mirror of https://github.com/python/cpython
122 lines
3.4 KiB
Python
122 lines
3.4 KiB
Python
# Copyright (C) 2002-2007 Python Software Foundation
|
||
# Author: Ben Gertzfield
|
||
# Contact: email-sig@python.org
|
||
|
||
"""Base64 content transfer encoding per RFCs 2045-2047.
|
||
|
||
This module handles the content transfer encoding method defined in RFC 2045
|
||
to encode arbitrary 8-bit data using the three 8-bit bytes in four 7-bit
|
||
characters encoding known as Base64.
|
||
|
||
It is used in the MIME standards for email to attach images, audio, and text
|
||
using some 8-bit character sets to messages.
|
||
|
||
This module provides an interface to encode and decode both headers and bodies
|
||
with Base64 encoding.
|
||
|
||
RFC 2045 defines a method for including character set information in an
|
||
`encoded-word' in a header. This method is commonly used for 8-bit real names
|
||
in To:, From:, Cc:, etc. fields, as well as Subject: lines.
|
||
|
||
This module does not do the line wrapping or end-of-line character conversion
|
||
necessary for proper internationalized headers; it only does dumb encoding and
|
||
decoding. To deal with the various line wrapping issues, use the email.Header
|
||
module.
|
||
"""
|
||
|
||
__all__ = [
|
||
'body_decode',
|
||
'body_encode',
|
||
'decode',
|
||
'decodestring',
|
||
'encode',
|
||
'encodestring',
|
||
'header_encode',
|
||
'header_length',
|
||
]
|
||
|
||
import re
|
||
|
||
from base64 import b64encode
|
||
from binascii import b2a_base64, a2b_base64
|
||
|
||
CRLF = '\r\n'
|
||
NL = '\n'
|
||
EMPTYSTRING = ''
|
||
|
||
# See also Charset.py
|
||
MISC_LEN = 7
|
||
|
||
|
||
|
||
# Helpers
|
||
def header_length(bytearray):
|
||
"""Return the length of s when it is encoded with base64."""
|
||
groups_of_3, leftover = divmod(len(bytearray), 3)
|
||
# 4 bytes out for each 3 bytes (or nonzero fraction thereof) in.
|
||
n = groups_of_3 * 4
|
||
if leftover:
|
||
n += 4
|
||
return n
|
||
|
||
|
||
|
||
def header_encode(header_bytes, charset='iso-8859-1'):
|
||
"""Encode a single header line with Base64 encoding in a given charset.
|
||
|
||
charset names the character set to use to encode the header. It defaults
|
||
to iso-8859-1. Base64 encoding is defined in RFC 2045.
|
||
"""
|
||
# Return empty headers unchanged
|
||
if not header_bytes:
|
||
return str(header_bytes)
|
||
encoded = b64encode(header_bytes)
|
||
return '=?%s?b?%s?=' % (charset, encoded)
|
||
|
||
|
||
|
||
def body_encode(s, maxlinelen=76, eol=NL):
|
||
"""Encode a string with base64.
|
||
|
||
Each line will be wrapped at, at most, maxlinelen characters (defaults to
|
||
76 characters).
|
||
|
||
Each line of encoded text will end with eol, which defaults to "\\n". Set
|
||
this to "\r\n" if you will be using the result of this function directly
|
||
in an email.
|
||
"""
|
||
if not s:
|
||
return s
|
||
|
||
encvec = []
|
||
max_unencoded = maxlinelen * 3 // 4
|
||
for i in range(0, len(s), max_unencoded):
|
||
# BAW: should encode() inherit b2a_base64()'s dubious behavior in
|
||
# adding a newline to the encoded string?
|
||
enc = str(b2a_base64(s[i:i + max_unencoded]))
|
||
if enc.endswith(NL) and eol != NL:
|
||
enc = enc[:-1] + eol
|
||
encvec.append(enc)
|
||
return EMPTYSTRING.join(encvec)
|
||
|
||
|
||
|
||
def decode(string):
|
||
"""Decode a raw base64 string, returning a bytes object.
|
||
|
||
This function does not parse a full MIME header value encoded with
|
||
base64 (like =?iso-8895-1?b?bmloISBuaWgh?=) -- please use the high
|
||
level email.Header class for that functionality.
|
||
"""
|
||
if not string:
|
||
return bytes()
|
||
elif isinstance(string, str):
|
||
return a2b_base64(string.encode('raw-unicode-escape'))
|
||
else:
|
||
return a2b_base64(s)
|
||
|
||
|
||
# For convenience and backwards compatibility w/ standard base64 module
|
||
body_decode = decode
|
||
decodestring = decode
|