# Copyright (C) 2002-2007 Python Software Foundation

[0] Fix | Delete

# Author: Ben Gertzfield

[1] Fix | Delete

# Contact: email-sig@python.org

[2] Fix | Delete

[3] Fix | Delete

"""Base64 content transfer encoding per RFCs 2045-2047.

[4] Fix | Delete

[5] Fix | Delete

This module handles the content transfer encoding method defined in RFC 2045

[6] Fix | Delete

to encode arbitrary 8-bit data using the three 8-bit bytes in four 7-bit

[7] Fix | Delete

characters encoding known as Base64.

[8] Fix | Delete

[9] Fix | Delete

It is used in the MIME standards for email to attach images, audio, and text

[10] Fix | Delete

using some 8-bit character sets to messages.

[11] Fix | Delete

[12] Fix | Delete

This module provides an interface to encode and decode both headers and bodies

[13] Fix | Delete

with Base64 encoding.

[14] Fix | Delete

[15] Fix | Delete

RFC 2045 defines a method for including character set information in an

[16] Fix | Delete

`encoded-word' in a header. This method is commonly used for 8-bit real names

[17] Fix | Delete

in To:, From:, Cc:, etc. fields, as well as Subject: lines.

[18] Fix | Delete

[19] Fix | Delete

This module does not do the line wrapping or end-of-line character conversion

[20] Fix | Delete

necessary for proper internationalized headers; it only does dumb encoding and

[21] Fix | Delete

decoding. To deal with the various line wrapping issues, use the email.header

[22] Fix | Delete

module.

[23] Fix | Delete

"""

[24] Fix | Delete

[25] Fix | Delete

__all__ = [

[26] Fix | Delete

'body_decode',

[27] Fix | Delete

'body_encode',

[28] Fix | Delete

'decode',

[29] Fix | Delete

'decodestring',

[30] Fix | Delete

'header_encode',

[31] Fix | Delete

'header_length',

[32] Fix | Delete

]

[33] Fix | Delete

[34] Fix | Delete

[35] Fix | Delete

from base64 import b64encode

[36] Fix | Delete

from binascii import b2a_base64, a2b_base64

[37] Fix | Delete

[38] Fix | Delete

CRLF = '\r\n'

[39] Fix | Delete

NL = '\n'

[40] Fix | Delete

EMPTYSTRING = ''

[41] Fix | Delete

[42] Fix | Delete

# See also Charset.py

[43] Fix | Delete

MISC_LEN = 7

[44] Fix | Delete

[45] Fix | Delete

[46] Fix | Delete



[47] Fix | Delete

# Helpers

[48] Fix | Delete

def header_length(bytearray):

[49] Fix | Delete

"""Return the length of s when it is encoded with base64."""

[50] Fix | Delete

groups_of_3, leftover = divmod(len(bytearray), 3)

[51] Fix | Delete

# 4 bytes out for each 3 bytes (or nonzero fraction thereof) in.

[52] Fix | Delete

n = groups_of_3 * 4

[53] Fix | Delete

if leftover:

[54] Fix | Delete

n += 4

[55] Fix | Delete

return n

[56] Fix | Delete

[57] Fix | Delete

[58] Fix | Delete



[59] Fix | Delete

def header_encode(header_bytes, charset='iso-8859-1'):

[60] Fix | Delete

"""Encode a single header line with Base64 encoding in a given charset.

[61] Fix | Delete

[62] Fix | Delete

charset names the character set to use to encode the header. It defaults

[63] Fix | Delete

to iso-8859-1. Base64 encoding is defined in RFC 2045.

[64] Fix | Delete

"""

[65] Fix | Delete

if not header_bytes:

[66] Fix | Delete

return ""

[67] Fix | Delete

if isinstance(header_bytes, str):

[68] Fix | Delete

header_bytes = header_bytes.encode(charset)

[69] Fix | Delete

encoded = b64encode(header_bytes).decode("ascii")

[70] Fix | Delete

return '=?%s?b?%s?=' % (charset, encoded)

[71] Fix | Delete

[72] Fix | Delete

[73] Fix | Delete



[74] Fix | Delete

def body_encode(s, maxlinelen=76, eol=NL):

[75] Fix | Delete

r"""Encode a string with base64.

[76] Fix | Delete

[77] Fix | Delete

Each line will be wrapped at, at most, maxlinelen characters (defaults to

[78] Fix | Delete

76 characters).

[79] Fix | Delete

[80] Fix | Delete

Each line of encoded text will end with eol, which defaults to "\n". Set

[81] Fix | Delete

this to "\r\n" if you will be using the result of this function directly

[82] Fix | Delete

in an email.

[83] Fix | Delete

"""

[84] Fix | Delete

if not s:

[85] Fix | Delete

return s

[86] Fix | Delete

[87] Fix | Delete

encvec = []

[88] Fix | Delete

max_unencoded = maxlinelen * 3 // 4

[89] Fix | Delete

for i in range(0, len(s), max_unencoded):

[90] Fix | Delete

# BAW: should encode() inherit b2a_base64()'s dubious behavior in

[91] Fix | Delete

# adding a newline to the encoded string?

[92] Fix | Delete

enc = b2a_base64(s[i:i + max_unencoded]).decode("ascii")

[93] Fix | Delete

if enc.endswith(NL) and eol != NL:

[94] Fix | Delete

enc = enc[:-1] + eol

[95] Fix | Delete

encvec.append(enc)

[96] Fix | Delete

return EMPTYSTRING.join(encvec)

[97] Fix | Delete

[98] Fix | Delete

[99] Fix | Delete



[100] Fix | Delete

def decode(string):

[101] Fix | Delete

"""Decode a raw base64 string, returning a bytes object.

[102] Fix | Delete

[103] Fix | Delete

This function does not parse a full MIME header value encoded with

[104] Fix | Delete

base64 (like =?iso-8859-1?b?bmloISBuaWgh?=) -- please use the high

[105] Fix | Delete

level email.header class for that functionality.

[106] Fix | Delete

"""

[107] Fix | Delete

if not string:

[108] Fix | Delete

return bytes()

[109] Fix | Delete

elif isinstance(string, str):

[110] Fix | Delete

return a2b_base64(string.encode('raw-unicode-escape'))

[111] Fix | Delete

else:

[112] Fix | Delete

return a2b_base64(string)

[113] Fix | Delete

[114] Fix | Delete

[115] Fix | Delete

# For convenience and backwards compatibility w/ standard base64 module

[116] Fix | Delete

body_decode = decode

[117] Fix | Delete

decodestring = decode

[118] Fix | Delete

[119] Fix | Delete