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