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
| import argparse
import datetime
import io
import os
import pickle
import re
import zlib
try:
import msgpack
except ImportError:
msgpack = None
class MsgpackReader:
def __init__(self, data):
self.data = data
self.offset = 0
def read(self, size):
value = self.data[self.offset : self.offset + size]
self.offset += size
return value
def read_int(self, size):
return int.from_bytes(self.read(size), "big")
def unpack(self):
marker = self.read(1)[0]
if marker <= 0x7F:
return marker
if 0x80 <= marker <= 0x8F:
return self.unpack_map(marker & 0x0F)
if 0x90 <= marker <= 0x9F:
return self.unpack_array(marker & 0x0F)
if 0xA0 <= marker <= 0xBF:
return self.read(marker & 0x1F).decode("utf-8", errors="replace")
if marker == 0xC0:
return None
if marker == 0xC2:
return False
if marker == 0xC3:
return True
if marker == 0xC4:
return self.read(self.read_int(1))
if marker == 0xC5:
return self.read(self.read_int(2))
if marker == 0xC6:
return self.read(self.read_int(4))
if marker == 0xCA:
return self.read(4)
if marker == 0xCB:
return self.read(8)
if marker == 0xCC:
return self.read_int(1)
if marker == 0xCD:
return self.read_int(2)
if marker == 0xCE:
return self.read_int(4)
if marker == 0xCF:
return self.read_int(8)
if marker == 0xD0:
return int.from_bytes(self.read(1), "big", signed=True)
if marker == 0xD1:
return int.from_bytes(self.read(2), "big", signed=True)
if marker == 0xD2:
return int.from_bytes(self.read(4), "big", signed=True)
if marker == 0xD3:
return int.from_bytes(self.read(8), "big", signed=True)
if marker == 0xD9:
return self.read(self.read_int(1)).decode("utf-8", errors="replace")
if marker == 0xDA:
return self.read(self.read_int(2)).decode("utf-8", errors="replace")
if marker == 0xDB:
return self.read(self.read_int(4)).decode("utf-8", errors="replace")
if marker == 0xDC:
return self.unpack_array(self.read_int(2))
if marker == 0xDD:
return self.unpack_array(self.read_int(4))
if marker == 0xDE:
return self.unpack_map(self.read_int(2))
if marker == 0xDF:
return self.unpack_map(self.read_int(4))
if marker >= 0xE0:
return marker - 0x100
raise ValueError(f"unsupported msgpack marker: 0x{marker:02x}")
def unpack_array(self, length):
return [self.unpack() for _ in range(length)]
def unpack_map(self, length):
result = {}
for _ in range(length):
key = self.unpack()
value = self.unpack()
result[key] = value
return result
def unpack_msgpack(raw):
if msgpack is not None:
return msgpack.unpackb(raw, raw=False)
return MsgpackReader(raw).unpack()
def timestamp_convert(timestamp):
if timestamp > 100000000000:
timestamp = timestamp / 1000
return datetime.datetime.fromtimestamp(timestamp).strftime("%Y-%m-%d %H:%M:%S")
def parse_file(path):
with open(path, "rb") as file:
data = file.read()
bio = io.BytesIO(data)
try:
timestamp = pickle.load(bio)
second = pickle.load(bio)
except Exception:
return None
if not isinstance(second, bytes):
return None
try:
raw = zlib.decompress(second)
except Exception:
raw = second
strings = [
item.decode("utf-8", errors="replace")
for item in re.findall(rb"[\x09\x0a\x0d\x20-\x7e]{2,}", raw)
]
changed_on = ""
for index, value in enumerate(strings):
if value in ("changedOn", "changed_on") and index + 1 < len(strings):
changed_on = strings[index + 1].replace("T", " ")
break
sql = ""
try:
obj = unpack_msgpack(raw)
if isinstance(obj, dict):
query = obj.get("query", {})
if isinstance(query, dict):
changed_on = (
query.get("changedOn", "")
or query.get("changed_on", "")
or changed_on
)
if changed_on:
changed_on = str(changed_on).replace("T", " ")
sql = query.get("sql", "") or query.get("executedSql", "")
except Exception:
sql = ""
if not sql:
for index, value in enumerate(strings):
if value == "executedSql" and index + 1 < len(strings):
sql = strings[index + 1]
break
if not sql:
for index, value in enumerate(strings):
if value == "sql" and index + 1 < len(strings):
sql = strings[index + 1]
break
sql = re.sub(
r"^[^A-Za-z]*(?=(SELECT|DROP|CREATE|COPY|UPDATE|INSERT|DELETE|WITH)\b)",
"",
sql,
flags=re.IGNORECASE,
)
if not sql:
return None
return {
"time": changed_on or timestamp_convert(timestamp),
"sql": sql,
}
def main():
parser = argparse.ArgumentParser(description="Extract Superset SQL Lab SQL cache")
parser.add_argument(
"-s",
"--src",
default="./sqllab_copy",
help="SQL Lab cache directory, default: ./sqllab_copy",
)
parser.add_argument(
"-o",
"--out",
default="sqllab_result.txt",
help="output txt file, default: sqllab_result.txt",
)
args = parser.parse_args()
with open(args.out, "w", encoding="utf-8") as output:
for filename in sorted(os.listdir(args.src)):
path = os.path.join(args.src, filename)
if not os.path.isfile(path):
continue
print("[+] Parsing:", filename)
result = parse_file(path)
if result is None:
continue
output.write("\n============================\n")
output.write("FILE: " + filename + "\n")
output.write("TIME: " + result["time"] + "\n")
output.write(result["sql"] + "\n")
print("[+] Done!")
print("[+] Output:", args.out)
if __name__ == "__main__":
main()
|
