From ba7a1989c7231a733e3c04417cc941d026066964 Mon Sep 17 00:00:00 2001
From: "Miss Islington (bot)"
<31488909+miss-islington@users.noreply.github.com>
Date: Mon, 22 May 2023 03:42:37 -0700
Subject: [PATCH] 00399: CVE-2023-24329
gh-102153: Start stripping C0 control and space chars in `urlsplit` (GH-102508)
`urllib.parse.urlsplit` has already been respecting the WHATWG spec a bit GH-25595.
This adds more sanitizing to respect the "Remove any leading C0 control or space from input" [rule](https://url.spec.whatwg.org/GH-url-parsing:~:text=Remove%20any%20leading%20and%20trailing%20C0%20control%20or%20space%20from%20input.) in response to [CVE-2023-24329](https://nvd.nist.gov/vuln/detail/CVE-2023-24329).
Backported from Python 3.12
(cherry picked from commit f48a96a28012d28ae37a2f4587a780a5eb779946)
Co-authored-by: Illia Volochii <illia.volochii@gmail.com>
Co-authored-by: Gregory P. Smith [Google] <greg@krypto.org>
---
Lib/test/test_urlparse.py | 61 ++++++++++++++++++++++++++++++++++++++-
Lib/urllib/parse.py | 12 ++++++++
2 files changed, 72 insertions(+), 1 deletion(-)
diff --git a/Lib/test/test_urlparse.py b/Lib/test/test_urlparse.py
index 68f633c..8dd9795 100644
--- a/Lib/test/test_urlparse.py
+++ b/Lib/test/test_urlparse.py
@@ -624,6 +624,65 @@ class UrlParseTestCase(unittest.TestCase):
with self.assertRaisesRegex(ValueError, "out of range"):
p.port
+ def test_urlsplit_strip_url(self):
+ noise = bytes(range(0, 0x20 + 1))
+ base_url = "http://User:Pass@www.python.org:080/doc/?query=yes#frag"
+
+ url = noise.decode("utf-8") + base_url
+ p = urllib.parse.urlsplit(url)
+ self.assertEqual(p.scheme, "http")
+ self.assertEqual(p.netloc, "User:Pass@www.python.org:080")
+ self.assertEqual(p.path, "/doc/")
+ self.assertEqual(p.query, "query=yes")
+ self.assertEqual(p.fragment, "frag")
+ self.assertEqual(p.username, "User")
+ self.assertEqual(p.password, "Pass")
+ self.assertEqual(p.hostname, "www.python.org")
+ self.assertEqual(p.port, 80)
+ self.assertEqual(p.geturl(), base_url)
+
+ url = noise + base_url.encode("utf-8")
+ p = urllib.parse.urlsplit(url)
+ self.assertEqual(p.scheme, b"http")
+ self.assertEqual(p.netloc, b"User:Pass@www.python.org:080")
+ self.assertEqual(p.path, b"/doc/")
+ self.assertEqual(p.query, b"query=yes")
+ self.assertEqual(p.fragment, b"frag")
+ self.assertEqual(p.username, b"User")
+ self.assertEqual(p.password, b"Pass")
+ self.assertEqual(p.hostname, b"www.python.org")
+ self.assertEqual(p.port, 80)
+ self.assertEqual(p.geturl(), base_url.encode("utf-8"))
+
+ # Test that trailing space is preserved as some applications rely on
+ # this within query strings.
+ query_spaces_url = "https://www.python.org:88/doc/?query= "
+ p = urllib.parse.urlsplit(noise.decode("utf-8") + query_spaces_url)
+ self.assertEqual(p.scheme, "https")
+ self.assertEqual(p.netloc, "www.python.org:88")
+ self.assertEqual(p.path, "/doc/")
+ self.assertEqual(p.query, "query= ")
+ self.assertEqual(p.port, 88)
+ self.assertEqual(p.geturl(), query_spaces_url)
+
+ p = urllib.parse.urlsplit("www.pypi.org ")
+ # That "hostname" gets considered a "path" due to the
+ # trailing space and our existing logic... YUCK...
+ # and re-assembles via geturl aka unurlsplit into the original.
+ # django.core.validators.URLValidator (at least through v3.2) relies on
+ # this, for better or worse, to catch it in a ValidationError via its
+ # regular expressions.
+ # Here we test the basic round trip concept of such a trailing space.
+ self.assertEqual(urllib.parse.urlunsplit(p), "www.pypi.org ")
+
+ # with scheme as cache-key
+ url = "//www.python.org/"
+ scheme = noise.decode("utf-8") + "https" + noise.decode("utf-8")
+ for _ in range(2):
+ p = urllib.parse.urlsplit(url, scheme=scheme)
+ self.assertEqual(p.scheme, "https")
+ self.assertEqual(p.geturl(), "https://www.python.org/")
+
def test_attributes_bad_port(self):
"""Check handling of invalid ports."""
for bytes in (False, True):
@@ -631,7 +690,7 @@ class UrlParseTestCase(unittest.TestCase):
for port in ("foo", "1.5", "-1", "0x10"):
with self.subTest(bytes=bytes, parse=parse, port=port):
netloc = "www.example.net:" + port
- url = "http://" + netloc
+ url = "http://" + netloc + "/"
if bytes:
netloc = netloc.encode("ascii")
url = url.encode("ascii")
diff --git a/Lib/urllib/parse.py b/Lib/urllib/parse.py
index fa8827a..6a470b2 100644
--- a/Lib/urllib/parse.py
+++ b/Lib/urllib/parse.py
@@ -25,6 +25,10 @@ currently not entirely compliant with this RFC due to defacto
scenarios for parsing, and for backward compatibility purposes, some
parsing quirks from older RFCs are retained. The testcases in
test_urlparse.py provides a good indicator of parsing behavior.
+
+The WHATWG URL Parser spec should also be considered. We are not compliant with
+it either due to existing user code API behavior expectations (Hyrum's Law).
+It serves as a useful guide when making changes.
"""
import re
@@ -76,6 +80,10 @@ scheme_chars = ('abcdefghijklmnopqrstuvwxyz'
'0123456789'
'+-.')
+# Leading and trailing C0 control and space to be stripped per WHATWG spec.
+# == "".join([chr(i) for i in range(0, 0x20 + 1)])
+_WHATWG_C0_CONTROL_OR_SPACE = '\x00\x01\x02\x03\x04\x05\x06\x07\x08\t\n\x0b\x0c\r\x0e\x0f\x10\x11\x12\x13\x14\x15\x16\x17\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f '
+
# XXX: Consider replacing with functools.lru_cache
MAX_CACHE_SIZE = 20
_parse_cache = {}
@@ -416,6 +424,10 @@ def urlsplit(url, scheme='', allow_fragments=True):
Note that we don't break the components up in smaller bits
(e.g. netloc is a single string) and we don't expand % escapes."""
url, scheme, _coerce_result = _coerce_args(url, scheme)
+ # Only lstrip url as some applications rely on preserving trailing space.
+ # (https://url.spec.whatwg.org/#concept-basic-url-parser would strip both)
+ url = url.lstrip(_WHATWG_C0_CONTROL_OR_SPACE)
+ scheme = scheme.strip(_WHATWG_C0_CONTROL_OR_SPACE)
allow_fragments = bool(allow_fragments)
key = url, scheme, allow_fragments, type(url), type(scheme)
cached = _parse_cache.get(key, None)
--
2.40.1