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
|
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
# ion.py
# Copyright © 2013-2020 Apprentice Harper et al.
__license__ = 'GPL v3'
__version__ = '3.0'
# Revision history:
# Pascal implementation by lulzkabulz.
# BinaryIon.pas + DrmIon.pas + IonSymbols.pas
# 1.0 - Python translation by apprenticenaomi.
# 1.1 - DeDRM integration by anon.
# 1.2 - Added pylzma import fallback
# 1.3 - Fixed lzma support for calibre 4.6+
# 2.0 - VoucherEnvelope v2/v3 support by apprenticesakuya.
# 3.0 - Added Python 3 compatibility for calibre 5.0
"""
Decrypt Kindle KFX files.
"""
import collections
import hashlib
import hmac
import os
import os.path
import struct
from io import BytesIO
try:
from Cryptodome.Cipher import AES
from Cryptodome.Util.py3compat import bchr
except ImportError:
from Crypto.Cipher import AES
from Crypto.Util.py3compat import bchr
try:
# lzma library from calibre 4.6.0 or later
import calibre_lzma.lzma1 as calibre_lzma
except ImportError:
calibre_lzma = None
# lzma library from calibre 2.35.0 or later
try:
import lzma.lzma1 as calibre_lzma
except ImportError:
calibre_lzma = None
try:
import lzma
except ImportError:
# Need pip backports.lzma on Python <3.3
try:
from backports import lzma
except ImportError:
# Windows-friendly choice: pylzma wheels
import pylzma as lzma
TID_NULL = 0
TID_BOOLEAN = 1
TID_POSINT = 2
TID_NEGINT = 3
TID_FLOAT = 4
TID_DECIMAL = 5
TID_TIMESTAMP = 6
TID_SYMBOL = 7
TID_STRING = 8
TID_CLOB = 9
TID_BLOB = 0xA
TID_LIST = 0xB
TID_SEXP = 0xC
TID_STRUCT = 0xD
TID_TYPEDECL = 0xE
TID_UNUSED = 0xF
SID_UNKNOWN = -1
SID_ION = 1
SID_ION_1_0 = 2
SID_ION_SYMBOL_TABLE = 3
SID_NAME = 4
SID_VERSION = 5
SID_IMPORTS = 6
SID_SYMBOLS = 7
SID_MAX_ID = 8
SID_ION_SHARED_SYMBOL_TABLE = 9
SID_ION_1_0_MAX = 10
LEN_IS_VAR_LEN = 0xE
LEN_IS_NULL = 0xF
VERSION_MARKER = [b"\x01", b"\x00", b"\xEA"]
# asserts must always raise exceptions for proper functioning
def _assert(test, msg="Exception"):
if not test:
raise Exception(msg)
class SystemSymbols(object):
ION = '$ion'
ION_1_0 = '$ion_1_0'
ION_SYMBOL_TABLE = '$ion_symbol_table'
NAME = 'name'
VERSION = 'version'
IMPORTS = 'imports'
SYMBOLS = 'symbols'
MAX_ID = 'max_id'
ION_SHARED_SYMBOL_TABLE = '$ion_shared_symbol_table'
class IonCatalogItem(object):
name = ""
version = 0
symnames = []
def __init__(self, name, version, symnames):
self.name = name
self.version = version
self.symnames = symnames
class SymbolToken(object):
text = ""
sid = 0
def __init__(self, text, sid):
if text == "" and sid == 0:
raise ValueError("Symbol token must have Text or SID")
self.text = text
self.sid = sid
class SymbolTable(object):
table = None
def __init__(self):
self.table = [None] * SID_ION_1_0_MAX
self.table[SID_ION] = SystemSymbols.ION
self.table[SID_ION_1_0] = SystemSymbols.ION_1_0
self.table[SID_ION_SYMBOL_TABLE] = SystemSymbols.ION_SYMBOL_TABLE
self.table[SID_NAME] = SystemSymbols.NAME
self.table[SID_VERSION] = SystemSymbols.VERSION
self.table[SID_IMPORTS] = SystemSymbols.IMPORTS
self.table[SID_SYMBOLS] = SystemSymbols.SYMBOLS
self.table[SID_MAX_ID] = SystemSymbols.MAX_ID
self.table[SID_ION_SHARED_SYMBOL_TABLE] = SystemSymbols.ION_SHARED_SYMBOL_TABLE
def findbyid(self, sid):
if sid < 1:
raise ValueError("Invalid symbol id")
if sid < len(self.table):
return self.table[sid]
else:
return ""
def import_(self, table, maxid):
for i in range(maxid):
self.table.append(table.symnames[i])
def importunknown(self, name, maxid):
for i in range(maxid):
self.table.append("%s#%d" % (name, i + 1))
class ParserState:
Invalid,BeforeField,BeforeTID,BeforeValue,AfterValue,EOF = 1,2,3,4,5,6
ContainerRec = collections.namedtuple("ContainerRec", "nextpos, tid, remaining")
class BinaryIonParser(object):
eof = False
state = None
localremaining = 0
needhasnext = False
isinstruct = False
valuetid = 0
valuefieldid = 0
parenttid = 0
valuelen = 0
valueisnull = False
valueistrue = False
value = None
didimports = False
def __init__(self, stream):
self.annotations = []
self.catalog = []
self.stream = stream
self.initpos = stream.tell()
self.reset()
self.symbols = SymbolTable()
def reset(self):
self.state = ParserState.BeforeTID
self.needhasnext = True
self.localremaining = -1
self.eof = False
self.isinstruct = False
self.containerstack = []
self.stream.seek(self.initpos)
def addtocatalog(self, name, version, symbols):
self.catalog.append(IonCatalogItem(name, version, symbols))
def hasnext(self):
while self.needhasnext and not self.eof:
self.hasnextraw()
if len(self.containerstack) == 0 and not self.valueisnull:
if self.valuetid == TID_SYMBOL:
if self.value == SID_ION_1_0:
self.needhasnext = True
elif self.valuetid == TID_STRUCT:
for a in self.annotations:
if a == SID_ION_SYMBOL_TABLE:
self.parsesymboltable()
self.needhasnext = True
break
return not self.eof
def hasnextraw(self):
self.clearvalue()
while self.valuetid == -1 and not self.eof:
self.needhasnext = False
if self.state == ParserState.BeforeField:
_assert(self.valuefieldid == SID_UNKNOWN)
self.valuefieldid = self.readfieldid()
if self.valuefieldid != SID_UNKNOWN:
self.state = ParserState.BeforeTID
else:
self.eof = True
elif self.state == ParserState.BeforeTID:
self.state = ParserState.BeforeValue
self.valuetid = self.readtypeid()
if self.valuetid == -1:
self.state = ParserState.EOF
self.eof = True
break
if self.valuetid == TID_TYPEDECL:
if self.valuelen == 0:
self.checkversionmarker()
else:
self.loadannotations()
elif self.state == ParserState.BeforeValue:
self.skip(self.valuelen)
self.state = ParserState.AfterValue
elif self.state == ParserState.AfterValue:
if self.isinstruct:
self.state = ParserState.BeforeField
else:
self.state = ParserState.BeforeTID
else:
_assert(self.state == ParserState.EOF)
def next(self):
if self.hasnext():
self.needhasnext = True
return self.valuetid
else:
return -1
def push(self, typeid, nextposition, nextremaining):
self.containerstack.append(ContainerRec(nextpos=nextposition, tid=typeid, remaining=nextremaining))
def stepin(self):
_assert(self.valuetid in [TID_STRUCT, TID_LIST, TID_SEXP] and not self.eof,
"valuetid=%s eof=%s" % (self.valuetid, self.eof))
_assert((not self.valueisnull or self.state == ParserState.AfterValue) and
(self.valueisnull or self.state == ParserState.BeforeValue))
nextrem = self.localremaining
if nextrem != -1:
nextrem -= self.valuelen
if nextrem < 0:
nextrem = 0
self.push(self.parenttid, self.stream.tell() + self.valuelen, nextrem)
self.isinstruct = (self.valuetid == TID_STRUCT)
if self.isinstruct:
self.state = ParserState.BeforeField
else:
self.state = ParserState.BeforeTID
self.localremaining = self.valuelen
self.parenttid = self.valuetid
self.clearvalue()
self.needhasnext = True
def stepout(self):
rec = self.containerstack.pop()
self.eof = False
self.parenttid = rec.tid
if self.parenttid == TID_STRUCT:
self.isinstruct = True
self.state = ParserState.BeforeField
else:
self.isinstruct = False
self.state = ParserState.BeforeTID
self.needhasnext = True
self.clearvalue()
curpos = self.stream.tell()
if rec.nextpos > curpos:
self.skip(rec.nextpos - curpos)
else:
_assert(rec.nextpos == curpos)
self.localremaining = rec.remaining
def read(self, count=1):
if self.localremaining != -1:
self.localremaining -= count
_assert(self.localremaining >= 0)
result = self.stream.read(count)
if len(result) == 0:
raise EOFError()
return result
def readfieldid(self):
if self.localremaining != -1 and self.localremaining < 1:
return -1
try:
return self.readvaruint()
except EOFError:
return -1
def readtypeid(self):
if self.localremaining != -1:
if self.localremaining < 1:
return -1
self.localremaining -= 1
b = self.stream.read(1)
if len(b) < 1:
return -1
b = ord(b)
result = b >> 4
ln = b & 0xF
if ln == LEN_IS_VAR_LEN:
ln = self.readvaruint()
elif ln == LEN_IS_NULL:
ln = 0
self.state = ParserState.AfterValue
elif result == TID_NULL:
# Must have LEN_IS_NULL
_assert(False)
elif result == TID_BOOLEAN:
_assert(ln <= 1)
self.valueistrue = (ln == 1)
ln = 0
self.state = ParserState.AfterValue
elif result == TID_STRUCT:
if ln == 1:
ln = self.readvaruint()
self.valuelen = ln
return result
def readvarint(self):
b = ord(self.read())
negative = ((b & 0x40) != 0)
result = (b & 0x3F)
i = 0
while (b & 0x80) == 0 and i < 4:
b = ord(self.read())
result = (result << 7) | (b & 0x7F)
i += 1
_assert(i < 4 or (b & 0x80) != 0, "int overflow")
if negative:
return -result
return result
def readvaruint(self):
b = ord(self.read())
result = (b & 0x7F)
i = 0
while (b & 0x80) == 0 and i < 4:
b = ord(self.read())
result = (result << 7) | (b & 0x7F)
i += 1
_assert(i < 4 or (b & 0x80) != 0, "int overflow")
return result
def readdecimal(self):
if self.valuelen == 0:
return 0.
rem = self.localremaining - self.valuelen
self.localremaining = self.valuelen
exponent = self.readvarint()
_assert(self.localremaining > 0, "Only exponent in ReadDecimal")
_assert(self.localremaining <= 8, "Decimal overflow")
signed = False
b = [ord(x) for x in self.read(self.localremaining)]
if (b[0] & 0x80) != 0:
b[0] = b[0] & 0x7F
signed = True
# Convert variably sized network order integer into 64-bit little endian
j = 0
vb = [0] * 8
for i in range(len(b), -1, -1):
vb[i] = b[j]
j += 1
v = struct.unpack("<Q", b"".join(bchr(x) for x in vb))[0]
result = v * (10 ** exponent)
if signed:
result = -result
self.localremaining = rem
return result
def skip(self, count):
if self.localremaining != -1:
self.localremaining -= count
if self.localremaining < 0:
raise EOFError()
self.stream.seek(count, os.SEEK_CUR)
def parsesymboltable(self):
self.next() # shouldn't do anything?
_assert(self.valuetid == TID_STRUCT)
if self.didimports:
return
self.stepin()
fieldtype = self.next()
while fieldtype != -1:
if not self.valueisnull:
_assert(self.valuefieldid == SID_IMPORTS, "Unsupported symbol table field id")
if fieldtype == TID_LIST:
self.gatherimports()
fieldtype = self.next()
self.stepout()
self.didimports = True
def gatherimports(self):
self.stepin()
t = self.next()
while t != -1:
if not self.valueisnull and t == TID_STRUCT:
self.readimport()
t = self.next()
self.stepout()
def readimport(self):
version = -1
maxid = -1
name = ""
self.stepin()
t = self.next()
while t != -1:
if not self.valueisnull and self.valuefieldid != SID_UNKNOWN:
if self.valuefieldid == SID_NAME:
name = self.stringvalue()
elif self.valuefieldid == SID_VERSION:
version = self.intvalue()
elif self.valuefieldid == SID_MAX_ID:
maxid = self.intvalue()
t = self.next()
self.stepout()
if name == "" or name == SystemSymbols.ION:
return
if version < 1:
version = 1
table = self.findcatalogitem(name)
if maxid < 0:
_assert(table is not None and version == table.version, "Import %s lacks maxid" % name)
maxid = len(table.symnames)
if table is not None:
self.symbols.import_(table, min(maxid, len(table.symnames)))
if len(table.symnames) < maxid:
self.symbols.importunknown(name + "-unknown", maxid - len(table.symnames))
else:
self.symbols.importunknown(name, maxid)
def intvalue(self):
_assert(self.valuetid in [TID_POSINT, TID_NEGINT], "Not an int")
self.preparevalue()
return self.value
def stringvalue(self):
_assert(self.valuetid == TID_STRING, "Not a string")
if self.valueisnull:
return ""
self.preparevalue()
return self.value
def symbolvalue(self):
_assert(self.valuetid == TID_SYMBOL, "Not a symbol")
self.preparevalue()
result = self.symbols.findbyid(self.value)
if result == "":
result = "SYMBOL#%d" % self.value
return result
def lobvalue(self):
_assert(self.valuetid in [TID_CLOB, TID_BLOB], "Not a LOB type: %s" % self.getfieldname())
if self.valueisnull:
return None
result = self.read(self.valuelen)
self.state = ParserState.AfterValue
return result
def decimalvalue(self):
_assert(self.valuetid == TID_DECIMAL, "Not a decimal")
self.preparevalue()
return self.value
def preparevalue(self):
if self.value is None:
self.loadscalarvalue()
def loadscalarvalue(self):
if self.valuetid not in [TID_NULL, TID_BOOLEAN, TID_POSINT, TID_NEGINT,
TID_FLOAT, TID_DECIMAL, TID_TIMESTAMP,
TID_SYMBOL, TID_STRING]:
return
if self.valueisnull:
self.value = None
return
if self.valuetid == TID_STRING:
self.value = self.read(self.valuelen).decode("UTF-8")
elif self.valuetid in (TID_POSINT, TID_NEGINT, TID_SYMBOL):
if self.valuelen == 0:
self.value = 0
else:
_assert(self.valuelen <= 4, "int too long: %d" % self.valuelen)
v = 0
for i in range(self.valuelen - 1, -1, -1):
v = (v | (ord(self.read()) << (i * 8)))
if self.valuetid == TID_NEGINT:
self.value = -v
else:
self.value = v
elif self.valuetid == TID_DECIMAL:
self.value = self.readdecimal()
#else:
# _assert(False, "Unhandled scalar type %d" % self.valuetid)
self.state = ParserState.AfterValue
def clearvalue(self):
self.valuetid = -1
self.value = None
self.valueisnull = False
self.valuefieldid = SID_UNKNOWN
self.annotations = []
def loadannotations(self):
ln = self.readvaruint()
maxpos = self.stream.tell() + ln
while self.stream.tell() < maxpos:
self.annotations.append(self.readvaruint())
self.valuetid = self.readtypeid()
def checkversionmarker(self):
for i in VERSION_MARKER:
_assert(self.read() == i, "Unknown version marker")
self.valuelen = 0
self.valuetid = TID_SYMBOL
self.value = SID_ION_1_0
self.valueisnull = False
self.valuefieldid = SID_UNKNOWN
self.state = ParserState.AfterValue
def findcatalogitem(self, name):
for result in self.catalog:
if result.name == name:
return result
def forceimport(self, symbols):
item = IonCatalogItem("Forced", 1, symbols)
self.symbols.import_(item, len(symbols))
def getfieldname(self):
if self.valuefieldid == SID_UNKNOWN:
return ""
return self.symbols.findbyid(self.valuefieldid)
def getfieldnamesymbol(self):
return SymbolToken(self.getfieldname(), self.valuefieldid)
def gettypename(self):
if len(self.annotations) == 0:
return ""
return self.symbols.findbyid(self.annotations[0])
@staticmethod
def printlob(b):
if b is None:
return "null"
result = ""
for i in b:
result += ("%02x " % ord(i))
if len(result) > 0:
result = result[:-1]
return result
def ionwalk(self, supert, indent, lst):
while self.hasnext():
if supert == TID_STRUCT:
L = self.getfieldname() + ":"
else:
L = ""
t = self.next()
if t in [TID_STRUCT, TID_LIST]:
if L != "":
lst.append(indent + L)
L = self.gettypename()
if L != "":
lst.append(indent + L + "::")
if t == TID_STRUCT:
lst.append(indent + "{")
else:
lst.append(indent + "[")
self.stepin()
self.ionwalk(t, indent + " ", lst)
self.stepout()
if t == TID_STRUCT:
lst.append(indent + "}")
else:
lst.append(indent + "]")
else:
if t == TID_STRING:
L += ('"%s"' % self.stringvalue())
elif t in [TID_CLOB, TID_BLOB]:
L += ("{%s}" % self.printlob(self.lobvalue()))
elif t == TID_POSINT:
L += str(self.intvalue())
elif t == TID_SYMBOL:
tn = self.gettypename()
if tn != "":
tn += "::"
L += tn + self.symbolvalue()
elif t == TID_DECIMAL:
L += str(self.decimalvalue())
else:
L += ("TID %d" % t)
lst.append(indent + L)
def print_(self, lst):
self.reset()
self.ionwalk(-1, "", lst)
SYM_NAMES = [ '[email protected]',
'[email protected]', 'size', 'page_size',
'encryption_key', 'encryption_transformation',
'encryption_voucher', 'signing_key', 'signing_algorithm',
'signing_voucher', '[email protected]',
'cipher_text', 'cipher_iv', '[email protected]',
'data', '[email protected]', 'length',
'offset', 'algorithm', 'encoded', 'encryption_algorithm',
'hashing_algorithm', 'expires', 'format', 'id',
'lock_parameters', 'strategy', '[email protected]',
'[email protected]', '[email protected]',
'[email protected]',
'[email protected]', '[email protected]',
'[email protected]', '[email protected]',
'[email protected]', 'public_key', 'private_key',
'[email protected]', '[email protected]',
'doctype', '[email protected]',
'enddoc', 'license_type', 'license', 'watermark', 'key', 'value',
'[email protected]', 'category', 'metadata',
'categorized_metadata', '[email protected]',
'[email protected]', 'mac', 'voucher',
'[email protected]',
'[email protected]',
'[email protected]',
'[email protected]',
'[email protected]', 'compression_algorithm',
'[email protected]', 'page_index_table',
] + ['com.amazon.drm.VoucherEnvelope@%d.0' % n
for n in list(range(2, 29)) + [
9708, 1031, 2069, 9041, 3646,
6052, 9479, 9888, 4648, 5683]]
def addprottable(ion):
ion.addtocatalog("ProtectedData", 1, SYM_NAMES)
def pkcs7pad(msg, blocklen):
paddinglen = blocklen - len(msg) % blocklen
padding = bchr(paddinglen) * paddinglen
return msg + padding
def pkcs7unpad(msg, blocklen):
_assert(len(msg) % blocklen == 0)
paddinglen = msg[-1]
_assert(paddinglen > 0 and paddinglen <= blocklen, "Incorrect padding - Wrong key")
_assert(msg[-paddinglen:] == bchr(paddinglen) * paddinglen, "Incorrect padding - Wrong key")
return msg[:-paddinglen]
# every VoucherEnvelope version has a corresponding "word" and magic number, used in obfuscating the shared secret
OBFUSCATION_TABLE = {
"V1": (0x00, None),
"V2": (0x05, b'Antidisestablishmentarianism'),
"V3": (0x08, b'Floccinaucinihilipilification'),
"V4": (0x07, b'>\x14\x0c\x12\x10-\x13&\x18U\x1d\x05Rlt\x03!\x19\x1b\x13\x04]Y\x19,\t\x1b'),
"V5": (0x06, b'~\x18~\x16J\\\x18\x10\x05\x0b\x07\t\x0cZ\r|\x1c\x15\x1d\x11>,\x1b\x0e\x03"4\x1b\x01'),
"V6": (0x09, b'3h\x055\x03[^>\x19\x1c\x08\x1b\rtm4\x02Rp\x0c\x16B\n'),
"V7": (0x05, b'\x10\x1bJ\x18\nh!\x10"\x03>Z\'\r\x01]W\x06\x1c\x1e?\x0f\x13'),
"V8": (0x09, b"K\x0c6\x1d\x1a\x17pO}Rk\x1d'w1^\x1f$\x1c{C\x02Q\x06\x1d`"),
"V9": (0x05, b'X.\x0eW\x1c*K\x12\x12\t\n\n\x17Wx\x01\x02Yf\x0f\x18\x1bVXPi\x01'),
"V10": (0x07, b'z3\n\x039\x12\x13`\x06=v,\x02MTK\x1e%}L\x1c\x1f\x15\x0c\x11\x02\x0c\n8\x17p'),
"V11": (0x05, b'L=\nhVm\x07go\n6\x14\x06\x16L\r\x02\x0b\x0c\x1b\x04#p\t'),
"V12": (0x06, b',n\x1d\rl\x13\x1c\x13\x16p\x14\x07U\x0c\x1f\x19w\x16\x16\x1d5T'),
"V13": (0x07, b'I\x05\t\x08\x03r)\x01$N\x0fr3n\x0b062D\x0f\x13'),
"V14": (0x05, b"\x03\x02\x1c9\x19\x15\x15q\x1057\x08\x16\x0cF\x1b.Fw\x01\x12\x03\x13\x02\x17S'hk6"),
"V15": (0x0A, b'&,4B\x1dcI\x0bU\x03I\x07\x04\x1c\t\x05c\x07%ws\x0cj\t\x1a\x08\x0f'),
"V16": (0x0A, b'\x06\x18`h,b><\x06PqR\x02Zc\x034\n\x16\x1e\x18\x06#e'),
"V17": (0x07, b'y\r\x12\x08fw.[\x02\t\n\x13\x11\x0c\x11b\x1e8L\x10(\x13<Jx6c\x0f'),
"V18": (0x07, b'I\x0b\x0e,\x19\x1aIa\x10s\x19g\\\x1b\x11!\x18yf\x0f\t\x1d7[bSp\x03'),
"V19": (0x05, b'\n6>)N\x02\x188\x016s\x13\x14\x1b\x16jeN\n\x146\x04\x18\x1c\x0c\x19\x1f,\x02]'),
"V20": (0x08, b'_\r\x01\x12]\\\x14*\x17i\x14\r\t!\x1e,~hZ\x12jK\x17\x1e*1'),
"V21": (0x07, b'e\x1d\x19|\ty\x1di|N\x13\x0e\x04\x1bj<h\x13\x15k\x12\x08=\x1f\x16~\x13l'),
"V22": (0x08, b'?\x17yi$k7Pc\tEo\x0c\x07\x07\t\x1f,*i\x12\x0cI0\x10I\x1a?2\x04'),
"V23": (0x08, b'\x16+db\x13\x04\x18\rc%\x14\x17\x0f\x13F\x0c[\t9\x1ay\x01\x1eH'),
"V24": (0x06, b'|6\\\x1a\r\x10\nP\x07\x0fu\x1f\t,\rr`uv\\~55\x11]N'),
"V25": (0x09, b'\x07\x14w\x1e,^y\x01:\x08\x07\x1fr\tU#j\x16\x12\x1eB\x04\x16=\x06fZ\x07\x02\x06'),
"V26": (0x06, b'\x03IL\x1e"K\x1f\x0f\x1fp0\x01`X\x02z0`\x03\x0eN\x07'),
"V27": (0x07, b'Xk\x10y\x02\x18\x10\x17\x1d,\x0e\x05e\x10\x15"e\x0fh(\x06s\x1c\x08I\x0c\x1b\x0e'),
"V28": (0x0A, b'6P\x1bs\x0f\x06V.\x1cM\x14\x02\n\x1b\x07{P0:\x18zaU\x05'),
"V9708": (0x05, b'\x1diIm\x08a\x17\x1e!am\x1d\x1aQ.\x16!\x06*\}x04\x11\t\x06\x04?'),
"V1031": (0x08, b'Antidisestablishmentarianism'),
"V2069": (0x07, b'Floccinaucinihilipilification'),
"V9041": (0x06, b'>\x14\x0c\x12\x10-\x13&\x18U\x1d\x05Rlt\x03!\x19\x1b\x13\x04]Y\x19,\t\x1b'),
"V3646": (0x09, b'~\x18~\x16J\\\x18\x10\x05\x0b\x07\t\x0cZ\r|\x1c\x15\x1d\x11>,\x1b\x0e\x03"4\x1b\x01'),
"V6052": (0x05, b'3h\x055\x03[^>\x19\x1c\x08\x1b\rtm4\x02Rp\x0c\x16B\n'),
"V9479": (0x09, b'\x10\x1bJ\x18\nh!\x10"\x03>Z\'\r\x01]W\x06\x1c\x1e?\x0f\x13'),
"V9888": (0x05, b"K\x0c6\x1d\x1a\x17pO}Rk\x1d'w1^\x1f$\x1c{C\x02Q\x06\x1d`"),
"V4648": (0x07, b'X.\x0eW\x1c*K\x12\x12\t\n\n\x17Wx\x01\x02Yf\x0f\x18\x1bVXPi\x01'),
"V5683": (0x05, b'z3\n\x039\x12\x13`\x06=v,\x02MTK\x1e%}L\x1c\x1f\x15\x0c\x11\x02\x0c\n8\x17p'),
}
# obfuscate shared secret according to the VoucherEnvelope version
def obfuscate(secret, version):
if version == 1: # v1 does not use obfuscation
return secret
magic, word = OBFUSCATION_TABLE["V%d" % version]
# extend secret so that its length is divisible by the magic number
if len(secret) % magic != 0:
secret = secret + b'\x00' * (magic - len(secret) % magic)
secret = bytearray(secret)
obfuscated = bytearray(len(secret))
wordhash = bytearray(hashlib.sha256(word).digest())
# shuffle secret and xor it with the first half of the word hash
for i in range(0, len(secret)):
index = i // (len(secret) // magic) + magic * (i % (len(secret) // magic))
obfuscated[index] = secret[i] ^ wordhash[index % 16]
return obfuscated
# scramble() and obfuscate2() from https://github.com/andrewc12/DeDRM_tools/commit/d9233d61f00d4484235863969919059f4d0b2057
def scramble(st,magic):
ret=bytearray(len(st))
padlen=len(st)
for counter in range(len(st)):
ivar2=(padlen//2)-2*(counter%magic)+magic+counter-1
ret[ivar2%padlen]=st[counter]
return ret
def obfuscate2(secret, version):
if version == 1: # v1 does not use obfuscation
return secret
magic, word = OBFUSCATION_TABLE["V%d" % version]
# extend secret so that its length is divisible by the magic number
if len(secret) % magic != 0:
secret = secret + b'\x00' * (magic - len(secret) % magic)
obfuscated = bytearray(len(secret))
wordhash = bytearray(hashlib.sha256(word).digest()[16:])
#print(wordhash.hex())
shuffled = bytearray(scramble(secret,magic))
for i in range(0, len(secret)):
obfuscated[i] = shuffled[i] ^ wordhash[i % 16]
return obfuscated
# scramble3() and obfuscate3() from https://github.com/Satsuoni/DeDRM_tools/commit/da6b6a0c911b6d45fe1b13042b690daebc1cc22f
def scramble3(st,magic):
ret=bytearray(len(st))
padlen=len(st)
divs = padlen // magic
cntr = 0
iVar6 = 0
offset = 0
if (0 < ((magic - 1) + divs)):
while True:
if (offset & 1) == 0 :
uVar4 = divs - 1
if offset < divs:
iVar3 = 0
uVar4 = offset
else:
iVar3 = (offset - divs) + 1
if uVar4>=0:
iVar5 = uVar4 * magic
index = ((padlen - 1) - cntr)
while True:
if (magic <= iVar3): break
ret[index] = st[iVar3 + iVar5]
iVar3 = iVar3 + 1
cntr = cntr + 1
uVar4 = uVar4 - 1
iVar5 = iVar5 - magic
index -= 1
if uVar4<=-1: break
else:
if (offset < magic):
iVar3 = 0
else :
iVar3 = (offset - magic) + 1
if (iVar3 < divs):
uVar4 = offset
if (magic <= offset):
uVar4 = magic - 1
index = ((padlen - 1) - cntr)
iVar5 = iVar3 * magic
while True:
if (uVar4 < 0) : break
iVar3 += 1
ret[index] = st[uVar4 + iVar5]
uVar4 -= 1
index=index-1
iVar5 = iVar5 + magic;
cntr += 1;
if iVar3>=divs: break
offset = offset + 1
if offset >= ((magic - 1) + divs) :break
return ret
#not sure if the third variant is used anywhere, but it is in Kindle, so I tried to add it
def obfuscate3(secret, version):
if version == 1: # v1 does not use obfuscation
return secret
magic, word = OBFUSCATION_TABLE["V%d" % version]
# extend secret so that its length is divisible by the magic number
if len(secret) % magic != 0:
secret = secret + b'\x00' * (magic - len(secret) % magic)
#secret = bytearray(secret)
obfuscated = bytearray(len(secret))
wordhash = bytearray(hashlib.sha256(word).digest())
#print(wordhash.hex())
shuffled=bytearray(scramble3(secret,magic))
#print(shuffled)
# shuffle secret and xor it with the first half of the word hash
for i in range(0, len(secret)):
obfuscated[i] = shuffled[i] ^ wordhash[i % 16]
return obfuscated
class DrmIonVoucher(object):
envelope = None
version = None
voucher = None
drmkey = None
license_type = "Unknown"
encalgorithm = ""
enctransformation = ""
hashalgorithm = ""
lockparams = None
ciphertext = b""
cipheriv = b""
secretkey = b""
def __init__(self, voucherenv, dsn, secret):
self.dsn, self.secret = dsn, secret
if isinstance(dsn, str):
self.dsn = dsn.encode('ASCII')
if isinstance(secret, str):
self.secret = secret.encode('ASCII')
self.lockparams = []
self.envelope = BinaryIonParser(voucherenv)
addprottable(self.envelope)
def decryptvoucher(self):
shared = ("PIDv3" + self.encalgorithm + self.enctransformation + self.hashalgorithm).encode('ASCII')
self.lockparams.sort()
for param in self.lockparams:
if param == "ACCOUNT_SECRET":
shared += param.encode('ASCII') + self.secret
elif param == "CLIENT_ID":
shared += param.encode('ASCII') + self.dsn
else:
_assert(False, "Unknown lock parameter: %s" % param)
sharedsecrets = [obfuscate(shared, self.version),obfuscate2(shared, self.version),obfuscate3(shared, self.version)]
decrypted=False
ex=None
for sharedsecret in sharedsecrets:
key = hmac.new(sharedsecret, b"PIDv3", digestmod=hashlib.sha256).digest()
aes = AES.new(key[:32], AES.MODE_CBC, self.cipheriv[:16])
try:
b = aes.decrypt(self.ciphertext)
b = pkcs7unpad(b, 16)
decrypted=True
print("Decryption succeeded")
break
except Exception as ex:
print("Decryption failed, trying next fallback ")
if not decrypted:
raise ex
sharedsecret = obfuscate(shared, self.version)
self.drmkey = BinaryIonParser(BytesIO(b))
addprottable(self.drmkey)
_assert(self.drmkey.hasnext() and self.drmkey.next() == TID_LIST and self.drmkey.gettypename() == "[email protected]",
"Expected KeySet, got %s" % self.drmkey.gettypename())
self.drmkey.stepin()
while self.drmkey.hasnext():
self.drmkey.next()
if self.drmkey.gettypename() != "[email protected]":
continue
self.drmkey.stepin()
while self.drmkey.hasnext():
self.drmkey.next()
if self.drmkey.getfieldname() == "algorithm":
_assert(self.drmkey.stringvalue() == "AES", "Unknown cipher algorithm: %s" % self.drmkey.stringvalue())
elif self.drmkey.getfieldname() == "format":
_assert(self.drmkey.stringvalue() == "RAW", "Unknown key format: %s" % self.drmkey.stringvalue())
elif self.drmkey.getfieldname() == "encoded":
self.secretkey = self.drmkey.lobvalue()
self.drmkey.stepout()
break
self.drmkey.stepout()
def parse(self):
self.envelope.reset()
_assert(self.envelope.hasnext(), "Envelope is empty")
_assert(self.envelope.next() == TID_STRUCT and str.startswith(self.envelope.gettypename(), "com.amazon.drm.VoucherEnvelope@"),
"Unknown type encountered in envelope, expected VoucherEnvelope")
self.version = int(self.envelope.gettypename().split('@')[1][:-2])
self.envelope.stepin()
while self.envelope.hasnext():
self.envelope.next()
field = self.envelope.getfieldname()
if field == "voucher":
self.voucher = BinaryIonParser(BytesIO(self.envelope.lobvalue()))
addprottable(self.voucher)
continue
elif field != "strategy":
continue
_assert(self.envelope.gettypename() == "[email protected]", "Unknown strategy: %s" % self.envelope.gettypename())
self.envelope.stepin()
while self.envelope.hasnext():
self.envelope.next()
field = self.envelope.getfieldname()
if field == "encryption_algorithm":
self.encalgorithm = self.envelope.stringvalue()
elif field == "encryption_transformation":
self.enctransformation = self.envelope.stringvalue()
elif field == "hashing_algorithm":
self.hashalgorithm = self.envelope.stringvalue()
elif field == "lock_parameters":
self.envelope.stepin()
while self.envelope.hasnext():
_assert(self.envelope.next() == TID_STRING, "Expected string list for lock_parameters")
self.lockparams.append(self.envelope.stringvalue())
self.envelope.stepout()
self.envelope.stepout()
self.parsevoucher()
def parsevoucher(self):
_assert(self.voucher.hasnext(), "Voucher is empty")
_assert(self.voucher.next() == TID_STRUCT and self.voucher.gettypename() == "[email protected]",
"Unknown type, expected Voucher")
self.voucher.stepin()
while self.voucher.hasnext():
self.voucher.next()
if self.voucher.getfieldname() == "cipher_iv":
self.cipheriv = self.voucher.lobvalue()
elif self.voucher.getfieldname() == "cipher_text":
self.ciphertext = self.voucher.lobvalue()
elif self.voucher.getfieldname() == "license":
_assert(self.voucher.gettypename() == "[email protected]",
"Unknown license: %s" % self.voucher.gettypename())
self.voucher.stepin()
while self.voucher.hasnext():
self.voucher.next()
if self.voucher.getfieldname() == "license_type":
self.license_type = self.voucher.stringvalue()
self.voucher.stepout()
def printenvelope(self, lst):
self.envelope.print_(lst)
def printkey(self, lst):
if self.voucher is None:
self.parse()
if self.drmkey is None:
self.decryptvoucher()
self.drmkey.print_(lst)
def printvoucher(self, lst):
if self.voucher is None:
self.parse()
self.voucher.print_(lst)
def getlicensetype(self):
return self.license_type
class DrmIon(object):
ion = None
voucher = None
vouchername = ""
key = b""
onvoucherrequired = None
def __init__(self, ionstream, onvoucherrequired):
self.ion = BinaryIonParser(ionstream)
addprottable(self.ion)
self.onvoucherrequired = onvoucherrequired
def parse(self, outpages):
self.ion.reset()
_assert(self.ion.hasnext(), "DRMION envelope is empty")
_assert(self.ion.next() == TID_SYMBOL and self.ion.gettypename() == "doctype", "Expected doctype symbol")
_assert(self.ion.next() == TID_LIST and self.ion.gettypename() in ["[email protected]", "[email protected]"],
"Unknown type encountered in DRMION envelope, expected Envelope, got %s" % self.ion.gettypename())
while True:
if self.ion.gettypename() == "enddoc":
break
self.ion.stepin()
while self.ion.hasnext():
self.ion.next()
if self.ion.gettypename() in ["[email protected]", "[email protected]"]:
self.ion.stepin()
while self.ion.hasnext():
self.ion.next()
if self.ion.getfieldname() != "encryption_voucher":
continue
if self.vouchername == "":
self.vouchername = self.ion.stringvalue()
self.voucher = self.onvoucherrequired(self.vouchername)
self.key = self.voucher.secretkey
_assert(self.key is not None, "Unable to obtain secret key from voucher")
else:
_assert(self.vouchername == self.ion.stringvalue(),
"Unexpected: Different vouchers required for same file?")
self.ion.stepout()
elif self.ion.gettypename() in ["[email protected]", "[email protected]"]:
decompress = False
decrypt = True
ct = None
civ = None
self.ion.stepin()
while self.ion.hasnext():
self.ion.next()
if self.ion.gettypename() == "[email protected]":
decompress = True
if self.ion.getfieldname() == "cipher_text":
ct = self.ion.lobvalue()
elif self.ion.getfieldname() == "cipher_iv":
civ = self.ion.lobvalue()
if ct is not None and civ is not None:
self.processpage(ct, civ, outpages, decompress, decrypt)
self.ion.stepout()
elif self.ion.gettypename() in ["[email protected]", "[email protected]"]:
decompress = False
decrypt = False
plaintext = None
self.ion.stepin()
while self.ion.hasnext():
self.ion.next()
if self.ion.gettypename() == "[email protected]":
decompress = True
if self.ion.getfieldname() == "data":
plaintext = self.ion.lobvalue()
if plaintext is not None:
self.processpage(plaintext, None, outpages, decompress, decrypt)
self.ion.stepout()
self.ion.stepout()
if not self.ion.hasnext():
break
self.ion.next()
def print_(self, lst):
self.ion.print_(lst)
def processpage(self, ct, civ, outpages, decompress, decrypt):
if decrypt:
aes = AES.new(self.key[:16], AES.MODE_CBC, civ[:16])
msg = pkcs7unpad(aes.decrypt(ct), 16)
else:
msg = ct
if not decompress:
outpages.write(msg)
return
_assert(msg[0] == 0, "LZMA UseFilter not supported")
if calibre_lzma is not None:
with calibre_lzma.decompress(msg[1:], bufsize=0x1000000) as f:
f.seek(0)
outpages.write(f.read())
return
decomp = lzma.LZMADecompressor(format=lzma.FORMAT_ALONE)
while not decomp.eof:
segment = decomp.decompress(msg[1:])
msg = b"" # Contents were internally buffered after the first call
outpages.write(segment)
|