bpo-27240 Rewrite the email header folding algorithm. (#3488)
The original algorithm tried to delegate the folding to the tokens so
that those tokens whose folding rules differed could specify the
differences. However, this resulted in a lot of duplicated code because
most of the rules were the same.
The new algorithm moves all folding logic into a set of functions
external to the token classes, but puts the information about which
tokens can be folded in which ways on the tokens...with the exception of
mime-parameters, which are a special case (which was not even
implemented in the old folder).
This algorithm can still probably be improved and hopefully simplified
somewhat.
Note that some of the test expectations are changed. I believe the
changes are toward more desirable and consistent behavior: in general
when (re) folding a line the canonical version of the tokens is
generated, rather than preserving errors or extra whitespace.
diff --git a/Lib/test/test_email/test__header_value_parser.py b/Lib/test/test_email/test__header_value_parser.py
index e0ec87d..1667617 100644
--- a/Lib/test/test_email/test__header_value_parser.py
+++ b/Lib/test/test_email/test__header_value_parser.py
@@ -14,18 +14,7 @@
self.assertEqual(x, ' \t')
self.assertEqual(str(x), '')
self.assertEqual(x.value, '')
- self.assertEqual(x.encoded, ' \t')
-
- # UnstructuredTokenList
-
- def test_undecodable_bytes_error_preserved(self):
- badstr = b"le pouf c\xaflebre".decode('ascii', 'surrogateescape')
- unst = parser.get_unstructured(badstr)
- self.assertDefectsEqual(unst.all_defects, [errors.UndecodableBytesDefect])
- parts = list(unst.parts)
- self.assertDefectsEqual(parts[0].all_defects, [])
- self.assertDefectsEqual(parts[1].all_defects, [])
- self.assertDefectsEqual(parts[2].all_defects, [errors.UndecodableBytesDefect])
+ self.assertEqual(x.token_type, 'fws')
class TestParserMixin:
@@ -139,7 +128,6 @@
'first second',
[],
'')
- self.assertEqual(ew.encoded, '=?us-ascii*jive?q?first_second?=')
self.assertEqual(ew.charset, 'us-ascii')
self.assertEqual(ew.lang, 'jive')
@@ -150,7 +138,6 @@
'first second',
[],
'')
- self.assertEqual(ew.encoded, '=?us-ascii?q?first_second?=')
self.assertEqual(ew.charset, 'us-ascii')
self.assertEqual(ew.lang, '')
@@ -2700,28 +2687,37 @@
# and with unicode tokens in the comments. Spaces inside the quotes
# currently don't do the right thing.
- def test_initial_whitespace_splitting(self):
+ def test_split_at_whitespace_after_header_before_long_token(self):
body = parser.get_unstructured(' ' + 'x'*77)
header = parser.Header([
parser.HeaderLabel([parser.ValueTerminal('test:', 'atext')]),
parser.CFWSList([parser.WhiteSpaceTerminal(' ', 'fws')]), body])
self._test(header, 'test: \n ' + 'x'*77 + '\n')
- def test_whitespace_splitting(self):
+ def test_split_at_whitespace_before_long_token(self):
self._test(parser.get_unstructured('xxx ' + 'y'*77),
'xxx \n ' + 'y'*77 + '\n')
+ def test_overlong_encodeable_is_wrapped(self):
+ first_token_with_whitespace = 'xxx '
+ chrome_leader = '=?utf-8?q?'
+ len_chrome = len(chrome_leader) + 2
+ len_non_y = len_chrome + len(first_token_with_whitespace)
+ self._test(parser.get_unstructured(first_token_with_whitespace +
+ 'y'*80),
+ first_token_with_whitespace + chrome_leader +
+ 'y'*(78-len_non_y) + '?=\n' +
+ ' ' + chrome_leader + 'y'*(80-(78-len_non_y)) + '?=\n')
+
def test_long_filename_attachment(self):
- folded = self.policy.fold('Content-Disposition', 'attachment; filename="TEST_TEST_TEST_TEST_TEST_TEST_TEST_TEST_TEST_TEST_TEST_TEST_TES.txt"')
- self.assertEqual(
- 'Content-Disposition: attachment;\n filename="TEST_TEST_TEST_TEST_TEST_TEST_TEST_TEST_TEST_TEST_TEST_TEST_TES.txt"\n',
- folded
- )
- folded = self.policy.fold('Content-Disposition', 'attachment; filename="TEST_TEST_TEST_TEST_TEST_TEST_TEST_TEST_TEST_TEST_TEST_TEST_TEST_TEST_T.txt"')
- self.assertEqual(
- 'Content-Disposition: attachment;\n filename="TEST_TEST_TEST_TEST_TEST_TEST_TEST_TEST_TEST_TEST_TEST_TEST_TEST_TEST_T.txt"\n',
- folded
- )
+ self._test(parser.parse_content_disposition_header(
+ 'attachment; filename="TEST_TEST_TEST_TEST'
+ '_TEST_TEST_TEST_TEST_TEST_TEST_TEST_TEST_TES.txt"'),
+ "attachment;\n"
+ " filename*0*=us-ascii''TEST_TEST_TEST_TEST_TEST_TEST"
+ "_TEST_TEST_TEST_TEST_TEST;\n"
+ " filename*1*=_TEST_TES.txt\n",
+ )
if __name__ == '__main__':
unittest.main()