def decode(ew):
"""Decode encoded word and return (string, charset, lang, defects) tuple.
An RFC 2047/2243 encoded word has the form:
=?charset*lang?cte?encoded_string?=
where '*lang' may be omitted but the other parts may not be.
This function expects exactly such a string (that is, it does not check the
syntax and may raise errors if the string is not well formed), and returns
the encoded_string decoded first from its Content Transfer Encoding and
then from the resulting bytes into unicode using the specified charset. If
the cte-decoded string does not successfully decode using the specified
character set, a defect is added to the defects list and the unknown octets
are replaced by the unicode 'unknown' character \\uFDFF.
The specified charset and language are returned. The default for language,
which is rarely if ever encountered, is the empty string.
"""
_, charset, cte, cte_string, _ = ew.split('?')
charset, _, lang = charset.partition('*')
cte = cte.lower()
# Recover the original bytes and do CTE decoding.
bstring = cte_string.encode('ascii', 'surrogateescape')
bstring, defects = _cte_decoders[cte](bstring)
# Turn the CTE decoded bytes into unicode.
try:
string = bstring.decode(charset)
except UnicodeError:
defects.append(
errors.UndecodableBytesDefect(
"Encoded word "
"contains bytes not decodable using {} charset".format(
charset)))
string = bstring.decode(charset, 'surrogateescape')
except LookupError:
string = bstring.decode('ascii', 'surrogateescape')
if charset.lower() != 'unknown-8bit':
defects.append(
errors.CharsetError(
"Unknown charset {} "
"in encoded word; decoded as unknown bytes".format(
charset)))
return string, charset, lang, defects
def decode(ew):
(_, charset, cte, cte_string, _) = ew.split('?')
(charset, _, lang) = charset.partition('*')
cte = cte.lower()
bstring = cte_string.encode('ascii', 'surrogateescape')
(bstring, defects) = _cte_decoders[cte](bstring)
try:
string = bstring.decode(charset)
except UnicodeError:
defects.append(
errors.UndecodableBytesDefect(
'Encoded word contains bytes not decodable using {} charset'.
format(charset)))
string = bstring.decode(charset, 'surrogateescape')
except LookupError:
string = bstring.decode('ascii', 'surrogateescape')
if charset.lower() != 'unknown-8bit':
defects.append(
errors.CharsetError(
'Unknown charset {} in encoded word; decoded as unknown bytes'
.format(charset)))
return (string, charset, lang, defects)
