"Port" the fix for issue 1974 from the trunk (2.7). Because Python 3.x does...

"Port" the fix for issue 1974 from the trunk (2.7).  Because Python 3.x does things much better, less changes are necessary.

This also shoves test_email_codecs_rename.py onto test_email_codecs.py even though the test needs to be ported to Python 3.

Doc/library/email.header.rst

@@ -72,7 +72,7 @@ Here is the :class:`Header` class description:
 
    Optional *continuation_ws* must be :rfc:`2822`\ -compliant folding whitespace,
    and is usually either a space or a hard tab character. This character will be
-   prepended to continuation lines.
+   prepended to continuation lines. *continuation_ws* defaults to a single space character (" ").
 
    Optional *errors* is passed straight through to the :meth:`append` method.
 

Lib/email/generator.py

@@ -138,7 +138,7 @@ class Generator:
             else:
                 # Header's got lots of smarts, so use it.
                 header = Header(v, maxlinelen=self._maxheaderlen,
-                                header_name=h, continuation_ws='\t')
+                                header_name=h)
                 print(header.encode(), file=self._fp)
         # A blank line always separates headers from body
         print(file=self._fp)

Lib/email/test/test_email.py

@@ -769,7 +769,7 @@ Reply-To: =?utf-8?q?Britische_Regierung_gibt_gr=C3=BCnes_Licht_f=C3=BCr_Offs?=
         msg['To'] = to
         eq(msg.as_string(maxheaderlen=78), '''\
 To: "Someone Test #A" <someone@eecs.umich.edu>,<someone@eecs.umich.edu>,
-\t"Someone Test #B" <someone@umich.edu>,
+ "Someone Test #B" <someone@umich.edu>,
  "Someone Test #C" <someone@eecs.umich.edu>,
  "Someone Test #D" <someone@eecs.umich.edu>
 
@@ -852,7 +852,7 @@ iVBORw0KGgoAAAANSUhEUgAAADAAAAAwBAMAAAClLOS0AAAAGFBMVEUAAAAkHiJeRUIcGBi9
         # snug against the field name.
         eq(msg.as_string(maxheaderlen=78), """\
 Face-1:\x20
-\tiVBORw0KGgoAAAANSUhEUgAAADAAAAAwBAMAAAClLOS0AAAAGFBMVEUAAAAkHiJeRUIcGBi9
+ iVBORw0KGgoAAAANSUhEUgAAADAAAAAwBAMAAAClLOS0AAAAGFBMVEUAAAAkHiJeRUIcGBi9
  locQDQ4zJykFBAXJfWDjAAACYUlEQVR4nF2TQY/jIAyFc6lydlG5x8Nyp1Y69wj1PN2I5gzp
 Face-2:\x20
  iVBORw0KGgoAAAANSUhEUgAAADAAAAAwBAMAAAClLOS0AAAAGFBMVEUAAAAkHiJeRUIcGBi9

Lib/email/test/test_email_codecs.py

@@ -6,9 +6,9 @@ import unittest
 from test.support import run_unittest
 
 from email.test.test_email import TestEmailBase
-from email.Charset import Charset
-from email.Header import Header, decode_header
-from email.Message import Message
+from email.charset import Charset
+from email.header import Header, decode_header
+from email.message import Message
 
 # We're compatible with Python 2.3, but it doesn't have the built-in Asian
 # codecs, so we have to skip all these tests.

Lib/email/test/test_email_codecs_renamed.py

-# Copyright (C) 2002-2006 Python Software Foundation
-# Contact: email-sig@python.org
-# email package unit tests for (optional) Asian codecs
-
-import unittest
-from test.support import run_unittest
-
-from email.test.test_email import TestEmailBase
-from email.charset import Charset
-from email.header import Header, decode_header
-from email.message import Message
-
-# We're compatible with Python 2.3, but it doesn't have the built-in Asian
-# codecs, so we have to skip all these tests.
-try:
-    str('foo', 'euc-jp')
-except LookupError:
-    raise unittest.SkipTest
-
-
-
-class TestEmailAsianCodecs(TestEmailBase):
-    def test_japanese_codecs(self):
-        eq = self.ndiffAssertEqual
-        j = Charset("euc-jp")
-        g = Charset("iso-8859-1")
-        h = Header("Hello World!")
-        jhello = '\xa5\xcf\xa5\xed\xa1\xbc\xa5\xef\xa1\xbc\xa5\xeb\xa5\xc9\xa1\xaa'
-        ghello = 'Gr\xfc\xdf Gott!'
-        h.append(jhello, j)
-        h.append(ghello, g)
-        # BAW: This used to -- and maybe should -- fold the two iso-8859-1
-        # chunks into a single encoded word.  However it doesn't violate the
-        # standard to have them as two encoded chunks and maybe it's
-        # reasonable <wink> for each .append() call to result in a separate
-        # encoded word.
-        eq(h.encode(), """\
-Hello World! =?iso-2022-jp?b?GyRCJU8lbSE8JW8hPCVrJUkhKhsoQg==?=
- =?iso-8859-1?q?Gr=FC=DF?= =?iso-8859-1?q?_Gott!?=""")
-        eq(decode_header(h.encode()),
-           [('Hello World!', None),
-            ('\x1b$B%O%m!<%o!<%k%I!*\x1b(B', 'iso-2022-jp'),
-            ('Gr\xfc\xdf Gott!', 'iso-8859-1')])
-        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'
-        h = Header(int, j, header_name="Subject")
-        # test a very long header
-        enc = h.encode()
-        # TK: splitting point may differ by codec design and/or Header encoding
-        eq(enc , """\
-=?iso-2022-jp?b?dGVzdC1qYSAbJEIkWEVqOUYkNSRsJD8lYSE8JWskTztKGyhC?=
- =?iso-2022-jp?b?GyRCMnE8VCROPjVHJyRyQlQkQyRGJCQkXiQ5GyhC?=""")
-        # TK: full decode comparison
-        eq(h.__unicode__().encode('euc-jp'), int)
-
-    def test_payload_encoding(self):
-        jhello = '\xa5\xcf\xa5\xed\xa1\xbc\xa5\xef\xa1\xbc\xa5\xeb\xa5\xc9\xa1\xaa'
-        jcode  = 'euc-jp'
-        msg = Message()
-        msg.set_payload(jhello, jcode)
-        ustr = str(msg.get_payload(), msg.get_content_charset())
-        self.assertEqual(jhello, ustr.encode(jcode))
-
-
-
-def suite():
-    suite = unittest.TestSuite()
-    suite.addTest(unittest.makeSuite(TestEmailAsianCodecs))
-    return suite
-
-
-def test_main():
-    run_unittest(TestEmailAsianCodecs)
-
-
-
-if __name__ == '__main__':
-    unittest.main(defaultTest='suite')