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
|
#!/usr/bin/env python3
import struct
import sys
import os
import hashlib
TOKENS_VERSION = 3
BLOCK_SIZE = 16384
ENTRY_SIZE = 158
MAX_ENTRIES = (BLOCK_SIZE - 8) // ENTRY_SIZE
ENTRY_CONTENTS_HEADER = b'\x55' * 32
ENTRY_CONTENTS_FOOTER = b'\xAA' * 32
def parse_entry(f, offset):
f.seek(offset)
unpacked = struct.unpack('<lllll', f.read(20))
if unpacked[0] != offset or unpacked[1] == 0 or unpacked[2] == 0:
return None
(name_b, ext_b) = struct.unpack('<130s8s', f.read(138))
name = (
name_b.decode('utf-16-le').rstrip('\0'),
ext_b.decode('utf-16-le').rstrip('\0')
)
return (unpacked[2], unpacked[3], name)
def parse_block_entries(f, offset):
o_entry = offset + ((MAX_ENTRIES - 1) * ENTRY_SIZE)
entries = []
for i in range(MAX_ENTRIES):
entry = parse_entry(f, o_entry)
o_entry -= ENTRY_SIZE
if entry != None:
entries.append(entry)
return entries
def parse_block(f, offset):
f.seek(offset)
unpacked = struct.unpack('<ll', f.read(8))
if unpacked[0] != offset:
return None
entries = parse_block_entries(f, f.tell())
return (entries, unpacked[1])
def get_token(f, entry):
(offset, length, name) = entry
f.seek(offset)
if f.read(32) != ENTRY_CONTENTS_HEADER:
return None
(h_len, h_sha256) = struct.unpack('<l32s', f.read(36))
if length != h_len:
return None
contents = f.read(h_len)
if f.read(32) != ENTRY_CONTENTS_FOOTER:
return None
return (name, contents)
def get_tokens(f):
f.seek(0)
if struct.unpack('<l32xl', f.read(40)) != (TOKENS_VERSION, 36):
return None
offset = 36
all_entries = []
while offset != 0:
(entries, offset) = parse_block(f, offset)
all_entries += entries
tokens = []
for entry in all_entries:
token = get_token(f, entry)
if token != None:
tokens.append(token)
return tokens
def build_entry_value(data):
d_len = len(data).to_bytes(4, "little")
d_sha256 = hashlib.sha256(data).digest()
value = ENTRY_CONTENTS_HEADER
value += d_len
value += d_sha256
value += data
value += ENTRY_CONTENTS_FOOTER
return (value, len(value))
def build_entry_meta(o_meta, populated, o_value, vd_len, name):
return struct.pack(
"<IIIII130s8s",
o_meta,
populated,
o_value,
vd_len,
vd_len,
name[0].encode('utf-16-le'),
name[1].encode('utf-16-le')
)
def build_entry(o_meta, o_value, entry):
value, v_len = build_entry_value(entry[1])
vd_len = len(entry[1])
meta = build_entry_meta(o_meta, True, o_value, vd_len, entry[0])
return (value, v_len, meta)
def build_entries_block(entries, o_start):
meta_block = b''
data_block = b''
o_meta = o_start + 8 + ((MAX_ENTRIES - 1) * ENTRY_SIZE)
o_data = o_start + BLOCK_SIZE + 32
next_block = 0
write_entries = len(entries)
write_next_block_offset = False
if len(entries) > MAX_ENTRIES:
write_entries = MAX_ENTRIES
write_next_block_offset = True
for _ in range(write_entries):
data, data_len, meta = build_entry(o_meta, o_data, entries.pop(0))
meta_block = meta + meta_block
o_meta -= ENTRY_SIZE
data_block += data
o_data += data_len
for _ in range(MAX_ENTRIES - write_entries):
meta = build_entry_meta(o_meta, False, 0, 0xFFFFFFFF, ('', ''))
meta_block = meta + meta_block
o_meta -= ENTRY_SIZE
if write_next_block_offset:
next_block = o_data
finished_block = struct.pack("<II", o_start, next_block)
finished_block += meta_block
finished_block += b'\0' * (BLOCK_SIZE - (MAX_ENTRIES * ENTRY_SIZE) - 8)
finished_block += hashlib.sha256(finished_block).digest()
finished_block += data_block
return (finished_block, next_block, entries)
def build_tokens(entries):
tokens_data = b''
header = TOKENS_VERSION.to_bytes(4, "little")
o_next = 36
entries_l = entries
while o_next != 0:
block, o_next, entries_l = build_entries_block(entries_l, o_next)
tokens_data += block
tokens_hash = hashlib.sha256(header + tokens_data).digest()
finished_tokens = header
finished_tokens += tokens_hash
finished_tokens += tokens_data
return finished_tokens
if __name__ == '__main__':
if len(sys.argv) != 3:
print(f'Usage: {sys.argv[0]} source_tokens_file destination_tokens_file')
exit(1)
source = sys.argv[1]
destination = sys.argv[2]
if not os.path.isfile(source):
print(f'Source {source} is not a file')
exit(1)
if os.path.isdir(destination):
print(f'Source {source} is a directory')
exit(1)
with open(source, 'rb') as f:
tokens = get_tokens(f)
with open(destination, 'wb') as f:
f.write(build_tokens(tokens))
|
