1 # Copyright (C) 2002-2006 Python Software Foundation 2 # Contact: email-sig (at] python.org 3 # email package unit tests for (optional) Asian codecs 4 5 import unittest 6 from test.test_support import run_unittest 7 8 from email.test.test_email import TestEmailBase 9 from email.charset import Charset 10 from email.header import Header, decode_header 11 from 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. 15 try: 16 unicode('foo', 'euc-jp') 17 except LookupError: 18 raise unittest.SkipTest 19 20 21 23 class TestEmailAsianCodecs(TestEmailBase): 24 def test_japanese_codecs(self): 25 eq = self.ndiffAssertEqual 26 j = Charset("euc-jp") 27 g = Charset("iso-8859-1") 28 h = Header("Hello World!") 29 jhello = '\xa5\xcf\xa5\xed\xa1\xbc\xa5\xef\xa1\xbc\xa5\xeb\xa5\xc9\xa1\xaa' 30 ghello = 'Gr\xfc\xdf Gott!' 31 h.append(jhello, j) 32 h.append(ghello, g) 33 # BAW: This used to -- and maybe should -- fold the two iso-8859-1 34 # chunks into a single encoded word. However it doesn't violate the 35 # standard to have them as two encoded chunks and maybe it's 36 # reasonable <wink> for each .append() call to result in a separate 37 # encoded word. 38 eq(h.encode(), """\ 39 Hello World! =?iso-2022-jp?b?GyRCJU8lbSE8JW8hPCVrJUkhKhsoQg==?= 40 =?iso-8859-1?q?Gr=FC=DF?= =?iso-8859-1?q?_Gott!?=""") 41 eq(decode_header(h.encode()), 42 [('Hello World!', None), 43 ('\x1b$B%O%m!<%o!<%k%I!*\x1b(B', 'iso-2022-jp'), 44 ('Gr\xfc\xdf Gott!', 'iso-8859-1')]) 45 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' 46 h = Header(long, j, header_name="Subject") 47 # test a very long header 48 enc = h.encode() 49 # TK: splitting point may differ by codec design and/or Header encoding 50 eq(enc , """\ 51 =?iso-2022-jp?b?dGVzdC1qYSAbJEIkWEVqOUYkNSRsJD8lYSE8JWskTztKGyhC?= 52 =?iso-2022-jp?b?GyRCMnE8VCROPjVHJyRyQlQkQyRGJCQkXiQ5GyhC?=""") 53 # TK: full decode comparison 54 eq(h.__unicode__().encode('euc-jp'), long) 55 56 def test_payload_encoding(self): 57 jhello = '\xa5\xcf\xa5\xed\xa1\xbc\xa5\xef\xa1\xbc\xa5\xeb\xa5\xc9\xa1\xaa' 58 jcode = 'euc-jp' 59 msg = Message() 60 msg.set_payload(jhello, jcode) 61 ustr = unicode(msg.get_payload(), msg.get_content_charset()) 62 self.assertEqual(jhello, ustr.encode(jcode)) 63 64 65 67 def suite(): 68 suite = unittest.TestSuite() 69 suite.addTest(unittest.makeSuite(TestEmailAsianCodecs)) 70 return suite 71 72 73 def test_main(): 74 run_unittest(TestEmailAsianCodecs) 75 76 77 79 if __name__ == '__main__': 80 unittest.main(defaultTest='suite') 81
