#12515: email now registers a defect if the MIME end boundary is missing.
This commit also restores the news item for 167256 that it looks like
Terry inadvertently deleted. (Either that, or I don't understand
now merging works...which is equally possible.)
diff --git a/Lib/email/errors.py b/Lib/email/errors.py
index aa836d4..d80b5b9 100644
--- a/Lib/email/errors.py
+++ b/Lib/email/errors.py
@@ -42,6 +42,9 @@
class StartBoundaryNotFoundDefect(MessageDefect):
"""The claimed start boundary was never found."""
+class CloseBoundaryNotFoundDefect(MessageDefect):
+ """A start boundary was found, but not the corresponding close boundary."""
+
class FirstHeaderLineIsContinuationDefect(MessageDefect):
"""A message had a continuation line as its first header line."""
diff --git a/Lib/email/feedparser.py b/Lib/email/feedparser.py
index c3a67c0..56f50df 100644
--- a/Lib/email/feedparser.py
+++ b/Lib/email/feedparser.py
@@ -324,6 +324,7 @@
capturing_preamble = True
preamble = []
linesep = False
+ close_boundary_seen = False
while True:
line = self._input.readline()
if line is NeedMoreData:
@@ -338,6 +339,7 @@
# the closing boundary, then we need to initialize the
# epilogue with the empty string (see below).
if mo.group('end'):
+ close_boundary_seen = True
linesep = mo.group('linesep')
break
# We saw an inter-part boundary. Were we in the preamble?
@@ -406,7 +408,6 @@
# We've seen either the EOF or the end boundary. If we're still
# capturing the preamble, we never saw the start boundary. Note
# that as a defect and store the captured text as the payload.
- # Everything from here to the EOF is epilogue.
if capturing_preamble:
defect = errors.StartBoundaryNotFoundDefect()
self.policy.handle_defect(self._cur, defect)
@@ -418,8 +419,15 @@
continue
self._cur.epilogue = EMPTYSTRING.join(epilogue)
return
- # If the end boundary ended in a newline, we'll need to make sure
- # the epilogue isn't None
+ # If we're not processing the preamble, then we might have seen
+ # EOF without seeing that end boundary...that is also a defect.
+ if not close_boundary_seen:
+ defect = errors.CloseBoundaryNotFoundDefect()
+ self.policy.handle_defect(self._cur, defect)
+ return
+ # Everything from here to the EOF is epilogue. If the end boundary
+ # ended in a newline, we'll need to make sure the epilogue isn't
+ # None
if linesep:
epilogue = ['']
else:
diff --git a/Lib/test/test_email/test_defect_handling.py b/Lib/test/test_email/test_defect_handling.py
index d3df1e4..fe72599 100644
--- a/Lib/test/test_email/test_defect_handling.py
+++ b/Lib/test/test_email/test_defect_handling.py
@@ -278,6 +278,39 @@
with self.assertRaises(errors.InvalidBase64CharactersDefect):
msg.get_payload(decode=True)
+ missing_ending_boundary = textwrap.dedent("""\
+ To: 1@harrydomain4.com
+ Subject: Fwd: 1
+ MIME-Version: 1.0
+ Content-Type: multipart/alternative;
+ boundary="------------000101020201080900040301"
+
+ --------------000101020201080900040301
+ Content-Type: text/plain; charset=ISO-8859-1
+ Content-Transfer-Encoding: 7bit
+
+ Alternative 1
+
+ --------------000101020201080900040301
+ Content-Type: text/html; charset=ISO-8859-1
+ Content-Transfer-Encoding: 7bit
+
+ Alternative 2
+
+ """)
+
+ def test_missing_ending_boundary(self):
+ msg = self._str_msg(self.missing_ending_boundary)
+ self.assertEqual(len(msg.get_payload()), 2)
+ self.assertEqual(msg.get_payload(1).get_payload(), 'Alternative 2\n')
+ self.assertDefectsEqual(self.get_defects(msg),
+ [errors.CloseBoundaryNotFoundDefect])
+
+ def test_missing_ending_boundary_raise_on_defect(self):
+ with self.assertRaises(errors.CloseBoundaryNotFoundDefect):
+ self._str_msg(self.missing_ending_boundary,
+ policy=self.policy.clone(raise_on_defect=True))
+
class TestMessageDefectDetection(TestMessageDefectDetectionBase, TestEmailBase):