#1672568: email now registers defects for base64 payload format errors.
Which also means that it is now producing *something* for any base64
payload, which is what leads to the couple of older test changes in
test_email. This is a slightly backward incompatible behavior change,
but the new behavior is so much more useful than the old (you can now
*reliably* detect errors, and any program that was detecting errors by
sniffing for a base64 return from get_payload(decode=True) and then doing
its own error-recovery decode will just get the error-recovery decode
right away). So this seems to me to be worth the small risk inherent
in this behavior change.
This patch also refactors the defect tests into a separate test file,
since they are no longer just parser tests.
diff --git a/Lib/email/message.py b/Lib/email/message.py
index 91976f1..62b82b7 100644
--- a/Lib/email/message.py
+++ b/Lib/email/message.py
@@ -17,6 +17,7 @@
from email import errors
from email._policybase import compat32
from email import charset as _charset
+from email._encoded_words import decode_b
Charset = _charset.Charset
SEMISPACE = '; '
@@ -249,11 +250,12 @@
if cte == 'quoted-printable':
return utils._qdecode(bpayload)
elif cte == 'base64':
- try:
- return base64.b64decode(bpayload)
- except binascii.Error:
- # Incorrect padding
- return bpayload
+ # XXX: this is a bit of a hack; decode_b should probably be factored
+ # out somewhere, but I haven't figured out where yet.
+ value, defects = decode_b(b''.join(bpayload.splitlines()))
+ for defect in defects:
+ self.policy.handle_defect(self, defect)
+ return value
elif cte in ('x-uuencode', 'uuencode', 'uue', 'x-uue'):
in_file = BytesIO(bpayload)
out_file = BytesIO()