wenlin_db_scanner 0.2.0
Sign up to get free protection for your applications and to get access to all the features.
- data/.document +5 -0
- data/Gemfile +13 -0
- data/Gemfile.lock +23 -0
- data/LICENSE.txt +122 -0
- data/README.md +102 -0
- data/Rakefile +36 -0
- data/VERSION +1 -0
- data/bin/wenlin_dbdump +24 -0
- data/bin/wenlin_dict +24 -0
- data/bin/wenlin_hanzi +13 -0
- data/bin/wenlin_parts +23 -0
- data/lib/wenlin_db_scanner.rb +13 -0
- data/lib/wenlin_db_scanner/chars.rb +210 -0
- data/lib/wenlin_db_scanner/db.rb +453 -0
- data/lib/wenlin_db_scanner/db_record.rb +43 -0
- data/lib/wenlin_db_scanner/dict.rb +373 -0
- data/lib/wenlin_db_scanner/speech_parts.rb +68 -0
- data/reversed/README.md +38 -0
- data/reversed/code.asm +1616 -0
- data/reversed/magic.txt +27 -0
- data/reversed/notes.txt +235 -0
- metadata +147 -0
@@ -0,0 +1,453 @@
|
|
1
|
+
module WenlinDbScanner
|
2
|
+
|
3
|
+
# Extracts the contents of .db files.
|
4
|
+
class Db
|
5
|
+
# New database file pointed at a path on disk.
|
6
|
+
#
|
7
|
+
# @param [String] path full or relative path to the .db file
|
8
|
+
def initialize(path)
|
9
|
+
@file = File.open path, mode: 'rb',
|
10
|
+
internal_encoding: Encoding::ASCII_8BIT,
|
11
|
+
external_encoding: Encoding::ASCII_8BIT
|
12
|
+
rewind
|
13
|
+
end
|
14
|
+
|
15
|
+
# The database's header string. Some of it is also in its tree file.
|
16
|
+
attr_reader :header
|
17
|
+
|
18
|
+
# The current position in the database file.
|
19
|
+
attr_reader :offset
|
20
|
+
|
21
|
+
# Closes the file handle used to read this databse.
|
22
|
+
#
|
23
|
+
# The database instance will be mostly unusable after this call.
|
24
|
+
def close
|
25
|
+
@file.close
|
26
|
+
@offset = nil
|
27
|
+
end
|
28
|
+
|
29
|
+
# An enumerator that returns all the records in the file.
|
30
|
+
def records
|
31
|
+
Enumerator.new do |yielder|
|
32
|
+
until @file.eof?
|
33
|
+
record = read_record
|
34
|
+
next unless record
|
35
|
+
yielder << record
|
36
|
+
end
|
37
|
+
end
|
38
|
+
end
|
39
|
+
|
40
|
+
# Reads the database record at the current position.
|
41
|
+
#
|
42
|
+
# @return [DbRecord, nil] nil returned if the entry at the current location
|
43
|
+
# is unused space
|
44
|
+
def read_record
|
45
|
+
record_offset = @offset
|
46
|
+
record_size, record_tag = read_record_header
|
47
|
+
|
48
|
+
# Easy case 1: unused areas.
|
49
|
+
unless record_tag
|
50
|
+
@file.seek record_size + 1, IO::SEEK_CUR
|
51
|
+
return nil
|
52
|
+
end
|
53
|
+
|
54
|
+
if record_tag & 2 == 0
|
55
|
+
# Easy case 2: binary records.
|
56
|
+
DbRecord.new record_offset, record_tag, record_size, true,
|
57
|
+
@file.read(record_size)
|
58
|
+
else
|
59
|
+
# The real deal: the text records.
|
60
|
+
text = utf8_bytes(record_size, record_tag).to_a.pack('C*')
|
61
|
+
DbRecord.new record_offset, record_tag, record_size, false,
|
62
|
+
text.force_encoding(Encoding::UTF_8)
|
63
|
+
end
|
64
|
+
end
|
65
|
+
|
66
|
+
# Reads the database record at a position.
|
67
|
+
#
|
68
|
+
# This method is intended to help debugging. It's not used during database
|
69
|
+
# scans.
|
70
|
+
#
|
71
|
+
# After the read, the database read position is set at the next record.
|
72
|
+
#
|
73
|
+
# @param [Integer] offset 0-based byte position in the database file
|
74
|
+
# @return [String, nil] a String with the record's contents; text records
|
75
|
+
# will be UTF8-encoded strings, binary will use the ASCII_8BIT encoding;
|
76
|
+
# if the area at the current position is unused, nil will be returned
|
77
|
+
def read_record_at(offset)
|
78
|
+
seek offset
|
79
|
+
read_record
|
80
|
+
end
|
81
|
+
|
82
|
+
# Reads the record header at the current position.
|
83
|
+
#
|
84
|
+
# This method is used internally by read_record, and should only be used
|
85
|
+
# directly for debugging purposes.
|
86
|
+
#
|
87
|
+
# Advances the internal offset field as if the entire record has already been
|
88
|
+
# read.
|
89
|
+
#
|
90
|
+
# @return [Array<(Fixnum, Fixnum)>] the size of the record, and the byte
|
91
|
+
# value of its tag; tags are nil for dead records
|
92
|
+
def read_record_header
|
93
|
+
record_size = @file.read(2).unpack('n').first
|
94
|
+
if record_size >= 0x8000
|
95
|
+
record_size = 65536 - record_size
|
96
|
+
live_record = false
|
97
|
+
else
|
98
|
+
live_record = true
|
99
|
+
end
|
100
|
+
@offset += 2 + record_size
|
101
|
+
|
102
|
+
if live_record
|
103
|
+
record_tag = @file.readbyte
|
104
|
+
else
|
105
|
+
record_tag = nil
|
106
|
+
end
|
107
|
+
return record_size - 1, record_tag
|
108
|
+
end
|
109
|
+
|
110
|
+
# Sets the read position in the database file.
|
111
|
+
#
|
112
|
+
# This method is used internally by read_record_at, and should only be used
|
113
|
+
# directly for debugging purposes.
|
114
|
+
#
|
115
|
+
# @param [Integer] offset 0-based byte position in the database file
|
116
|
+
# @return [Db] self
|
117
|
+
def seek(offset)
|
118
|
+
@file.seek offset, IO::SEEK_SET
|
119
|
+
@offset = offset
|
120
|
+
self
|
121
|
+
end
|
122
|
+
|
123
|
+
|
124
|
+
# Resets the read head.
|
125
|
+
def rewind
|
126
|
+
@file.rewind
|
127
|
+
@offset = 0
|
128
|
+
read_header
|
129
|
+
end
|
130
|
+
private :rewind
|
131
|
+
|
132
|
+
# This method's main use is to advance the read head to the actual records.
|
133
|
+
def read_header
|
134
|
+
header_size = @file.read(2).unpack('n').first
|
135
|
+
@version = @file.read(2).unpack('n').first + 1
|
136
|
+
@offset += 4 + header_size
|
137
|
+
@header = @file.read header_size
|
138
|
+
@format_switching = true # archiveDifferent in the reversed code
|
139
|
+
@header
|
140
|
+
end
|
141
|
+
private :read_header
|
142
|
+
end # class WenlinDbScanner::WenlinDb
|
143
|
+
|
144
|
+
# Stream of de-compressed UTF-8 bytes.
|
145
|
+
class Db
|
146
|
+
# An enumerator that produces UTF-8 bytes.
|
147
|
+
#
|
148
|
+
# @param [Integer] record_size raw number of bytes in the record; assumes
|
149
|
+
# that the file position does not change
|
150
|
+
# @param [Fixnum] record_tag the byte value of the 1-byte record tag
|
151
|
+
# @return [Enumerator<Fixnum>]
|
152
|
+
def utf8_bytes(record_size, record_tag)
|
153
|
+
Enumerator.new do |yielder|
|
154
|
+
bits = compressed_bits record_size, record_tag
|
155
|
+
loop do
|
156
|
+
# Use the Huffman tree to decode the first character.
|
157
|
+
node = tree_root
|
158
|
+
while node < 0x100
|
159
|
+
# p ['node', node]
|
160
|
+
bit = bits.next
|
161
|
+
# p ['bit', bit]
|
162
|
+
node = (bit == 0) ? tree_left[node] : tree_right[node]
|
163
|
+
end
|
164
|
+
first_byte = node - 0x100
|
165
|
+
# p ['utf8 start', first_byte]
|
166
|
+
yielder << first_byte
|
167
|
+
|
168
|
+
# The other characters are 10xxxxxx, where x'es are raw bits.
|
169
|
+
2.upto utf8_char_bytes(first_byte) do
|
170
|
+
byte = 0b10
|
171
|
+
6.times do
|
172
|
+
byte = (byte << 1) | bits.next
|
173
|
+
end
|
174
|
+
# p ['utf8 byte', byte]
|
175
|
+
yielder << byte
|
176
|
+
end
|
177
|
+
end
|
178
|
+
end
|
179
|
+
end
|
180
|
+
|
181
|
+
# Number of bytes in a UTF-8 character.
|
182
|
+
#
|
183
|
+
# @param [Fixnum] the byte value of the first byte in the UTF-8 character
|
184
|
+
# @return [Fixnum] 1..4
|
185
|
+
def utf8_char_bytes(first_byte)
|
186
|
+
return 1 if first_byte < 0x80
|
187
|
+
return 2 if first_byte <= 0xDF
|
188
|
+
return 3 if first_byte <= 0xEF
|
189
|
+
return 4 if first_byte <= 0xF7
|
190
|
+
return 5 if first_byte <= 0xFB
|
191
|
+
return 6 if first_byte <= 0xFD
|
192
|
+
1
|
193
|
+
end
|
194
|
+
|
195
|
+
# Some sort of Huffman tree.
|
196
|
+
def tree_root
|
197
|
+
0xFE
|
198
|
+
end
|
199
|
+
|
200
|
+
# Some sort of Huffman tree.
|
201
|
+
def tree_left
|
202
|
+
@_tree_left ||= [
|
203
|
+
0x01, 0x01, 0x03, 0x01, 0x05, 0x01, 0x07, 0x01, 0x0B, 0x01, 0x0D, 0x01,
|
204
|
+
0x0F, 0x01, 0x11, 0x01, 0x13, 0x01, 0x15, 0x01, 0x17, 0x01, 0x19, 0x01,
|
205
|
+
0x1B, 0x01, 0x1D, 0x01, 0x1F, 0x01, 0x40, 0x01, 0x5E, 0x01, 0x60, 0x01,
|
206
|
+
0x80, 0x01, 0x82, 0x01, 0x84, 0x01, 0x86, 0x01, 0x88, 0x01, 0x8A, 0x01,
|
207
|
+
0x8C, 0x01, 0x8E, 0x01, 0x90, 0x01, 0x92, 0x01, 0x94, 0x01, 0x96, 0x01,
|
208
|
+
0x98, 0x01, 0x9A, 0x01, 0x9C, 0x01, 0x9E, 0x01, 0xA0, 0x01, 0xA2, 0x01,
|
209
|
+
0xA4, 0x01, 0xA6, 0x01, 0xA8, 0x01, 0xAA, 0x01, 0xAC, 0x01, 0xAE, 0x01,
|
210
|
+
0xB0, 0x01, 0xB2, 0x01, 0xB4, 0x01, 0xB6, 0x01, 0xB8, 0x01, 0xBA, 0x01,
|
211
|
+
0xBC, 0x01, 0xBE, 0x01, 0xC0, 0x01, 0xC6, 0x01, 0xC9, 0x01, 0xCB, 0x01,
|
212
|
+
0xCE, 0x01, 0xD0, 0x01, 0xD2, 0x01, 0xD4, 0x01, 0xD6, 0x01, 0xD8, 0x01,
|
213
|
+
0xDA, 0x01, 0xDC, 0x01, 0xDE, 0x01, 0xE0, 0x01, 0xEA, 0x01, 0xEC, 0x01,
|
214
|
+
0xF0, 0x01, 0xF2, 0x01, 0xF4, 0x01, 0xF6, 0x01, 0xF8, 0x01, 0xFA, 0x01,
|
215
|
+
0xFC, 0x01, 0xFE, 0x01, 0x7E, 0x01, 0x01, 0x00, 0x03, 0x00, 0x05, 0x00,
|
216
|
+
0x07, 0x00, 0x09, 0x00, 0x0B, 0x00, 0x0D, 0x00, 0x0F, 0x00, 0x11, 0x00,
|
217
|
+
0x13, 0x00, 0x15, 0x00, 0x17, 0x00, 0x19, 0x00, 0x1B, 0x00, 0x1D, 0x00,
|
218
|
+
0x1F, 0x00, 0x21, 0x00, 0x23, 0x00, 0x25, 0x00, 0x27, 0x00, 0x29, 0x00,
|
219
|
+
0x2B, 0x00, 0x2D, 0x00, 0x2F, 0x00, 0x31, 0x00, 0x33, 0x00, 0x35, 0x00,
|
220
|
+
0x37, 0x00, 0x39, 0x00, 0x3B, 0x00, 0x3D, 0x00, 0x3F, 0x00, 0x41, 0x00,
|
221
|
+
0x43, 0x00, 0x45, 0x00, 0x47, 0x00, 0x49, 0x00, 0xCC, 0x01, 0x4B, 0x00,
|
222
|
+
0x4D, 0x00, 0x4F, 0x00, 0x51, 0x00, 0x53, 0x00, 0x55, 0x00, 0x57, 0x00,
|
223
|
+
0x59, 0x00, 0x5B, 0x00, 0x5D, 0x00, 0x5F, 0x00, 0x61, 0x00, 0x63, 0x00,
|
224
|
+
0x65, 0x00, 0x67, 0x00, 0x69, 0x00, 0x6B, 0x00, 0x6D, 0x00, 0x6F, 0x00,
|
225
|
+
0x71, 0x00, 0x73, 0x00, 0x75, 0x00, 0x77, 0x00, 0x79, 0x00, 0x7B, 0x00,
|
226
|
+
0x7D, 0x00, 0x7F, 0x00, 0x81, 0x00, 0x83, 0x00, 0xC2, 0x01, 0x85, 0x00,
|
227
|
+
0x87, 0x00, 0x89, 0x00, 0x8B, 0x00, 0x8D, 0x00, 0x8F, 0x00, 0x91, 0x00,
|
228
|
+
0x93, 0x00, 0x3C, 0x01, 0x2A, 0x01, 0x95, 0x00, 0x58, 0x01, 0x97, 0x00,
|
229
|
+
0x2B, 0x01, 0x98, 0x00, 0x4A, 0x01, 0x52, 0x01, 0x9B, 0x00, 0x21, 0x01,
|
230
|
+
0x9D, 0x00, 0x7D, 0x01, 0x26, 0x01, 0x9F, 0x00, 0xA1, 0x00, 0x47, 0x01,
|
231
|
+
0x45, 0x01, 0xA2, 0x00, 0x4D, 0x01, 0x44, 0x01, 0x4E, 0x01, 0x48, 0x01,
|
232
|
+
0x3D, 0x01, 0x4C, 0x01, 0xA6, 0x00, 0xA8, 0x00, 0xAA, 0x00, 0xAC, 0x00,
|
233
|
+
0x41, 0x01, 0xAF, 0x00, 0xB1, 0x00, 0x43, 0x01, 0xB3, 0x00, 0xB5, 0x00,
|
234
|
+
0x39, 0x01, 0x36, 0x01, 0xB6, 0x00, 0xB7, 0x00, 0xB8, 0x00, 0x4B, 0x01,
|
235
|
+
0x71, 0x01, 0x33, 0x01, 0xC5, 0x01, 0xBA, 0x00, 0x09, 0x01, 0x30, 0x01,
|
236
|
+
0xBD, 0x00, 0xBE, 0x00, 0xBF, 0x00, 0xC0, 0x00, 0x6B, 0x01, 0xC3, 0x00,
|
237
|
+
0xC4, 0x00, 0xC5, 0x00, 0x78, 0x01, 0xC7, 0x00, 0xC7, 0x01, 0xC8, 0x00,
|
238
|
+
0xC9, 0x00, 0x62, 0x01, 0x2C, 0x01, 0x79, 0x01, 0xE9, 0x01, 0x66, 0x01,
|
239
|
+
0x5B, 0x01, 0xCE, 0x00, 0xCF, 0x00, 0x70, 0x01, 0xD1, 0x00, 0x29, 0x01,
|
240
|
+
0xD2, 0x00, 0x6D, 0x01, 0x67, 0x01, 0xD5, 0x00, 0x2E, 0x01, 0xD7, 0x00,
|
241
|
+
0x6C, 0x01, 0xC3, 0x01, 0xE5, 0x01, 0x68, 0x01, 0xDB, 0x00, 0x73, 0x01,
|
242
|
+
0xDE, 0x00, 0x74, 0x01, 0xE1, 0x00, 0x69, 0x01, 0x61, 0x01, 0xE3, 0x00,
|
243
|
+
0xE5, 0x00, 0xE6, 0x00, 0x65, 0x01, 0x6E, 0x01, 0xEA, 0x00, 0xEC, 0x00,
|
244
|
+
0xEE, 0x00, 0xF0, 0x00, 0xF2, 0x00, 0xF4, 0x00, 0x20, 0x01, 0xF7, 0x00,
|
245
|
+
0xF9, 0x00, 0xFB, 0x00, 0xFD, 0x00, 0x00, 0x01
|
246
|
+
].pack('C*').unpack('v*')
|
247
|
+
end
|
248
|
+
|
249
|
+
# Some sort of Huffman tree.
|
250
|
+
def tree_right
|
251
|
+
@_tree_right ||= [
|
252
|
+
0x01, 0x00, 0x02, 0x01, 0x04, 0x01, 0x06, 0x01, 0x08, 0x01, 0x0C, 0x01,
|
253
|
+
0x0E, 0x01, 0x10, 0x01, 0x12, 0x01, 0x14, 0x01, 0x16, 0x01, 0x18, 0x01,
|
254
|
+
0x1A, 0x01, 0x1C, 0x01, 0x1E, 0x01, 0x25, 0x01, 0x5C, 0x01, 0x5F, 0x01,
|
255
|
+
0x7F, 0x01, 0x81, 0x01, 0x83, 0x01, 0x85, 0x01, 0x87, 0x01, 0x89, 0x01,
|
256
|
+
0x8B, 0x01, 0x8D, 0x01, 0x8F, 0x01, 0x91, 0x01, 0x93, 0x01, 0x95, 0x01,
|
257
|
+
0x97, 0x01, 0x99, 0x01, 0x9B, 0x01, 0x9D, 0x01, 0x9F, 0x01, 0xA1, 0x01,
|
258
|
+
0xA3, 0x01, 0xA5, 0x01, 0xA7, 0x01, 0xA9, 0x01, 0xAB, 0x01, 0xAD, 0x01,
|
259
|
+
0xAF, 0x01, 0xB1, 0x01, 0xB3, 0x01, 0xB5, 0x01, 0xB7, 0x01, 0xB9, 0x01,
|
260
|
+
0xBB, 0x01, 0xBD, 0x01, 0xBF, 0x01, 0xC1, 0x01, 0xC8, 0x01, 0xCA, 0x01,
|
261
|
+
0xCD, 0x01, 0xCF, 0x01, 0xD1, 0x01, 0xD3, 0x01, 0xD5, 0x01, 0xD7, 0x01,
|
262
|
+
0xD9, 0x01, 0xDB, 0x01, 0xDD, 0x01, 0xDF, 0x01, 0xE1, 0x01, 0xEB, 0x01,
|
263
|
+
0xED, 0x01, 0xF1, 0x01, 0xF3, 0x01, 0xF5, 0x01, 0xF7, 0x01, 0xF9, 0x01,
|
264
|
+
0xFB, 0x01, 0xFD, 0x01, 0xFF, 0x01, 0x00, 0x00, 0x02, 0x00, 0x04, 0x00,
|
265
|
+
0x06, 0x00, 0x08, 0x00, 0x0A, 0x00, 0x0C, 0x00, 0x0E, 0x00, 0x10, 0x00,
|
266
|
+
0x12, 0x00, 0x14, 0x00, 0x16, 0x00, 0x18, 0x00, 0x1A, 0x00, 0x1C, 0x00,
|
267
|
+
0x1E, 0x00, 0x20, 0x00, 0x22, 0x00, 0x24, 0x00, 0x26, 0x00, 0x28, 0x00,
|
268
|
+
0x2A, 0x00, 0x2C, 0x00, 0x2E, 0x00, 0x30, 0x00, 0x32, 0x00, 0x34, 0x00,
|
269
|
+
0x36, 0x00, 0x38, 0x00, 0x3A, 0x00, 0x3C, 0x00, 0x3E, 0x00, 0x40, 0x00,
|
270
|
+
0x42, 0x00, 0x44, 0x00, 0x46, 0x00, 0x48, 0x00, 0x4A, 0x00, 0x24, 0x01,
|
271
|
+
0x4C, 0x00, 0x4E, 0x00, 0x50, 0x00, 0x52, 0x00, 0x54, 0x00, 0x56, 0x00,
|
272
|
+
0x58, 0x00, 0x5A, 0x00, 0x5C, 0x00, 0x5E, 0x00, 0x60, 0x00, 0x62, 0x00,
|
273
|
+
0x64, 0x00, 0x66, 0x00, 0x68, 0x00, 0x6A, 0x00, 0x6C, 0x00, 0x6E, 0x00,
|
274
|
+
0x70, 0x00, 0x72, 0x00, 0x74, 0x00, 0x76, 0x00, 0x78, 0x00, 0x7A, 0x00,
|
275
|
+
0x7C, 0x00, 0x7E, 0x00, 0x80, 0x00, 0x82, 0x00, 0x7C, 0x01, 0x84, 0x00,
|
276
|
+
0x86, 0x00, 0x88, 0x00, 0x8A, 0x00, 0x8C, 0x00, 0x8E, 0x00, 0x90, 0x00,
|
277
|
+
0x92, 0x00, 0x51, 0x01, 0x94, 0x00, 0x56, 0x01, 0x96, 0x00, 0x3E, 0x01,
|
278
|
+
0x5A, 0x01, 0x55, 0x01, 0x99, 0x00, 0x9A, 0x00, 0x2F, 0x01, 0xEF, 0x01,
|
279
|
+
0x9C, 0x00, 0x7B, 0x01, 0x59, 0x01, 0x9E, 0x00, 0xA0, 0x00, 0x3F, 0x01,
|
280
|
+
0xE2, 0x01, 0x4F, 0x01, 0x42, 0x01, 0xE3, 0x01, 0xA3, 0x00, 0xA4, 0x00,
|
281
|
+
0x50, 0x01, 0xA5, 0x00, 0x49, 0x01, 0xA7, 0x00, 0xA9, 0x00, 0xAB, 0x00,
|
282
|
+
0xAD, 0x00, 0xAE, 0x00, 0xB0, 0x00, 0x57, 0x01, 0xB2, 0x00, 0xB4, 0x00,
|
283
|
+
0x54, 0x01, 0x37, 0x01, 0x38, 0x01, 0xEE, 0x01, 0x22, 0x01, 0x35, 0x01,
|
284
|
+
0x34, 0x01, 0xB9, 0x00, 0x2D, 0x01, 0x3A, 0x01, 0x32, 0x01, 0xBB, 0x00,
|
285
|
+
0xBC, 0x00, 0x53, 0x01, 0x31, 0x01, 0x7A, 0x01, 0xC1, 0x00, 0xC2, 0x00,
|
286
|
+
0x46, 0x01, 0x6A, 0x01, 0xC6, 0x00, 0xE4, 0x01, 0x3B, 0x01, 0x76, 0x01,
|
287
|
+
0x77, 0x01, 0xC4, 0x01, 0xCA, 0x00, 0xCB, 0x00, 0xCC, 0x00, 0xCD, 0x00,
|
288
|
+
0x27, 0x01, 0x5D, 0x01, 0xE7, 0x01, 0xE8, 0x01, 0xD0, 0x00, 0x28, 0x01,
|
289
|
+
0xE6, 0x01, 0xD3, 0x00, 0xD4, 0x00, 0x75, 0x01, 0x23, 0x01, 0xD6, 0x00,
|
290
|
+
0x64, 0x01, 0xD8, 0x00, 0xD9, 0x00, 0x63, 0x01, 0xDA, 0x00, 0xDC, 0x00,
|
291
|
+
0xDD, 0x00, 0xDF, 0x00, 0xE0, 0x00, 0x72, 0x01, 0xE2, 0x00, 0x6F, 0x01,
|
292
|
+
0xE4, 0x00, 0x0A, 0x01, 0xE7, 0x00, 0xE8, 0x00, 0xE9, 0x00, 0xEB, 0x00,
|
293
|
+
0xED, 0x00, 0xEF, 0x00, 0xF1, 0x00, 0xF3, 0x00, 0xF5, 0x00, 0xF6, 0x00,
|
294
|
+
0xF8, 0x00, 0xFA, 0x00, 0xFC, 0x00, 0x00, 0x01
|
295
|
+
].pack('C*').unpack('v*')
|
296
|
+
end
|
297
|
+
end
|
298
|
+
|
299
|
+
# Stream of unscrambled, compressed bits.
|
300
|
+
class Db
|
301
|
+
# An enumerator that produces the bits of the compressed stream.
|
302
|
+
#
|
303
|
+
# @param [Integer] record_size raw number of bytes in the record; assumes
|
304
|
+
# that the file position does not change
|
305
|
+
# @param [Fixnum] record_tag the byte value of the 1-byte record tag
|
306
|
+
# @return [Enumerator<Fixnum>]
|
307
|
+
def compressed_bits(record_size, record_tag)
|
308
|
+
Enumerator.new do |yielder|
|
309
|
+
mask_offset = if @version == 1 or !@format_switching
|
310
|
+
8 * (record_size & 7)
|
311
|
+
else
|
312
|
+
8 * ((record_size + (record_tag & 1)) & 7)
|
313
|
+
end
|
314
|
+
sub_mask = mask[mask_offset, 8]
|
315
|
+
scrambled_bytes(record_size, record_tag).each do |byte|
|
316
|
+
# p ['scrabled byte', byte]
|
317
|
+
sub_mask.each do |mask_byte|
|
318
|
+
yielder << ((byte & mask_byte) == 0 ? 0 : 1)
|
319
|
+
end
|
320
|
+
end
|
321
|
+
end
|
322
|
+
end
|
323
|
+
|
324
|
+
# Each mask element points to a bit.
|
325
|
+
def mask
|
326
|
+
@_mask ||= if @version == 1
|
327
|
+
[
|
328
|
+
0x08, 0x40, 0x80, 0x01, 0x20, 0x02, 0x04, 0x10, 0x04, 0x10, 0x01, 0x80,
|
329
|
+
0x08, 0x02, 0x40, 0x20, 0x40, 0x80, 0x08, 0x20, 0x04, 0x10, 0x02, 0x01,
|
330
|
+
0x02, 0x04, 0x10, 0x01, 0x80, 0x40, 0x20, 0x08, 0x80, 0x04, 0x02, 0x20,
|
331
|
+
0x01, 0x08, 0x10, 0x40, 0x01, 0x40, 0x04, 0x20, 0x10, 0x80, 0x08, 0x02,
|
332
|
+
0x10, 0x04, 0x08, 0x40, 0x20, 0x80, 0x01, 0x02, 0x20, 0x40, 0x08, 0x10,
|
333
|
+
0x01, 0x04, 0x02, 0x80
|
334
|
+
]
|
335
|
+
else
|
336
|
+
[
|
337
|
+
0x08, 0x40, 0x80, 0x01, 0x20, 0x02, 0x04, 0x10, 0x04, 0x10, 0x01, 0x80,
|
338
|
+
0x08, 0x02, 0x40, 0x20, 0x40, 0x80, 0x08, 0x20, 0x04, 0x10, 0x02, 0x01,
|
339
|
+
0x02, 0x04, 0x10, 0x01, 0x80, 0x40, 0x20, 0x08, 0x80, 0x04, 0x02, 0x20,
|
340
|
+
0x01, 0x08, 0x10, 0x40, 0x01, 0x40, 0x04, 0x20, 0x10, 0x80, 0x08, 0x02,
|
341
|
+
0x10, 0x04, 0x08, 0x40, 0x20, 0x80, 0x01, 0x02, 0x20, 0x40, 0x08, 0x10,
|
342
|
+
0x01, 0x04, 0x02, 0x80
|
343
|
+
]
|
344
|
+
end
|
345
|
+
end
|
346
|
+
end # Stream of unscrambled, compressed bits
|
347
|
+
|
348
|
+
# Stream of xor-decrypted bytes.
|
349
|
+
class Db
|
350
|
+
# An enumerator that produces decrypted bytes.
|
351
|
+
#
|
352
|
+
# @param [Integer] record_size raw number of bytes in the record; assumes
|
353
|
+
# that the file position does not change
|
354
|
+
# @param [Fixnum] record_tag the byte value of the 1-byte record tag
|
355
|
+
# @return [Enumerator<Fixnum>]
|
356
|
+
def scrambled_bytes(record_size, record_tag)
|
357
|
+
Enumerator.new do |yielder|
|
358
|
+
pad_offset = if @version == 1 or !@format_switching
|
359
|
+
record_size % xor_pad.length
|
360
|
+
else
|
361
|
+
(record_size + (record_tag & 1) * 8) % xor_pad.length
|
362
|
+
end
|
363
|
+
|
364
|
+
xored_bytes(record_size, record_tag).each do |byte|
|
365
|
+
# p ['xored byte', byte]
|
366
|
+
yielder << (byte ^ xor_pad[pad_offset])
|
367
|
+
pad_offset -= 1
|
368
|
+
pad_offset = xor_pad.length - 1 if pad_offset < 0
|
369
|
+
end
|
370
|
+
end
|
371
|
+
end
|
372
|
+
|
373
|
+
# XOR pad for the encrypted bytes.
|
374
|
+
def xor_pad
|
375
|
+
@_xor_pad ||= if @version == 1
|
376
|
+
[
|
377
|
+
0xC9, 0xE3, 0x72, 0x38, 0xEC, 0x16, 0x13, 0x58, 0xC2, 0x2C, 0xA2, 0x26,
|
378
|
+
0xB1, 0x13, 0xF1, 0xC9, 0xBD, 0xD4, 0x58, 0xF2, 0xAB, 0x52, 0x2E, 0x61,
|
379
|
+
0xA7, 0xA1, 0xCB, 0x8F, 0x71, 0x29, 0xCE, 0x84, 0xE2, 0x78, 0x68, 0xBB,
|
380
|
+
0x3C, 0x2E, 0x16, 0x89, 0xBE, 0x8C, 0x93, 0xCD, 0xE9, 0xEF, 0x49, 0x75,
|
381
|
+
0x84, 0xA9, 0xEF, 0x92, 0x56, 0x78, 0x3C, 0x1E, 0x17, 0x13, 0x8D, 0xB9,
|
382
|
+
0xC7, 0x64, 0xEF, 0xB4
|
383
|
+
]
|
384
|
+
else
|
385
|
+
[
|
386
|
+
0xE2, 0x68, 0xBB, 0x3C, 0x2E, 0x16, 0x89, 0xBE, 0x8C, 0x95, 0xCD, 0xE9,
|
387
|
+
0xEF, 0x49, 0x75, 0x78, 0x84, 0xA9, 0xEF, 0x92, 0x56, 0x72, 0x2C, 0x1E,
|
388
|
+
0x15, 0x16, 0x8D, 0xB9, 0xC6, 0x64, 0xEF, 0xB4, 0xC9, 0xE3, 0x75, 0x38,
|
389
|
+
0xEC, 0x17, 0x13, 0x52, 0x2C, 0xA2, 0x27, 0xB1, 0x13, 0xF1, 0xC9, 0xC2,
|
390
|
+
0xBD, 0xD4, 0x58, 0xF3, 0xAB, 0x52, 0x2E, 0x61, 0xA6, 0xA1, 0xCB, 0x8F,
|
391
|
+
0x71, 0x29, 0xCE, 0x84
|
392
|
+
]
|
393
|
+
end
|
394
|
+
end
|
395
|
+
end # Stream of xor-decrypted bytes
|
396
|
+
|
397
|
+
# Stream of xor-encrypted bytes.
|
398
|
+
class Db
|
399
|
+
# An enumerator that produces encrypted bytes.
|
400
|
+
#
|
401
|
+
# @param [Integer] record_size raw number of bytes in the record; assumes
|
402
|
+
# that the file position does not change
|
403
|
+
# @param [Fixnum] record_tag the byte value of the 1-byte record tag
|
404
|
+
# @return [Enumerator<Fixnum>]
|
405
|
+
def xored_bytes(record_size, record_tag)
|
406
|
+
Enumerator.new do |yielder|
|
407
|
+
record_offset = 0
|
408
|
+
if @version != 1 and record_size >= 8
|
409
|
+
vector = @file.read(9).unpack('C*')
|
410
|
+
vector.each_index do |i|
|
411
|
+
sum = 0
|
412
|
+
vector.each.with_index do |byte, j|
|
413
|
+
sum = sum + byte * inverse_matrix[i * 9 + j]
|
414
|
+
end
|
415
|
+
yielder << (sum & 0xFF)
|
416
|
+
end
|
417
|
+
record_offset += 9
|
418
|
+
end
|
419
|
+
record_offset.upto(record_size - 1) { yielder << @file.readbyte }
|
420
|
+
end
|
421
|
+
end
|
422
|
+
|
423
|
+
# Currently unused, but let's keep it around just in case.
|
424
|
+
def matrix
|
425
|
+
@_matrix ||= [
|
426
|
+
0x47, 0xFC, 0x6D, 0x84, 0x28, 0xFD, 0x4C, 0xB8, 0x7F, 0x7B, 0xAC, 0x44,
|
427
|
+
0x72, 0x46, 0xDC, 0x0D, 0x3C, 0x5B, 0xFE, 0x0C, 0xD9, 0x25, 0x97, 0xE9,
|
428
|
+
0x76, 0x76, 0xD5, 0x5F, 0x9B, 0x44, 0xA4, 0x4F, 0x16, 0x24, 0x6F, 0xA1,
|
429
|
+
0xA7, 0x86, 0xB6, 0xDE, 0x6D, 0xB6, 0x54, 0x8E, 0x13, 0x8E, 0x8E, 0x53,
|
430
|
+
0xBA, 0xFC, 0xDB, 0xC2, 0xA5, 0x37, 0x75, 0x04, 0xA6, 0xC0, 0xA4, 0x31,
|
431
|
+
0x4C, 0x1B, 0xC5, 0x68, 0xC9, 0x4A, 0x1D, 0xAE, 0xA5, 0x0E, 0x60, 0x8C,
|
432
|
+
0x25, 0xDD, 0xFF, 0x67, 0x79, 0xA2, 0x35, 0x9D, 0xA8
|
433
|
+
]
|
434
|
+
end
|
435
|
+
private :matrix
|
436
|
+
|
437
|
+
# Used to scramble the first 9 bytes of each record.
|
438
|
+
def inverse_matrix
|
439
|
+
@_inverse_matrix ||= [
|
440
|
+
0x19, 0xFA, 0xCB, 0xED, 0xE4, 0xB6, 0xD9, 0xAF, 0x7A, 0x8E, 0xA8, 0x8F,
|
441
|
+
0x20, 0x2F, 0xA1, 0x27, 0x17, 0x5A, 0xA5, 0x24, 0xF1, 0x0B, 0x44, 0xB9,
|
442
|
+
0x32, 0xB7, 0xAA, 0xFE, 0x99, 0x78, 0xB9, 0x3A, 0xA7, 0x2F, 0x56, 0x5D,
|
443
|
+
0x68, 0x2D, 0x00, 0xDC, 0x5E, 0xEB, 0xB2, 0x73, 0x5B, 0x02, 0xB9, 0xEF,
|
444
|
+
0xE9, 0x15, 0x82, 0x66, 0xE2, 0x05, 0xE2, 0xE6, 0x8C, 0xB2, 0x35, 0xC7,
|
445
|
+
0x8E, 0xCB, 0x3B, 0xCA, 0x16, 0xA1, 0x77, 0x26, 0xA7, 0xD9, 0x15, 0xE0,
|
446
|
+
0xF1, 0x63, 0x89, 0xD3, 0x59, 0xA5, 0x57, 0x1E, 0xF1
|
447
|
+
]
|
448
|
+
end
|
449
|
+
private :inverse_matrix
|
450
|
+
end # Stream of encrypted bytes.
|
451
|
+
|
452
|
+
end # namespace WenlinDbScanner
|
453
|
+
|