Issue #7143: get_payload used to strip any trailing newline from a
base64 transfer-encoded payload *after* decoding it; it no longer does.
email had a special method in utils, _bdecode, specifically to do this,
so it must have served a purpose at some point, yet it is clearly wrong
per RFC. Fixed with Barry's approval, but no backport. Email package
minor version number is bumped, now version 4.0.1.
Patch by Joaquin Cuenca Abela.
diff --git a/Lib/email/__init__.py b/Lib/email/__init__.py
index 8d230fd..a793436 100644
--- a/Lib/email/__init__.py
+++ b/Lib/email/__init__.py
@@ -4,7 +4,7 @@
"""A package for parsing, handling, and generating email messages."""
-__version__ = '4.0.1'
+__version__ = '4.0.2'
__all__ = [
# Old names
diff --git a/Lib/email/test/data/msg_10.txt b/Lib/email/test/data/msg_10.txt
index bd30d13..0790396 100644
--- a/Lib/email/test/data/msg_10.txt
+++ b/Lib/email/test/data/msg_10.txt
@@ -26,6 +26,13 @@
--BOUNDARY
Content-Type: text/plain; charset="iso-8859-1"
+Content-Transfer-Encoding: Base64
+
+VGhpcyBpcyBhIEJhc2U2NCBlbmNvZGVkIG1lc3NhZ2UuCg==
+
+
+--BOUNDARY
+Content-Type: text/plain; charset="iso-8859-1"
This has no Content-Transfer-Encoding: header.
diff --git a/Lib/email/test/test_email.py b/Lib/email/test/test_email.py
index aa16ce2..36b308f 100644
--- a/Lib/email/test/test_email.py
+++ b/Lib/email/test/test_email.py
@@ -205,8 +205,12 @@
# Subpart 3 is base64
eq(msg.get_payload(2).get_payload(decode=True),
'This is a Base64 encoded message.')
- # Subpart 4 has no Content-Transfer-Encoding: header.
+ # Subpart 4 is base64 with a trailing newline, which
+ # used to be stripped (issue 7143).
eq(msg.get_payload(3).get_payload(decode=True),
+ 'This is a Base64 encoded message.\n')
+ # Subpart 5 has no Content-Transfer-Encoding: header.
+ eq(msg.get_payload(4).get_payload(decode=True),
'This has no Content-Transfer-Encoding: header.\n')
def test_get_decoded_uu_payload(self):
diff --git a/Lib/email/test/test_email_renamed.py b/Lib/email/test/test_email_renamed.py
index fc8f30a..976d892 100644
--- a/Lib/email/test/test_email_renamed.py
+++ b/Lib/email/test/test_email_renamed.py
@@ -194,8 +194,12 @@
# Subpart 3 is base64
eq(msg.get_payload(2).get_payload(decode=True),
'This is a Base64 encoded message.')
- # Subpart 4 has no Content-Transfer-Encoding: header.
+ # Subpart 4 is base64 with a trailing newline, which
+ # used to be stripped (issue 7143).
eq(msg.get_payload(3).get_payload(decode=True),
+ 'This is a Base64 encoded message.\n')
+ # Subpart 5 has no Content-Transfer-Encoding: header.
+ eq(msg.get_payload(4).get_payload(decode=True),
'This has no Content-Transfer-Encoding: header.\n')
def test_get_decoded_uu_payload(self):
diff --git a/Lib/email/utils.py b/Lib/email/utils.py
index b9a7642..6d22ca7 100644
--- a/Lib/email/utils.py
+++ b/Lib/email/utils.py
@@ -60,14 +60,15 @@
def _bdecode(s):
- # We can't quite use base64.encodestring() since it tacks on a "courtesy
- # newline". Blech!
+ """Decodes a base64 string.
+
+ This function is equivalent to base64.decodestring and it's retained only
+ for backward compatibility. It used to remove the last \n of the decoded
+ string, if it had any (see issue 7143).
+ """
if not s:
return s
- value = base64.decodestring(s)
- if not s.endswith('\n') and value.endswith('\n'):
- return value[:-1]
- return value
+ return base64.decodestring(s)