From f74e51229c83e3265f905dc15283bfe0ec1a659e Mon Sep 17 00:00:00 2001 From: Serhiy Storchaka Date: Wed, 17 Apr 2024 10:44:41 +0300 Subject: gh-86650: Fix IndexError when parse emails with invalid Message-ID (GH-117934) In particularly, one-off addresses generated by Microsoft Outlook: https://learn.microsoft.com/en-us/office/client-developer/outlook/mapi/one-off-addresses Co-authored-by: fsc-eriker <72394365+fsc-eriker@users.noreply.github.com> --- Lib/email/_header_value_parser.py | 5 +++++ Lib/test/test_email/test__header_value_parser.py | 25 ++++++++++++++++++++++ .../2024-04-16-18-34-11.gh-issue-86650.Zeydyg.rst | 2 ++ 3 files changed, 32 insertions(+) create mode 100644 Misc/NEWS.d/next/Library/2024-04-16-18-34-11.gh-issue-86650.Zeydyg.rst diff --git a/Lib/email/_header_value_parser.py b/Lib/email/_header_value_parser.py index 0cf23fc..7755e62 100644 --- a/Lib/email/_header_value_parser.py +++ b/Lib/email/_header_value_parser.py @@ -1520,13 +1520,18 @@ def get_obs_local_part(value): raise token, value = get_cfws(value) obs_local_part.append(token) + if not obs_local_part: + raise errors.HeaderParseError( + "expected obs-local-part but found '{}'".format(value)) if (obs_local_part[0].token_type == 'dot' or obs_local_part[0].token_type=='cfws' and + len(obs_local_part) > 1 and obs_local_part[1].token_type=='dot'): obs_local_part.defects.append(errors.InvalidHeaderDefect( "Invalid leading '.' in local part")) if (obs_local_part[-1].token_type == 'dot' or obs_local_part[-1].token_type=='cfws' and + len(obs_local_part) > 1 and obs_local_part[-2].token_type=='dot'): obs_local_part.defects.append(errors.InvalidHeaderDefect( "Invalid trailing '.' in local part")) diff --git a/Lib/test/test_email/test__header_value_parser.py b/Lib/test/test_email/test__header_value_parser.py index dd1af99..39ed4ee 100644 --- a/Lib/test/test_email/test__header_value_parser.py +++ b/Lib/test/test_email/test__header_value_parser.py @@ -2724,6 +2724,31 @@ class TestParser(TestParserMixin, TestEmailBase): ) self.assertEqual(msg_id.token_type, 'msg-id') + def test_get_msg_id_empty_id_left(self): + with self.assertRaises(errors.HeaderParseError): + parser.get_msg_id("<@domain>") + + def test_get_msg_id_empty_id_right(self): + with self.assertRaises(errors.HeaderParseError): + parser.get_msg_id("") + + def test_get_msg_id_with_brackets(self): + # Microsof Outlook generates non-standard one-off addresses: + # https://learn.microsoft.com/en-us/office/client-developer/outlook/mapi/one-off-addresses + with self.assertRaises(errors.HeaderParseError): + parser.get_msg_id("<[abrakadabra@microsoft.com]>") + + def test_get_msg_id_ws_only_local(self): + msg_id = self._test_get_x( + parser.get_msg_id, + "< @domain>", + "< @domain>", + "< @domain>", + [errors.ObsoleteHeaderDefect], + "" + ) + self.assertEqual(msg_id.token_type, 'msg-id') + @parameterize diff --git a/Misc/NEWS.d/next/Library/2024-04-16-18-34-11.gh-issue-86650.Zeydyg.rst b/Misc/NEWS.d/next/Library/2024-04-16-18-34-11.gh-issue-86650.Zeydyg.rst new file mode 100644 index 0000000..8a1626f --- /dev/null +++ b/Misc/NEWS.d/next/Library/2024-04-16-18-34-11.gh-issue-86650.Zeydyg.rst @@ -0,0 +1,2 @@ +Fix IndexError when parse some emails with invalid Message-ID (including +one-off addresses generated by Microsoft Outlook). -- cgit v0.12