#16948: Fix quopri encoding of non-latin1 character sets.

This commit is contained in:
R David Murray 2013-02-05 10:49:49 -05:00
parent 43536e9e37
commit f581b37200
3 changed files with 38 additions and 0 deletions

View File

@ -392,6 +392,19 @@ class Charset:
string = string.encode(self.output_charset)
return email.base64mime.body_encode(string)
elif self.body_encoding is QP:
# quopromime.body_encode takes a string, but operates on it as if
# it were a list of byte codes. For a (minimal) history on why
# this is so, see changeset 0cf700464177. To correctly encode a
# character set, then, we must turn it into pseudo bytes via the
# latin1 charset, which will encode any byte as a single code point
# between 0 and 255, which is what body_encode is expecting.
#
# Note that this clause doesn't handle the case of a _payload that
# is already bytes. It never did, and the semantics of _payload
# being bytes has never been nailed down, so fixing that is a
# longer term TODO.
if isinstance(string, str):
string = string.encode(self.output_charset).decode('latin1')
return email.quoprimime.body_encode(string)
else:
if isinstance(string, str):

View File

@ -670,6 +670,27 @@ class TestEncoders(unittest.TestCase):
msg = MIMEText('', _charset='euc-jp')
eq(msg['content-transfer-encoding'], '7bit')
def test_qp_encode_latin1(self):
msg = MIMEText('\xe1\xf6\n', 'text', 'ISO-8859-1')
self.assertEqual(str(msg), textwrap.dedent("""\
MIME-Version: 1.0
Content-Type: text/text; charset="iso-8859-1"
Content-Transfer-Encoding: quoted-printable
=E1=F6
"""))
def test_qp_encode_non_latin1(self):
# Issue 16948
msg = MIMEText('\u017c\n', 'text', 'ISO-8859-2')
self.assertEqual(str(msg), textwrap.dedent("""\
MIME-Version: 1.0
Content-Type: text/text; charset="iso-8859-2"
Content-Transfer-Encoding: quoted-printable
=BF
"""))
# Test long header wrapping
class TestLongHeaders(TestEmailBase):

View File

@ -212,6 +212,10 @@ Core and Builtins
Library
-------
- Issue #16948: Fix quoted printable body encoding for non-latin1 character
sets in the email package.
- Issue #17089: Expat parser now correctly works with string input not only when
an internal XML encoding is UTF-8 or US-ASCII. It now accepts bytes and
strings larger than 2 GiB.