From 8ca0a0a2d8cf70fc2d644aea41030c8dc3d81035 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Tom=C3=A1=C5=A1=20Hrn=C4=8Diar?= Date: Wed, 7 Jun 2023 22:32:30 +0200 Subject: [PATCH] Update to 3.11.4 --- 00399-cve-2023-24329.patch | 229 ------------------------------------- python3.11.spec | 21 +--- sources | 4 +- 3 files changed, 8 insertions(+), 246 deletions(-) delete mode 100644 00399-cve-2023-24329.patch diff --git a/00399-cve-2023-24329.patch b/00399-cve-2023-24329.patch deleted file mode 100644 index e7d5159..0000000 --- a/00399-cve-2023-24329.patch +++ /dev/null @@ -1,229 +0,0 @@ -From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001 -From: "Miss Islington (bot)" - <31488909+miss-islington@users.noreply.github.com> -Date: Wed, 17 May 2023 14:41:25 -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). - ---------- - -(cherry picked from commit 2f630e1ce18ad2e07428296532a68b11dc66ad10) - -Co-authored-by: Illia Volochii -Co-authored-by: Gregory P. Smith [Google] ---- - Doc/library/urllib.parse.rst | 46 +++++++++++++- - Lib/test/test_urlparse.py | 61 ++++++++++++++++++- - Lib/urllib/parse.py | 12 ++++ - ...-03-07-20-59-17.gh-issue-102153.14CLSZ.rst | 3 + - 4 files changed, 119 insertions(+), 3 deletions(-) - create mode 100644 Misc/NEWS.d/next/Security/2023-03-07-20-59-17.gh-issue-102153.14CLSZ.rst - -diff --git a/Doc/library/urllib.parse.rst b/Doc/library/urllib.parse.rst -index 96b3965107..a326e82e30 100644 ---- a/Doc/library/urllib.parse.rst -+++ b/Doc/library/urllib.parse.rst -@@ -159,6 +159,10 @@ or on combining URL components into a URL string. - ParseResult(scheme='http', netloc='www.cwi.nl:80', path='/%7Eguido/Python.html', - params='', query='', fragment='') - -+ .. warning:: -+ -+ :func:`urlparse` does not perform validation. See :ref:`URL parsing -+ security ` for details. - - .. versionchanged:: 3.2 - Added IPv6 URL parsing capabilities. -@@ -324,8 +328,14 @@ or on combining URL components into a URL string. - ``#``, ``@``, or ``:`` will raise a :exc:`ValueError`. If the URL is - decomposed before parsing, no error will be raised. - -- Following the `WHATWG spec`_ that updates RFC 3986, ASCII newline -- ``\n``, ``\r`` and tab ``\t`` characters are stripped from the URL. -+ Following some of the `WHATWG spec`_ that updates RFC 3986, leading C0 -+ control and space characters are stripped from the URL. ``\n``, -+ ``\r`` and tab ``\t`` characters are removed from the URL at any position. -+ -+ .. warning:: -+ -+ :func:`urlsplit` does not perform validation. See :ref:`URL parsing -+ security ` for details. - - .. versionchanged:: 3.6 - Out-of-range port numbers now raise :exc:`ValueError`, instead of -@@ -338,6 +348,9 @@ or on combining URL components into a URL string. - .. versionchanged:: 3.10 - ASCII newline and tab characters are stripped from the URL. - -+ .. versionchanged:: 3.11.4 -+ Leading WHATWG C0 control and space characters are stripped from the URL. -+ - .. _WHATWG spec: https://url.spec.whatwg.org/#concept-basic-url-parser - - .. function:: urlunsplit(parts) -@@ -414,6 +427,35 @@ or on combining URL components into a URL string. - or ``scheme://host/path``). If *url* is not a wrapped URL, it is returned - without changes. - -+.. _url-parsing-security: -+ -+URL parsing security -+-------------------- -+ -+The :func:`urlsplit` and :func:`urlparse` APIs do not perform **validation** of -+inputs. They may not raise errors on inputs that other applications consider -+invalid. They may also succeed on some inputs that might not be considered -+URLs elsewhere. Their purpose is for practical functionality rather than -+purity. -+ -+Instead of raising an exception on unusual input, they may instead return some -+component parts as empty strings. Or components may contain more than perhaps -+they should. -+ -+We recommend that users of these APIs where the values may be used anywhere -+with security implications code defensively. Do some verification within your -+code before trusting a returned component part. Does that ``scheme`` make -+sense? Is that a sensible ``path``? Is there anything strange about that -+``hostname``? etc. -+ -+What constitutes a URL is not universally well defined. Different applications -+have different needs and desired constraints. For instance the living `WHATWG -+spec`_ describes what user facing web clients such as a web browser require. -+While :rfc:`3986` is more general. These functions incorporate some aspects of -+both, but cannot be claimed compliant with either. The APIs and existing user -+code with expectations on specific behaviors predate both standards leading us -+to be very cautious about making API behavior changes. -+ - .. _parsing-ascii-encoded-bytes: - - Parsing ASCII Encoded Bytes -diff --git a/Lib/test/test_urlparse.py b/Lib/test/test_urlparse.py -index b426110723..40f13d631c 100644 ---- a/Lib/test/test_urlparse.py -+++ b/Lib/test/test_urlparse.py -@@ -649,6 +649,65 @@ def test_urlsplit_remove_unsafe_bytes(self): - self.assertEqual(p.scheme, "http") - self.assertEqual(p.geturl(), "http://www.python.org/javascript:alert('msg')/?query=something#fragment") - -+ 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): -@@ -656,7 +715,7 @@ def test_attributes_bad_port(self): - for port in ("foo", "1.5", "-1", "0x10", "-0", "1_1", " 1", "1 ", "६"): - with self.subTest(bytes=bytes, parse=parse, port=port): - netloc = "www.example.net:" + port -- url = "http://" + netloc -+ url = "http://" + netloc + "/" - if bytes: - if netloc.isascii() and port.isascii(): - netloc = netloc.encode("ascii") -diff --git a/Lib/urllib/parse.py b/Lib/urllib/parse.py -index 69631cbb81..4f06fd509e 100644 ---- a/Lib/urllib/parse.py -+++ b/Lib/urllib/parse.py -@@ -25,6 +25,10 @@ - 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. - """ - - from collections import namedtuple -@@ -79,6 +83,10 @@ - '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 ' -+ - # Unsafe bytes to be removed per WHATWG spec - _UNSAFE_URL_BYTES_TO_REMOVE = ['\t', '\r', '\n'] - -@@ -452,6 +460,10 @@ def urlsplit(url, scheme='', allow_fragments=True): - """ - - 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) - - for b in _UNSAFE_URL_BYTES_TO_REMOVE: - url = url.replace(b, "") -diff --git a/Misc/NEWS.d/next/Security/2023-03-07-20-59-17.gh-issue-102153.14CLSZ.rst b/Misc/NEWS.d/next/Security/2023-03-07-20-59-17.gh-issue-102153.14CLSZ.rst -new file mode 100644 -index 0000000000..e57ac4ed3a ---- /dev/null -+++ b/Misc/NEWS.d/next/Security/2023-03-07-20-59-17.gh-issue-102153.14CLSZ.rst -@@ -0,0 +1,3 @@ -+:func:`urllib.parse.urlsplit` now strips leading C0 control and space -+characters following the specification for URLs defined by WHATWG in -+response to CVE-2023-24329. Patch by Illia Volochii. diff --git a/python3.11.spec b/python3.11.spec index aa37a07..83123a7 100644 --- a/python3.11.spec +++ b/python3.11.spec @@ -13,11 +13,11 @@ URL: https://www.python.org/ # WARNING When rebasing to a new Python version, # remember to update the python3-docs package as well -%global general_version %{pybasever}.3 +%global general_version %{pybasever}.4 #global prerel ... %global upstream_version %{general_version}%{?prerel} Version: %{general_version}%{?prerel:~%{prerel}} -Release: 2%{?dist} +Release: 1%{?dist} License: Python-2.0.1 @@ -67,7 +67,7 @@ License: Python-2.0.1 # If the rpmwheels condition is disabled, we use the bundled wheel packages # from Python with the versions below. # This needs to be manually updated when we update Python. -%global pip_version 22.3.1 +%global pip_version 23.1.2 %global setuptools_version 65.5.0 # Expensive optimizations (mainly, profile-guided optimizations) @@ -315,18 +315,6 @@ Patch251: 00251-change-user-install-location.patch # https://github.com/GrahamDumpleton/mod_wsgi/issues/730 Patch371: 00371-revert-bpo-1596321-fix-threading-_shutdown-for-the-main-thread-gh-28549-gh-28589.patch -# 00399 # 62614243969f1c717a02a1c65e55ef173ad9a6dd -# 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). -# -# --------- -Patch399: 00399-cve-2023-24329.patch - # (New patches go here ^^^) # # When adding new patches to "python" and "python3" in Fedora, EL, etc., @@ -1615,6 +1603,9 @@ CheckPython optimized # ====================================================== %changelog +* Wed Jun 07 2023 Tomáš Hrnčiar - 3.11.4-1 +- Update to 3.11.4 + * Wed May 24 2023 Lumír Balhar - 3.11.3-2 - Fix for CVE-2023-24329 diff --git a/sources b/sources index ecff347..6b8930e 100644 --- a/sources +++ b/sources @@ -1,2 +1,2 @@ -SHA512 (Python-3.11.3.tar.xz) = a3bba4b69322a47bfeefe42ba0fd7331b5b67fd2ab41441e2219d16ef8c6f307f1a48977afd073c18cfd24ec6cb1bfe0c4bb4b273031eb524dc7e9fb5fbcc3b6 -SHA512 (Python-3.11.3.tar.xz.asc) = 34bfb6e74e2bbec15bf3f653e32a3d705961b5f724e3f4713cf9b6b530f9c9e7e94f5cf855798bdf9763235b97a60ec9ad554d24cdc793e21a0c39540b5818d8 +SHA512 (Python-3.11.4.tar.xz) = 7eb14fecbf60824d10c22a9057584c3a142c2866f4af6caa2525c10c8bcb24e6e7afb32a44a0e118df0a2b2543d578c3b422ffd4a5fa317dfe6ea371cc7ee1ee +SHA512 (Python-3.11.4.tar.xz.asc) = 8ee82bf116b2cc7407e260eccf53e7fee4d7497165d0b9c3e59931c73f3b419bc0299b459eee9544a6e51e323ff0a6aa07827efd89f9c320b54556feeea04a78