c8-stream-3.8
imports/c8-stream-3.8/python38-3.8.17-2.module+el8.9.0+19642+a12b4af6
MSVSphere Packaging Team
11 months ago
parent
5afd777359
commit
86b2f9c6dc
@ -1 +1 @@
|
||||
SOURCES/Python-3.8.16-noexe.tar.xz
|
||||
SOURCES/Python-3.8.17-noexe.tar.xz
|
||||
|
||||
@ -1 +1 @@
|
||||
ec97523b167d5b0e915b37e58f03da6384b15caa SOURCES/Python-3.8.16-noexe.tar.xz
|
||||
5ecdca78a141bb6d7e13732920886affd7338fca SOURCES/Python-3.8.17-noexe.tar.xz
|
||||
|
||||
@ -0,0 +1,357 @@
|
||||
From f36519078bde3cce4328c03fffccb846121fb5bc Mon Sep 17 00:00:00 2001
|
||||
From: Petr Viktorin <encukou@gmail.com>
|
||||
Date: Wed, 9 Aug 2023 20:23:03 +0200
|
||||
Subject: [PATCH] Fix symlink handling for tarfile.data_filter
|
||||
|
||||
---
|
||||
Doc/library/tarfile.rst | 5 +++++
|
||||
Lib/tarfile.py | 9 ++++++++-
|
||||
Lib/test/test_tarfile.py | 26 ++++++++++++++++++++++++--
|
||||
3 files changed, 37 insertions(+), 3 deletions(-)
|
||||
|
||||
diff --git a/Doc/library/tarfile.rst b/Doc/library/tarfile.rst
|
||||
index 00f3070324e..e0511bfeb64 100644
|
||||
--- a/Doc/library/tarfile.rst
|
||||
+++ b/Doc/library/tarfile.rst
|
||||
@@ -740,6 +740,11 @@ A ``TarInfo`` object has the following public data attributes:
|
||||
Name of the target file name, which is only present in :class:`TarInfo` objects
|
||||
of type :const:`LNKTYPE` and :const:`SYMTYPE`.
|
||||
|
||||
+ For symbolic links (``SYMTYPE``), the linkname is relative to the directory
|
||||
+ that contains the link.
|
||||
+ For hard links (``LNKTYPE``), the linkname is relative to the root of
|
||||
+ the archive.
|
||||
+
|
||||
|
||||
.. attribute:: TarInfo.uid
|
||||
:type: int
|
||||
diff --git a/Lib/tarfile.py b/Lib/tarfile.py
|
||||
index df4e41f7a0d..d62323715b4 100755
|
||||
--- a/Lib/tarfile.py
|
||||
+++ b/Lib/tarfile.py
|
||||
@@ -802,7 +802,14 @@ def _get_filtered_attrs(member, dest_path, for_data=True):
|
||||
if member.islnk() or member.issym():
|
||||
if os.path.isabs(member.linkname):
|
||||
raise AbsoluteLinkError(member)
|
||||
- target_path = os.path.realpath(os.path.join(dest_path, member.linkname))
|
||||
+ if member.issym():
|
||||
+ target_path = os.path.join(dest_path,
|
||||
+ os.path.dirname(name),
|
||||
+ member.linkname)
|
||||
+ else:
|
||||
+ target_path = os.path.join(dest_path,
|
||||
+ member.linkname)
|
||||
+ target_path = os.path.realpath(target_path)
|
||||
if os.path.commonpath([target_path, dest_path]) != dest_path:
|
||||
raise LinkOutsideDestinationError(member, target_path)
|
||||
return new_attrs
|
||||
diff --git a/Lib/test/test_tarfile.py b/Lib/test/test_tarfile.py
|
||||
index 2eda7fc4cea..79fc35c2895 100644
|
||||
--- a/Lib/test/test_tarfile.py
|
||||
+++ b/Lib/test/test_tarfile.py
|
||||
@@ -3337,10 +3337,12 @@ def __exit__(self, *exc):
|
||||
self.bio = None
|
||||
|
||||
def add(self, name, *, type=None, symlink_to=None, hardlink_to=None,
|
||||
- mode=None, **kwargs):
|
||||
+ mode=None, size=None, **kwargs):
|
||||
"""Add a member to the test archive. Call within `with`."""
|
||||
name = str(name)
|
||||
tarinfo = tarfile.TarInfo(name).replace(**kwargs)
|
||||
+ if size is not None:
|
||||
+ tarinfo.size = size
|
||||
if mode:
|
||||
tarinfo.mode = _filemode_to_int(mode)
|
||||
if symlink_to is not None:
|
||||
@@ -3416,7 +3418,8 @@ def check_context(self, tar, filter):
|
||||
raise self.raised_exception
|
||||
self.assertEqual(self.expected_paths, set())
|
||||
|
||||
- def expect_file(self, name, type=None, symlink_to=None, mode=None):
|
||||
+ def expect_file(self, name, type=None, symlink_to=None, mode=None,
|
||||
+ size=None):
|
||||
"""Check a single file. See check_context."""
|
||||
if self.raised_exception:
|
||||
raise self.raised_exception
|
||||
@@ -3445,6 +3448,8 @@ def expect_file(self, name, type=None, symlink_to=None, mode=None):
|
||||
self.assertTrue(path.is_fifo())
|
||||
else:
|
||||
raise NotImplementedError(type)
|
||||
+ if size is not None:
|
||||
+ self.assertEqual(path.stat().st_size, size)
|
||||
for parent in path.parents:
|
||||
self.expected_paths.discard(parent)
|
||||
|
||||
@@ -3649,6 +3654,22 @@ def test_sly_relative2(self):
|
||||
+ """['"].*moo['"], which is outside the """
|
||||
+ "destination")
|
||||
|
||||
+ def test_deep_symlink(self):
|
||||
+ with ArchiveMaker() as arc:
|
||||
+ arc.add('targetdir/target', size=3)
|
||||
+ arc.add('linkdir/hardlink', hardlink_to='targetdir/target')
|
||||
+ arc.add('linkdir/symlink', symlink_to='../targetdir/target')
|
||||
+
|
||||
+ for filter in 'tar', 'data', 'fully_trusted':
|
||||
+ with self.check_context(arc.open(), filter):
|
||||
+ self.expect_file('targetdir/target', size=3)
|
||||
+ self.expect_file('linkdir/hardlink', size=3)
|
||||
+ if support.can_symlink():
|
||||
+ self.expect_file('linkdir/symlink', size=3,
|
||||
+ symlink_to='../targetdir/target')
|
||||
+ else:
|
||||
+ self.expect_file('linkdir/symlink', size=3)
|
||||
+
|
||||
def test_modes(self):
|
||||
# Test how file modes are extracted
|
||||
# (Note that the modes are ignored on platforms without working chmod)
|
||||
--
|
||||
2.41.0
|
||||
|
||||
From dc84087083c5ad99a5016e8349c96d9654a08f46 Mon Sep 17 00:00:00 2001
|
||||
From: Petr Viktorin <encukou@gmail.com>
|
||||
Date: Mon, 6 Mar 2023 17:24:24 +0100
|
||||
Subject: [PATCH 2/2] CVE-2007-4559, PEP-706: Add filters for tarfile
|
||||
extraction (downstream)
|
||||
|
||||
Add and test RHEL-specific ways of configuring the default behavior: environment
|
||||
variable and config file.
|
||||
---
|
||||
Lib/tarfile.py | 42 +++++++++++++
|
||||
Lib/test/test_shutil.py | 3 +-
|
||||
Lib/test/test_tarfile.py | 124 ++++++++++++++++++++++++++++++++++++++-
|
||||
3 files changed, 165 insertions(+), 4 deletions(-)
|
||||
|
||||
diff --git a/Lib/tarfile.py b/Lib/tarfile.py
|
||||
index 5291622ab8e..12ab00d748a 100755
|
||||
--- a/Lib/tarfile.py
|
||||
+++ b/Lib/tarfile.py
|
||||
@@ -72,6 +72,13 @@ __all__ = ["TarFile", "TarInfo", "is_tarfile", "TarError", "ReadError",
|
||||
"ENCODING", "USTAR_FORMAT", "GNU_FORMAT", "PAX_FORMAT",
|
||||
"DEFAULT_FORMAT", "open"]
|
||||
|
||||
+# If true, use the safer (but backwards-incompatible) 'tar' extraction filter,
|
||||
+# rather than 'fully_trusted', by default.
|
||||
+# The emitted warning is changed to match.
|
||||
+_RH_SAFER_DEFAULT = True
|
||||
+
|
||||
+# System-wide configuration file
|
||||
+_CONFIG_FILENAME = '/etc/python/tarfile.cfg'
|
||||
|
||||
#---------------------------------------------------------
|
||||
# tar constants
|
||||
@@ -2188,6 +2195,41 @@ class TarFile(object):
|
||||
if filter is None:
|
||||
filter = self.extraction_filter
|
||||
if filter is None:
|
||||
+ name = os.environ.get('PYTHON_TARFILE_EXTRACTION_FILTER')
|
||||
+ if name is None:
|
||||
+ try:
|
||||
+ file = bltn_open(_CONFIG_FILENAME)
|
||||
+ except FileNotFoundError:
|
||||
+ pass
|
||||
+ else:
|
||||
+ import configparser
|
||||
+ conf = configparser.ConfigParser(
|
||||
+ interpolation=None,
|
||||
+ comment_prefixes=('#', ),
|
||||
+ )
|
||||
+ with file:
|
||||
+ conf.read_file(file)
|
||||
+ name = conf.get('tarfile',
|
||||
+ 'PYTHON_TARFILE_EXTRACTION_FILTER',
|
||||
+ fallback='')
|
||||
+ if name:
|
||||
+ try:
|
||||
+ filter = _NAMED_FILTERS[name]
|
||||
+ except KeyError:
|
||||
+ raise ValueError(f"filter {filter!r} not found") from None
|
||||
+ self.extraction_filter = filter
|
||||
+ return filter
|
||||
+ if _RH_SAFER_DEFAULT:
|
||||
+ warnings.warn(
|
||||
+ 'The default behavior of tarfile extraction has been '
|
||||
+ + 'changed to disallow common exploits '
|
||||
+ + '(including CVE-2007-4559). '
|
||||
+ + 'By default, absolute/parent paths are disallowed '
|
||||
+ + 'and some mode bits are cleared. '
|
||||
+ + 'See https://access.redhat.com/articles/7004769 '
|
||||
+ + 'for more details.',
|
||||
+ RuntimeWarning)
|
||||
+ return tar_filter
|
||||
return fully_trusted_filter
|
||||
if isinstance(filter, str):
|
||||
raise TypeError(
|
||||
diff --git a/Lib/test/test_shutil.py b/Lib/test/test_shutil.py
|
||||
index 5cef59ea9c6..73fffe0fd33 100644
|
||||
--- a/Lib/test/test_shutil.py
|
||||
+++ b/Lib/test/test_shutil.py
|
||||
@@ -1494,7 +1494,8 @@ class TestShutil(unittest.TestCase):
|
||||
def check_unpack_tarball(self, format):
|
||||
self.check_unpack_archive(format, filter='fully_trusted')
|
||||
self.check_unpack_archive(format, filter='data')
|
||||
- with support.check_no_warnings(self):
|
||||
+ with support.check_warnings(
|
||||
+ ('.*CVE-2007-4559', RuntimeWarning)):
|
||||
self.check_unpack_archive(format)
|
||||
|
||||
def test_unpack_archive_tar(self):
|
||||
diff --git a/Lib/test/test_tarfile.py b/Lib/test/test_tarfile.py
|
||||
index 03be10b1fee..15df6a9ced6 100644
|
||||
--- a/Lib/test/test_tarfile.py
|
||||
+++ b/Lib/test/test_tarfile.py
|
||||
@@ -2,7 +2,7 @@
|
||||
import os
|
||||
import io
|
||||
from hashlib import sha256
|
||||
-from contextlib import contextmanager
|
||||
+from contextlib import contextmanager, ExitStack
|
||||
from random import Random
|
||||
import pathlib
|
||||
import shutil
|
||||
@@ -2744,7 +2744,11 @@ class NoneInfoExtractTests(ReadTest):
|
||||
tar = tarfile.open(tarname, mode='r', encoding="iso8859-1")
|
||||
cls.control_dir = pathlib.Path(TEMPDIR) / "extractall_ctrl"
|
||||
tar.errorlevel = 0
|
||||
- tar.extractall(cls.control_dir, filter=cls.extraction_filter)
|
||||
+ with ExitStack() as cm:
|
||||
+ if cls.extraction_filter is None:
|
||||
+ cm.enter_context(warnings.catch_warnings())
|
||||
+ warnings.simplefilter(action="ignore", category=RuntimeWarning)
|
||||
+ tar.extractall(cls.control_dir, filter=cls.extraction_filter)
|
||||
tar.close()
|
||||
cls.control_paths = set(
|
||||
p.relative_to(cls.control_dir)
|
||||
@@ -3407,7 +3411,8 @@ class TestExtractionFilters(unittest.TestCase):
|
||||
"""Ensure the default filter does not warn (like in 3.12)"""
|
||||
with ArchiveMaker() as arc:
|
||||
arc.add('foo')
|
||||
- with support.check_no_warnings(self):
|
||||
+ with support.check_warnings(
|
||||
+ ('.*CVE-2007-4559', RuntimeWarning)):
|
||||
with self.check_context(arc.open(), None):
|
||||
self.expect_file('foo')
|
||||
|
||||
@@ -3577,6 +3582,119 @@ class TestExtractionFilters(unittest.TestCase):
|
||||
self.expect_exception(TypeError) # errorlevel is not int
|
||||
|
||||
|
||||
+ @contextmanager
|
||||
+ def rh_config_context(self, config_lines=None):
|
||||
+ """Set up for testing various ways of overriding the default filter
|
||||
+
|
||||
+ return a triple with:
|
||||
+ - temporary directory
|
||||
+ - EnvironmentVarGuard()
|
||||
+ - a test archive for use with check_* methods below
|
||||
+
|
||||
+ If config_lines is given, write them to the config file. Otherwise
|
||||
+ the config file is missing.
|
||||
+ """
|
||||
+ tempdir = pathlib.Path(TEMPDIR) / 'tmp'
|
||||
+ configfile = tempdir / 'tarfile.cfg'
|
||||
+ with ArchiveMaker() as arc:
|
||||
+ arc.add('good')
|
||||
+ arc.add('ugly', symlink_to='/etc/passwd')
|
||||
+ arc.add('../bad')
|
||||
+ with ExitStack() as cm:
|
||||
+ cm.enter_context(support.temp_dir(tempdir))
|
||||
+ cm.enter_context(support.swap_attr(tarfile, '_CONFIG_FILENAME', str(configfile)))
|
||||
+ env = cm.enter_context(support.EnvironmentVarGuard())
|
||||
+ tar = cm.enter_context(arc.open())
|
||||
+ if config_lines is not None:
|
||||
+ with configfile.open('w') as f:
|
||||
+ for line in config_lines:
|
||||
+ print(line, file=f)
|
||||
+ yield tempdir, env, tar
|
||||
+
|
||||
+ def check_rh_default_behavior(self, tar, tempdir):
|
||||
+ """Check RH default: warn and refuse to extract dangerous files."""
|
||||
+ with ExitStack() as cm:
|
||||
+ cm.enter_context(support.check_warnings(
|
||||
+ ('.*CVE-2007-4559', RuntimeWarning)))
|
||||
+ cm.enter_context(self.assertRaises(tarfile.OutsideDestinationError))
|
||||
+ tar.extractall(tempdir / 'outdir')
|
||||
+
|
||||
+ def check_trusted_default(self, tar, tempdir):
|
||||
+ """Check 'fully_trusted' is configured as the default filter."""
|
||||
+ with support.check_no_warnings(self):
|
||||
+ tar.extractall(tempdir / 'outdir')
|
||||
+ self.assertTrue((tempdir / 'outdir/good').exists())
|
||||
+ self.assertEqual(os.readlink(str(tempdir / 'outdir/ugly')),
|
||||
+ '/etc/passwd')
|
||||
+ self.assertTrue((tempdir / 'bad').exists())
|
||||
+
|
||||
+ def test_rh_default_no_conf(self):
|
||||
+ with self.rh_config_context() as (tempdir, env, tar):
|
||||
+ self.check_rh_default_behavior(tar, tempdir)
|
||||
+
|
||||
+ def test_rh_default_from_file(self):
|
||||
+ lines = ['[tarfile]', 'PYTHON_TARFILE_EXTRACTION_FILTER=fully_trusted']
|
||||
+ with self.rh_config_context(lines) as (tempdir, env, tar):
|
||||
+ self.check_trusted_default(tar, tempdir)
|
||||
+
|
||||
+ def test_rh_empty_config_file(self):
|
||||
+ """Empty config file -> default behavior"""
|
||||
+ lines = []
|
||||
+ with self.rh_config_context(lines) as (tempdir, env, tar):
|
||||
+ self.check_rh_default_behavior(tar, tempdir)
|
||||
+
|
||||
+ def test_empty_config_section(self):
|
||||
+ """Empty section in config file -> default behavior"""
|
||||
+ lines = ['[tarfile]']
|
||||
+ with self.rh_config_context(lines) as (tempdir, env, tar):
|
||||
+ self.check_rh_default_behavior(tar, tempdir)
|
||||
+
|
||||
+ def test_rh_default_empty_config_option(self):
|
||||
+ """Empty option value in config file -> default behavior"""
|
||||
+ lines = ['[tarfile]', 'PYTHON_TARFILE_EXTRACTION_FILTER=']
|
||||
+ with self.rh_config_context(lines) as (tempdir, env, tar):
|
||||
+ self.check_rh_default_behavior(tar, tempdir)
|
||||
+
|
||||
+ def test_bad_config_option(self):
|
||||
+ """Bad option value in config file -> ValueError"""
|
||||
+ lines = ['[tarfile]', 'PYTHON_TARFILE_EXTRACTION_FILTER=unknown!']
|
||||
+ with self.rh_config_context(lines) as (tempdir, env, tar):
|
||||
+ with self.assertRaises(ValueError):
|
||||
+ tar.extractall(tempdir / 'outdir')
|
||||
+
|
||||
+ def test_default_from_envvar(self):
|
||||
+ with self.rh_config_context() as (tempdir, env, tar):
|
||||
+ env['PYTHON_TARFILE_EXTRACTION_FILTER'] = 'fully_trusted'
|
||||
+ self.check_trusted_default(tar, tempdir)
|
||||
+
|
||||
+ def test_empty_envvar(self):
|
||||
+ """Empty env variable -> default behavior"""
|
||||
+ with self.rh_config_context() as (tempdir, env, tar):
|
||||
+ env['PYTHON_TARFILE_EXTRACTION_FILTER'] = ''
|
||||
+ self.check_rh_default_behavior(tar, tempdir)
|
||||
+
|
||||
+ def test_bad_envvar(self):
|
||||
+ with self.rh_config_context() as (tempdir, env, tar):
|
||||
+ env['PYTHON_TARFILE_EXTRACTION_FILTER'] = 'unknown!'
|
||||
+ with self.assertRaises(ValueError):
|
||||
+ tar.extractall(tempdir / 'outdir')
|
||||
+
|
||||
+ def test_envvar_overrides_file(self):
|
||||
+ lines = ['[tarfile]', 'PYTHON_TARFILE_EXTRACTION_FILTER=data']
|
||||
+ with self.rh_config_context(lines) as (tempdir, env, tar):
|
||||
+ env['PYTHON_TARFILE_EXTRACTION_FILTER'] = 'fully_trusted'
|
||||
+ self.check_trusted_default(tar, tempdir)
|
||||
+
|
||||
+ def test_monkeypatch_overrides_envvar(self):
|
||||
+ with self.rh_config_context(None) as (tempdir, env, tar):
|
||||
+ env['PYTHON_TARFILE_EXTRACTION_FILTER'] = 'data'
|
||||
+ with support.swap_attr(
|
||||
+ tarfile.TarFile, 'extraction_filter',
|
||||
+ staticmethod(tarfile.fully_trusted_filter)
|
||||
+ ):
|
||||
+ self.check_trusted_default(tar, tempdir)
|
||||
+
|
||||
+
|
||||
def setUpModule():
|
||||
support.unlink(TEMPDIR)
|
||||
os.makedirs(TEMPDIR)
|
||||
--
|
||||
2.41.0
|
||||
|
||||
@ -1,222 +0,0 @@
|
||||
From 0000000000000000000000000000000000000000 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).
|
||||
|
||||
(cherry picked from commit d7f8a5fe07b0ff3a419ccec434cc405b21a5a304)
|
||||
(cherry picked from commit 2f630e1ce18ad2e07428296532a68b11dc66ad10)
|
||||
(cherry picked from commit 610cc0ab1b760b2abaac92bd256b96191c46b941)
|
||||
(cherry picked from commit f48a96a28012d28ae37a2f4587a780a5eb779946)
|
||||
|
||||
Co-authored-by: Illia Volochii <illia.volochii@gmail.com>
|
||||
Co-authored-by: Gregory P. Smith [Google] <greg@krypto.org>
|
||||
---
|
||||
Doc/library/urllib.parse.rst | 38 +++++++++++-
|
||||
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, 111 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 a6cfc5d3dc..7dda121f26 100644
|
||||
--- a/Doc/library/urllib.parse.rst
|
||||
+++ b/Doc/library/urllib.parse.rst
|
||||
@@ -147,6 +147,10 @@ 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 <url-parsing-security>` for details.
|
||||
|
||||
.. versionchanged:: 3.2
|
||||
Added IPv6 URL parsing capabilities.
|
||||
@@ -312,8 +316,14 @@ 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 <url-parsing-security>` for details.
|
||||
|
||||
.. versionchanged:: 3.6
|
||||
Out-of-range port numbers now raise :exc:`ValueError`, instead of
|
||||
@@ -326,6 +336,9 @@ or on combining URL components into a URL string.
|
||||
.. versionchanged:: 3.8.10
|
||||
ASCII newline and tab characters are stripped from the URL.
|
||||
|
||||
+ .. versionchanged:: 3.8.17
|
||||
+ 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)
|
||||
@@ -402,6 +415,27 @@ 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.
|
||||
+
|
||||
.. _parsing-ascii-encoded-bytes:
|
||||
|
||||
Parsing ASCII Encoded Bytes
|
||||
diff --git a/Lib/test/test_urlparse.py b/Lib/test/test_urlparse.py
|
||||
index 0f99130f5d..0ad3bf128b 100644
|
||||
--- a/Lib/test/test_urlparse.py
|
||||
+++ b/Lib/test/test_urlparse.py
|
||||
@@ -660,6 +660,65 @@ class UrlParseTestCase(unittest.TestCase):
|
||||
self.assertEqual(p.scheme, "https")
|
||||
self.assertEqual(p.geturl(), "https://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):
|
||||
@@ -667,7 +726,7 @@ 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 f0d9d4d803..979e6d2127 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
|
||||
@@ -77,6 +81,10 @@ 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 '
|
||||
+
|
||||
# Unsafe bytes to be removed per WHATWG spec
|
||||
_UNSAFE_URL_BYTES_TO_REMOVE = ['\t', '\r', '\n']
|
||||
|
||||
@@ -431,6 +439,10 @@ def urlsplit(url, scheme='', allow_fragments=True):
|
||||
url, scheme, _coerce_result = _coerce_args(url, scheme)
|
||||
url = _remove_unsafe_bytes_from_url(url)
|
||||
scheme = _remove_unsafe_bytes_from_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)
|
||||
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.
|
||||
Loading…
Reference in new issue