gh-75171: Fix parsing invalid email address headers starting or ending with a dot...

Co-authored-by: Tim Bell <timothybell@gmail.com>
Co-authored-by: Serhiy Storchaka <storchaka@gmail.com>

diff --git a/Lib/email/_header_value_parser.py b/Lib/email/_header_value_parser.py
index e4a342d446f6a38418a7247d65faa7af96f88da6..0cf23fc9f656b1bd6c47b64e153533effff654e2 100644 (file)
--- a/Lib/email/_header_value_parser.py
+++ b/Lib/email/_header_value_parser.py
@@ -566,12 +566,14 @@ class DisplayName(Phrase):
         if res[0].token_type == 'cfws':
             res.pop(0)
         else:
-            if res[0][0].token_type == 'cfws':
+            if (isinstance(res[0], TokenList) and
+                    res[0][0].token_type == 'cfws'):
                 res[0] = TokenList(res[0][1:])
         if res[-1].token_type == 'cfws':
             res.pop()
         else:
-            if res[-1][-1].token_type == 'cfws':
+            if (isinstance(res[-1], TokenList) and
+                    res[-1][-1].token_type == 'cfws'):
                 res[-1] = TokenList(res[-1][:-1])
         return res.value
 
@@ -586,9 +588,13 @@ class DisplayName(Phrase):
                     quote = True
         if len(self) != 0 and quote:
             pre = post = ''
-            if self[0].token_type=='cfws' or self[0][0].token_type=='cfws':
+            if (self[0].token_type == 'cfws' or
+                isinstance(self[0], TokenList) and
+                self[0][0].token_type == 'cfws'):
                 pre = ' '
-            if self[-1].token_type=='cfws' or self[-1][-1].token_type=='cfws':
+            if (self[-1].token_type == 'cfws' or
+                isinstance(self[-1], TokenList) and
+                self[-1][-1].token_type == 'cfws'):
                 post = ' '
             return pre+quote_string(self.display_name)+post
         else:
@@ -1772,7 +1778,10 @@ def get_name_addr(value):
             raise errors.HeaderParseError(
                 "expected name-addr but found '{}'".format(token))
         if leader is not None:
-            token[0][:0] = [leader]
+            if isinstance(token[0], TokenList):
+                token[0][:0] = [leader]
+            else:
+                token[:0] = [leader]
             leader = None
         name_addr.append(token)
     token, value = get_angle_addr(value)

diff --git a/Lib/test/test_email/test__header_value_parser.py b/Lib/test/test_email/test__header_value_parser.py
index f7e80749c456f8fdc92ce56aa2645c54e1b680e7..dd1af9954c61dac4d07455af7253801bb63d5061 100644 (file)
--- a/Lib/test/test_email/test__header_value_parser.py
+++ b/Lib/test/test_email/test__header_value_parser.py
@@ -1805,6 +1805,32 @@ class TestParser(TestParserMixin, TestEmailBase):
         self.assertIsNone(name_addr.route)
         self.assertEqual(name_addr.addr_spec, 'dinsdale@example.com')
 
+    def test_get_name_addr_ending_with_dot_without_space(self):
+        name_addr = self._test_get_x(parser.get_name_addr,
+            'John X.<jxd@example.com>',
+            'John X.<jxd@example.com>',
+            '"John X."<jxd@example.com>',
+            [errors.ObsoleteHeaderDefect],
+            '')
+        self.assertEqual(name_addr.display_name, 'John X.')
+        self.assertEqual(name_addr.local_part, 'jxd')
+        self.assertEqual(name_addr.domain, 'example.com')
+        self.assertIsNone(name_addr.route)
+        self.assertEqual(name_addr.addr_spec, 'jxd@example.com')
+
+    def test_get_name_addr_starting_with_dot(self):
+        name_addr = self._test_get_x(parser.get_name_addr,
+            '. Doe <jxd@example.com>',
+            '. Doe <jxd@example.com>',
+            '". Doe" <jxd@example.com>',
+            [errors.InvalidHeaderDefect, errors.ObsoleteHeaderDefect],
+            '')
+        self.assertEqual(name_addr.display_name, '. Doe')
+        self.assertEqual(name_addr.local_part, 'jxd')
+        self.assertEqual(name_addr.domain, 'example.com')
+        self.assertIsNone(name_addr.route)
+        self.assertEqual(name_addr.addr_spec, 'jxd@example.com')
+
     def test_get_name_addr_with_route(self):
         name_addr = self._test_get_x(parser.get_name_addr,
             '"Roy.A.Bear" <@two.example.com: dinsdale@example.com>',

diff --git a/Lib/test/test_email/test_headerregistry.py b/Lib/test/test_email/test_headerregistry.py
index 25347ef13c21475ae9293902946f6b334ccd5776..bb7ca8dfd8c52cc44fab74b9c59b00985d44906d 100644 (file)
--- a/Lib/test/test_email/test_headerregistry.py
+++ b/Lib/test/test_email/test_headerregistry.py
@@ -1237,6 +1237,26 @@ class TestAddressHeader(TestHeaderBase):
             'example.com',
             None),
 
+        'name_ending_with_dot_without_space':
+            ('John X.<jxd@example.com>',
+             [errors.ObsoleteHeaderDefect],
+             '"John X." <jxd@example.com>',
+             'John X.',
+             'jxd@example.com',
+             'jxd',
+             'example.com',
+             None),
+
+        'name_starting_with_dot':
+            ('. Doe <jxd@example.com>',
+             [errors.InvalidHeaderDefect, errors.ObsoleteHeaderDefect],
+             '". Doe" <jxd@example.com>',
+             '. Doe',
+             'jxd@example.com',
+             'jxd',
+             'example.com',
+             None),
+
         }
 
         # XXX: Need many more examples, and in particular some with names in

diff --git a/Misc/NEWS.d/next/Library/2019-08-29-20-26-08.bpo-30988.b-_h5O.rst b/Misc/NEWS.d/next/Library/2019-08-29-20-26-08.bpo-30988.b-_h5O.rst
new file mode 100644 (file)
index 0000000..c776c73
--- /dev/null
+++ b/Misc/NEWS.d/next/Library/2019-08-29-20-26-08.bpo-30988.b-_h5O.rst
@@ -0,0 +1 @@
+Fix parsing of emails with invalid address headers having a leading or trailing dot. Patch by tsufeki.