diff options
| -rw-r--r-- | Lib/email/_header_value_parser.py | 15 | ||||
| -rw-r--r-- | Lib/test/test_email/test__header_value_parser.py | 12 | ||||
| -rw-r--r-- | Misc/NEWS.d/next/Library/2024-05-16-17-31-46.gh-issue-118643.hAWH4C.rst | 2 |
3 files changed, 24 insertions, 5 deletions
diff --git a/Lib/email/_header_value_parser.py b/Lib/email/_header_value_parser.py index 6148801..ab3c303 100644 --- a/Lib/email/_header_value_parser.py +++ b/Lib/email/_header_value_parser.py @@ -956,6 +956,7 @@ class _InvalidEwError(errors.HeaderParseError): DOT = ValueTerminal('.', 'dot') ListSeparator = ValueTerminal(',', 'list-separator') ListSeparator.as_ew_allowed = False +ListSeparator.syntactic_break = False RouteComponentMarker = ValueTerminal('@', 'route-component-marker') # @@ -2844,7 +2845,9 @@ def _refold_parse_tree(parse_tree, *, policy): if not hasattr(part, 'encode'): # It's not a Terminal, do each piece individually. parts = list(part) + parts - else: + want_encoding = False + continue + elif part.as_ew_allowed: # It's a terminal, wrap it as an encoded word, possibly # combining it with previously encoded words if allowed. if (last_ew is not None and @@ -2858,8 +2861,14 @@ def _refold_parse_tree(parse_tree, *, policy): # so clear it now. leading_whitespace = '' last_charset = charset - want_encoding = False - continue + want_encoding = False + continue + else: + # It's a terminal which should be kept non-encoded + # (e.g. a ListSeparator). + last_ew = None + want_encoding = False + # fall through if len(tstr) <= maxlen - len(lines[-1]): lines[-1] += tstr diff --git a/Lib/test/test_email/test__header_value_parser.py b/Lib/test/test_email/test__header_value_parser.py index 56a1e3a..5413319 100644 --- a/Lib/test/test_email/test__header_value_parser.py +++ b/Lib/test/test_email/test__header_value_parser.py @@ -3077,9 +3077,17 @@ class TestFolding(TestEmailBase): ' =?utf-8?q?bei=C3=9Ft_bei=C3=9Ft?= <biter@example.com>\n') def test_address_list_with_list_separator_after_fold(self): - to = '0123456789' * 8 + '@foo, ä <foo@bar>' + a = 'x' * 66 + '@example.com' + to = f'{a}, "Hübsch Kaktus" <beautiful@example.com>' self._test(parser.get_address_list(to)[0], - '0123456789' * 8 + '@foo,\n =?utf-8?q?=C3=A4?= <foo@bar>\n') + f'{a},\n =?utf-8?q?H=C3=BCbsch?= Kaktus <beautiful@example.com>\n') + + a = '.' * 79 + to = f'"{a}" <xyz@example.com>, "Hübsch Kaktus" <beautiful@example.com>' + self._test(parser.get_address_list(to)[0], + f'{a}\n' + ' <xyz@example.com>, =?utf-8?q?H=C3=BCbsch?= Kaktus ' + '<beautiful@example.com>\n') # XXX Need tests with comments on various sides of a unicode token, # and with unicode tokens in the comments. Spaces inside the quotes diff --git a/Misc/NEWS.d/next/Library/2024-05-16-17-31-46.gh-issue-118643.hAWH4C.rst b/Misc/NEWS.d/next/Library/2024-05-16-17-31-46.gh-issue-118643.hAWH4C.rst new file mode 100644 index 0000000..e86a49a --- /dev/null +++ b/Misc/NEWS.d/next/Library/2024-05-16-17-31-46.gh-issue-118643.hAWH4C.rst @@ -0,0 +1,2 @@ +Fix an AttributeError in the :mod:`email` module when re-fold a long address +list. Also fix more cases of incorrect encoding of the address separator in the address list. |