Fixed #22971 -- Properly parsed RFC 2388 encoded headers
Thanks homm for the report, Cea Stapleton for patch improvements and Ian Cordasco, Christian Schmitt and Tim Graham for the review.
This commit is contained in:
parent
7244a8d0ae
commit
b42e5ca058
|
@ -16,6 +16,7 @@ from django.core.exceptions import SuspiciousMultipartForm
|
|||
from django.utils.datastructures import MultiValueDict
|
||||
from django.utils.encoding import force_text
|
||||
from django.utils import six
|
||||
from django.utils.six.moves.urllib.parse import unquote
|
||||
from django.utils.text import unescape_entities
|
||||
from django.core.files.uploadhandler import StopUpload, SkipFile, StopFutureHandlers
|
||||
|
||||
|
@ -631,8 +632,20 @@ def parse_header(line):
|
|||
for p in plist:
|
||||
i = p.find(b'=')
|
||||
if i >= 0:
|
||||
has_encoding = False
|
||||
name = p[:i].strip().lower().decode('ascii')
|
||||
if name.endswith('*'):
|
||||
# Lang/encoding embedded in the value (like "filename*=UTF-8''file.ext")
|
||||
# http://tools.ietf.org/html/rfc2231#section-4
|
||||
name = name[:-1]
|
||||
has_encoding = True
|
||||
value = p[i + 1:].strip()
|
||||
if has_encoding:
|
||||
encoding, lang, value = value.split(b"'")
|
||||
if six.PY3:
|
||||
value = unquote(value.decode(), encoding=encoding.decode())
|
||||
else:
|
||||
value = unquote(value).decode(encoding)
|
||||
if len(value) >= 2 and value[:1] == value[-1:] == b'"':
|
||||
value = value[1:-1]
|
||||
value = value.replace(b'\\\\', b'\\').replace(b'\\"', b'"')
|
||||
|
|
|
@ -12,10 +12,11 @@ import unittest
|
|||
|
||||
from django.core.files import temp as tempfile
|
||||
from django.core.files.uploadedfile import SimpleUploadedFile
|
||||
from django.http.multipartparser import MultiPartParser
|
||||
from django.http.multipartparser import MultiPartParser, parse_header
|
||||
from django.test import TestCase, client
|
||||
from django.test import override_settings
|
||||
from django.utils.encoding import force_bytes
|
||||
from django.utils.http import urlquote
|
||||
from django.utils.six import StringIO
|
||||
|
||||
from . import uploadhandler
|
||||
|
@ -120,6 +121,56 @@ class FileUploadTests(TestCase):
|
|||
|
||||
self.assertEqual(response.status_code, 200)
|
||||
|
||||
def test_unicode_file_name_rfc2231(self):
|
||||
"""
|
||||
Test receiving file upload when filename is encoded with RFC2231
|
||||
(#22971).
|
||||
"""
|
||||
payload = client.FakePayload()
|
||||
payload.write('\r\n'.join([
|
||||
'--' + client.BOUNDARY,
|
||||
'Content-Disposition: form-data; name="file_unicode"; filename*=UTF-8\'\'%s' % urlquote(UNICODE_FILENAME),
|
||||
'Content-Type: application/octet-stream',
|
||||
'',
|
||||
'You got pwnd.\r\n',
|
||||
'\r\n--' + client.BOUNDARY + '--\r\n'
|
||||
]))
|
||||
|
||||
r = {
|
||||
'CONTENT_LENGTH': len(payload),
|
||||
'CONTENT_TYPE': client.MULTIPART_CONTENT,
|
||||
'PATH_INFO': "/unicode_name/",
|
||||
'REQUEST_METHOD': 'POST',
|
||||
'wsgi.input': payload,
|
||||
}
|
||||
response = self.client.request(**r)
|
||||
self.assertEqual(response.status_code, 200)
|
||||
|
||||
def test_unicode_name_rfc2231(self):
|
||||
"""
|
||||
Test receiving file upload when filename is encoded with RFC2231
|
||||
(#22971).
|
||||
"""
|
||||
payload = client.FakePayload()
|
||||
payload.write('\r\n'.join([
|
||||
'--' + client.BOUNDARY,
|
||||
'Content-Disposition: form-data; name*=UTF-8\'\'file_unicode; filename*=UTF-8\'\'%s' % urlquote(UNICODE_FILENAME),
|
||||
'Content-Type: application/octet-stream',
|
||||
'',
|
||||
'You got pwnd.\r\n',
|
||||
'\r\n--' + client.BOUNDARY + '--\r\n'
|
||||
]))
|
||||
|
||||
r = {
|
||||
'CONTENT_LENGTH': len(payload),
|
||||
'CONTENT_TYPE': client.MULTIPART_CONTENT,
|
||||
'PATH_INFO': "/unicode_name/",
|
||||
'REQUEST_METHOD': 'POST',
|
||||
'wsgi.input': payload,
|
||||
}
|
||||
response = self.client.request(**r)
|
||||
self.assertEqual(response.status_code, 200)
|
||||
|
||||
def test_dangerous_file_names(self):
|
||||
"""Uploaded file names should be sanitized before ever reaching the view."""
|
||||
# This test simulates possible directory traversal attacks by a
|
||||
|
@ -483,3 +534,16 @@ class MultiParserTests(unittest.TestCase):
|
|||
'CONTENT_TYPE': 'multipart/form-data; boundary=_foo',
|
||||
'CONTENT_LENGTH': '1'
|
||||
}, StringIO('x'), [], 'utf-8')
|
||||
|
||||
def test_rfc2231_parsing(self):
|
||||
test_data = (
|
||||
(b"Content-Type: application/x-stuff; title*=us-ascii'en-us'This%20is%20%2A%2A%2Afun%2A%2A%2A",
|
||||
"This is ***fun***"),
|
||||
(b"Content-Type: application/x-stuff; title*=UTF-8''foo-%c3%a4.html",
|
||||
"foo-ä.html"),
|
||||
(b"Content-Type: application/x-stuff; title*=iso-8859-1''foo-%E4.html",
|
||||
"foo-ä.html"),
|
||||
)
|
||||
for raw_line, expected_title in test_data:
|
||||
parsed = parse_header(raw_line)
|
||||
self.assertEqual(parsed[1]['title'], expected_title)
|
||||
|
|
Loading…
Reference in New Issue