#14925: email now registers a defect for missing header/body separator.
This patch also deprecates the MalformedHeaderDefect. My best guess is that
this defect was rendered obsolete by a refactoring of the parser, and the
corresponding defect for the new parser (which this patch introduces) was
overlooked.
diff --git a/Lib/test/test_email/test_email.py b/Lib/test/test_email/test_email.py
index ac6ee65..c04952c 100644
--- a/Lib/test/test_email/test_email.py
+++ b/Lib/test/test_email/test_email.py
@@ -1960,15 +1960,27 @@
# test_parser.TestMessageDefectDetectionBase
def test_first_line_is_continuation_header(self):
eq = self.assertEqual
- m = ' Line 1\nLine 2\nLine 3'
+ m = ' Line 1\nSubject: test\n\nbody'
msg = email.message_from_string(m)
- eq(msg.keys(), [])
- eq(msg.get_payload(), 'Line 2\nLine 3')
+ eq(msg.keys(), ['Subject'])
+ eq(msg.get_payload(), 'body')
eq(len(msg.defects), 1)
- self.assertTrue(isinstance(msg.defects[0],
- errors.FirstHeaderLineIsContinuationDefect))
+ self.assertDefectsEqual(msg.defects,
+ [errors.FirstHeaderLineIsContinuationDefect])
eq(msg.defects[0].line, ' Line 1\n')
+ # test_parser.TestMessageDefectDetectionBase
+ def test_missing_header_body_separator(self):
+ # Our heuristic if we see a line that doesn't look like a header (no
+ # leading whitespace but no ':') is to assume that the blank line that
+ # separates the header from the body is missing, and to stop parsing
+ # headers and start parsing the body.
+ msg = self._str_msg('Subject: test\nnot a header\nTo: abc\n\nb\n')
+ self.assertEqual(msg.keys(), ['Subject'])
+ self.assertEqual(msg.get_payload(), 'not a header\nTo: abc\n\nb\n')
+ self.assertDefectsEqual(msg.defects,
+ [errors.MissingHeaderBodySeparatorDefect])
+
# Test RFC 2047 header encoding and decoding
class TestRFC2047(TestEmailBase):
diff --git a/Lib/test/test_email/test_parser.py b/Lib/test/test_email/test_parser.py
index 864e4c1..f58e7c1 100644
--- a/Lib/test/test_email/test_parser.py
+++ b/Lib/test/test_email/test_parser.py
@@ -237,17 +237,33 @@
policy=self.policy.clone(raise_on_defect=True))
def test_first_line_is_continuation_header(self):
- msg = self._str_msg(' Line 1\nLine 2\nLine 3')
- self.assertEqual(msg.keys(), [])
- self.assertEqual(msg.get_payload(), 'Line 2\nLine 3')
+ msg = self._str_msg(' Line 1\nSubject: test\n\nbody')
+ self.assertEqual(msg.keys(), ['Subject'])
+ self.assertEqual(msg.get_payload(), 'body')
self.assertEqual(len(self.get_defects(msg)), 1)
- self.assertTrue(isinstance(self.get_defects(msg)[0],
- errors.FirstHeaderLineIsContinuationDefect))
+ self.assertDefectsEqual(self.get_defects(msg),
+ [errors.FirstHeaderLineIsContinuationDefect])
self.assertEqual(self.get_defects(msg)[0].line, ' Line 1\n')
def test_first_line_is_continuation_header_raise_on_defect(self):
with self.assertRaises(errors.FirstHeaderLineIsContinuationDefect):
- self._str_msg(' Line 1\nLine 2\nLine 3',
+ self._str_msg(' Line 1\nSubject: test\n\nbody\n',
+ policy=self.policy.clone(raise_on_defect=True))
+
+ def test_missing_header_body_separator(self):
+ # Our heuristic if we see a line that doesn't look like a header (no
+ # leading whitespace but no ':') is to assume that the blank line that
+ # separates the header from the body is missing, and to stop parsing
+ # headers and start parsing the body.
+ msg = self._str_msg('Subject: test\nnot a header\nTo: abc\n\nb\n')
+ self.assertEqual(msg.keys(), ['Subject'])
+ self.assertEqual(msg.get_payload(), 'not a header\nTo: abc\n\nb\n')
+ self.assertDefectsEqual(self.get_defects(msg),
+ [errors.MissingHeaderBodySeparatorDefect])
+
+ def test_missing_header_body_separator_raise_on_defect(self):
+ with self.assertRaises(errors.MissingHeaderBodySeparatorDefect):
+ self._str_msg('Subject: test\nnot a header\nTo: abc\n\nb\n',
policy=self.policy.clone(raise_on_defect=True))