#18431: Decode encoded words in atoms in new email parser.

There is more to be done here in terms of accepting RFC invalid
input that some mailers accept, but this covers the valid
RFC places where encoded words can occur in structured headers.

2 files changed, 49 insertions, 1 deletions

diff --git a/Lib/test/test_email/test__header_value_parser.py b/Lib/test/test_email/test__header_value_parser.py
index 8917447..646082b 100644
--- a/Lib/test/test_email/test__header_value_parser.py
+++ b/Lib/test/test_email/test__header_value_parser.py
@@ -808,9 +808,13 @@ class TestParser(TestParserMixin, TestEmailBase):
         self.assertEqual(atom[2].comments, ['bar'])
 
     def test_get_atom_atom_ends_at_noncfws(self):
-        atom = self._test_get_x(parser.get_atom,
+        self._test_get_x(parser.get_atom,
             'bob  fred', 'bob  ', 'bob ', [], 'fred')
 
+    def test_get_atom_rfc2047_atom(self):
+        self._test_get_x(parser.get_atom,
+            '=?utf-8?q?=20bob?=', ' bob', ' bob', [], '')
+
     # get_dot_atom_text
 
     def test_get_dot_atom_text(self):
@@ -885,6 +889,10 @@ class TestParser(TestParserMixin, TestEmailBase):
         with self.assertRaises(errors.HeaderParseError):
             parser.get_dot_atom(' (foo) bar.bang. foo')
 
+    def test_get_dot_atom_rfc2047_atom(self):
+        self._test_get_x(parser.get_dot_atom,
+            '=?utf-8?q?=20bob?=', ' bob', ' bob', [], '')
+
     # get_word (if this were black box we'd repeat all the qs/atom tests)
 
     def test_get_word_atom_yields_atom(self):
@@ -2156,6 +2164,22 @@ class TestParser(TestParserMixin, TestEmailBase):
         self.assertEqual(address[0].token_type,
                          'mailbox')
 
+    def test_get_address_rfc2047_display_name(self):
+        address = self._test_get_x(parser.get_address,
+            '=?utf-8?q?=C3=89ric?= <foo@example.com>',
+            'Éric <foo@example.com>',
+            'Éric <foo@example.com>',
+            [],
+            '')
+        self.assertEqual(address.token_type, 'address')
+        self.assertEqual(len(address.mailboxes), 1)
+        self.assertEqual(address.mailboxes,
+                         address.all_mailboxes)
+        self.assertEqual(address.mailboxes[0].display_name,
+                         'Éric')
+        self.assertEqual(address[0].token_type,
+                         'mailbox')
+
     def test_get_address_empty_group(self):
         address = self._test_get_x(parser.get_address,
             'Monty Python:;',
diff --git a/Lib/test/test_email/test_headerregistry.py b/Lib/test/test_email/test_headerregistry.py
index 80f1c02..f754a32 100644
--- a/Lib/test/test_email/test_headerregistry.py
+++ b/Lib/test/test_email/test_headerregistry.py
@@ -158,6 +158,10 @@ class TestUnstructuredHeader(TestHeaderBase):
             '=?utf-8?q?=C3=89ric?=',
             'Éric'),
 
+        'rfc2047_quopri_with_regular_text': (
+            'The =?utf-8?q?=C3=89ric=2C?= Himself',
+            'The Éric, Himself'),
+
     }
 
 
@@ -1119,6 +1123,26 @@ class TestAddressHeader(TestHeaderBase):
              'example.com',
              None),
 
+        'rfc2047_atom_is_decoded':
+            ('=?utf-8?q?=C3=89ric?= <foo@example.com>',
+            [],
+            'Éric <foo@example.com>',
+            'Éric',
+            'foo@example.com',
+            'foo',
+            'example.com',
+            None),
+
+        'rfc2047_atom_in_phrase_is_decoded':
+            ('The =?utf-8?q?=C3=89ric=2C?= Himself <foo@example.com>',
+            [],
+            '"The Éric, Himself" <foo@example.com>',
+            'The Éric, Himself',
+            'foo@example.com',
+            'foo',
+            'example.com',
+            None),
+
         }
 
         # XXX: Need many more examples, and in particular some with names in