Python code coverage for Lib/test/test_email/test_asian_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
7	n/a	from test.test_email import TestEmailBase
8	n/a	from email.charset import Charset
9	n/a	from email.header import Header, decode_header
10	n/a	from email.message import Message
11	n/a
12	n/a	# We're compatible with Python 2.3, but it doesn't have the built-in Asian
13	n/a	# codecs, so we have to skip all these tests.
14	n/a	try:
15	n/a	str(b'foo', 'euc-jp')
16	n/a	except LookupError:
17	n/a	raise unittest.SkipTest
18	n/a
19	n/a
20	n/a
21	n/a	class TestEmailAsianCodecs(TestEmailBase):
22	n/a	def test_japanese_codecs(self):
23	n/a	eq = self.ndiffAssertEqual
24	n/a	jcode = "euc-jp"
25	n/a	gcode = "iso-8859-1"
26	n/a	j = Charset(jcode)
27	n/a	g = Charset(gcode)
28	n/a	h = Header("Hello World!")
29	n/a	jhello = str(b'\xa5\xcf\xa5\xed\xa1\xbc\xa5\xef\xa1\xbc'
30	n/a	b'\xa5\xeb\xa5\xc9\xa1\xaa', jcode)
31	n/a	ghello = str(b'Gr\xfc\xdf Gott!', gcode)
32	n/a	h.append(jhello, j)
33	n/a	h.append(ghello, g)
34	n/a	# BAW: This used to -- and maybe should -- fold the two iso-8859-1
35	n/a	# chunks into a single encoded word. However it doesn't violate the
36	n/a	# standard to have them as two encoded chunks and maybe it's
37	n/a	# reasonable <wink> for each .append() call to result in a separate
38	n/a	# encoded word.
39	n/a	eq(h.encode(), """\
40	n/a	Hello World! =?iso-2022-jp?b?GyRCJU8lbSE8JW8hPCVrJUkhKhsoQg==?=
41	n/a	=?iso-8859-1?q?Gr=FC=DF_Gott!?=""")
42	n/a	eq(decode_header(h.encode()),
43	n/a	[(b'Hello World! ', None),
44	n/a	(b'\x1b$B%O%m!<%o!<%k%I!*\x1b(B', 'iso-2022-jp'),
45	n/a	(b'Gr\xfc\xdf Gott!', gcode)])
46	n/a	subject_bytes = (b'test-ja \xa4\xd8\xc5\xea\xb9\xc6\xa4\xb5'
47	n/a	b'\xa4\xec\xa4\xbf\xa5\xe1\xa1\xbc\xa5\xeb\xa4\xcf\xbb\xca\xb2'
48	n/a	b'\xf1\xbc\xd4\xa4\xce\xbe\xb5\xc7\xa7\xa4\xf2\xc2\xd4\xa4\xc3'
49	n/a	b'\xa4\xc6\xa4\xa4\xa4\xde\xa4\xb9')
50	n/a	subject = str(subject_bytes, jcode)
51	n/a	h = Header(subject, j, header_name="Subject")
52	n/a	# test a very long header
53	n/a	enc = h.encode()
54	n/a	# TK: splitting point may differ by codec design and/or Header encoding
55	n/a	eq(enc , """\
56	n/a	=?iso-2022-jp?b?dGVzdC1qYSAbJEIkWEVqOUYkNSRsJD8lYSE8JWskTztKGyhC?=
57	n/a	=?iso-2022-jp?b?GyRCMnE8VCROPjVHJyRyQlQkQyRGJCQkXiQ5GyhC?=""")
58	n/a	# TK: full decode comparison
59	n/a	eq(str(h).encode(jcode), subject_bytes)
60	n/a
61	n/a	def test_payload_encoding_utf8(self):
62	n/a	jhello = str(b'\xa5\xcf\xa5\xed\xa1\xbc\xa5\xef\xa1\xbc'
63	n/a	b'\xa5\xeb\xa5\xc9\xa1\xaa', 'euc-jp')
64	n/a	msg = Message()
65	n/a	msg.set_payload(jhello, 'utf-8')
66	n/a	ustr = msg.get_payload(decode=True).decode(msg.get_content_charset())
67	n/a	self.assertEqual(jhello, ustr)
68	n/a
69	n/a	def test_payload_encoding(self):
70	n/a	jcode = 'euc-jp'
71	n/a	jhello = str(b'\xa5\xcf\xa5\xed\xa1\xbc\xa5\xef\xa1\xbc'
72	n/a	b'\xa5\xeb\xa5\xc9\xa1\xaa', jcode)
73	n/a	msg = Message()
74	n/a	msg.set_payload(jhello, jcode)
75	n/a	ustr = msg.get_payload(decode=True).decode(msg.get_content_charset())
76	n/a	self.assertEqual(jhello, ustr)
77	n/a
78	n/a
79	n/a
80	n/a	if __name__ == '__main__':
81	n/a	unittest.main()