Python code coverage for Lib/email/test/test_email_codecs.py

#	count	content
1	n/a	# Copyright (C) 2002-2006 Python Software Foundation
2	n/a	# Contact: email-sig@python.org
3	n/a	# email package unit tests for (optional) Asian codecs
4	n/a
5	n/a	import unittest
6	n/a	from test.support import run_unittest
7	n/a
8	n/a	from email.test.test_email import TestEmailBase
9	n/a	from email.charset import Charset
10	n/a	from email.header import Header, decode_header
11	n/a	from email.message import Message
12	n/a
13	n/a	# We're compatible with Python 2.3, but it doesn't have the built-in Asian
14	n/a	# codecs, so we have to skip all these tests.
15	n/a	try:
16	n/a	str('foo', 'euc-jp')
17	n/a	except LookupError:
18	n/a	raise unittest.SkipTest
19	n/a
20	n/a
21	n/a
22	n/a	class TestEmailAsianCodecs(TestEmailBase):
23	n/a	def test_japanese_codecs(self):
24	n/a	eq = self.ndiffAssertEqual
25	n/a	j = Charset("euc-jp")
26	n/a	g = Charset("iso-8859-1")
27	n/a	h = Header("Hello World!")
28	n/a	jhello = '\xa5\xcf\xa5\xed\xa1\xbc\xa5\xef\xa1\xbc\xa5\xeb\xa5\xc9\xa1\xaa'
29	n/a	ghello = 'Gr\xfc\xdf Gott!'
30	n/a	h.append(jhello, j)
31	n/a	h.append(ghello, g)
32	n/a	# BAW: This used to -- and maybe should -- fold the two iso-8859-1
33	n/a	# chunks into a single encoded word. However it doesn't violate the
34	n/a	# standard to have them as two encoded chunks and maybe it's
35	n/a	# reasonable <wink> for each .append() call to result in a separate
36	n/a	# encoded word.
37	n/a	eq(h.encode(), """\
38	n/a	Hello World! =?iso-2022-jp?b?GyRCJU8lbSE8JW8hPCVrJUkhKhsoQg==?=
39	n/a	=?iso-8859-1?q?Gr=FC=DF?= =?iso-8859-1?q?_Gott!?=""")
40	n/a	eq(decode_header(h.encode()),
41	n/a	[('Hello World!', None),
42	n/a	('\x1b$B%O%m!<%o!<%k%I!*\x1b(B', 'iso-2022-jp'),
43	n/a	('Gr\xfc\xdf Gott!', 'iso-8859-1')])
44	n/a	int = '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'
45	n/a	h = Header(int, j, header_name="Subject")
46	n/a	# test a very long header
47	n/a	enc = h.encode()
48	n/a	# TK: splitting point may differ by codec design and/or Header encoding
49	n/a	eq(enc , """\
50	n/a	=?iso-2022-jp?b?dGVzdC1qYSAbJEIkWEVqOUYkNSRsJD8lYSE8JWskTztKGyhC?=
51	n/a	=?iso-2022-jp?b?GyRCMnE8VCROPjVHJyRyQlQkQyRGJCQkXiQ5GyhC?=""")
52	n/a	# TK: full decode comparison
53	n/a	eq(h.__unicode__().encode('euc-jp'), int)
54	n/a
55	n/a	def test_payload_encoding(self):
56	n/a	jhello = '\xa5\xcf\xa5\xed\xa1\xbc\xa5\xef\xa1\xbc\xa5\xeb\xa5\xc9\xa1\xaa'
57	n/a	jcode = 'euc-jp'
58	n/a	msg = Message()
59	n/a	msg.set_payload(jhello, jcode)
60	n/a	ustr = str(msg.get_payload(), msg.get_content_charset())
61	n/a	self.assertEqual(jhello, ustr.encode(jcode))
62	n/a
63	n/a
64	n/a
65	n/a	def suite():
66	n/a	suite = unittest.TestSuite()
67	n/a	suite.addTest(unittest.makeSuite(TestEmailAsianCodecs))
68	n/a	return suite
69	n/a
70	n/a
71	n/a	def test_main():
72	n/a	run_unittest(TestEmailAsianCodecs)
73	n/a
74	n/a
75	n/a
76	n/a	if __name__ == '__main__':
77	n/a	unittest.main(defaultTest='suite')