https://github.com/python/cpython/commit/9148b77e0af91cdacaa7fe3dfac09635c3fe9a74 commit: 9148b77e0af91cdacaa7fe3dfac09635c3fe9a74 branch: 3.12 author: Miss Islington (bot) <[email protected]> committer: serhiy-storchaka <[email protected]> date: 2024-02-17T15:00:39+02:00 summary:
[3.12] gh-100884: email/_header_value_parser: don't encode list separators (GH-100885) (GH-115592) ListSeparator should not be encoded. This could happen when a long line pushes its separator to the next line, which would have been encoded. (cherry picked from commit 09fab93c3d857496c0bd162797fab816c311ee48) Co-authored-by: Thomas Weißschuh <[email protected]> files: A Misc/NEWS.d/next/Library/2023-01-09-14-08-02.gh-issue-100884.DcmdLl.rst M Lib/email/_header_value_parser.py M Lib/test/test_email/test__header_value_parser.py diff --git a/Lib/email/_header_value_parser.py b/Lib/email/_header_value_parser.py index 5b653f66c18554..e4a342d446f6a3 100644 --- a/Lib/email/_header_value_parser.py +++ b/Lib/email/_header_value_parser.py @@ -949,6 +949,7 @@ class _InvalidEwError(errors.HeaderParseError): # up other parse trees. Maybe should have tests for that, too. DOT = ValueTerminal('.', 'dot') ListSeparator = ValueTerminal(',', 'list-separator') +ListSeparator.as_ew_allowed = False RouteComponentMarker = ValueTerminal('@', 'route-component-marker') # @@ -2022,7 +2023,7 @@ def get_address_list(value): address_list.defects.append(errors.InvalidHeaderDefect( "invalid address in address-list")) if value: # Must be a , at this point. - address_list.append(ValueTerminal(',', 'list-separator')) + address_list.append(ListSeparator) value = value[1:] return address_list, value diff --git a/Lib/test/test_email/test__header_value_parser.py b/Lib/test/test_email/test__header_value_parser.py index bdb0e55f21069f..f7e80749c456f8 100644 --- a/Lib/test/test_email/test__header_value_parser.py +++ b/Lib/test/test_email/test__header_value_parser.py @@ -2985,6 +2985,11 @@ def test_address_list_with_unicode_names_in_quotes(self): '=?utf-8?q?H=C3=BCbsch?= Kaktus <[email protected]>,\n' ' =?utf-8?q?bei=C3=9Ft_bei=C3=9Ft?= <[email protected]>\n') + def test_address_list_with_list_separator_after_fold(self): + to = '0123456789' * 8 + '@foo, ä <foo@bar>' + self._test(parser.get_address_list(to)[0], + '0123456789' * 8 + '@foo,\n =?utf-8?q?=C3=A4?= <foo@bar>\n') + # XXX Need tests with comments on various sides of a unicode token, # and with unicode tokens in the comments. Spaces inside the quotes # currently don't do the right thing. diff --git a/Misc/NEWS.d/next/Library/2023-01-09-14-08-02.gh-issue-100884.DcmdLl.rst b/Misc/NEWS.d/next/Library/2023-01-09-14-08-02.gh-issue-100884.DcmdLl.rst new file mode 100644 index 00000000000000..2a388178810835 --- /dev/null +++ b/Misc/NEWS.d/next/Library/2023-01-09-14-08-02.gh-issue-100884.DcmdLl.rst @@ -0,0 +1,2 @@ +email: fix misfolding of comma in address-lists over multiple lines in +combination with unicode encoding. _______________________________________________ Python-checkins mailing list -- [email protected] To unsubscribe send an email to [email protected] https://mail.python.org/mailman3/lists/python-checkins.python.org/ Member address: [email protected]
