bpo-27397: Make email module properly handle invalid-length base64 strings (#7583)

When attempting to base64-decode a payload of invalid length (1 mod 4),
properly recognize and handle it.  The given data will be returned as-is,
i.e. not decoded, along with a new defect, InvalidBase64LengthDefect.

3 files changed, 32 insertions, 0 deletions

diff --git a/Lib/test/test_email/test__encoded_words.py b/Lib/test/test_email/test__encoded_words.py
index 900e1d0e64..5a59aebba8 100644
--- a/Lib/test/test_email/test__encoded_words.py
+++ b/Lib/test/test_email/test__encoded_words.py
@@ -33,7 +33,10 @@ class TestDecodeB(TestEmailBase):
         self._test(b'Zm9v', b'foo')
 
     def test_missing_padding(self):
+        # 1 missing padding character
         self._test(b'dmk', b'vi', [errors.InvalidBase64PaddingDefect])
+        # 2 missing padding characters
+        self._test(b'dg', b'v', [errors.InvalidBase64PaddingDefect])
 
     def test_invalid_character(self):
         self._test(b'dm\x01k===', b'vi', [errors.InvalidBase64CharactersDefect])
@@ -42,6 +45,9 @@ class TestDecodeB(TestEmailBase):
         self._test(b'dm\x01k', b'vi', [errors.InvalidBase64CharactersDefect,
                                        errors.InvalidBase64PaddingDefect])
 
+    def test_invalid_length(self):
+        self._test(b'abcde', b'abcde', [errors.InvalidBase64LengthDefect])
+
 
 class TestDecode(TestEmailBase):
 
diff --git a/Lib/test/test_email/test__header_value_parser.py b/Lib/test/test_email/test__header_value_parser.py
index 5cdc4bceca..5036de2ca0 100644
--- a/Lib/test/test_email/test__header_value_parser.py
+++ b/Lib/test/test_email/test__header_value_parser.py
@@ -347,6 +347,15 @@ class TestParser(TestParserMixin, TestEmailBase):
              errors.InvalidBase64PaddingDefect],
             '')
 
+    def test_get_unstructured_invalid_base64_length(self):
+        # bpo-27397: Return the encoded string since there's no way to decode.
+        self._test_get_x(self._get_unst,
+            '=?utf-8?b?abcde?=',
+            'abcde',
+            'abcde',
+            [errors.InvalidBase64LengthDefect],
+            '')
+
     def test_get_unstructured_no_whitespace_between_ews(self):
         self._test_get_x(self._get_unst,
             '=?utf-8?q?foo?==?utf-8?q?bar?=',
diff --git a/Lib/test/test_email/test_defect_handling.py b/Lib/test/test_email/test_defect_handling.py
index f36b907573..781f657418 100644
--- a/Lib/test/test_email/test_defect_handling.py
+++ b/Lib/test/test_email/test_defect_handling.py
@@ -254,6 +254,23 @@ class TestDefectsBase:
         self.assertDefectsEqual(self.get_defects(msg),
                                 [errors.InvalidBase64CharactersDefect])
 
+    def test_invalid_length_of_base64_payload(self):
+        source = textwrap.dedent("""\
+            Subject: test
+            MIME-Version: 1.0
+            Content-Type: text/plain; charset="utf-8"
+            Content-Transfer-Encoding: base64
+
+            abcde
+            """)
+        msg = self._str_msg(source)
+        with self._raise_point(errors.InvalidBase64LengthDefect):
+            payload = msg.get_payload(decode=True)
+        if self.raise_expected: return
+        self.assertEqual(payload, b'abcde')
+        self.assertDefectsEqual(self.get_defects(msg),
+                                [errors.InvalidBase64LengthDefect])
+
     def test_missing_ending_boundary(self):
         source = textwrap.dedent("""\
             To: 1@harrydomain4.com