def test_remove_next_part_from_content(self):
with open(get_test_file("pipermail_nextpart.txt")) as email_file:
msg = message_from_file(email_file)
scrubber = Scrubber(msg)
contents = scrubber.scrub()[0]
self.failIf("-------------- next part --------------" in contents)
def test_remove_next_part_from_content(self):
with open(get_test_file("pipermail_nextpart.txt")) as email_file:
msg = message_from_file(email_file, policy=policy.SMTP)
scrubber = Scrubber(msg)
contents = scrubber.scrub()[0]
self.assertFalse("-------------- next part --------------" in contents)
def test_html_only_email(self):
# This email only has an HTML part, thus the scrubbed content will be
# empty. It should be an unicode empty string, not str.
with open(get_test_file("html-email-2.txt")) as email_file:
msg = message_from_file(email_file, policy=policy.SMTP)
scrubber = Scrubber(msg)
contents = scrubber.scrub()[0]
self.assertTrue(isinstance(contents, str),
"Scrubbed content should always be unicode")
def test_name_unicode(self):
for num in range(1, 6):
with open(get_test_file("attachment-%d.txt" % num)) as email_file:
msg = message_from_file(email_file)
scrubber = Scrubber(msg)
attachments = scrubber.scrub()[1]
for attachment in attachments:
name = attachment[1]
self.assertTrue(isinstance(name, unicode),
"attachment %r must be unicode" % name)
def _test_non_ascii_payload(self, enc):
with open(get_test_file("payload-%s.txt" % enc), 'rb') as email_file:
msg = message_from_binary_file(email_file, policy=policy.SMTP)
scrubber = Scrubber(msg)
contents = scrubber.scrub()[0]
self.assertTrue(isinstance(contents, str))
self.assertEqual(
contents,
'This message contains non-ascii characters:\n\xe9 \xe8 \xe7 \xe0 \xee \xef \xeb \u20ac\n' # noqa
)
def test_bad_content_type(self):
"""Scrubber must handle unknown content-types"""
with open(get_test_file("payload-unknown.txt")) as email_file:
msg = message_from_file(email_file)
scrubber = Scrubber(msg)
try:
contents = scrubber.scrub()[0]
except LookupError, e:
import traceback
print(traceback.format_exc())
self.fail(e) # codec not found
def test_non_ascii_payload(self):
"""Scrubber must handle non-ascii messages"""
for enc in ["utf8", "iso8859"]:
with open(get_test_file("payload-%s.txt" % enc)) as email_file:
msg = message_from_file(email_file)
scrubber = Scrubber(msg)
contents = scrubber.scrub()[0]
self.assertTrue(isinstance(contents, unicode))
self.assertEqual(
contents,
u'This message contains non-ascii '
u'characters:\n\xe9 \xe8 \xe7 \xe0 \xee \xef \xeb \u20ac\n')
def test_html_email_1(self):
with open(get_test_file("html-email-1.txt")) as email_file:
msg = message_from_file(email_file, policy=policy.SMTP)
scrubber = Scrubber(msg)
contents, attachments = scrubber.scrub()
self.assertEqual(len(attachments), 1)
# HTML part
self._check_html_attachment(
attachments[0], (2, "attachment.html", "text/html", "iso-8859-1"))
self.assertEqual(len(attachments[0][4]), 2688)
# Scrubbed content
self.assertEqual(
contents, "This is a test message\n"
"Non-ASCII chars: r\xe9ponse fran\xe7ais \n\n\n")
def test_attachment_1(self):
with open(get_test_file("attachment-1.txt")) as email_file:
msg = message_from_file(email_file, policy=policy.SMTP)
scrubber = Scrubber(msg)
contents, attachments = scrubber.scrub()
self.assertEqual(len(attachments), 1)
self.assertEqual(attachments[0],
(2, 'puntogil.vcf', 'text/x-vcard', "utf-8",
'begin:vcard\nfn:gil\nn:;gil\nversion:2.1\n'
'end:vcard\n\n'))
self.assertEqual(
contents, "This is a test message.\n\n"
"\n-- \ndevel mailing list\[email protected]\n"
"https://admin.fedoraproject.org/mailman/listinfo/devel\n")
def test_attachment_5(self):
with open(get_test_file("attachment-5.txt")) as email_file:
msg = message_from_file(email_file, policy=policy.SMTP)
scrubber = Scrubber(msg)
contents, attachments = scrubber.scrub()
self.assertEqual(len(attachments), 1)
# text attachment
self.assertEqual(attachments[0][0:4],
(2, "todo-déjeuner.txt", "text/plain", "utf-8"))
self.assertEqual(len(attachments[0][4]), 110)
# Scrubbed content
self.assertEqual(
contents, 'This is a test, HTML message with '
'accented letters : \xe9 \xe8 \xe7 \xe0.\nAnd an '
'attachment with an accented filename\n\n\n\n\n\n')
def test_attachment_3(self):
with open(get_test_file("attachment-3.txt")) as email_file:
msg = message_from_file(email_file, policy=policy.SMTP)
scrubber = Scrubber(msg)
contents, attachments = scrubber.scrub()
self.assertEqual(len(attachments), 2)
# HTML part
self._check_html_attachment(
attachments[0], (3, "attachment.html", "text/html", "iso-8859-1"))
self.assertEqual(len(attachments[0][4]), 3114)
# Image attachment
self.assertEqual(attachments[1][0:4],
(4, "GeoffreyRoucourt.jpg", "image/jpeg", None))
self.assertEqual(len(attachments[1][4]), 282180)
# Scrubbed content
self.assertEqual(contents, "This is a test message\n\n\n")
def test_attachment_name_badly_encoded(self):
with open(get_test_file("email-bad-filename.txt"), 'rb') as email_file:
msg = message_from_binary_file(email_file, policy=policy.SMTP)
scrubber = Scrubber(msg)
try:
attachments = scrubber.scrub()[1]
except UnicodeDecodeError:
print(format_exc())
self.fail("Could not decode the filename")
# The filename has non-ascii characters without the encoding specified,
# Python will try to decode their name with best guess (ascii) and then
# replace the characters that don't correspond to an ascii code
# point. Then, we scrub the filename to allow only alpahun with dash,
# underscore and dot.
self.assertEqual(
attachments,
[(0, 'non-ascii-u3b5.jpg', 'text/plain', None, 'Dummy content\n')])
def test_attachment_2(self):
with open(get_test_file("attachment-2.txt")) as email_file:
msg = message_from_file(email_file)
scrubber = Scrubber(msg)
contents, attachments = scrubber.scrub()
self.assertEqual(len(attachments), 1)
self.assertEqual(attachments[0], (
3, u'signature.asc', u'application/pgp-signature', None,
'-----BEGIN PGP SIGNATURE-----\r\nVersion: GnuPG v1.4.12 '
'(GNU/Linux)\r\nComment: Using GnuPG with Mozilla - '
'http://www.enigmail.net/\r\n\r\niEYEARECAAYFAlBhm3oACgkQhmBj'
'z394AnmMnQCcC+6tWcqE1dPQmIdRbLXgKGVp\r\nEeUAn2OqtaXaXaQV7rx+'
'SmOldmSzcFw4\r\n=OEJv\r\n-----END PGP SIGNATURE-----\r\n'))
self.assertEqual(
contents,
u"This is a test message\r\nNon-ascii chars: Hofm\xfchlgasse\r\n"
u"\n-- \ndevel mailing list\[email protected]\n"
u"https://admin.fedoraproject.org/mailman/listinfo/devel\n"
)
def test_attachment_4(self):
with open(get_test_file("attachment-4.txt")) as email_file:
msg = message_from_file(email_file, policy=policy.SMTP)
scrubber = Scrubber(msg)
contents, attachments = scrubber.scrub()
self.assertEqual(len(attachments), 2)
# HTML part
self._check_html_attachment(
attachments[0], (3, "attachment.html", "text/html", "iso-8859-1"))
self.assertEqual(len(attachments[0][4]), 113)
# text attachment
self.assertEqual(attachments[1][0:4],
(4, "todo-déjeuner.txt", "text/plain", "utf-8"))
self.assertEqual(len(attachments[1][4]), 110)
# Scrubbed content
self.assertEqual(
contents, 'This is a test, HTML message with '
'accented letters : \xe9 \xe8 \xe7 \xe0.\nAnd an '
'attachment with an accented filename\n\n\n\n\n')