bpo-37482: Fix email address name with encoded words and special chars (GH-14561)

bsiem · miss-islington · commit df0c21ff46c5 · 2019-08-21T16:00:39.000-07:00
Special characters in email address header display names are normally put within double quotes. However, encoded words (=?charset?x?...?=) are not allowed withing double quotes. When the header contains a word with special characters and another word that must be encoded, the first one must also be encoded. In the next example, the display name in the From header is quoted and therefore the comma is allowed; in the To header, the comma is not within quotes and not encoded, which is not allowed and therefore rejected by some mail servers. From: "Foo Bar, France" <foo@example.com> To: Foo Bar, =?utf-8?q?Espa=C3=B1a?= <foo@example.com> https://bugs.python.org/issue37482
diff --git a/Lib/email/_header_value_parser.py b/Lib/email/_header_value_parser.py
@@ -2743,6 +2743,9 @@ def _refold_parse_tree(parse_tree, *, policy):
             wrap_as_ew_blocked -= 1
             continue
         tstr = str(part)
+        if part.token_type == 'ptext' and set(tstr) & SPECIALS:
+            # Encode if tstr contains special characters.
+            want_encoding = True
         try:
             tstr.encode(encoding)
             charset = encoding
diff --git a/Lib/test/test_email/test_headerregistry.py b/Lib/test/test_email/test_headerregistry.py
@@ -1547,6 +1547,30 @@ def test_group_comparison(self):
 
 class TestFolding(TestHeaderBase):
 
+    def test_address_display_names(self):
+        """Test the folding and encoding of address headers."""
+        for name, result in (
+                ('Foo Bar, France', '"Foo Bar, France"'),
+                ('Foo Bar (France)', '"Foo Bar (France)"'),
+                ('Foo Bar, España', 'Foo =?utf-8?q?Bar=2C_Espa=C3=B1a?='),
+                ('Foo Bar (España)', 'Foo Bar =?utf-8?b?KEVzcGHDsWEp?='),
+                ('Foo, Bar España', '=?utf-8?q?Foo=2C_Bar_Espa=C3=B1a?='),
+                ('Foo, Bar [España]', '=?utf-8?q?Foo=2C_Bar_=5BEspa=C3=B1a=5D?='),
+                ('Foo Bär, France', 'Foo =?utf-8?q?B=C3=A4r=2C?= France'),
+                ('Foo Bär <France>', 'Foo =?utf-8?q?B=C3=A4r_=3CFrance=3E?='),
+                (
+                    'Lôrem ipsum dôlôr sit amet, cônsectetuer adipiscing. '
+                    'Suspendisse pôtenti. Aliquam nibh. Suspendisse pôtenti.',
+                    '=?utf-8?q?L=C3=B4rem_ipsum_d=C3=B4l=C3=B4r_sit_amet=2C_c'
+                    '=C3=B4nsectetuer?=\n =?utf-8?q?adipiscing=2E_Suspendisse'
+                    '_p=C3=B4tenti=2E_Aliquam_nibh=2E?=\n Suspendisse =?utf-8'
+                    '?q?p=C3=B4tenti=2E?=',
+                    ),
+                ):
+            h = self.make_header('To', Address(name, addr_spec='a@b.com'))
+            self.assertEqual(h.fold(policy=policy.default),
+                                    'To: %s <a@b.com>\n' % result)
+
     def test_short_unstructured(self):
         h = self.make_header('subject', 'this is a test')
         self.assertEqual(h.fold(policy=policy.default),
diff --git a/Misc/NEWS.d/next/Library/2019-07-09-11-20-21.bpo-37482.auzvev.rst b/Misc/NEWS.d/next/Library/2019-07-09-11-20-21.bpo-37482.auzvev.rst
@@ -0,0 +1 @@
+Fix serialization of display name in originator or destination address fields with both encoded words and special chars.

Original file line number	Diff line number	Diff line change
`@@ -0,0 +1 @@`
	`1`	`+Fix serialization of display name in originator or destination address fields with both encoded words and special chars.`