cpython/Lib/email/test/test_email_codecs.py

60 lines
2.2 KiB
Python
Raw Blame History

This file contains invisible Unicode characters

This file contains invisible Unicode characters that are indistinguishable to humans but may be processed differently by a computer. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

# Copyright (C) 2002 Python Software Foundation
# email package unit tests for (optional) Asian codecs
import unittest
from test.test_support import TestSkipped, run_unittest
from email.test.test_email import TestEmailBase
from email.Charset import Charset
from email.Header import Header, decode_header
class TestEmailAsianCodecs(TestEmailBase):
def test_japanese_codecs(self):
eq = self.ndiffAssertEqual
j = Charset("euc-jp")
g = Charset("iso-8859-1")
h = Header("Hello World!")
jhello = '\xa5\xcf\xa5\xed\xa1\xbc\xa5\xef\xa1\xbc\xa5\xeb\xa5\xc9\xa1\xaa'
ghello = 'Gr\xfc\xdf Gott!'
h.append(jhello, j)
h.append(ghello, g)
# BAW: This used to -- and maybe should -- fold the two iso-8859-1
# chunks into a single encoded word. However it doesn't violate the
# standard to have them as two encoded chunks and maybe it's
# reasonable <wink> for each .append() call to result in a separate
# encoded word.
eq(h.encode(), """\
Hello World! =?iso-2022-jp?b?GyRCJU8lbSE8JW8hPCVrJUkhKhsoQg==?=
=?iso-8859-1?q?Gr=FC=DF?= =?iso-8859-1?q?_Gott!?=""")
eq(decode_header(h.encode()),
[('Hello World!', None),
('\x1b$B%O%m!<%o!<%k%I!*\x1b(B', 'iso-2022-jp'),
('Gr\xfc\xdf Gott!', 'iso-8859-1')])
long = 'test-ja \xa4\xd8\xc5\xea\xb9\xc6\xa4\xb5\xa4\xec\xa4\xbf\xa5\xe1\xa1\xbc\xa5\xeb\xa4\xcf\xbb\xca\xb2\xf1\xbc\xd4\xa4\xce\xbe\xb5\xc7\xa7\xa4\xf2\xc2\xd4\xa4\xc3\xa4\xc6\xa4\xa4\xa4\xde\xa4\xb9'
h = Header(long, j, header_name="Subject")
# test a very long header
enc = h.encode()
# TK: splitting point may differ by codec design and/or Header encoding
eq(enc , """\
=?iso-2022-jp?b?dGVzdC1qYSAbJEIkWEVqOUYkNSRsJD8lYSE8JWskTztKGyhC?=
=?iso-2022-jp?b?GyRCMnE8VCROPjVHJyRyQlQkQyRGJCQkXiQ5GyhC?=""")
# TK: full decode comparison
eq(h.__unicode__().encode('euc-jp'), long)
def suite():
suite = unittest.TestSuite()
suite.addTest(unittest.makeSuite(TestEmailAsianCodecs))
return suite
def test_main():
run_unittest(TestEmailAsianCodecs)
if __name__ == '__main__':
unittest.main(defaultTest='suite')