gh-98188: Fix EmailMessage.get_payload to decode data when CTE value has extra text (GH-127547)

Up to this point message handling has been very strict with regards to content encoding values: mixed case was accepted, but trailing blanks or other text would cause decoding failure, even if the first token was a valid encoding.  By Postel's Rule we should go ahead and decode as long as we can recognize that first token.  We have not thought of any security or backward compatibility concerns with this fix.

This fix does introduce a new technique/pattern to the Message code: we look to see if the header has a 'cte' attribute, and if so we use that.  This effectively promotes the header API exposed by HeaderRegistry to an API that any header parser "should" support.  This seems like a reasonable thing to do.  It is not, however, a requirement, as the string value of the header is still used if there is no cte attribute.

The full fix (ignore any trailing blanks or blank-separated trailing text) applies only to the non-compat32 API.  compat32 is only fixed to the extent that it now ignores trailing spaces.  Note that the HeaderRegistry parsing still records a HeaderDefect if there is extra text.

(cherry picked from commit a62ba52)

Co-authored-by: RanKKI <[email protected]>
Co-authored-by: Bénédikt Tran <[email protected]>

Author: 2 people

Lib/email/message.py

@@ -286,8 +286,12 @@ def get_payload(self, i=None, decode=False):
         if i is not None and not isinstance(self._payload, list):
             raise TypeError('Expected list, got %s' % type(self._payload))
         payload = self._payload
-        # cte might be a Header, so for now stringify it.
-        cte = str(self.get('content-transfer-encoding', '')).lower()
+        cte = self.get('content-transfer-encoding', '')
+        if hasattr(cte, 'cte'):
+            cte = cte.cte
+        else:
+            # cte might be a Header, so for now stringify it.
+            cte = str(cte).strip().lower()
         # payload may be bytes here.
         if not decode:
             if isinstance(payload, str) and utils._has_surrogates(payload):

Lib/test/test_email/test_email.py

@@ -810,6 +810,16 @@ def test_unicode_body_defaults_to_utf8_encoding(self):
             w4kgdGVzdGFiYwo=
             """))
 
+    def test_string_payload_with_base64_cte(self):
+        msg = email.message_from_string(textwrap.dedent("""\
+        Content-Transfer-Encoding: base64
+
+        SGVsbG8uIFRlc3Rpbmc=
+        """), policy=email.policy.default)
+        self.assertEqual(msg.get_payload(decode=True), b"Hello. Testing")
+        self.assertDefectsEqual(msg['content-transfer-encoding'].defects, [])
+
+
 
 # Test the email.encoders module
 class TestEncoders(unittest.TestCase):
@@ -2352,6 +2362,40 @@ def test_missing_header_body_separator(self):
         self.assertDefectsEqual(msg.defects,
                                 [errors.MissingHeaderBodySeparatorDefect])
 
+    def test_string_payload_with_extra_space_after_cte(self):
+        # https://github.com/python/cpython/issues/98188
+        cte = "base64 "
+        msg = email.message_from_string(textwrap.dedent(f"""\
+        Content-Transfer-Encoding: {cte}
+
+        SGVsbG8uIFRlc3Rpbmc=
+        """), policy=email.policy.default)
+        self.assertEqual(msg.get_payload(decode=True), b"Hello. Testing")
+        self.assertDefectsEqual(msg['content-transfer-encoding'].defects, [])
+
+    def test_string_payload_with_extra_text_after_cte(self):
+        msg = email.message_from_string(textwrap.dedent("""\
+        Content-Transfer-Encoding: base64 some text
+
+        SGVsbG8uIFRlc3Rpbmc=
+        """), policy=email.policy.default)
+        self.assertEqual(msg.get_payload(decode=True), b"Hello. Testing")
+        cte = msg['content-transfer-encoding']
+        self.assertDefectsEqual(cte.defects, [email.errors.InvalidHeaderDefect])
+
+    def test_string_payload_with_extra_space_after_cte_compat32(self):
+        cte = "base64 "
+        msg = email.message_from_string(textwrap.dedent(f"""\
+        Content-Transfer-Encoding: {cte}
+
+        SGVsbG8uIFRlc3Rpbmc=
+        """), policy=email.policy.compat32)
+        pasted_cte = msg['content-transfer-encoding']
+        self.assertEqual(pasted_cte, cte)
+        self.assertEqual(msg.get_payload(decode=True), b"Hello. Testing")
+        self.assertDefectsEqual(msg.defects, [])
+
+
 
 # Test RFC 2047 header encoding and decoding
 class TestRFC2047(TestEmailBase):

Lib/test/test_email/test_headerregistry.py

@@ -838,6 +838,11 @@ def cte_as_value(self,
             '7bit',
             [errors.InvalidHeaderDefect]),
 
+        'extra_space_after_cte': (
+            'base64 ',
+            'base64',
+            []),
+
     }
 
 

Misc/ACKS

@@ -1122,6 +1122,7 @@ Gregor Lingl
 Everett Lipman
 Mirko Liss
 Alexander Liu
+Hui Liu
 Yuan Liu
 Nick Lockwood
 Stephanie Lockwood

Misc/NEWS.d/next/Library/2024-12-03-14-45-16.gh-issue-98188.GX9i2b.rst

@@ -0,0 +1,3 @@
+Fix an issue in :meth:`email.message.Message.get_payload` where data
+cannot be decoded if the Content Transfer Encoding mechanism contains
+trailing whitespaces or additional junk text. Patch by Hui Liu.