[issue41307] "email.message.Message.as_bytes": fails to correctly handle "charset"

2020-07-15 Thread Dieter Maurer 


Dieter Maurer  added the comment:

The following fixes the example:
from copy import copy
from io import BytesIO
from email.message import Message
from email.generator import BytesGenerator, _has_surrogates
from email._policybase import Compat32


class FixedBytesGenerator(BytesGenerator):
def _handle_text(self, msg):
payload = msg._payload
if payload is None:
return
charset = msg.get_param("charset")
if charset is not None \
   and not self.policy.cte_type=='7bit' \
   and not _has_surrogates(payload):
msg = copy(msg)
msg._payload = payload.encode(charset).decode(
"ascii", "surrogateescape")
super()._handle_text(msg)

_writeBody = _handle_text


class FixedMessage(Message):
def as_bytes(self, unixfrom=False, policy=None):
policy = self.policy if policy is None else policy
fp = BytesIO()
g = FixedBytesGenerator(fp, mangle_from_=False, policy=policy)
g.flatten(self, unixfrom=unixfrom)
return fp.getvalue()


fixed_policy = Compat32(message_factory=FixedMessage)

ms = message_from_string(mt, policy=fixed_policy)
ms.as_bytes()

--

___
Python tracker 

___
___
Python-bugs-list mailing list
Unsubscribe: 
https://mail.python.org/mailman/options/python-bugs-list/archive%40mail-archive.com

[issue41307] "email.message.Message.as_bytes": fails to correctly handle "charset"

2020-07-15 Thread Dieter Maurer 

New submission from Dieter Maurer :

In the transscript below, "ms" and "mb" should be equivalent:

>>> from email import message_from_string, message_from_bytes
>>> mt = """\
... Mime-Version: 1.0
... Content-Type: text/plain; charset=UTF-8
... Content-Transfer-Encoding: 8bit
... 
... รค
... """
>>> ms = message_from_string(mt)
>>> mb = message_from_bytes(mt.encode("UTF-8"))

But "mb.as_bytes" succeeds while "ms.as_bytes" raises a "UnicodeEncodeError":

>>> mb.as_bytes()
b'Mime-Version: 1.0\nContent-Type: text/plain; 
charset=UTF-8\nContent-Transfer-Encoding: 8bit\n\n\xc3\xa4\n'
>>> ms.as_bytes()
Traceback (most recent call last):
...
  File "/usr/local/lib/python3.9/email/generator.py", line 155, in _write_lines
self.write(line)
  File "/usr/local/lib/python3.9/email/generator.py", line 406, in write
self._fp.write(s.encode('ascii', 'surrogateescape'))
UnicodeEncodeError: 'ascii' codec can't encode character '\xe4' in position 0: 
ordinal not in range(128)

Apparently, the "as_bytes" ignores the "charset" parameter from the 
"Content-Type" header (it should use "utf-8", not "ascii" for the encoding).

--
components: email
messages: 373711
nosy: barry, dmaurer, r.david.murray
priority: normal
severity: normal
status: open
title: "email.message.Message.as_bytes":  fails to correctly handle "charset"
type: behavior
versions: Python 3.9

___
Python tracker 

___
___
Python-bugs-list mailing list
Unsubscribe: 
https://mail.python.org/mailman/options/python-bugs-list/archive%40mail-archive.com