#5610: use \Z not $ so we don't eat extra chars when body part ends with \r\n.

If a body part ended with \r\n, feedparser, using '$' to terminate its
search for the newline, would match on the \r\n, and think that it needed
to strip two characters in order to account for the line end before the
boundary.  That made it chop one too many characters off the end of
the body part.  Using \Z makes the match correct.

Patch and test by Tony Nelson.
This commit is contained in:
R. David Murray 2010-06-03 15:43:20 +00:00
parent 23152ea5bd
commit 61746d580e
3 changed files with 22 additions and 1 deletions

View File

@ -28,7 +28,7 @@ from email import message
NLCRE = re.compile('\r\n|\r|\n')
NLCRE_bol = re.compile('(\r\n|\r|\n)')
NLCRE_eol = re.compile('(\r\n|\r|\n)$')
NLCRE_eol = re.compile('(\r\n|\r|\n)\Z')
NLCRE_crack = re.compile('(\r\n|\r|\n)')
# RFC 2822 $3.6.8 Optional fields. ftext is %d33-57 / %d59-126, Any character
# except controls, SP, and ":".

View File

@ -2610,6 +2610,24 @@ Here's the message body
eq(headers, ['A', 'B', 'CC'])
eq(msg.get_payload(), 'body')
def test_CRLFLF_at_end_of_part(self):
# issue 5610: feedparser should not eat two chars from body part ending
# with "\r\n\n".
m = (
"From: foo@bar.com\n"
"To: baz\n"
"Mime-Version: 1.0\n"
"Content-Type: multipart/mixed; boundary=BOUNDARY\n"
"\n"
"--BOUNDARY\n"
"Content-Type: text/plain\n"
"\n"
"body ending with CRLF newline\r\n"
"\n"
"--BOUNDARY--\n"
)
msg = email.message_from_string(m)
self.assertTrue(msg.get_payload(0).get_payload().endswith('\r\n'))
class TestBase64(unittest.TestCase):

View File

@ -46,6 +46,9 @@ C-API
Library
-------
- Issue #5610: feedparser no longer eats extra characters at the end of
a body part if the body part ends with a \r\n.
- Issue #8833: tarfile created hard link entries with a size field != 0 by
mistake.