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>

diff --git a/Lib/email/_header_value_parser.py b/Lib/email/_header_value_parser.py
index 0cf23fc9f656b1bd6c47b64e153533effff654e2..7755e629500a8fb793a10bafb06fea8065305e73 100644 (file)
--- 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 dd1af9954c61dac4d07455af7253801bb63d5061..39ed4ee2a381590dae149392873e1b0ac2286f79 100644 (file)
--- 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("<simplelocal@>")
+
+    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 (file)
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).