From ec317a8985967a7c8f150ec8c5db42443a18bdbe Mon Sep 17 00:00:00 2001 From: R David Murray Date: Mon, 11 Feb 2013 10:51:28 -0500 Subject: [PATCH] #17171: fix email.encoders.encode_7or8bit when applied to binary data. --- Lib/email/encoders.py | 4 +++- Lib/email/test/test_email.py | 19 ++++++++++++++++++- Misc/NEWS | 3 +++ 3 files changed, 24 insertions(+), 2 deletions(-) diff --git a/Lib/email/encoders.py b/Lib/email/encoders.py index 88b2f57d092..82a28cf3445 100644 --- a/Lib/email/encoders.py +++ b/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')) diff --git a/Lib/email/test/test_email.py b/Lib/email/test/test_email.py index e66a410fee7..daed3b0d63f 100644 --- a/Lib/email/test/test_email.py +++ b/Lib/email/test/test_email.py @@ -1438,7 +1438,24 @@ 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. diff --git a/Misc/NEWS b/Misc/NEWS index 1f772b72412..dc2e4ecf686 100644 --- a/Misc/NEWS +++ b/Misc/NEWS @@ -221,6 +221,9 @@ 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 #17141: random.vonmisesvariate() no more hangs for large kappas.