2010-03-12 06:53:45 +08:00
|
|
|
#! /usr/bin/env python3
|
1997-04-02 13:47:39 +08:00
|
|
|
|
2013-11-18 06:52:25 +08:00
|
|
|
"""Base16, Base32, Base64 (RFC 3548), Base85 and Ascii85 data encodings"""
|
2000-02-02 23:10:15 +08:00
|
|
|
|
2004-01-04 09:12:26 +08:00
|
|
|
# Modified 04-Oct-1995 by Jack Jansen to use binascii module
|
|
|
|
# Modified 30-Dec-2003 by Barry Warsaw to add full RFC 3548 support
|
2007-05-23 05:56:47 +08:00
|
|
|
# Modified 22-May-2007 by Guido van Rossum to use bytes everywhere
|
1995-06-15 07:43:44 +08:00
|
|
|
|
2004-01-04 09:12:26 +08:00
|
|
|
import re
|
|
|
|
import struct
|
1995-10-05 00:39:20 +08:00
|
|
|
import binascii
|
1995-06-15 07:43:44 +08:00
|
|
|
|
2004-01-04 09:12:26 +08:00
|
|
|
|
|
|
|
__all__ = [
|
2016-02-24 06:30:50 +08:00
|
|
|
# Legacy interface exports traditional RFC 2045 Base64 encodings
|
2009-06-04 17:11:51 +08:00
|
|
|
'encode', 'decode', 'encodebytes', 'decodebytes',
|
2004-01-04 09:12:26 +08:00
|
|
|
# Generalized interface for other encodings
|
|
|
|
'b64encode', 'b64decode', 'b32encode', 'b32decode',
|
2020-08-10 22:48:20 +08:00
|
|
|
'b32hexencode', 'b32hexdecode', 'b16encode', 'b16decode',
|
2013-11-18 06:52:25 +08:00
|
|
|
# Base85 and Ascii85 encodings
|
|
|
|
'b85encode', 'b85decode', 'a85encode', 'a85decode',
|
2004-01-04 09:12:26 +08:00
|
|
|
# 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',
|
|
|
|
]
|
|
|
|
|
|
|
|
|
2007-11-22 03:29:53 +08:00
|
|
|
bytes_types = (bytes, bytearray) # Types acceptable as binary data
|
2007-11-07 05:34:58 +08:00
|
|
|
|
2012-02-21 02:30:23 +08:00
|
|
|
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')
|
2013-10-02 22:43:22 +08:00
|
|
|
if isinstance(s, bytes_types):
|
2012-02-21 02:30:23 +08:00
|
|
|
return s
|
2013-10-02 22:43:22 +08:00
|
|
|
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
|
2004-01-04 09:12:26 +08:00
|
|
|
|
2008-08-20 01:56:33 +08:00
|
|
|
|
2004-01-04 09:12:26 +08:00
|
|
|
# Base64 encoding/decoding uses binascii
|
|
|
|
|
|
|
|
def b64encode(s, altchars=None):
|
2016-02-24 06:30:50 +08:00
|
|
|
"""Encode the bytes-like object s using Base64 and return a bytes object.
|
2004-01-04 09:12:26 +08:00
|
|
|
|
2016-02-24 06:30:50 +08:00
|
|
|
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.
|
2004-01-04 09:12:26 +08:00
|
|
|
"""
|
2015-10-11 17:01:02 +08:00
|
|
|
encoded = binascii.b2a_base64(s, newline=False)
|
2004-01-04 09:12:26 +08:00
|
|
|
if altchars is not None:
|
2007-05-23 05:56:47 +08:00
|
|
|
assert len(altchars) == 2, repr(altchars)
|
2012-06-23 06:16:09 +08:00
|
|
|
return encoded.translate(bytes.maketrans(b'+/', altchars))
|
2004-01-04 09:12:26 +08:00
|
|
|
return encoded
|
|
|
|
|
|
|
|
|
2010-11-12 04:09:20 +08:00
|
|
|
def b64decode(s, altchars=None, validate=False):
|
2016-02-24 06:30:50 +08:00
|
|
|
"""Decode the Base64 encoded bytes-like object or ASCII string s.
|
2004-01-04 09:12:26 +08:00
|
|
|
|
2016-02-24 06:30:50 +08:00
|
|
|
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.
|
2004-01-04 09:12:26 +08:00
|
|
|
|
2016-02-24 06:30:50 +08:00
|
|
|
The result is returned as a bytes object. A binascii.Error is raised if
|
|
|
|
s is incorrectly padded.
|
2010-11-12 04:09:20 +08:00
|
|
|
|
2016-02-24 06:30:50 +08:00
|
|
|
If validate is False (the default), 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.
|
2021-08-24 07:44:28 +08:00
|
|
|
For more information about the strict base64 check, see:
|
|
|
|
|
|
|
|
https://docs.python.org/3.11/library/binascii.html#binascii.a2b_base64
|
2004-01-04 09:12:26 +08:00
|
|
|
"""
|
2012-02-21 02:30:23 +08:00
|
|
|
s = _bytes_from_decode_data(s)
|
2004-01-04 09:12:26 +08:00
|
|
|
if altchars is not None:
|
2012-02-21 02:30:23 +08:00
|
|
|
altchars = _bytes_from_decode_data(altchars)
|
2007-05-23 05:56:47 +08:00
|
|
|
assert len(altchars) == 2, repr(altchars)
|
2012-06-23 06:16:09 +08:00
|
|
|
s = s.translate(bytes.maketrans(altchars, b'+/'))
|
2021-08-24 07:44:28 +08:00
|
|
|
return binascii.a2b_base64(s, strict_mode=validate)
|
2004-01-04 09:12:26 +08:00
|
|
|
|
|
|
|
|
|
|
|
def standard_b64encode(s):
|
2016-02-24 06:30:50 +08:00
|
|
|
"""Encode bytes-like object s using the standard Base64 alphabet.
|
2004-01-04 09:12:26 +08:00
|
|
|
|
2016-02-24 06:30:50 +08:00
|
|
|
The result is returned as a bytes object.
|
2004-01-04 09:12:26 +08:00
|
|
|
"""
|
|
|
|
return b64encode(s)
|
|
|
|
|
|
|
|
def standard_b64decode(s):
|
2016-02-24 06:30:50 +08:00
|
|
|
"""Decode bytes encoded with the standard Base64 alphabet.
|
2004-01-04 09:12:26 +08:00
|
|
|
|
2016-02-24 06:30:50 +08:00
|
|
|
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.
|
2004-01-04 09:12:26 +08:00
|
|
|
"""
|
|
|
|
return b64decode(s)
|
|
|
|
|
2012-06-23 06:16:09 +08:00
|
|
|
|
|
|
|
_urlsafe_encode_translation = bytes.maketrans(b'+/', b'-_')
|
|
|
|
_urlsafe_decode_translation = bytes.maketrans(b'-_', b'+/')
|
|
|
|
|
2004-01-04 09:12:26 +08:00
|
|
|
def urlsafe_b64encode(s):
|
2016-02-24 06:30:50 +08:00
|
|
|
"""Encode bytes using the URL- and filesystem-safe Base64 alphabet.
|
2004-01-04 09:12:26 +08:00
|
|
|
|
2016-02-24 06:30:50 +08:00
|
|
|
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
|
2007-05-23 05:56:47 +08:00
|
|
|
'/'.
|
2004-01-04 09:12:26 +08:00
|
|
|
"""
|
2012-06-23 06:16:09 +08:00
|
|
|
return b64encode(s).translate(_urlsafe_encode_translation)
|
2004-01-04 09:12:26 +08:00
|
|
|
|
|
|
|
def urlsafe_b64decode(s):
|
2016-02-24 06:30:50 +08:00
|
|
|
"""Decode bytes using the URL- and filesystem-safe Base64 alphabet.
|
2004-01-04 09:12:26 +08:00
|
|
|
|
2016-02-24 06:30:50 +08:00
|
|
|
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.
|
2004-01-04 09:12:26 +08:00
|
|
|
|
|
|
|
The alphabet uses '-' instead of '+' and '_' instead of '/'.
|
|
|
|
"""
|
2012-06-23 06:16:09 +08:00
|
|
|
s = _bytes_from_decode_data(s)
|
|
|
|
s = s.translate(_urlsafe_decode_translation)
|
|
|
|
return b64decode(s)
|
2004-01-04 09:12:26 +08:00
|
|
|
|
|
|
|
|
2008-08-20 01:56:33 +08:00
|
|
|
|
2004-01-04 09:12:26 +08:00
|
|
|
# Base32 encoding/decoding must be done in Python
|
2020-08-10 22:48:20 +08:00
|
|
|
_B32_ENCODE_DOCSTRING = '''
|
|
|
|
Encode the bytes-like objects using {encoding} and return a bytes object.
|
|
|
|
'''
|
|
|
|
_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.
|
|
|
|
{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.
|
|
|
|
'''
|
2013-05-19 16:49:32 +08:00
|
|
|
_b32alphabet = b'ABCDEFGHIJKLMNOPQRSTUVWXYZ234567'
|
2020-08-10 22:48:20 +08:00
|
|
|
_b32hexalphabet = b'0123456789ABCDEFGHIJKLMNOPQRSTUV'
|
|
|
|
_b32tab2 = {}
|
|
|
|
_b32rev = {}
|
2004-01-04 09:12:26 +08:00
|
|
|
|
2020-08-10 22:48:20 +08:00
|
|
|
def _b32encode(alphabet, s):
|
2014-03-18 05:38:41 +08:00
|
|
|
# Delay the initialization of the table to not waste memory
|
|
|
|
# if the function is never called
|
2020-08-10 22:48:20 +08:00
|
|
|
if alphabet not in _b32tab2:
|
|
|
|
b32tab = [bytes((i,)) for i in alphabet]
|
|
|
|
_b32tab2[alphabet] = [a + b for a in b32tab for b in b32tab]
|
2014-03-18 05:38:41 +08:00
|
|
|
b32tab = None
|
|
|
|
|
2007-11-22 03:29:53 +08:00
|
|
|
if not isinstance(s, bytes_types):
|
2013-10-02 22:43:22 +08:00
|
|
|
s = memoryview(s).tobytes()
|
2013-05-19 16:49:32 +08:00
|
|
|
leftover = len(s) % 5
|
2004-01-04 09:12:26 +08:00
|
|
|
# Pad the last quantum with zero bits if necessary
|
|
|
|
if leftover:
|
2016-09-11 19:41:02 +08:00
|
|
|
s = s + b'\0' * (5 - leftover) # Don't use += !
|
2013-05-19 16:41:15 +08:00
|
|
|
encoded = bytearray()
|
2013-05-19 16:49:32 +08:00
|
|
|
from_bytes = int.from_bytes
|
2020-08-10 22:48:20 +08:00
|
|
|
b32tab2 = _b32tab2[alphabet]
|
2013-05-19 16:49:32 +08:00
|
|
|
for i in range(0, len(s), 5):
|
2021-09-21 02:22:55 +08:00
|
|
|
c = from_bytes(s[i: i + 5]) # big endian
|
2013-05-19 16:49:32 +08:00
|
|
|
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
|
|
|
|
)
|
2004-01-04 09:12:26 +08:00
|
|
|
# Adjust for any leftover partial quanta
|
|
|
|
if leftover == 1:
|
2013-05-19 16:41:15 +08:00
|
|
|
encoded[-6:] = b'======'
|
2004-01-04 09:12:26 +08:00
|
|
|
elif leftover == 2:
|
2013-05-19 16:41:15 +08:00
|
|
|
encoded[-4:] = b'===='
|
2004-01-04 09:12:26 +08:00
|
|
|
elif leftover == 3:
|
2013-05-19 16:41:15 +08:00
|
|
|
encoded[-3:] = b'==='
|
2004-01-04 09:12:26 +08:00
|
|
|
elif leftover == 4:
|
2013-05-19 16:41:15 +08:00
|
|
|
encoded[-1:] = b'='
|
|
|
|
return bytes(encoded)
|
2004-01-04 09:12:26 +08:00
|
|
|
|
2020-08-10 22:48:20 +08:00
|
|
|
def _b32decode(alphabet, s, casefold=False, map01=None):
|
2014-03-18 05:38:41 +08:00
|
|
|
# Delay the initialization of the table to not waste memory
|
|
|
|
# if the function is never called
|
2020-08-10 22:48:20 +08:00
|
|
|
if alphabet not in _b32rev:
|
|
|
|
_b32rev[alphabet] = {v: k for k, v in enumerate(alphabet)}
|
2012-02-21 02:30:23 +08:00
|
|
|
s = _bytes_from_decode_data(s)
|
2013-05-19 16:49:32 +08:00
|
|
|
if len(s) % 8:
|
2007-05-23 05:56:47 +08:00
|
|
|
raise binascii.Error('Incorrect padding')
|
2004-01-04 09:12:26 +08:00
|
|
|
# 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).
|
2008-05-03 12:39:38 +08:00
|
|
|
if map01 is not None:
|
2012-02-21 02:30:23 +08:00
|
|
|
map01 = _bytes_from_decode_data(map01)
|
2007-05-23 05:56:47 +08:00
|
|
|
assert len(map01) == 1, repr(map01)
|
2012-06-23 06:16:09 +08:00
|
|
|
s = s.translate(bytes.maketrans(b'01', b'O' + map01))
|
2004-01-04 09:12:26 +08:00
|
|
|
if casefold:
|
2007-11-07 05:34:58 +08:00
|
|
|
s = s.upper()
|
2004-01-04 09:12:26 +08:00
|
|
|
# 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.
|
2013-05-19 16:49:32 +08:00
|
|
|
l = len(s)
|
|
|
|
s = s.rstrip(b'=')
|
|
|
|
padchars = l - len(s)
|
2004-01-04 09:12:26 +08:00
|
|
|
# Now decode the full quanta
|
2013-05-19 16:49:32 +08:00
|
|
|
decoded = bytearray()
|
2020-08-10 22:48:20 +08:00
|
|
|
b32rev = _b32rev[alphabet]
|
2013-05-19 16:49:32 +08:00
|
|
|
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:
|
2013-05-28 20:42:34 +08:00
|
|
|
raise binascii.Error('Non-base32 digit found') from None
|
2021-09-21 02:22:55 +08:00
|
|
|
decoded += acc.to_bytes(5) # big endian
|
2004-01-04 09:12:26 +08:00
|
|
|
# Process the last, partial quanta
|
2018-07-24 17:52:51 +08:00
|
|
|
if l % 8 or padchars not in {0, 1, 3, 4, 6}:
|
|
|
|
raise binascii.Error('Incorrect padding')
|
|
|
|
if padchars and decoded:
|
2013-05-19 16:49:32 +08:00
|
|
|
acc <<= 5 * padchars
|
2021-09-21 02:22:55 +08:00
|
|
|
last = acc.to_bytes(5) # big endian
|
2018-07-24 17:52:51 +08:00
|
|
|
leftover = (43 - 5 * padchars) // 8 # 1: 4, 3: 3, 4: 2, 6: 1
|
|
|
|
decoded[-5:] = last[:leftover]
|
2013-05-19 16:49:32 +08:00
|
|
|
return bytes(decoded)
|
2004-01-04 09:12:26 +08:00
|
|
|
|
|
|
|
|
2020-08-10 22:48:20 +08:00
|
|
|
def b32encode(s):
|
|
|
|
return _b32encode(_b32alphabet, s)
|
|
|
|
b32encode.__doc__ = _B32_ENCODE_DOCSTRING.format(encoding='base32')
|
|
|
|
|
|
|
|
def b32decode(s, casefold=False, map01=None):
|
|
|
|
return _b32decode(_b32alphabet, s, casefold, map01)
|
|
|
|
b32decode.__doc__ = _B32_DECODE_DOCSTRING.format(encoding='base32',
|
|
|
|
extra_args=_B32_DECODE_MAP01_DOCSTRING)
|
|
|
|
|
|
|
|
def b32hexencode(s):
|
|
|
|
return _b32encode(_b32hexalphabet, s)
|
|
|
|
b32hexencode.__doc__ = _B32_ENCODE_DOCSTRING.format(encoding='base32hex')
|
|
|
|
|
|
|
|
def b32hexdecode(s, casefold=False):
|
|
|
|
# base32hex does not have the 01 mapping
|
|
|
|
return _b32decode(_b32hexalphabet, s, casefold)
|
|
|
|
b32hexdecode.__doc__ = _B32_DECODE_DOCSTRING.format(encoding='base32hex',
|
|
|
|
extra_args='')
|
|
|
|
|
|
|
|
|
2004-01-04 09:12:26 +08:00
|
|
|
# RFC 3548, Base 16 Alphabet specifies uppercase, but hexlify() returns
|
|
|
|
# lowercase. The RFC also recommends against accepting input case
|
|
|
|
# insensitively.
|
|
|
|
def b16encode(s):
|
2016-02-24 06:30:50 +08:00
|
|
|
"""Encode the bytes-like object s using Base16 and return a bytes object.
|
2004-01-04 09:12:26 +08:00
|
|
|
"""
|
2007-11-07 05:34:58 +08:00
|
|
|
return binascii.hexlify(s).upper()
|
2004-01-04 09:12:26 +08:00
|
|
|
|
|
|
|
|
|
|
|
def b16decode(s, casefold=False):
|
2016-02-24 06:30:50 +08:00
|
|
|
"""Decode the Base16 encoded bytes-like object or ASCII string s.
|
2004-01-04 09:12:26 +08:00
|
|
|
|
2016-02-24 06:30:50 +08:00
|
|
|
Optional casefold is a flag specifying whether a lowercase alphabet is
|
|
|
|
acceptable as input. For security purposes, the default is False.
|
2004-01-04 09:12:26 +08:00
|
|
|
|
2016-02-24 06:30:50 +08:00
|
|
|
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.
|
2004-01-04 09:12:26 +08:00
|
|
|
"""
|
2012-02-21 02:30:23 +08:00
|
|
|
s = _bytes_from_decode_data(s)
|
2004-01-04 09:12:26 +08:00
|
|
|
if casefold:
|
2007-11-07 05:34:58 +08:00
|
|
|
s = s.upper()
|
2008-08-20 01:56:33 +08:00
|
|
|
if re.search(b'[^0-9A-F]', s):
|
2007-05-23 05:56:47 +08:00
|
|
|
raise binascii.Error('Non-base16 digit found')
|
2004-01-04 09:12:26 +08:00
|
|
|
return binascii.unhexlify(s)
|
|
|
|
|
2013-11-18 06:52:25 +08:00
|
|
|
#
|
|
|
|
# Ascii85 encoding/decoding
|
|
|
|
#
|
2004-01-04 09:12:26 +08:00
|
|
|
|
2014-03-18 05:38:41 +08:00
|
|
|
_a85chars = None
|
|
|
|
_a85chars2 = None
|
|
|
|
_A85START = b"<~"
|
|
|
|
_A85END = b"~>"
|
|
|
|
|
2013-11-18 06:52:25 +08:00
|
|
|
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)
|
|
|
|
|
|
|
|
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)
|
|
|
|
|
|
|
|
def a85encode(b, *, foldspaces=False, wrapcol=0, pad=False, adobe=False):
|
2016-02-24 06:30:50 +08:00
|
|
|
"""Encode bytes-like object b using Ascii85 and return a bytes object.
|
2013-11-18 06:52:25 +08:00
|
|
|
|
|
|
|
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.
|
|
|
|
|
2016-02-24 06:30:50 +08:00
|
|
|
wrapcol controls whether the output should have newline (b'\\n') characters
|
2013-11-18 06:52:25 +08:00
|
|
|
added to it. If this is non-zero, each output line will be at most this
|
|
|
|
many characters long.
|
|
|
|
|
2016-02-24 06:30:50 +08:00
|
|
|
pad controls whether the input is padded to a multiple of 4 before
|
2013-11-18 06:52:25 +08:00
|
|
|
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.
|
|
|
|
"""
|
2014-03-18 05:38:41 +08:00
|
|
|
global _a85chars, _a85chars2
|
|
|
|
# Delay the initialization of tables to not waste memory
|
|
|
|
# if the function is never called
|
2020-12-31 17:44:46 +08:00
|
|
|
if _a85chars2 is None:
|
2014-03-18 05:38:41 +08:00
|
|
|
_a85chars = [bytes((i,)) for i in range(33, 118)]
|
|
|
|
_a85chars2 = [(a + b) for a in _a85chars for b in _a85chars]
|
|
|
|
|
2013-11-18 06:52:25 +08:00
|
|
|
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'):
|
2016-02-24 06:30:50 +08:00
|
|
|
"""Decode the Ascii85 encoded bytes-like object or ASCII string b.
|
2013-11-18 06:52:25 +08:00
|
|
|
|
|
|
|
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.
|
2016-02-24 06:30:50 +08:00
|
|
|
|
|
|
|
The result is returned as a bytes object.
|
2013-11-18 06:52:25 +08:00
|
|
|
"""
|
|
|
|
b = _bytes_from_decode_data(b)
|
|
|
|
if adobe:
|
2016-02-24 18:05:50 +08:00
|
|
|
if not b.endswith(_A85END):
|
|
|
|
raise ValueError(
|
|
|
|
"Ascii85 encoded byte sequences must end "
|
|
|
|
"with {!r}".format(_A85END)
|
|
|
|
)
|
|
|
|
if b.startswith(_A85START):
|
|
|
|
b = b[2:-2] # Strip off start/end markers
|
|
|
|
else:
|
|
|
|
b = b[:-2]
|
2013-11-18 06:52:25 +08:00
|
|
|
#
|
|
|
|
# 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
|
|
|
|
|
2014-03-18 05:38:41 +08:00
|
|
|
_b85alphabet = (b"0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZ"
|
|
|
|
b"abcdefghijklmnopqrstuvwxyz!#$%&()*+-;<=>?@^_`{|}~")
|
|
|
|
_b85chars = None
|
|
|
|
_b85chars2 = None
|
2013-11-18 06:52:25 +08:00
|
|
|
_b85dec = None
|
|
|
|
|
|
|
|
def b85encode(b, pad=False):
|
2016-02-24 06:30:50 +08:00
|
|
|
"""Encode bytes-like object b in base85 format and return a bytes object.
|
2013-11-18 06:52:25 +08:00
|
|
|
|
2016-02-24 06:30:50 +08:00
|
|
|
If pad is true, the input is padded with b'\\0' so its length is a multiple of
|
|
|
|
4 bytes before encoding.
|
2013-11-18 06:52:25 +08:00
|
|
|
"""
|
2014-03-18 05:38:41 +08:00
|
|
|
global _b85chars, _b85chars2
|
|
|
|
# Delay the initialization of tables to not waste memory
|
|
|
|
# if the function is never called
|
2020-12-31 17:44:46 +08:00
|
|
|
if _b85chars2 is None:
|
2014-03-18 05:38:41 +08:00
|
|
|
_b85chars = [bytes((i,)) for i in _b85alphabet]
|
|
|
|
_b85chars2 = [(a + b) for a in _b85chars for b in _b85chars]
|
2013-11-18 06:52:25 +08:00
|
|
|
return _85encode(b, _b85chars, _b85chars2, pad)
|
|
|
|
|
|
|
|
def b85decode(b):
|
2016-02-24 06:30:50 +08:00
|
|
|
"""Decode the base85-encoded bytes-like object or ASCII string b
|
|
|
|
|
|
|
|
The result is returned as a bytes object.
|
|
|
|
"""
|
2013-11-18 06:52:25 +08:00
|
|
|
global _b85dec
|
2014-03-18 05:38:41 +08:00
|
|
|
# Delay the initialization of tables to not waste memory
|
|
|
|
# if the function is never called
|
2013-11-18 06:52:25 +08:00
|
|
|
if _b85dec is None:
|
|
|
|
_b85dec = [None] * 256
|
2014-03-18 05:38:41 +08:00
|
|
|
for i, c in enumerate(_b85alphabet):
|
|
|
|
_b85dec[c] = i
|
2013-11-18 06:52:25 +08:00
|
|
|
|
2014-03-18 05:38:41 +08:00
|
|
|
b = _bytes_from_decode_data(b)
|
2013-11-18 06:52:25 +08:00
|
|
|
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
|
2008-08-20 01:56:33 +08:00
|
|
|
|
2004-01-04 09:12:26 +08:00
|
|
|
# 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
|
2007-05-23 05:56:47 +08:00
|
|
|
# though. The files should be opened in binary mode.
|
2001-01-21 03:54:20 +08:00
|
|
|
|
1995-10-05 00:39:20 +08:00
|
|
|
MAXLINESIZE = 76 # Excluding the CRLF
|
2001-09-05 03:14:14 +08:00
|
|
|
MAXBINSIZE = (MAXLINESIZE//4)*3
|
1995-06-15 07:43:44 +08:00
|
|
|
|
|
|
|
def encode(input, output):
|
2007-08-28 06:27:41 +08:00
|
|
|
"""Encode a file; input and output are binary files."""
|
2022-11-27 06:33:25 +08:00
|
|
|
while s := input.read(MAXBINSIZE):
|
|
|
|
while len(s) < MAXBINSIZE and (ns := input.read(MAXBINSIZE-len(s))):
|
2004-01-04 09:12:26 +08:00
|
|
|
s += ns
|
2000-02-02 23:10:15 +08:00
|
|
|
line = binascii.b2a_base64(s)
|
|
|
|
output.write(line)
|
1995-06-15 07:43:44 +08:00
|
|
|
|
2004-01-04 09:12:26 +08:00
|
|
|
|
1995-06-15 07:43:44 +08:00
|
|
|
def decode(input, output):
|
2007-08-28 06:27:41 +08:00
|
|
|
"""Decode a file; input and output are binary files."""
|
2022-11-27 06:33:25 +08:00
|
|
|
while line := input.readline():
|
2000-02-02 23:10:15 +08:00
|
|
|
s = binascii.a2b_base64(line)
|
|
|
|
output.write(s)
|
1995-06-15 07:43:44 +08:00
|
|
|
|
2013-10-02 22:43:22 +08:00
|
|
|
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)
|
|
|
|
|
2004-01-04 09:12:26 +08:00
|
|
|
|
2009-06-04 17:11:51 +08:00
|
|
|
def encodebytes(s):
|
2016-02-24 06:30:50 +08:00
|
|
|
"""Encode a bytestring into a bytes object containing multiple lines
|
2009-06-04 17:11:51 +08:00
|
|
|
of base-64 data."""
|
2013-10-02 22:43:22 +08:00
|
|
|
_input_type_check(s)
|
2001-06-08 02:56:13 +08:00
|
|
|
pieces = []
|
|
|
|
for i in range(0, len(s), MAXBINSIZE):
|
|
|
|
chunk = s[i : i + MAXBINSIZE]
|
|
|
|
pieces.append(binascii.b2a_base64(chunk))
|
2007-05-23 05:56:47 +08:00
|
|
|
return b"".join(pieces)
|
1995-06-15 07:43:44 +08:00
|
|
|
|
2007-08-28 06:27:41 +08:00
|
|
|
|
2009-06-04 17:11:51 +08:00
|
|
|
def decodebytes(s):
|
2016-02-24 06:30:50 +08:00
|
|
|
"""Decode a bytestring of base-64 data into a bytes object."""
|
2013-10-02 22:43:22 +08:00
|
|
|
_input_type_check(s)
|
2001-06-08 02:56:13 +08:00
|
|
|
return binascii.a2b_base64(s)
|
1995-06-15 07:43:44 +08:00
|
|
|
|
2008-08-20 01:56:33 +08:00
|
|
|
|
2007-05-23 05:56:47 +08:00
|
|
|
# Usable as a script...
|
|
|
|
def main():
|
|
|
|
"""Small main program"""
|
2000-02-02 23:10:15 +08:00
|
|
|
import sys, getopt
|
2023-04-02 13:05:50 +08:00
|
|
|
usage = f"""usage: {sys.argv[0]} [-h|-d|-e|-u] [file|-]
|
2021-10-07 09:38:43 +08:00
|
|
|
-h: print this help message and exit
|
|
|
|
-d, -u: decode
|
2022-07-02 14:53:43 +08:00
|
|
|
-e: encode (default)"""
|
2000-02-02 23:10:15 +08:00
|
|
|
try:
|
2023-04-02 13:05:50 +08:00
|
|
|
opts, args = getopt.getopt(sys.argv[1:], 'hdeu')
|
2007-01-11 00:19:56 +08:00
|
|
|
except getopt.error as msg:
|
2000-02-02 23:10:15 +08:00
|
|
|
sys.stdout = sys.stderr
|
2007-02-09 13:37:30 +08:00
|
|
|
print(msg)
|
2021-10-07 09:38:43 +08:00
|
|
|
print(usage)
|
2000-02-02 23:10:15 +08:00
|
|
|
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
|
2021-10-07 09:38:43 +08:00
|
|
|
if o == '-h': print(usage); return
|
2000-02-02 23:10:15 +08:00
|
|
|
if args and args[0] != '-':
|
2010-10-15 05:15:17 +08:00
|
|
|
with open(args[0], 'rb') as f:
|
|
|
|
func(f, sys.stdout.buffer)
|
2000-02-02 23:10:15 +08:00
|
|
|
else:
|
2010-05-26 05:12:34 +08:00
|
|
|
func(sys.stdin.buffer, sys.stdout.buffer)
|
1995-06-15 07:43:44 +08:00
|
|
|
|
2004-01-04 09:12:26 +08:00
|
|
|
|
1995-06-15 07:43:44 +08:00
|
|
|
if __name__ == '__main__':
|
2007-05-23 05:56:47 +08:00
|
|
|
main()
|