summaryrefslogtreecommitdiffstats
path: root/Lib/base64.py
blob: 573f76d361579b6c14a865d0db7be6dee3d040a4 (plain)
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
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
#! /usr/bin/env python3

"""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 re
import struct
import binascii
import itertools


__all__ = [
    # Legacy interface exports traditional RFC 1521 Base64 encodings
    'encode', 'decode', 'encodebytes', 'decodebytes',
    # Generalized interface for other encodings
    'b64encode', 'b64decode', 'b32encode', 'b32decode',
    'b16encode', 'b16decode',
    # Base85 and Ascii85 encodings
    'b85encode', 'b85decode', 'a85encode', 'a85decode',
    # 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',
    ]


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):
    """Encode a byte string using Base64.

    s is the byte string to encode.  Optional altchars must 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.

    The encoded byte string is returned.
    """
    # Strip off the trailing newline
    encoded = binascii.b2a_base64(s)[:-1]
    if altchars is not None:
        assert len(altchars) == 2, repr(altchars)
        return encoded.translate(bytes.maketrans(b'+/', altchars))
    return encoded


def b64decode(s, altchars=None, validate=False):
    """Decode a Base64 encoded byte string.

    s is the byte string to decode.  Optional altchars must be a
    string of length 2 which specifies the alternative alphabet used
    instead of the '+' and '/' characters.

    The decoded string is returned.  A binascii.Error is raised if s is
    incorrectly padded.

    If validate is False (the default), non-base64-alphabet characters are
    discarded prior to the padding check.  If validate is True,
    non-base64-alphabet characters in the input result in a binascii.Error.
    """
    s = _bytes_from_decode_data(s)
    if altchars is not None:
        altchars = _bytes_from_decode_data(altchars)
        assert len(altchars) == 2, repr(altchars)
        s = s.translate(bytes.maketrans(altchars, b'+/'))
    if validate and not re.match(b'^[A-Za-z0-9+/]*={0,2}$', s):
        raise binascii.Error('Non-base64 digit found')
    return binascii.a2b_base64(s)


def standard_b64encode(s):
    """Encode a byte string using the standard Base64 alphabet.

    s is the byte string to encode.  The encoded byte string is returned.
    """
    return b64encode(s)

def standard_b64decode(s):
    """Decode a byte string encoded with the standard Base64 alphabet.

    s is the byte string to decode.  The decoded byte string is
    returned.  binascii.Error is raised if the input is incorrectly
    padded or if there are non-alphabet characters present in the
    input.
    """
    return b64decode(s)


_urlsafe_encode_translation = bytes.maketrans(b'+/', b'-_')
_urlsafe_decode_translation = bytes.maketrans(b'-_', b'+/')

def urlsafe_b64encode(s):
    """Encode a byte string using a url-safe Base64 alphabet.

    s is the byte string to encode.  The encoded byte string is
    returned.  The alphabet uses '-' instead of '+' and '_' instead of
    '/'.
    """
    return b64encode(s).translate(_urlsafe_encode_translation)

def urlsafe_b64decode(s):
    """Decode a byte string encoded with the standard Base64 alphabet.

    s is the byte string to decode.  The decoded byte string is
    returned.  binascii.Error is raised if the input is incorrectly
    padded or if there are non-alphabet characters present in the
    input.

    The alphabet uses '-' instead of '+' and '_' instead of '/'.
    """
    s = _bytes_from_decode_data(s)
    s = s.translate(_urlsafe_decode_translation)
    return b64decode(s)



# Base32 encoding/decoding must be done in Python
_b32alphabet = b'ABCDEFGHIJKLMNOPQRSTUVWXYZ234567'
_b32tab = [bytes([i]) for i in _b32alphabet]
_b32tab2 = [a + b for a in _b32tab for b in _b32tab]
_b32rev = {v: k for k, v in enumerate(_b32alphabet)}

def b32encode(s):
    """Encode a byte string using Base32.

    s is the byte string to encode.  The encoded byte string is returned.
    """
    if not isinstance(s, bytes_types):
        s = memoryview(s).tobytes()
    leftover = len(s) % 5
    # Pad the last quantum with zero bits if necessary
    if leftover:
        s = s + bytes(5 - leftover)  # Don't use += !
    encoded = bytearray()
    from_bytes = int.from_bytes
    b32tab2 = _b32tab2
    for i in range(0, len(s), 5):
        c = from_bytes(s[i: i + 5], 'big')
        encoded += (b32tab2[c >> 30] +           # bits 1 - 10
                    b32tab2[(c >> 20) & 0x3ff] + # bits 11 - 20
                    b32tab2[(c >> 10) & 0x3ff] + # bits 21 - 30
                    b32tab2[c & 0x3ff]           # bits 31 - 40
                   )
    # Adjust for any leftover partial quanta
    if leftover == 1:
        encoded[-6:] = b'======'
    elif leftover == 2:
        encoded[-4:] = b'===='
    elif leftover == 3:
        encoded[-3:] = b'==='
    elif leftover == 4:
        encoded[-1:] = b'='
    return bytes(encoded)

def b32decode(s, casefold=False, map01=None):
    """Decode a Base32 encoded byte string.

    s is the byte string to decode.  Optional casefold is a flag
    specifying whether a lowercase alphabet is acceptable as input.
    For security purposes, the default is False.

    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.

    The decoded byte string is returned.  binascii.Error is raised if
    the input is incorrectly padded or if there are non-alphabet
    characters present in the input.
    """
    s = _bytes_from_decode_data(s)
    if len(s) % 8:
        raise binascii.Error('Incorrect padding')
    # 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)
        assert len(map01) == 1, repr(map01)
        s = s.translate(bytes.maketrans(b'01', b'O' + map01))
    if casefold:
        s = s.upper()
    # Strip off pad characters from the right.  We need to count the pad
    # characters because this will tell us how many null bytes to remove from
    # the end of the decoded string.
    l = len(s)
    s = s.rstrip(b'=')
    padchars = l - len(s)
    # Now decode the full quanta
    decoded = bytearray()
    b32rev = _b32rev
    for i in range(0, len(s), 8):
        quanta = s[i: i + 8]
        acc = 0
        try:
            for c in quanta:
                acc = (acc << 5) + b32rev[c]
        except KeyError:
            raise binascii.Error('Non-base32 digit found') from None
        decoded += acc.to_bytes(5, 'big')
    # Process the last, partial quanta
    if padchars:
        acc <<= 5 * padchars
        last = acc.to_bytes(5, 'big')
        if padchars == 1:
            decoded[-5:] = last[:-1]
        elif padchars == 3:
            decoded[-5:] = last[:-2]
        elif padchars == 4:
            decoded[-5:] = last[:-3]
        elif padchars == 6:
            decoded[-5:] = last[:-4]
        else:
            raise binascii.Error('Incorrect padding')
    return bytes(decoded)



# RFC 3548, Base 16 Alphabet specifies uppercase, but hexlify() returns
# lowercase.  The RFC also recommends against accepting input case
# insensitively.
def b16encode(s):
    """Encode a byte string using Base16.

    s is the byte string to encode.  The encoded byte string is returned.
    """
    return binascii.hexlify(s).upper()


def b16decode(s, casefold=False):
    """Decode a Base16 encoded byte string.

    s is the byte string to decode.  Optional casefold is a flag
    specifying whether a lowercase alphabet is acceptable as input.
    For security purposes, the default is False.

    The decoded byte string is returned.  binascii.Error is raised if
    s were incorrectly padded or if there are non-alphabet characters
    present in the string.
    """
    s = _bytes_from_decode_data(s)
    if casefold:
        s = s.upper()
    if re.search(b'[^0-9A-F]', s):
        raise binascii.Error('Non-base16 digit found')
    return binascii.unhexlify(s)

#
# Ascii85 encoding/decoding
#

def _85encode(b, chars, chars2, pad=False, foldnuls=False, foldspaces=False):
    # Helper function for a85encode and b85encode
    if not isinstance(b, bytes_types):
        b = memoryview(b).tobytes()

    padding = (-len(b)) % 4
    if padding:
        b = b + b'\0' * padding
    words = struct.Struct('!%dI' % (len(b) // 4)).unpack(b)

    a85chars2 = _a85chars2
    a85chars = _a85chars
    chunks = [b'z' if foldnuls and not word else
              b'y' if foldspaces and word == 0x20202020 else
              (chars2[word // 614125] +
               chars2[word // 85 % 7225] +
               chars[word % 85])
              for word in words]

    if padding and not pad:
        if chunks[-1] == b'z':
            chunks[-1] = chars[0] * 5
        chunks[-1] = chunks[-1][:-padding]

    return b''.join(chunks)

_A85START = b"<~"
_A85END = b"~>"
_a85chars = [bytes([i]) for i in range(33, 118)]
_a85chars2 = [(a + b) for a in _a85chars for b in _a85chars]

def a85encode(b, *, foldspaces=False, wrapcol=0, pad=False, adobe=False):
    """Encode a byte string using Ascii85.

    b is the byte string to encode. The encoded byte string is returned.

    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" Adobe encoding.

    wrapcol controls whether the output should have newline ('\n') characters
    added to it. If this is non-zero, each output line will be at most this
    many characters long.

    pad controls whether the input string is padded to a multiple of 4 before
    encoding. Note that the btoa implementation always pads.

    adobe controls whether the encoded byte sequence is framed with <~ and ~>,
    which is used by the Adobe implementation.
    """
    result = _85encode(b, _a85chars, _a85chars2, pad, True, foldspaces)

    if adobe:
        result = _A85START + result
    if wrapcol:
        wrapcol = max(2 if adobe else 1, wrapcol)
        chunks = [result[i: i + wrapcol]
                  for i in range(0, len(result), wrapcol)]
        if adobe:
            if len(chunks[-1]) + 2 > wrapcol:
                chunks.append(b'')
        result = b'\n'.join(chunks)
    if adobe:
        result += _A85END

    return result

def a85decode(b, *, foldspaces=False, adobe=False, ignorechars=b' \t\n\r\v'):
    """Decode an Ascii85 encoded byte string.

    s is the byte string to decode.

    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" Adobe encoding.

    adobe controls whether the input sequence is in Adobe Ascii85 format (i.e.
    is framed with <~ and ~>).

    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.
    """
    b = _bytes_from_decode_data(b)
    if adobe:
        if not (b.startswith(_A85START) and b.endswith(_A85END)):
            raise ValueError("Ascii85 encoded byte sequences must be bracketed "
                             "by {!r} and {!r}".format(_A85START, _A85END))
        b = b[2:-2] # Strip off start/end markers
    #
    # We have to go through this stepwise, so as to ignore spaces and handle
    # special short sequences
    #
    packI = struct.Struct('!I').pack
    decoded = []
    decoded_append = decoded.append
    curr = []
    curr_append = curr.append
    curr_clear = curr.clear
    for x in b + b'u' * 4:
        if b'!'[0] <= x <= b'u'[0]:
            curr_append(x)
            if len(curr) == 5:
                acc = 0
                for x in curr:
                    acc = 85 * acc + (x - 33)
                try:
                    decoded_append(packI(acc))
                except struct.error:
                    raise ValueError('Ascii85 overflow') from None
                curr_clear()
        elif x == b'z'[0]:
            if curr:
                raise ValueError('z inside Ascii85 5-tuple')
            decoded_append(b'\0\0\0\0')
        elif foldspaces and x == b'y'[0]:
            if curr:
                raise ValueError('y inside Ascii85 5-tuple')
            decoded_append(b'\x20\x20\x20\x20')
        elif x in ignorechars:
            # Skip whitespace
            continue
        else:
            raise ValueError('Non-Ascii85 digit found: %c' % x)

    result = b''.join(decoded)
    padding = 4 - len(curr)
    if padding:
        # Throw away the extra padding
        result = result[:-padding]
    return result

# The following code is originally taken (with permission) from Mercurial

_b85chars = b"0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZ" \
            b"abcdefghijklmnopqrstuvwxyz!#$%&()*+-;<=>?@^_`{|}~"
_b85chars = [bytes([i]) for i in _b85chars]
_b85chars2 = [(a + b) for a in _b85chars for b in _b85chars]
_b85dec = None

def b85encode(b, pad=False):
    """Encode an ASCII-encoded byte array in base85 format.

    If pad is true, the input is padded with "\0" so its length is a multiple of
    4 characters before encoding.
    """
    return _85encode(b, _b85chars, _b85chars2, pad)

def b85decode(b):
    """Decode base85-encoded byte array"""
    b = _bytes_from_decode_data(b)
    global _b85dec
    if _b85dec is None:
        _b85dec = [None] * 256
        for i, c in enumerate(_b85chars):
            _b85dec[c[0]] = i

    padding = (-len(b)) % 5
    b = b + b'~' * padding
    out = []
    packI = struct.Struct('!I').pack
    for i in range(0, len(b), 5):
        chunk = b[i:i + 5]
        acc = 0
        try:
            for c in chunk:
                acc = acc * 85 + _b85dec[c]
        except TypeError:
            for j, c in enumerate(chunk):
                if _b85dec[c] is None:
                    raise ValueError('bad base85 character at position %d'
                                    % (i + j)) from None
            raise
        try:
            out.append(packI(acc))
        except struct.error:
            raise ValueError('base85 overflow in hunk starting at byte %d'
                             % i) from None

    result = b''.join(out)
    if padding:
        result = result[:-padding]
    return result

# 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 True:
        s = input.read(MAXBINSIZE)
        if not s:
            break
        while len(s) < MAXBINSIZE:
            ns = input.read(MAXBINSIZE-len(s))
            if not ns:
                break
            s += ns
        line = binascii.b2a_base64(s)
        output.write(line)


def decode(input, output):
    """Decode a file; input and output are binary files."""
    while True:
        line = input.readline()
        if not line:
            break
        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 bytestring containing multiple lines
    of base-64 data."""
    _input_type_check(s)
    pieces = []
    for i in range(0, len(s), MAXBINSIZE):
        chunk = s[i : i + MAXBINSIZE]
        pieces.append(binascii.b2a_base64(chunk))
    return b"".join(pieces)

def encodestring(s):
    """Legacy alias of encodebytes()."""
    import warnings
    warnings.warn("encodestring() is a deprecated alias, use encodebytes()",
                  DeprecationWarning, 2)
    return encodebytes(s)


def decodebytes(s):
    """Decode a bytestring of base-64 data into a bytestring."""
    _input_type_check(s)
    return binascii.a2b_base64(s)

def decodestring(s):
    """Legacy alias of decodebytes()."""
    import warnings
    warnings.warn("decodestring() is a deprecated alias, use decodebytes()",
                  DeprecationWarning, 2)
    return decodebytes(s)


# Usable as a script...
def main():
    """Small main program"""
    import sys, getopt
    try:
        opts, args = getopt.getopt(sys.argv[1:], 'deut')
    except getopt.error as msg:
        sys.stdout = sys.stderr
        print(msg)
        print("""usage: %s [-d|-e|-u|-t] [file|-]
        -d, -u: decode
        -e: encode (default)
        -t: encode and decode string 'Aladdin:open sesame'"""%sys.argv[0])
        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 == '-t': test(); return
    if args and args[0] != '-':
        with open(args[0], 'rb') as f:
            func(f, sys.stdout.buffer)
    else:
        func(sys.stdin.buffer, sys.stdout.buffer)


def test():
    s0 = b"Aladdin:open sesame"
    print(repr(s0))
    s1 = encodebytes(s0)
    print(repr(s1))
    s2 = decodebytes(s1)
    print(repr(s2))
    assert s0 == s2


if __name__ == '__main__':
    main()