_atom}, sa_mempool)
if not expression then
rspamd_logger.errx(rspamd_config, 'Cannot parse expression ' .. r['meta'])
else
if r['score'] then
rspamd_config:set_metric_symbol({
name = k, score = r['score'],
description = r['description'],
priority = 2,
one_shot = true })
scores_added[k] = 1
end
rspamd_config:register_symbol({
name = k,
weight = calculate_score(k, r),
callback = meta_cb
})
r['expression'] = expression
if not atoms[k] then
atoms[k] = meta_cb
end
end
end,
filter(function(k, r)
return r['type'] == 'meta'
end,
rules))
-- Check meta rules for foreign symbols and register dependencies
-- First direct dependencies:
each(function(k, r)
if r['expression'] then
local expr_atoms = r['expression']:atoms()
for i,a in ipairs(expr_atoms) do
if not atoms[a] then
local rspamd_symbol, replaced_symbol = replace_symbol(a)
rspamd_logger.debugx('atom %1 is a direct foreign dependency, ' ..
'register dependency for %2 on %3',
a, k, rspamd_symbol)
rspamd_config:register_dependency(k, rspamd_symbol)
if not external_deps[k] then
external_deps[k] = {rspamd_symbol}
else
table.insert(external_deps[k], rspamd_symbol)
end
end
end
end
end,
filter(function(k, r)
return r['type'] == 'meta'
end,
rules))
-- ... And then indirect ones ...
each(function(k, r)
if r['expression'] then
local expr_atoms = r['expression']:atoms()
for i,a in ipairs(expr_atoms) do
if type(external_deps[a]) == 'table' then
for _,dep in ipairs(external_deps[a]) do
rspamd_logger.debugx('atom %1 holds a foreign dependency, ' ..
'register dependency for %2 on %3',
a, k, dep);
rspamd_config:register_dependency(k, dep)
end
else
local rspamd_symbol, replaced_symbol = replace_symbol(a)
if replaced_symbol then
external_deps[a] = rspamd_symbol
else
external_deps[a] = 1
end
end
end
end
end,
filter(function(k, r)
return r['type'] == 'meta'
end,
rules))
-- Set missing symbols
each(function(key, score)
if not scores_added[key] then
rspamd_config:set_metric_symbol({
name = key, score = score,
priority = 2, flags = 'ignore'})
end
end, scores)
-- Logging output
if freemail_domains then
freemail_trie = rspamd_trie.create(freemail_domains)
rspamd_logger.infox(rspamd_config, 'loaded %1 freemail domains definitions',
#freemail_domains)
end
rspamd_logger.infox(rspamd_config, 'loaded %1 blacklist/whitelist elements',
sa_lists['elts'])
end
local has_rules = false
if type(section) == "table" then
for k, fn in pairs(section) do
if k == 'alpha' and type(fn) == 'number' then
meta_score_alpha = fn
elseif k == 'match_limit' and type(fn) == 'number' then
match_limit = fn
elseif k == 'pcre_only' and type(fn) == 'table' then
for i,s in ipairs(fn) do
pcre_only_regexps[s] = 1
end
else
if type(fn) == 'table' then
for k, elt in ipairs(fn) do
local files = util.glob(elt)
for i,matched in ipairs(files) do
f = io.open(matched, "r")
if f then
process_sa_conf(f)
has_rules = true
else
rspamd_logger.errx(rspamd_config, "cannot open %1", matched)
end
end
end
else
-- assume string
local files = util.glob(fn)
for i,matched in ipairs(files) do
f = io.open(matched, "r")
if f then
process_sa_conf(f)
has_rules = true
else
rspamd_logger.errx(rspamd_config, "cannot open %1", matched)
end
end
end
end
end
end
if has_rules then
post_process()
end
|