bpo-35805: Add parser for Message-ID email header. (GH-13397)

* bpo-35805: Add parser for Message-ID header.

This parser is based on the definition of Identification Fields from RFC 5322
Sec 3.6.4.

This should also prevent folding of Message-ID header using RFC 2047 encoded
words and hence fix bpo-35805.

* Prevent folding of non-ascii message-id headers.
* Add fold method to MsgID token to prevent folding.

2 files changed, 100 insertions, 0 deletions

diff --git a/Lib/test/test_email/test__header_value_parser.py b/Lib/test/test_email/test__header_value_parser.py
index 676732b..12da3cf 100644
--- a/Lib/test/test_email/test__header_value_parser.py
+++ b/Lib/test/test_email/test__header_value_parser.py
@@ -2494,6 +2494,78 @@ class TestParser(TestParserMixin, TestEmailBase):
             ";foo", ";foo", ";foo", [errors.InvalidHeaderDefect]*3
         )
 
+    # get_msg_id
+
+    def test_get_msg_id_valid(self):
+        msg_id = self._test_get_x(
+            parser.get_msg_id,
+            "<simeple.local@example.something.com>",
+            "<simeple.local@example.something.com>",
+            "<simeple.local@example.something.com>",
+            [],
+            '',
+            )
+        self.assertEqual(msg_id.token_type, 'msg-id')
+
+    def test_get_msg_id_obsolete_local(self):
+        msg_id = self._test_get_x(
+            parser.get_msg_id,
+            '<"simeple.local"@example.com>',
+            '<"simeple.local"@example.com>',
+            '<simeple.local@example.com>',
+            [errors.ObsoleteHeaderDefect],
+            '',
+            )
+        self.assertEqual(msg_id.token_type, 'msg-id')
+
+    def test_get_msg_id_non_folding_literal_domain(self):
+        msg_id = self._test_get_x(
+            parser.get_msg_id,
+            "<simple.local@[someexamplecom.domain]>",
+            "<simple.local@[someexamplecom.domain]>",
+            "<simple.local@[someexamplecom.domain]>",
+            [],
+            "",
+            )
+        self.assertEqual(msg_id.token_type, 'msg-id')
+
+
+    def test_get_msg_id_obsolete_domain_part(self):
+        msg_id = self._test_get_x(
+            parser.get_msg_id,
+            "<simplelocal@(old)example.com>",
+            "<simplelocal@(old)example.com>",
+            "<simplelocal@ example.com>",
+            [errors.ObsoleteHeaderDefect],
+            ""
+        )
+
+    def test_get_msg_id_no_id_right_part(self):
+        msg_id = self._test_get_x(
+            parser.get_msg_id,
+            "<simplelocal>",
+            "<simplelocal>",
+            "<simplelocal>",
+            [errors.InvalidHeaderDefect],
+            ""
+        )
+        self.assertEqual(msg_id.token_type, 'msg-id')
+
+    def test_get_msg_id_no_angle_start(self):
+        with self.assertRaises(errors.HeaderParseError):
+            parser.get_msg_id("msgwithnoankle")
+
+    def test_get_msg_id_no_angle_end(self):
+        msg_id = self._test_get_x(
+            parser.get_msg_id,
+            "<simplelocal@domain",
+            "<simplelocal@domain>",
+            "<simplelocal@domain>",
+            [errors.InvalidHeaderDefect],
+            ""
+        )
+        self.assertEqual(msg_id.token_type, 'msg-id')
+
 
 @parameterize
 class Test_parse_mime_parameters(TestParserMixin, TestEmailBase):
diff --git a/Lib/test/test_email/test_headerregistry.py b/Lib/test/test_email/test_headerregistry.py
index d100709..7550546 100644
--- a/Lib/test/test_email/test_headerregistry.py
+++ b/Lib/test/test_email/test_headerregistry.py
@@ -1648,6 +1648,34 @@ class TestFolding(TestHeaderBase):
                 'xxxxxxxxxxxxxxxxxxxx=3D=3D-xxx-xx-xx?=\n'
             ' =?utf-8?q?=3E?=\n')
 
+    def test_message_id_header_is_not_folded(self):
+        h = self.make_header(
+            'Message-ID',
+            '<somemessageidlongerthan@maxlinelength.com>')
+        self.assertEqual(
+            h.fold(policy=policy.default.clone(max_line_length=20)),
+            'Message-ID: <somemessageidlongerthan@maxlinelength.com>\n')
+
+        # Test message-id isn't folded when id-right is no-fold-literal.
+        h = self.make_header(
+            'Message-ID',
+            '<somemessageidlongerthan@[127.0.0.0.0.0.0.0.0.1]>')
+        self.assertEqual(
+            h.fold(policy=policy.default.clone(max_line_length=20)),
+            'Message-ID: <somemessageidlongerthan@[127.0.0.0.0.0.0.0.0.1]>\n')
+
+        # Test message-id isn't folded when id-right is non-ascii characters.
+        h = self.make_header('Message-ID', '<ईमेल@wők.com>')
+        self.assertEqual(
+            h.fold(policy=policy.default.clone(max_line_length=30)),
+            'Message-ID: <ईमेल@wők.com>\n')
+
+        # Test message-id is folded without breaking the msg-id token into
+        # encoded words, *even* if they don't fit into max_line_length.
+        h = self.make_header('Message-ID', '<ईमेलfromMessage@wők.com>')
+        self.assertEqual(
+            h.fold(policy=policy.default.clone(max_line_length=20)),
+            'Message-ID:\n <ईमेलfromMessage@wők.com>\n')
 
 if __name__ == '__main__':
     unittest.main()