/Lib/email/test/test_email_codecs.py

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