Merge: #17171: fix email.encoders.encode_7or8bit when applied to binary data.

Lib/email/encoders.py

@@ -62,15 +62,17 @@ def encode_7or8bit(msg):
         else:
             orig.decode('ascii')
     except UnicodeError:
-        # iso-2022-* is non-ASCII but still 7-bit
         charset = msg.get_charset()
         output_cset = charset and charset.output_charset
+        # iso-2022-* is non-ASCII but encodes to a 7-bit representation
         if output_cset and output_cset.lower().startswith('iso-2022-'):
             msg['Content-Transfer-Encoding'] = '7bit'
         else:
             msg['Content-Transfer-Encoding'] = '8bit'
     else:
         msg['Content-Transfer-Encoding'] = '7bit'
+    if not isinstance(orig, str):
+        msg.set_payload(orig.decode('ascii', 'surrogateescape'))
 
 
 

Lib/test/test_email/test_email.py

@@ -1440,7 +1440,24 @@ class TestMIMEApplication(unittest.TestCase):
         eq(msg.get_payload().strip(), '+vv8/f7/')
         eq(msg.get_payload(decode=True), bytesdata)
 
-    def test_body_with_encode_noop(self):
+    def test_binary_body_with_encode_7or8bit(self):
+        # Issue 17171.
+        bytesdata = b'\xfa\xfb\xfc\xfd\xfe\xff'
+        msg = MIMEApplication(bytesdata, _encoder=encoders.encode_7or8bit)
+        # Treated as a string, this will be invalid code points.
+        self.assertEqual(msg.get_payload(), '\uFFFD' * len(bytesdata))
+        self.assertEqual(msg.get_payload(decode=True), bytesdata)
+        self.assertEqual(msg['Content-Transfer-Encoding'], '8bit')
+        s = BytesIO()
+        g = BytesGenerator(s)
+        g.flatten(msg)
+        wireform = s.getvalue()
+        msg2 = email.message_from_bytes(wireform)
+        self.assertEqual(msg.get_payload(), '\uFFFD' * len(bytesdata))
+        self.assertEqual(msg2.get_payload(decode=True), bytesdata)
+        self.assertEqual(msg2['Content-Transfer-Encoding'], '8bit')
+
+    def test_binary_body_with_encode_noop(self):
         # Issue 16564: This does not produce an RFC valid message, since to be
         # valid it should have a CTE of binary.  But the below works in
         # Python2, and is documented as working this way.

Misc/NEWS

@@ -175,6 +175,9 @@ Core and Builtins
 Library
 -------
 
+- Issue #16564: Fixed regression relative to Python2 in the operation of
+  email.encoders.encode_7or8bit when used with binary data.
+
 - Issue #17052: unittest discovery should use self.testLoader.
 
 - Issue #4591: Uid and gid values larger than 2**31 are supported now.