123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358359360361362363364365366367368369370371372373374375376377378379380381382383384385386387388389390391392393394395396397398399400401402403404405406407408409410411412413414415416417418419420421422423424425426427428429430431432433434435436437438439440441442443444445446447448449450451452453454455456457458459460461462463464465466467468469470471472473474475476477478479480481482483484485486487488489490491492493494495496497498499500501502503504505506507508509510511512513514515516517518519520521522523524525526527528529530531532533534535536537538539540541542543544545546547548549550551552553554555556557558559560561562563564565566567568569570571572573574575576577578579580581582583584585586587588589590591592593594595596597598599600601 |
- """Base16, Base32, Base64 (RFC 3548), Base85 and Ascii85 data encodings"""
- import re
- import struct
- import binascii
- __all__ = [
-
- 'encode', 'decode', 'encodebytes', 'decodebytes',
-
- 'b64encode', 'b64decode', 'b32encode', 'b32decode',
- 'b16encode', 'b16decode',
-
- 'b85encode', 'b85decode', 'a85encode', 'a85decode',
-
- 'standard_b64encode', 'standard_b64decode',
-
-
-
-
- 'urlsafe_b64encode', 'urlsafe_b64decode',
- ]
- bytes_types = (bytes, bytearray)
- 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
- def b64encode(s, altchars=None):
- """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.
- """
-
- 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 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.
- The result is returned as a bytes object. A binascii.Error is raised if
- s is incorrectly padded.
- 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.
- """
- 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 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_encode_translation = bytes.maketrans(b'+/', b'-_')
- _urlsafe_decode_translation = bytes.maketrans(b'-_', b'+/')
- def urlsafe_b64encode(s):
- """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
- '/'.
- """
- return b64encode(s).translate(_urlsafe_encode_translation)
- def urlsafe_b64decode(s):
- """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.
- The alphabet uses '-' instead of '+' and '_' instead of '/'.
- """
- s = _bytes_from_decode_data(s)
- s = s.translate(_urlsafe_decode_translation)
- return b64decode(s)
- _b32alphabet = b'ABCDEFGHIJKLMNOPQRSTUVWXYZ234567'
- _b32tab2 = None
- _b32rev = None
- def b32encode(s):
- """Encode the bytes-like object s using Base32 and return a bytes object.
- """
- global _b32tab2
-
-
- if _b32tab2 is None:
- b32tab = [bytes((i,)) for i in _b32alphabet]
- _b32tab2 = [a + b for a in b32tab for b in b32tab]
- b32tab = None
- if not isinstance(s, bytes_types):
- s = memoryview(s).tobytes()
- leftover = len(s) % 5
-
- if leftover:
- s = s + bytes(5 - leftover)
- 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] +
- b32tab2[(c >> 20) & 0x3ff] +
- b32tab2[(c >> 10) & 0x3ff] +
- b32tab2[c & 0x3ff]
- )
-
- 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 the Base32 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.
- 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 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.
- """
- global _b32rev
-
-
- if _b32rev is None:
- _b32rev = {v: k for k, v in enumerate(_b32alphabet)}
- s = _bytes_from_decode_data(s)
- if len(s) % 8:
- raise binascii.Error('Incorrect padding')
-
-
-
- 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()
-
-
-
- l = len(s)
- s = s.rstrip(b'=')
- padchars = l - len(s)
-
- 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')
-
- 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)
- def b16encode(s):
- """Encode the bytes-like object s using Base16 and return a bytes object.
- """
- return binascii.hexlify(s).upper()
- def b16decode(s, casefold=False):
- """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.
- 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.
- """
- 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)
- _a85chars = None
- _a85chars2 = None
- _A85START = b"<~"
- _A85END = b"~>"
- def _85encode(b, chars, chars2, pad=False, foldnuls=False, foldspaces=False):
-
- 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):
- """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" Adobe encoding.
- wrapcol controls whether the output should have newline (b'\\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 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.
- """
- global _a85chars, _a85chars2
-
-
- if _a85chars is None:
- _a85chars = [bytes((i,)) for i in range(33, 118)]
- _a85chars2 = [(a + b) for a in _a85chars for b in _a85chars]
- 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 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" 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.
- The result is returned as a bytes object.
- """
- b = _bytes_from_decode_data(b)
- if adobe:
- 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]
- else:
- b = b[:-2]
-
-
-
-
- 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:
-
- continue
- else:
- raise ValueError('Non-Ascii85 digit found: %c' % x)
- result = b''.join(decoded)
- padding = 4 - len(curr)
- if padding:
-
- result = result[:-padding]
- return result
- _b85alphabet = (b"0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZ"
- b"abcdefghijklmnopqrstuvwxyz!#$%&()*+-;<=>?@^_`{|}~")
- _b85chars = None
- _b85chars2 = None
- _b85dec = None
- def b85encode(b, pad=False):
- """Encode bytes-like object b in base85 format and return a bytes object.
- If pad is true, the input is padded with b'\\0' so its length is a multiple of
- 4 bytes before encoding.
- """
- global _b85chars, _b85chars2
-
-
- if _b85chars is None:
- _b85chars = [bytes((i,)) for i in _b85alphabet]
- _b85chars2 = [(a + b) for a in _b85chars for b in _b85chars]
- return _85encode(b, _b85chars, _b85chars2, pad)
- def b85decode(b):
- """Decode the base85-encoded bytes-like object or ASCII string b
- The result is returned as a bytes object.
- """
- global _b85dec
-
-
- if _b85dec is None:
- _b85dec = [None] * 256
- for i, c in enumerate(_b85alphabet):
- _b85dec[c] = i
- b = _bytes_from_decode_data(b)
- 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
- MAXLINESIZE = 76
- 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 bytes object 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 bytes object."""
- _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)
- 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()
|