parser: Don't crash when From: is list email but has weird mangle format

get_original_sender() tries to demangle DMARC-mangled From headers, in
the case where the email's From address is the list address. It knows how
to handle Google Groups and Mailman style mangling, where the original
submitter's name will be turned into e.g. "Andrew Donnellan via
linuxppc-dev".

If an email has the From header set to the list address but has a name that
doesn't include " via ", we'll throw an exception because stripped_name
hasn't been set. Sometimes this is because the list name is seemingly
empty, resulting in a mangled name like "Andrew Donnellan via"
without the space after "via" that we detect. Handle this as well as we can
instead, and add a test.

Fixes: 8279a84 ("parser: Unmangle From: headers that have been mangled for DMARC purposes")
Reported-by: Jeremy Kerr <[email protected]>
Signed-off-by: Andrew Donnellan <[email protected]>
Reviewed-by: Stephen Finucane <[email protected]>

Author: ajdlinux

patchwork/parser.py

@@ -373,6 +373,13 @@ def get_original_sender(mail, name, email):
         # Mailman uses the format "<name> via <list>"
         # Google Groups uses "'<name>' via <list>"
         stripped_name = name[:name.rfind(' via ')].strip().strip("'")
+    elif name.endswith(' via'):
+        # Sometimes this seems to happen (perhaps if Mailman isn't set up with
+        # any list name)
+        stripped_name = name[:name.rfind(' via')].strip().strip("'")
+    else:
+        # We've hit a format that we don't expect
+        stripped_name = None
 
     original_from = clean_header(mail.get('X-Original-From', ''))
     if original_from:

patchwork/tests/test_parser.py

@@ -366,6 +366,29 @@ def test_google_dmarc_munging(self):
         self.assertEqual(person_b._state.adding, False)
         self.assertEqual(person_b.id, person_a.id)
 
+    def test_weird_dmarc_munging(self):
+        project = create_project()
+        real_sender = 'Existing Sender <[email protected]>'
+        munged_sender1 = "'Existing Sender' via <{}>".format(project.listemail)
+        munged_sender2 = "'Existing Sender' <{}>".format(project.listemail)
+
+        # Unmunged author
+        mail = self._create_email(real_sender)
+        person_a = get_or_create_author(mail, project)
+        person_a.save()
+
+        # Munged with no list name
+        mail = self._create_email(munged_sender1, None, None, real_sender)
+        person_b = get_or_create_author(mail, project)
+        self.assertEqual(person_b._state.adding, False)
+        self.assertEqual(person_b.id, person_a.id)
+
+        # Munged with no 'via'
+        mail = self._create_email(munged_sender2, None, None, real_sender)
+        person_b = get_or_create_author(mail, project)
+        self.assertEqual(person_b._state.adding, False)
+        self.assertEqual(person_b.id, person_a.id)
+
 
 class SeriesCorrelationTest(TestCase):
     """Validate correct behavior of find_series."""