diff options
Diffstat (limited to 'Lib/base64.py')
| -rwxr-xr-x | Lib/base64.py | 328 |
1 files changed, 188 insertions, 140 deletions
diff --git a/Lib/base64.py b/Lib/base64.py index 85204dd022a..895d813f7ee 100755 --- a/Lib/base64.py +++ b/Lib/base64.py @@ -1,9 +1,10 @@ -#! /usr/bin/env python +#! /usr/bin/env python3 """RFC 3548: Base16, Base32, Base64 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 @@ -12,7 +13,7 @@ import binascii __all__ = [ # Legacy interface exports traditional RFC 1521 Base64 encodings - 'encode', 'decode', 'encodestring', 'decodestring', + 'encode', 'decode', 'encodebytes', 'decodebytes', # Generalized interface for other encodings 'b64encode', 'b64decode', 'b32encode', 'b32decode', 'b16encode', 'b16decode', @@ -25,124 +26,142 @@ __all__ = [ 'urlsafe_b64encode', 'urlsafe_b64decode', ] -_translation = [chr(_x) for _x in range(256)] -EMPTYSTRING = '' + +bytes_types = (bytes, bytearray) # Types acceptable as binary data def _translate(s, altchars): - translation = _translation[:] + if not isinstance(s, bytes_types): + raise TypeError("expected bytes, not %s" % s.__class__.__name__) + translation = bytearray(range(256)) for k, v in altchars.items(): - translation[ord(k)] = v - return s.translate(''.join(translation)) + translation[ord(k)] = v[0] + return s.translate(translation) + - # Base64 encoding/decoding uses binascii def b64encode(s, altchars=None): - """Encode a string using Base64. + """Encode a byte string using Base64. - s is the string to encode. Optional altchars must be a string of at least - length 2 (additional characters are ignored) which specifies an - alternative alphabet for the '+' and '/' characters. This allows an - application to e.g. generate url or filesystem safe Base64 strings. + 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 string is returned. + The encoded byte string is returned. """ + if not isinstance(s, bytes_types): + raise TypeError("expected bytes, not %s" % s.__class__.__name__) # Strip off the trailing newline encoded = binascii.b2a_base64(s)[:-1] if altchars is not None: - return _translate(encoded, {'+': altchars[0], '/': altchars[1]}) + if not isinstance(altchars, bytes_types): + raise TypeError("expected bytes, not %s" + % altchars.__class__.__name__) + assert len(altchars) == 2, repr(altchars) + return _translate(encoded, {'+': altchars[0:1], '/': altchars[1:2]}) return encoded -def b64decode(s, altchars=None): - """Decode a Base64 encoded string. +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. - s is the string to decode. Optional altchars must be a string of at least - length 2 (additional characters are ignored) 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. - The decoded string is returned. A TypeError is raised if s were - incorrectly padded or if there are non-alphabet characters present in the - string. + 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. """ + if not isinstance(s, bytes_types): + raise TypeError("expected bytes, not %s" % s.__class__.__name__) if altchars is not None: - s = _translate(s, {altchars[0]: '+', altchars[1]: '/'}) - try: - return binascii.a2b_base64(s) - except binascii.Error, msg: - # Transform this exception for consistency - raise TypeError(msg) + if not isinstance(altchars, bytes_types): + raise TypeError("expected bytes, not %s" + % altchars.__class__.__name__) + assert len(altchars) == 2, repr(altchars) + s = _translate(s, {chr(altchars[0]): b'+', chr(altchars[1]): 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 string using the standard Base64 alphabet. + """Encode a byte string using the standard Base64 alphabet. - s is the string to encode. The encoded string is returned. + s is the byte string to encode. The encoded byte string is returned. """ return b64encode(s) def standard_b64decode(s): - """Decode a string encoded with the standard Base64 alphabet. + """Decode a byte string encoded with the standard Base64 alphabet. - s is the string to decode. The decoded string is returned. A TypeError - is raised if the string is incorrectly padded or if there are non-alphabet - characters present in the string. + 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) def urlsafe_b64encode(s): - """Encode a string using a url-safe Base64 alphabet. + """Encode a byte string using a url-safe Base64 alphabet. - s is the string to encode. The encoded string is returned. The alphabet - uses '-' instead of '+' and '_' instead of '/'. + s is the byte string to encode. The encoded byte string is + returned. The alphabet uses '-' instead of '+' and '_' instead of + '/'. """ - return b64encode(s, '-_') + return b64encode(s, b'-_') def urlsafe_b64decode(s): - """Decode a string encoded with the standard Base64 alphabet. + """Decode a byte string encoded with the standard Base64 alphabet. - s is the string to decode. The decoded string is returned. A TypeError - is raised if the string is incorrectly padded or if there are non-alphabet - characters present in the string. + 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 '/'. """ - return b64decode(s, '-_') + return b64decode(s, b'-_') + - # Base32 encoding/decoding must be done in Python _b32alphabet = { - 0: 'A', 9: 'J', 18: 'S', 27: '3', - 1: 'B', 10: 'K', 19: 'T', 28: '4', - 2: 'C', 11: 'L', 20: 'U', 29: '5', - 3: 'D', 12: 'M', 21: 'V', 30: '6', - 4: 'E', 13: 'N', 22: 'W', 31: '7', - 5: 'F', 14: 'O', 23: 'X', - 6: 'G', 15: 'P', 24: 'Y', - 7: 'H', 16: 'Q', 25: 'Z', - 8: 'I', 17: 'R', 26: '2', + 0: b'A', 9: b'J', 18: b'S', 27: b'3', + 1: b'B', 10: b'K', 19: b'T', 28: b'4', + 2: b'C', 11: b'L', 20: b'U', 29: b'5', + 3: b'D', 12: b'M', 21: b'V', 30: b'6', + 4: b'E', 13: b'N', 22: b'W', 31: b'7', + 5: b'F', 14: b'O', 23: b'X', + 6: b'G', 15: b'P', 24: b'Y', + 7: b'H', 16: b'Q', 25: b'Z', + 8: b'I', 17: b'R', 26: b'2', } -_b32tab = _b32alphabet.items() -_b32tab.sort() -_b32tab = [v for k, v in _b32tab] -_b32rev = dict([(v, long(k)) for k, v in _b32alphabet.items()]) +_b32tab = [v[0] for k, v in sorted(_b32alphabet.items())] +_b32rev = dict([(v[0], k) for k, v in _b32alphabet.items()]) def b32encode(s): - """Encode a string using Base32. + """Encode a byte string using Base32. - s is the string to encode. The encoded string is returned. + s is the byte string to encode. The encoded byte string is returned. """ - parts = [] + if not isinstance(s, bytes_types): + raise TypeError("expected bytes, not %s" % s.__class__.__name__) quanta, leftover = divmod(len(s), 5) # Pad the last quantum with zero bits if necessary if leftover: - s += ('\0' * (5 - leftover)) + s = s + bytes(5 - leftover) # Don't use += ! quanta += 1 + encoded = bytes() for i in range(quanta): # c1 and c2 are 16 bits wide, c3 is 8 bits wide. The intent of this # code is to process the 40 bits in units of 5 bits. So we take the 1 @@ -152,62 +171,66 @@ def b32encode(s): c1, c2, c3 = struct.unpack('!HHB', s[i*5:(i+1)*5]) c2 += (c1 & 1) << 16 # 17 bits wide c3 += (c2 & 3) << 8 # 10 bits wide - parts.extend([_b32tab[c1 >> 11], # bits 1 - 5 - _b32tab[(c1 >> 6) & 0x1f], # bits 6 - 10 - _b32tab[(c1 >> 1) & 0x1f], # bits 11 - 15 - _b32tab[c2 >> 12], # bits 16 - 20 (1 - 5) - _b32tab[(c2 >> 7) & 0x1f], # bits 21 - 25 (6 - 10) - _b32tab[(c2 >> 2) & 0x1f], # bits 26 - 30 (11 - 15) - _b32tab[c3 >> 5], # bits 31 - 35 (1 - 5) - _b32tab[c3 & 0x1f], # bits 36 - 40 (1 - 5) - ]) - encoded = EMPTYSTRING.join(parts) + encoded += bytes([_b32tab[c1 >> 11], # bits 1 - 5 + _b32tab[(c1 >> 6) & 0x1f], # bits 6 - 10 + _b32tab[(c1 >> 1) & 0x1f], # bits 11 - 15 + _b32tab[c2 >> 12], # bits 16 - 20 (1 - 5) + _b32tab[(c2 >> 7) & 0x1f], # bits 21 - 25 (6 - 10) + _b32tab[(c2 >> 2) & 0x1f], # bits 26 - 30 (11 - 15) + _b32tab[c3 >> 5], # bits 31 - 35 (1 - 5) + _b32tab[c3 & 0x1f], # bits 36 - 40 (1 - 5) + ]) # Adjust for any leftover partial quanta if leftover == 1: - return encoded[:-6] + '======' + return encoded[:-6] + b'======' elif leftover == 2: - return encoded[:-4] + '====' + return encoded[:-4] + b'====' elif leftover == 3: - return encoded[:-3] + '===' + return encoded[:-3] + b'===' elif leftover == 4: - return encoded[:-1] + '=' + return encoded[:-1] + b'=' return encoded def b32decode(s, casefold=False, map01=None): - """Decode a Base32 encoded string. - - s is the 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 string is returned. A TypeError is raised if s were - incorrectly padded or if there are non-alphabet characters present in the - string. + """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. """ + if not isinstance(s, bytes_types): + raise TypeError("expected bytes, not %s" % s.__class__.__name__) quanta, leftover = divmod(len(s), 8) if leftover: - raise TypeError('Incorrect padding') + 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: - s = _translate(s, {'0': 'O', '1': map01}) + if map01 is not None: + if not isinstance(map01, bytes_types): + raise TypeError("expected bytes, not %s" % map01.__class__.__name__) + assert len(map01) == 1, repr(map01) + s = _translate(s, {b'0': b'O', b'1': 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. padchars = 0 - mo = re.search('(?P<pad>[=]*)$', s) + mo = re.search(b'(?P<pad>[=]*)$', s) if mo: padchars = len(mo.group('pad')) if padchars > 0: @@ -223,13 +246,13 @@ def b32decode(s, casefold=False, map01=None): acc += _b32rev[c] << shift shift -= 5 if shift < 0: - parts.append(binascii.unhexlify('%010x' % acc)) + parts.append(binascii.unhexlify(bytes('%010x' % acc, "ascii"))) acc = 0 shift = 35 # Process the last, partial quanta - last = binascii.unhexlify('%010x' % acc) + last = binascii.unhexlify(bytes('%010x' % acc, "ascii")) if padchars == 0: - last = '' # No characters + last = b'' # No characters elif padchars == 1: last = last[:-1] elif padchars == 3: @@ -239,51 +262,55 @@ def b32decode(s, casefold=False, map01=None): elif padchars == 6: last = last[:-4] else: - raise TypeError('Incorrect padding') + raise binascii.Error('Incorrect padding') parts.append(last) - return EMPTYSTRING.join(parts) + return b''.join(parts) + - # 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 string using Base16. + """Encode a byte string using Base16. - s is the string to encode. The encoded string is returned. + s is the byte string to encode. The encoded byte string is returned. """ + if not isinstance(s, bytes_types): + raise TypeError("expected bytes, not %s" % s.__class__.__name__) return binascii.hexlify(s).upper() def b16decode(s, casefold=False): - """Decode a Base16 encoded string. + """Decode a Base16 encoded byte string. - s is the string to decode. Optional casefold is a flag specifying whether - a lowercase alphabet is acceptable as input. For security purposes, the - default is False. + 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 string is returned. A TypeError is raised if s were - incorrectly padded or if there are non-alphabet characters present in the - string. + 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. """ + if not isinstance(s, bytes_types): + raise TypeError("expected bytes, not %s" % s.__class__.__name__) if casefold: s = s.upper() - if re.search('[^0-9A-F]', s): - raise TypeError('Non-base16 digit found') + if re.search(b'[^0-9A-F]', s): + raise binascii.Error('Non-base16 digit found') return binascii.unhexlify(s) - + # 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. +# 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.""" + """Encode a file; input and output are binary files.""" while True: s = input.read(MAXBINSIZE) if not s: @@ -298,7 +325,7 @@ def encode(input, output): def decode(input, output): - """Decode a file.""" + """Decode a file; input and output are binary files.""" while True: line = input.readline() if not line: @@ -307,54 +334,75 @@ def decode(input, output): output.write(s) -def encodestring(s): - """Encode a string into multiple lines of base-64 data.""" +def encodebytes(s): + """Encode a bytestring into a bytestring containing multiple lines + of base-64 data.""" + if not isinstance(s, bytes_types): + raise TypeError("expected bytes, not %s" % s.__class__.__name__) pieces = [] for i in range(0, len(s), MAXBINSIZE): chunk = s[i : i + MAXBINSIZE] pieces.append(binascii.b2a_base64(chunk)) - return "".join(pieces) + 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 decodestring(s): - """Decode a string.""" + +def decodebytes(s): + """Decode a bytestring of base-64 data into a bytestring.""" + if not isinstance(s, bytes_types): + raise TypeError("expected bytes, not %s" % s.__class__.__name__) 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) - -# Useable as a script... -def test(): - """Small test program""" + +# Usable as a script... +def main(): + """Small main program""" import sys, getopt try: opts, args = getopt.getopt(sys.argv[1:], 'deut') - except getopt.error, msg: + except getopt.error as msg: sys.stdout = sys.stderr - print msg - print """usage: %s [-d|-e|-u|-t] [file|-] + 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] + -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': test1(); return + if o == '-t': test(); return if args and args[0] != '-': with open(args[0], 'rb') as f: - func(f, sys.stdout) + func(f, sys.stdout.buffer) else: - func(sys.stdin, sys.stdout) + func(sys.stdin.buffer, sys.stdout.buffer) -def test1(): - s0 = "Aladdin:open sesame" - s1 = encodestring(s0) - s2 = decodestring(s1) - print s0, repr(s1), s2 +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__': - test() + main() |