summaryrefslogtreecommitdiffstats
path: root/Lib
diff options
context:
space:
mode:
authorR David Murray <rdmurray@bitdance.com>2011-03-15 01:13:03 (GMT)
committerR David Murray <rdmurray@bitdance.com>2011-03-15 01:13:03 (GMT)
commit3a6152f3b3346f00371faad8fc8a9cfb3085682f (patch)
treee876113081ac14159447af678d9568aaf8458c07 /Lib
parentf2db4de4d82101a900ff3b000e39ee9207ff8bf7 (diff)
downloadcpython-3a6152f3b3346f00371faad8fc8a9cfb3085682f.zip
cpython-3a6152f3b3346f00371faad8fc8a9cfb3085682f.tar.gz
cpython-3a6152f3b3346f00371faad8fc8a9cfb3085682f.tar.bz2
Fix header encoding of long headers when using euc-jp and shift_jis.
When a header was long enough to need to be split across lines, the input charset name was used instead of the output charset name in the encoded words. This make a difference only for the two charsets above.
Diffstat (limited to 'Lib')
-rw-r--r--Lib/email/charset.py2
-rw-r--r--Lib/email/test/test_email.py14
2 files changed, 15 insertions, 1 deletions
diff --git a/Lib/email/charset.py b/Lib/email/charset.py
index 8591527..24d5545 100644
--- a/Lib/email/charset.py
+++ b/Lib/email/charset.py
@@ -321,7 +321,7 @@ class Charset:
codec = self.output_codec or 'us-ascii'
header_bytes = _encode(string, codec)
encoder_module = self._get_encoder(header_bytes)
- encoder = partial(encoder_module.header_encode, charset=str(self))
+ encoder = partial(encoder_module.header_encode, charset=codec)
# Calculate the number of characters that the RFC 2047 chrome will
# contribute to each line.
charset = self.get_output_charset()
diff --git a/Lib/email/test/test_email.py b/Lib/email/test/test_email.py
index 16772b1..f8bdaa2 100644
--- a/Lib/email/test/test_email.py
+++ b/Lib/email/test/test_email.py
@@ -725,6 +725,20 @@ wasnipoop; giraffes="very-long-necked-animals";
wasnipoop; giraffes="very-long-necked-animals";
\tspooge="yummy"; hippos="gargantuan"; marshmallows="gooey"''')
+ def test_header_encode_with_different_output_charset(self):
+ h = Header('文', 'euc-jp')
+ self.assertEqual(h.encode(), "=?iso-2022-jp?b?GyRCSjgbKEI=?=")
+
+ def test_long_header_encode_with_different_output_charset(self):
+ h = Header(b'test-ja \xa4\xd8\xc5\xea\xb9\xc6\xa4\xb5\xa4\xec\xa4'
+ b'\xbf\xa5\xe1\xa1\xbc\xa5\xeb\xa4\xcf\xbb\xca\xb2\xf1\xbc\xd4'
+ b'\xa4\xce\xbe\xb5\xc7\xa7\xa4\xf2\xc2\xd4\xa4\xc3\xa4\xc6\xa4'
+ b'\xa4\xa4\xde\xa4\xb9'.decode('euc-jp'), 'euc-jp')
+ res = """\
+=?iso-2022-jp?b?dGVzdC1qYSAbJEIkWEVqOUYkNSRsJD8lYSE8JWskTztKMnE8VCROPjUbKEI=?=
+ =?iso-2022-jp?b?GyRCRyckckJUJEMkRiQkJF4kORsoQg==?="""
+ self.assertEqual(h.encode(), res)
+
def test_header_splitter(self):
eq = self.ndiffAssertEqual
msg = MIMEText('')