/
lib_encode.py
399 lines (290 loc) · 10.4 KB
/
lib_encode.py
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
# coding: utf-8
import sys
import base64
import quopri
import re
import json
import hashlib
import urllib.parse
from .escape_table import *
quote_plus = urllib.parse.quote_plus
unquote_plus = urllib.parse.unquote_plus
ENC = 'utf8'
try:
unichr(32)
except NameError:
def unichr(val):
return chr(val)
class StringEncode():
pass
class HtmlEntitizeCommand(StringEncode):
def encode(self, text):
text = text.replace('&', '&')
for k in html_escape_table:
v = html_escape_table[k]
text = text.replace(k, v)
ret = ''
for i, c in enumerate(text):
if ord(c) > 127:
ret += hex(ord(c)).replace('0x', '&#x') + ';'
else:
ret += c
return ret
class HtmlDeentitizeCommand(StringEncode):
def encode(self, text):
for k in html_escape_table:
v = html_escape_table[k]
text = text.replace(v, k)
while re.search('&#[xX][a-fA-F0-9]+;', text):
match = re.search('&#[xX]([a-fA-F0-9]+);', text)
text = text.replace(
match.group(0), unichr(int('0x' + match.group(1), 16)))
text = text.replace('&', '&')
return text
class CssEscapeCommand(StringEncode):
def encode(self, text):
ret = ''
for i, c in enumerate(text):
if ord(c) > 127:
ret += hex(ord(c)).replace('0x', '\\')
else:
ret += c
return ret
class CssUnescapeCommand(StringEncode):
def encode(self, text):
while re.search(r'\\[a-fA-F0-9]+', text):
match = re.search(r'\\([a-fA-F0-9]+)', text)
text = text.replace(
match.group(0), unichr(int('0x' + match.group(1), 16)))
return text
class SafeHtmlEntitizeCommand(StringEncode):
def encode(self, text):
for k in html_escape_table:
# skip HTML reserved characters
if k in html_reserved_list:
continue
v = html_escape_table[k]
text = text.replace(k, v)
ret = ''
for i, c in enumerate(text):
if ord(c) > 127:
ret += hex(ord(c)).replace('0x', '&#x') + ';'
else:
ret += c
return ret
class SafeHtmlDeentitizeCommand(StringEncode):
def encode(self, text):
for k in html_escape_table:
# skip HTML reserved characters
if k in html_reserved_list:
continue
v = html_escape_table[k]
text = text.replace(v, k)
while re.search('&#[xX][a-fA-F0-9]+;', text):
match = re.search('&#[xX]([a-fA-F0-9]+);', text)
text = text.replace(
match.group(0), unichr(int('0x' + match.group(1), 16)))
text = text.replace('&', '&')
return text
class XmlEntitizeCommand(StringEncode):
def encode(self, text):
text = text.replace('&', '&')
for k in xml_escape_table:
v = xml_escape_table[k]
text = text.replace(k, v)
ret = ''
for i, c in enumerate(text):
if ord(c) > 127:
ret += hex(ord(c)).replace('0x', '&#x') + ';'
else:
ret += c
return ret
class XmlDeentitizeCommand(StringEncode):
def encode(self, text):
for k in xml_escape_table:
v = xml_escape_table[k]
text = text.replace(v, k)
text = text.replace('&', '&')
return text
class JsonEscapeCommand(StringEncode):
def encode(self, text):
return json.dumps(text)
class JsonUnescapeCommand(StringEncode):
def encode(self, text):
return json.loads(text)
class UrlEncodeCommand(StringEncode):
def encode(self, text, old_school=True):
quoted = quote_plus(text, safe='/():;.,[]@&-'+'\n\r')
if old_school:
return quoted.replace("+", "%20")
return quoted
class UrlDecodeCommand(StringEncode):
def encode(self, text):
return unquote_plus(text)
class Base64EncodeCommand(StringEncode):
def encode(self, text):
return base64.b64encode(bytes(text, ENC)).decode(ENC)
class Base64DecodeCommand(StringEncode):
def encode(self, text):
return base64.b64decode(bytes(text, ENC)).decode(ENC)
class Base32EncodeCommand(StringEncode):
def encode(self, text):
return base64.b32encode(bytes(text, ENC)).decode(ENC)
class Base32DecodeCommand(StringEncode):
def encode(self, text):
return base64.b32decode(bytes(text, ENC)).decode(ENC)
class Base16EncodeCommand(StringEncode):
def encode(self, text):
return base64.b16encode(bytes(text, ENC)).decode(ENC)
class Base16DecodeCommand(StringEncode):
def encode(self, text):
return base64.b16decode(bytes(text, ENC)).decode(ENC)
class QuoPriEncodeCommand(StringEncode):
def encode(self, text):
return quopri.encodestring(bytes(text, ENC)).decode(ENC)
class QuoPriDecodeCommand(StringEncode):
def encode(self, text):
return quopri.decodestring(bytes(text, ENC)).decode(ENC)
class UnicodeEscapeEncodeCommand(StringEncode):
def encode(self, text):
return bytes(text, 'unicode-escape').decode(ENC)
class UnicodeEscapeDecodeCommand(StringEncode):
def encode(self, text):
return bytes(text, ENC).decode('unicode-escape')
class Md5EncodeCommand(StringEncode):
def encode(self, text):
hasher = hashlib.md5()
hasher.update(bytes(text, 'utf-8'))
return hasher.hexdigest()
class Sha256EncodeCommand(StringEncode):
def encode(self, text):
hasher = hashlib.sha256()
hasher.update(bytes(text, 'utf-8'))
return hasher.hexdigest()
class Sha512EncodeCommand(StringEncode):
def encode(self, text):
hasher = hashlib.sha512()
hasher.update(bytes(text, 'utf-8'))
return hasher.hexdigest()
class Escaper(StringEncode):
def encode(self, text):
return re.sub(r'(?<!\\)(%s)' % self.meta, r'\\\1', text)
class EscapeRegexCommand(Escaper):
meta = r'[\\*.+^$()\[\]\{\}]'
class EscapeLikeCommand(Escaper):
meta = r'[%_]'
class HexDecCommand(StringEncode):
def encode(self, text):
return str(int(text, 16))
class DecHexCommand(StringEncode):
def encode(self, text):
return hex(int(text))
class UnicodeHexCommand(StringEncode):
def encode(self, text):
hex_text = u''
text_bytes = bytes(text, 'utf-16')
if text_bytes[0:2] == b'\xff\xfe':
endian = 'little'
text_bytes = text_bytes[2:]
elif text_bytes[0:2] == b'\xfe\xff':
endian = 'big'
text_bytes = text_bytes[2:]
char_index = 0
for c in text_bytes:
if char_index == 0:
c1 = c
char_index += 1
elif char_index == 1:
c2 = c
if endian == 'little':
c1, c2 = c2, c1
tmp = (c1 << 8) + c2
if tmp < 0x80:
hex_text += chr(tmp)
char_index = 0
elif tmp >= 0xd800 and tmp <= 0xdbff:
char_index += 1
else:
hex_text += '\\u' + '{0:04x}'.format(tmp)
char_index = 0
elif char_index == 2:
c3 = c
char_index += 1
elif char_index == 3:
c4 = c
if endian == 'little':
c3, c4 = c4, c3
tmp1 = ((c1 << 8) + c2) - 0xd800
tmp2 = ((c3 << 8) + c4) - 0xdc00
tmp = (tmp1 * 0x400) + tmp2 + 0x10000
hex_text += '\\U' + '{0:08x}'.format(tmp)
char_index = 0
return hex_text
class HexUnicodeCommand(StringEncode):
def encode(self, text):
uni_text = text
endian = sys.byteorder
r = re.compile(r'\\u([0-9a-fA-F]{2})([0-9a-fA-F]{2})')
rr = r.search(uni_text)
while rr:
first_byte = int(rr.group(1), 16)
if first_byte >= 0xd8 and first_byte <= 0xdf:
# Surrogate pair
pass
else:
if endian == 'little':
b1 = int(rr.group(2), 16)
b2 = int(rr.group(1), 16)
else:
b1 = int(rr.group(1), 16)
b2 = int(rr.group(2), 16)
ch = bytes([b1, b2]).decode('utf-16')
uni_text = uni_text.replace(rr.group(0), ch)
rr = r.search(uni_text, rr.start(0) + 1)
# Surrogate pair (2 bytes + 2 bytes)
r = re.compile(
r'\\u([0-9a-fA-F]{2})([0-9a-fA-F]{2})\\u([0-9a-fA-F]{2})([0-9a-fA-F]{2})')
rr = r.search(uni_text)
while rr:
if endian == 'little':
b1 = int(rr.group(2), 16)
b2 = int(rr.group(1), 16)
b3 = int(rr.group(4), 16)
b4 = int(rr.group(3), 16)
else:
b1 = int(rr.group(1), 16)
b2 = int(rr.group(2), 16)
b3 = int(rr.group(3), 16)
b4 = int(rr.group(4), 16)
ch = bytes([b1, b2, b3, b4]).decode('utf-16')
uni_text = uni_text.replace(rr.group(0), ch)
rr = r.search(uni_text)
# Surrogate pair (4 bytes)
r = re.compile(
r'\\U([0-9a-fA-F]{2})([0-9a-fA-F]{2})([0-9a-fA-F]{2})([0-9a-fA-F]{2})')
rr = r.search(uni_text)
while rr:
tmp = (int(rr.group(1), 16) << 24) \
+ (int(rr.group(2), 16) << 16) \
+ (int(rr.group(3), 16) << 8) \
+ (int(rr.group(4), 16))
if (tmp <= 0xffff):
ch = chr(tmp)
else:
tmp -= 0x10000
c1 = 0xd800 + int(tmp / 0x400)
c2 = 0xdc00 + int(tmp % 0x400)
if endian == 'little':
b1 = c1 & 0xff
b2 = c1 >> 8
b3 = c2 & 0xff
b4 = c2 >> 8
else:
b1 = c1 >> 8
b2 = c1 & 0xff
b3 = c2 >> 8
b4 = c2 & 0xff
ch = bytes([b1, b2, b3, b4]).decode('utf-16')
uni_text = uni_text.replace(rr.group(0), ch)
rr = r.search(uni_text)
return uni_text