[Python-checkins] cpython (merge 3.2 -> 3.3): Merge: #16948: Fix quopri encoding of non-latin1 character sets.
r.david.murray
python-checkins at python.org
Tue Feb 5 17:35:04 CET 2013
http://hg.python.org/cpython/rev/e644058e8e7b
changeset: 82022:e644058e8e7b
branch: 3.3
parent: 82019:4553dfcafac7
parent: 82021:801cb3918212
user: R David Murray <rdmurray at bitdance.com>
date: Tue Feb 05 10:55:27 2013 -0500
summary:
Merge: #16948: Fix quopri encoding of non-latin1 character sets.
files:
Lib/email/charset.py | 13 +++++++++++
Lib/test/test_email/test_email.py | 21 +++++++++++++++++++
Misc/NEWS | 3 ++
3 files changed, 37 insertions(+), 0 deletions(-)
diff --git a/Lib/email/charset.py b/Lib/email/charset.py
--- a/Lib/email/charset.py
+++ b/Lib/email/charset.py
@@ -392,6 +392,19 @@
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):
diff --git a/Lib/test/test_email/test_email.py b/Lib/test/test_email/test_email.py
--- a/Lib/test/test_email/test_email.py
+++ b/Lib/test/test_email/test_email.py
@@ -677,6 +677,27 @@
msg = MIMEText('文', _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):
diff --git a/Misc/NEWS b/Misc/NEWS
--- a/Misc/NEWS
+++ b/Misc/NEWS
@@ -163,6 +163,9 @@
Library
-------
+- Issue #16948: Fix quoted printable body encoding for non-latin1 character
+ sets in the email package.
+
- Issue #16811: Fix folding of headers with no value in the provisional email
policies.
--
Repository URL: http://hg.python.org/cpython
More information about the Python-checkins
mailing list