[Python-checkins] cpython: #12515: email now registers a defect if the MIME end boundary is missing.

[r.david.murray]

http://hg.python.org/cpython/rev/81e008f13b4f
changeset:   77198:81e008f13b4f
user:        R David Murray <rdmurray at bitdance.com>
date:        Sun May 27 22:20:42 2012 -0400
summary:
  #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.)

files:
  Doc/library/email.errors.rst                |   5 +
  Lib/email/errors.py                         |   3 +
  Lib/email/feedparser.py                     |  14 +++-
  Lib/test/test_email/test_defect_handling.py |  33 ++++++++++
  Misc/NEWS                                   |   7 ++
  5 files changed, 59 insertions(+), 3 deletions(-)


diff --git a/Doc/library/email.errors.rst b/Doc/library/email.errors.rst
--- a/Doc/library/email.errors.rst
+++ b/Doc/library/email.errors.rst
@@ -73,6 +73,11 @@
 * :class:`StartBoundaryNotFoundDefect` -- The start boundary claimed in the
   :mailheader:`Content-Type` header was never found.
 
+* :class:`CloseBoundaryNotFoundDefect` -- A start boundary was found, but
+  no corresponding close boundary was ever found.
+
+  .. versionadded: 3.3
+
 * :class:`FirstHeaderLineIsContinuationDefect` -- The message had a continuation
   line as its first header line.
 
diff --git a/Lib/email/errors.py b/Lib/email/errors.py
--- 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
--- 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
--- 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 at 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):
 
diff --git a/Misc/NEWS b/Misc/NEWS
--- a/Misc/NEWS
+++ b/Misc/NEWS
@@ -49,9 +49,16 @@
 Library
 -------
 
+- Issue #12515: email now registers a defect if it gets to EOF while parsing
+  a MIME part without seeing the closing MIME boundary.
+
 - Issue12510: Attempting to get invalid tooltip no longer closes Idle.
   Original patch by Roger Serwy.
 
+- Issue #1672568: email now always decodes base64 payloads, adding padding and
+  ignoring non-base64-alphabet characters if needed, and registering defects
+  for any such problems.
+
 - Issue #14925: email now registers a defect when the parser decides that there
   is a missing header/body separator line.  MalformedHeaderDefect, which the
   existing code would never actually generate, is deprecated.

-- 
Repository URL: http://hg.python.org/cpython