{{ message }}
forked from python/cpython
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathbase64.py
More file actions
498 lines (404 loc) · 19 KB
/
Copy pathbase64.py
File metadata and controls
498 lines (404 loc) · 19 KB
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
"""Base16, Base32, Base64 (RFC 3548), Base85 and Ascii85 data encodings"""
# Modified 04-Oct-1995 by Jack Jansen to use binascii module
# Modified 30-Dec-2003 by Barry Warsaw to add full RFC 3548 support
# Modified 22-May-2007 by Guido van Rossum to use bytes everywhere
import binascii
__all__ = [
# Legacy interface exports traditional RFC 2045 Base64 encodings
'encode', 'decode', 'encodebytes', 'decodebytes',
# Generalized interface for other encodings
'b64encode', 'b64decode', 'b32encode', 'b32decode',
'b32hexencode', 'b32hexdecode', 'b16encode', 'b16decode',
# Base85 and Ascii85 encodings
'b85encode', 'b85decode', 'a85encode', 'a85decode', 'z85encode', 'z85decode',
# Standard Base64 encoding
'standard_b64encode', 'standard_b64decode',
# Some common Base64 alternatives. As referenced by RFC 3458, see thread
# starting at:
#
# http://zgp.org/pipermail/p2p-hackers/2001-September/000316.html
'urlsafe_b64encode', 'urlsafe_b64decode',
]
_NOT_SPECIFIED = ['NOT SPECIFIED']
bytes_types = (bytes, bytearray) # Types acceptable as binary data
def _bytes_from_decode_data(s):
if isinstance(s, str):
try:
return s.encode('ascii')
except UnicodeEncodeError:
raise ValueError('string argument should contain only ASCII characters')
if isinstance(s, bytes_types):
return s
try:
return memoryview(s).tobytes()
except TypeError:
raise TypeError("argument should be a bytes-like object or ASCII "
"string, not %r" % s.__class__.__name__) from None
# Base64 encoding/decoding uses binascii
def b64encode(s, altchars=None, *, padded=True, wrapcol=0):
"""Encode the bytes-like object s using Base64 and return a bytes object.
Optional altchars should be a byte string of length 2 which specifies an
alternative alphabet for the '+' and '/' characters. This allows an
application to e.g. generate url or filesystem safe Base64 strings.
If padded is false, omit padding in the output.
If wrapcol is non-zero, insert a newline (b'\\n') character after at most
every wrapcol characters.
"""
if altchars is not None:
if len(altchars) != 2:
raise ValueError(f'invalid altchars: {altchars!r}')
alphabet = binascii.BASE64_ALPHABET[:-2] + altchars
return binascii.b2a_base64(s, padded=padded, wrapcol=wrapcol, newline=False,
alphabet=alphabet)
return binascii.b2a_base64(s, padded=padded, wrapcol=wrapcol, newline=False)
def b64decode(s, altchars=None, validate=_NOT_SPECIFIED,
*, padded=True, ignorechars=_NOT_SPECIFIED, canonical=False):
"""Decode the Base64 encoded bytes-like object or ASCII string s.
Optional altchars must be a bytes-like object or ASCII string of length 2
which specifies the alternative alphabet used instead of the '+' and '/'
characters.
If padded is false, padding in input is not required.
The result is returned as a bytes object. A binascii.Error is raised if
s is incorrectly padded.
If ignorechars is specified, it should be a byte string containing
characters to ignore from the input. The default value of validate is
True if ignorechars is specified, False otherwise.
If validate is false, characters that are neither in the normal base-64
alphabet nor the alternative alphabet are discarded prior to the
padding check. If validate is true, these non-alphabet characters in
the input result in a binascii.Error if they are not in ignorechars.
For more information about the strict base64 check, see:
https://docs.python.org/3.11/library/binascii.html#binascii.a2b_base64
"""
s = _bytes_from_decode_data(s)
if validate is _NOT_SPECIFIED:
validate = ignorechars is not _NOT_SPECIFIED
badchar = None
if altchars is not None:
altchars = _bytes_from_decode_data(altchars)
if len(altchars) != 2:
raise ValueError(f'invalid altchars: {altchars!r}')
if ignorechars is _NOT_SPECIFIED:
for b in b'+/':
if b not in altchars and b in s:
badchar = b
break
s = s.translate(bytes.maketrans(altchars, b'+/'))
else:
alphabet = binascii.BASE64_ALPHABET[:-2] + altchars
return binascii.a2b_base64(s, strict_mode=validate,
alphabet=alphabet,
padded=padded, ignorechars=ignorechars,
canonical=canonical)
if ignorechars is _NOT_SPECIFIED:
ignorechars = b''
result = binascii.a2b_base64(s, strict_mode=validate,
padded=padded, ignorechars=ignorechars,
canonical=canonical)
if badchar is not None:
import warnings
if validate:
warnings.warn(f'invalid character {chr(badchar)!a} in Base64 data '
f'with altchars={altchars!r} and validate=True '
f'will be an error in future Python versions',
DeprecationWarning, stacklevel=2)
else:
warnings.warn(f'invalid character {chr(badchar)!a} in Base64 data '
f'with altchars={altchars!r} and validate=False '
f'will be discarded in future Python versions',
FutureWarning, stacklevel=2)
return result
def standard_b64encode(s):
"""Encode bytes-like object s using the standard Base64 alphabet.
The result is returned as a bytes object.
"""
return b64encode(s)
def standard_b64decode(s):
"""Decode bytes encoded with the standard Base64 alphabet.
Argument s is a bytes-like object or ASCII string to decode. The result
is returned as a bytes object. A binascii.Error is raised if the input
is incorrectly padded. Characters that are not in the standard alphabet
are discarded prior to the padding check.
"""
return b64decode(s)
_urlsafe_decode_translation = bytes.maketrans(b'-_', b'+/')
def urlsafe_b64encode(s, *, padded=True):
"""Encode bytes using the URL- and filesystem-safe Base64 alphabet.
Argument s is a bytes-like object to encode. The result is returned as a
bytes object. The alphabet uses '-' instead of '+' and '_' instead of
'/'.
If padded is false, omit padding in the output.
"""
return binascii.b2a_base64(s, padded=padded, newline=False,
alphabet=binascii.URLSAFE_BASE64_ALPHABET)
def urlsafe_b64decode(s, *, padded=False):
"""Decode bytes using the URL- and filesystem-safe Base64 alphabet.
Argument s is a bytes-like object or ASCII string to decode. The result
is returned as a bytes object. A binascii.Error is raised if the input
is incorrectly padded. Characters that are not in the URL-safe base-64
alphabet, and are not a plus '+' or slash '/', are discarded prior to the
padding check.
If padded is false, padding in input is not required.
The alphabet uses '-' instead of '+' and '_' instead of '/'.
"""
s = _bytes_from_decode_data(s)
badchar = None
for b in b'+/':
if b in s:
badchar = b
break
s = s.translate(_urlsafe_decode_translation)
result = binascii.a2b_base64(s, strict_mode=False, padded=padded)
if badchar is not None:
import warnings
warnings.warn(f'invalid character {chr(badchar)!a} in URL-safe Base64 data '
f'will be discarded in future Python versions',
FutureWarning, stacklevel=2)
return result
# Base32 encoding/decoding must be done in Python
_B32_ENCODE_DOCSTRING = '''
Encode the bytes-like objects using {encoding} and return a bytes object.
If padded is false, omit padding in the output.
If wrapcol is non-zero, insert a newline (b'\\n') character after at most
every wrapcol characters.
'''
_B32_DECODE_DOCSTRING = '''
Decode the {encoding} encoded bytes-like object or ASCII string s.
Optional casefold is a flag specifying whether a lowercase alphabet is
acceptable as input. For security purposes, the default is False.
If padded is false, padding in input is not required.
ignorechars should be a byte string containing characters to ignore
from the input.
{extra_args}
The result is returned as a bytes object. A binascii.Error is raised if
the input is incorrectly padded or if there are non-alphabet
characters present in the input.
'''
_B32_DECODE_MAP01_DOCSTRING = '''
RFC 3548 allows for optional mapping of the digit 0 (zero) to the
letter O (oh), and for optional mapping of the digit 1 (one) to
either the letter I (eye) or letter L (el). The optional argument
map01 when not None, specifies which letter the digit 1 should be
mapped to (when map01 is not None, the digit 0 is always mapped to
the letter O). For security purposes the default is None, so that
0 and 1 are not allowed in the input.
'''
def b32encode(s, *, padded=True, wrapcol=0):
return binascii.b2a_base32(s, padded=padded, wrapcol=wrapcol)
b32encode.__doc__ = _B32_ENCODE_DOCSTRING.format(encoding='base32')
def b32decode(s, casefold=False, map01=None, *, padded=True, ignorechars=b'',
canonical=False):
s = _bytes_from_decode_data(s)
# Handle section 2.4 zero and one mapping. The flag map01 will be either
# False, or the character to map the digit 1 (one) to. It should be
# either L (el) or I (eye).
if map01 is not None:
map01 = _bytes_from_decode_data(map01)
s = s.translate(bytes.maketrans(b'01', b'O' + map01))
if casefold:
s = s.upper()
return binascii.a2b_base32(s, padded=padded, ignorechars=ignorechars,
canonical=canonical)
b32decode.__doc__ = _B32_DECODE_DOCSTRING.format(encoding='base32',
extra_args=_B32_DECODE_MAP01_DOCSTRING)
def b32hexencode(s, *, padded=True, wrapcol=0):
return binascii.b2a_base32(s, padded=padded, wrapcol=wrapcol,
alphabet=binascii.BASE32HEX_ALPHABET)
b32hexencode.__doc__ = _B32_ENCODE_DOCSTRING.format(encoding='base32hex')
def b32hexdecode(s, casefold=False, *, padded=True, ignorechars=b'',
canonical=False):
s = _bytes_from_decode_data(s)
# base32hex does not have the 01 mapping
if casefold:
s = s.upper()
return binascii.a2b_base32(s, alphabet=binascii.BASE32HEX_ALPHABET,
padded=padded, ignorechars=ignorechars,
canonical=canonical)
b32hexdecode.__doc__ = _B32_DECODE_DOCSTRING.format(encoding='base32hex',
extra_args='')
# RFC 3548, Base 16 Alphabet specifies uppercase, but hexlify() returns
# lowercase. The RFC also recommends against accepting input case
# insensitively.
def b16encode(s, *, wrapcol=0):
"""Encode the bytes-like object s using Base16 and return a bytes object.
If wrapcol is non-zero, insert a newline (b'\\n') character after at most
every wrapcol characters.
"""
if not wrapcol:
return binascii.hexlify(s).upper()
if wrapcol < 0:
raise ValueError('Negative wrapcol')
if wrapcol < 2:
wrapcol = 2
return binascii.hexlify(s, bytes_per_sep=-(wrapcol//2), sep=b'\n').upper()
def b16decode(s, casefold=False, *, ignorechars=b''):
"""Decode the Base16 encoded bytes-like object or ASCII string s.
Optional casefold is a flag specifying whether a lowercase alphabet is
acceptable as input. For security purposes, the default is False.
ignorechars should be a byte string containing characters to ignore
from the input.
The result is returned as a bytes object. A binascii.Error is raised if
s is incorrectly padded or if there are non-alphabet characters present
in the input.
"""
if not casefold:
s = _bytes_from_decode_data(s)
if not isinstance(ignorechars, bytes):
ignorechars = bytes(memoryview(ignorechars))
for b in b'abcdef':
if b in s and b not in ignorechars:
raise binascii.Error('Non-base16 digit found')
s = s.translate(None, delete=b'abcdef')
return binascii.unhexlify(s, ignorechars=ignorechars)
#
# Ascii85 encoding/decoding
#
def a85encode(b, *, foldspaces=False, wrapcol=0, pad=False, adobe=False):
"""Encode bytes-like object b using Ascii85 and return a bytes object.
foldspaces is an optional flag that uses the special short sequence 'y'
instead of 4 consecutive spaces (ASCII 0x20) as supported by 'btoa'. This
feature is not supported by the standard encoding used in PDF.
If wrapcol is non-zero, insert a newline (b'\\n') character after at most
every wrapcol characters.
pad controls whether zero-padding applied to the end of the input
is fully retained in the output encoding, as done by btoa,
producing an exact multiple of 5 bytes of output.
adobe controls whether the encoded byte sequence is framed with <~
and ~>, as in a PostScript base-85 string literal. Note that
while ASCII85Decode streams in PDF documents must be terminated
with ~>, they must not use a leading <~.
"""
return binascii.b2a_ascii85(b, foldspaces=foldspaces,
adobe=adobe, wrapcol=wrapcol, pad=pad)
def a85decode(b, *, foldspaces=False, adobe=False, ignorechars=b' \t\n\r\v',
canonical=False):
"""Decode the Ascii85 encoded bytes-like object or ASCII string b.
foldspaces is a flag that specifies whether the 'y' short sequence
should be accepted as shorthand for 4 consecutive spaces (ASCII
0x20). This feature is not supported by the standard Ascii85
encoding used in PDF and PostScript.
adobe controls whether the <~ and ~> markers are present. While
the leading <~ is not required, the input must end with ~>, or a
ValueError is raised.
ignorechars should be a byte string containing characters to ignore from the
input. This should only contain whitespace characters, and by default
contains all whitespace characters in ASCII.
If canonical is true, non-canonical encodings are rejected.
The result is returned as a bytes object.
"""
return binascii.a2b_ascii85(b, foldspaces=foldspaces,
adobe=adobe, ignorechars=ignorechars,
canonical=canonical)
def b85encode(b, pad=False, *, wrapcol=0):
"""Encode bytes-like object b in base85 format and return a bytes object.
If wrapcol is non-zero, insert a newline (b'\\n') character after at most
every wrapcol characters.
The input is padded with b'\0' so its length is a multiple of 4
bytes before encoding. If pad is true, all the resulting
characters are retained in the output, which will always be a
multiple of 5 bytes.
"""
return binascii.b2a_base85(b, wrapcol=wrapcol, pad=pad)
def b85decode(b, *, ignorechars=b'', canonical=False):
"""Decode the base85-encoded bytes-like object or ASCII string b
If canonical is true, non-canonical encodings are rejected.
The result is returned as a bytes object.
"""
return binascii.a2b_base85(b, ignorechars=ignorechars,
canonical=canonical)
def z85encode(s, pad=False, *, wrapcol=0):
"""Encode bytes-like object b in z85 format and return a bytes object.
If wrapcol is non-zero, insert a newline (b'\\n') character after at most
every wrapcol characters.
The input is padded with b'\0' so its length is a multiple of
bytes before encoding. If pad is true, all the resulting
characters are retained in the output, which will always be a
multiple of 5 bytes, as required by the ZeroMQ standard.
"""
return binascii.b2a_base85(s, wrapcol=wrapcol, pad=pad,
alphabet=binascii.Z85_ALPHABET)
def z85decode(s, *, ignorechars=b'', canonical=False):
"""Decode the z85-encoded bytes-like object or ASCII string b
If canonical is true, non-canonical encodings are rejected.
The result is returned as a bytes object.
"""
return binascii.a2b_base85(s, alphabet=binascii.Z85_ALPHABET,
ignorechars=ignorechars, canonical=canonical)
# Legacy interface. This code could be cleaned up since I don't believe
# binascii has any line length limitations. It just doesn't seem worth it
# though. The files should be opened in binary mode.
MAXLINESIZE = 76 # Excluding the CRLF
MAXBINSIZE = (MAXLINESIZE//4)*3
def encode(input, output):
"""Encode a file; input and output are binary files."""
while s := input.read(MAXBINSIZE):
while len(s) < MAXBINSIZE and (ns := input.read(MAXBINSIZE-len(s))):
s += ns
line = binascii.b2a_base64(s)
output.write(line)
def decode(input, output):
"""Decode a file; input and output are binary files."""
while line := input.readline():
s = binascii.a2b_base64(line)
output.write(s)
def _input_type_check(s):
try:
m = memoryview(s)
except TypeError as err:
msg = "expected bytes-like object, not %s" % s.__class__.__name__
raise TypeError(msg) from err
if m.format not in ('c', 'b', 'B'):
msg = ("expected single byte elements, not %r from %s" %
(m.format, s.__class__.__name__))
raise TypeError(msg)
if m.ndim != 1:
msg = ("expected 1-D data, not %d-D data from %s" %
(m.ndim, s.__class__.__name__))
raise TypeError(msg)
def encodebytes(s):
"""Encode a bytestring into a bytes object containing multiple lines
of base-64 data."""
_input_type_check(s)
result = binascii.b2a_base64(s, wrapcol=MAXLINESIZE)
if result == b'\n':
return b''
return result
def decodebytes(s):
"""Decode a bytestring of base-64 data into a bytes object."""
_input_type_check(s)
return binascii.a2b_base64(s)
# Usable as a script...
def main():
"""Small main program"""
import sys, getopt
usage = f"""usage: {sys.argv[0]} [-h|-d|-e|-u] [file|-]
-h: print this help message and exit
-d, -u: decode
-e: encode (default)"""
try:
opts, args = getopt.getopt(sys.argv[1:], 'hdeu')
except getopt.error as msg:
sys.stdout = sys.stderr
print(msg)
print(usage)
sys.exit(2)
func = encode
for o, a in opts:
if o == '-e': func = encode
if o == '-d': func = decode
if o == '-u': func = decode
if o == '-h': print(usage); return
if args and args[0] != '-':
with open(args[0], 'rb') as f:
func(f, sys.stdout.buffer)
else:
if sys.stdin.isatty():
# gh-138775: read terminal input data all at once to detect EOF
import io
data = sys.stdin.buffer.read()
buffer = io.BytesIO(data)
else:
buffer = sys.stdin.buffer
func(buffer, sys.stdout.buffer)
if __name__ == '__main__':
main()
You can’t perform that action at this time.