packages/python3
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Compare commits

base: packages:a7762d83a92d437d15649ff7f2705bd238d42c73
Branches Tags
packages:main
...
compare: packages:caebf6a75a44e51ecd81a1d89446102849365fc2
Branches Tags
packages:main

10 Commits
a7762d83a9 ... caebf6a75a

Author SHA1 Message Date
openeuler-ci-bot
caebf6a75a
!406 [backport-3.7] fix CVE-2024-9287 
From: @fuowang 
Reviewed-by: @yangyuan32 
Signed-off-by: @yangyuan32
 2024-12-20 08:16:19 +00:00
wangshuo
fdd4347c4b backport-3.7-gh-124651-CVE-2024-9287 2024-12-19 02:55:27 +08:00
openeuler-ci-bot
7f1b1a2665
!400 完善加密算法测试用例 
From: @fuowang 
Reviewed-by: @yangyuan32 
Signed-off-by: @yangyuan32
 2024-12-11 01:55:30 +00:00
wangshuo
e9a34e198f support TLS_SM4 2024-12-11 01:08:33 +08:00
openeuler-ci-bot
e9d921e1e8
!370 [backport-3.7]回合两个安全相关的上游补丁 
From: @fuowang 
Reviewed-by: @dillon_chen 
Signed-off-by: @dillon_chen
 2024-10-30 08:20:17 +00:00
wangshuo
25d18d0e7d backport some security-related upstream patches 2024-10-30 09:15:50 +08:00
openeuler-ci-bot
c9709da6e2
!366 sync release 39 from 20.03-LTS-SP3, and fix CVE-2007-4559, fix test_xml_etree error 
From: @fuowang 
Reviewed-by: @dillon_chen 
Signed-off-by: @dillon_chen
 2024-10-28 07:18:08 +00:00
wangshuo
5f32441d05 sync release 39 from 20.03-LTS-SP3, and fix CVE-2007-4559, fix test_xml_etree error 2024-10-25 17:19:29 +08:00
openeuler-ci-bot
358ea4752a
!310 [sync] PR-309: Fix CVE-2023-27043 
From: @openeuler-sync-bot 
Reviewed-by: @zhuchunyi 
Signed-off-by: @zhuchunyi
 2024-04-07 07:13:15 +00:00
GuoCe
8d29a3ae78 Fix CVE-2023-27043 
(cherry picked from commit f4576b13e1bea5494119813487d71400b39428c8)
 2024-03-06 17:54:18 +08:00
12 changed files with 4468 additions and 3 deletions
Show Stats Expand all files Collapse all files

24
0001-expected_algs-list-to-include-TLS_SM4.patch Normal file
View File

@ -0,0 +1,24 @@
From e9125a4a29e9c615a2562446f07c1b1ffaa6061f Mon Sep 17 00:00:00 2001
From: wangshuo <wangshuo@kylinos.cn>
Date: Wed, 11 Dec 2024 01:05:25 +0800
Subject: [PATCH] expected_algs list to include TLS_SM4
---
Lib/test/test_ssl.py | 1 +
1 file changed, 1 insertion(+)
diff --git a/Lib/test/test_ssl.py b/Lib/test/test_ssl.py
index 50734f6..0db51bc 100644
--- a/Lib/test/test_ssl.py
+++ b/Lib/test/test_ssl.py
@@ -4222,6 +4222,7 @@ class ThreadedTests(unittest.TestCase):
"AES256", "AES-256",
# TLS 1.3 ciphers are always enabled
"TLS_CHACHA20", "TLS_AES",
+ "TLS_SM4",
]
stats = server_params_test(client_context, server_context,
--
2.43.0

61
Add-loongarch-support.patch Normal file
View File

@ -0,0 +1,61 @@
From b87dad459825a407084c9acde88f42d86139715e Mon Sep 17 00:00:00 2001
From: GuoCe <guoce@kylinos.cn>
Date: Wed, 6 Mar 2024 18:17:32 +0800
Subject: [PATCH] Add loongarch support
---
config.guess | 3 +++
config.sub | 2 ++
configure.ac | 2 ++
3 files changed, 7 insertions(+)
diff --git a/config.guess b/config.guess
index 256083a..33fafea 100755
--- a/config.guess
+++ b/config.guess
@@ -970,6 +970,9 @@ EOF
m68*:Linux:*:*)
echo "$UNAME_MACHINE"-unknown-linux-"$LIBC"
exit ;;
+ loongarch32:Linux:*:* | loongarch64:Linux:*:* | loongarchx32:Linux:*:*)
+ echo "$UNAME_MACHINE"-unknown-linux-"$LIBC"
+ exit ;;
mips:Linux:*:* | mips64:Linux:*:*)
eval "$set_cc_for_build"
sed 's/^ //' << EOF > "$dummy.c"
diff --git a/config.sub b/config.sub
index ba37cf9..d971b78 100755
--- a/config.sub
+++ b/config.sub
@@ -265,6 +265,7 @@ case $basic_machine in
| k1om \
| le32 | le64 \
| lm32 \
+ | loongarch32 | loongarch64 | loongarchx32 \
| m32c | m32r | m32rle | m68000 | m68k | m88k \
| maxq | mb | microblaze | microblazeel | mcore | mep | metag \
| mips | mipsbe | mipseb | mipsel | mipsle \
@@ -394,6 +395,7 @@ case $basic_machine in
| k1om-* \
| le32-* | le64-* \
| lm32-* \
+ | loongarch32 | loongarch64 | loongarchx32 \
| m32c-* | m32r-* | m32rle-* \
| m68000-* | m680[012346]0-* | m68360-* | m683?2-* | m68k-* \
| m88110-* | m88k-* | maxq-* | mcore-* | metag-* \
diff --git a/configure.ac b/configure.ac
index c2e9fbb..b83fdcf 100644
--- a/configure.ac
+++ b/configure.ac
@@ -779,6 +779,8 @@ cat >> conftest.c <<EOF
hppa-linux-gnu
# elif defined(__ia64__)
ia64-linux-gnu
+# elif defined(__loongarch64)
+ loongarch64-linux-gnu
# elif defined(__m68k__) && !defined(__mcoldfire__)
m68k-linux-gnu
# elif defined(__mips_hard_float) && defined(__mips_isa_rev) && (__mips_isa_rev >=6) && defined(_MIPSEL)
--
2.27.0

2469
backport-3.7-gh-102950-Implement-PEP-706-Filter-for-tarfile.e.patch Normal file
View File

File diff suppressed because it is too large Load Diff

64
backport-3.7-gh-104049-do-not-expose-on-disk-location-from-Si.patch Normal file
View File

@ -0,0 +1,64 @@
From 4e2dd0c3626649224b87b757a292959d94152a00 Mon Sep 17 00:00:00 2001
From: "Miss Islington (bot)"
<31488909+miss-islington@users.noreply.github.com>
Date: Fri, 26 May 2023 23:41:46 -0700
Subject: [PATCH] [3.7] gh-104049: do not expose on-disk location from
SimpleHTTPRequestHandler (GH-104122)
Do not expose the local server's on-disk location from `SimpleHTTPRequestHandler` when generating a directory index. (unnecessary information disclosure)
(cherry picked from commit c7c3a60c88de61a79ded9fdaf6bc6a29da4efb9a)
Co-authored-by: Ethan Furman <ethan@stoneleaf.us>
Co-authored-by: Gregory P. Smith <greg@krypto.org>
Co-authored-by: Jelle Zijlstra <jelle.zijlstra@gmail.com>
---
Lib/http/server.py | 2 +-
Lib/test/test_httpservers.py | 8 ++++++++
.../2023-05-01-15-03-25.gh-issue-104049.b01Y3g.rst | 2 ++
3 files changed, 11 insertions(+), 1 deletion(-)
create mode 100644 Misc/NEWS.d/next/Security/2023-05-01-15-03-25.gh-issue-104049.b01Y3g.rst
diff --git a/Lib/http/server.py b/Lib/http/server.py
index ba2acbc98bf..beabe3de7ab 100644
--- a/Lib/http/server.py
+++ b/Lib/http/server.py
@@ -777,7 +777,7 @@ class SimpleHTTPRequestHandler(BaseHTTPRequestHandler):
displaypath = urllib.parse.unquote(self.path,
errors='surrogatepass')
except UnicodeDecodeError:
- displaypath = urllib.parse.unquote(path)
+ displaypath = urllib.parse.unquote(self.path)
displaypath = html.escape(displaypath, quote=False)
enc = sys.getfilesystemencoding()
title = 'Directory listing for %s' % displaypath
diff --git a/Lib/test/test_httpservers.py b/Lib/test/test_httpservers.py
index b3e15c475a4..8c9be689003 100644
--- a/Lib/test/test_httpservers.py
+++ b/Lib/test/test_httpservers.py
@@ -413,6 +413,14 @@ class SimpleHTTPServerTestCase(BaseTestCase):
self.check_status_and_reason(response, HTTPStatus.OK,
data=support.TESTFN_UNDECODABLE)
+ def test_undecodable_parameter(self):
+ # sanity check using a valid parameter
+ response = self.request(self.base_url + '/?x=123').read()
+ self.assertRegex(response, f'listing for {self.base_url}/\?x=123'.encode('latin1'))
+ # now the bogus encoding
+ response = self.request(self.base_url + '/?x=%bb').read()
+ self.assertRegex(response, f'listing for {self.base_url}/\?x=\xef\xbf\xbd'.encode('latin1'))
+
def test_get_dir_redirect_location_domain_injection_bug(self):
"""Ensure //evil.co/..%2f../../X does not put //evil.co/ in Location.
diff --git a/Misc/NEWS.d/next/Security/2023-05-01-15-03-25.gh-issue-104049.b01Y3g.rst b/Misc/NEWS.d/next/Security/2023-05-01-15-03-25.gh-issue-104049.b01Y3g.rst
new file mode 100644
index 00000000000..969deb26bfe
--- /dev/null
+++ b/Misc/NEWS.d/next/Security/2023-05-01-15-03-25.gh-issue-104049.b01Y3g.rst
@@ -0,0 +1,2 @@
+Do not expose the local on-disk location in directory indexes
+produced by :class:`http.client.SimpleHTTPRequestHandler`.
--
2.25.1

308
backport-3.7-gh-107845-Fix-symlink-handling-for-tarfile.data_.patch Normal file
View File

@ -0,0 +1,308 @@
From 4e32d16aa771abb1787e5e9faecb0bec0d639e3c Mon Sep 17 00:00:00 2001
From: wangshuo <wangshuo@kylinos.cn>
Date: Thu, 24 Oct 2024 18:25:51 +0800
Subject: [PATCH 2/3] [3.7] gh-107845: Fix symlink handling for
tarfile.data_filter (GH-107846)
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
(cherry picked from commit acbd3f9)
https://github.com/python/cpython/commit/acbd3f9c5c5f23e95267714e41236140d84fe962
Co-authored-by: Petr Viktorin <encukou@gmail.com>
Co-authored-by: Victor Stinner <vstinner@python.org>
Co-authored-by: Lumír 'Frenzy' Balhar <frenzy.madness@gmail.com>
Refer to:
https://github.com/python/cpython/issues/107845
https://github.com/encukou/cpython/commit/63556bccc21ef6726ad7bc5769c2dbb08cf5910f
https://github.com/encukou/cpython/commit/8e15c2e44cbdbd48522db678ab2519a50f9d41b1
---
Doc/library/tarfile.rst | 5 +
Lib/tarfile.py | 11 +-
Lib/test/test_tarfile.py | 144 +++++++++++++++++-
...-08-10-17-36-22.gh-issue-107845.dABiMJ.rst | 3 +
4 files changed, 154 insertions(+), 9 deletions(-)
create mode 100644 Misc/NEWS.d/next/Library/2023-08-10-17-36-22.gh-issue-107845.dABiMJ.rst
diff --git a/Doc/library/tarfile.rst b/Doc/library/tarfile.rst
index 3f544c3..950e00d 100644
--- a/Doc/library/tarfile.rst
+++ b/Doc/library/tarfile.rst
@@ -715,6 +715,11 @@ 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
diff --git a/Lib/tarfile.py b/Lib/tarfile.py
index 71c5112..9a8d2dd 100755
--- a/Lib/tarfile.py
+++ b/Lib/tarfile.py
@@ -750,7 +750,7 @@ class SpecialFileError(FilterError):
class AbsoluteLinkError(FilterError):
def __init__(self, tarinfo):
self.tarinfo = tarinfo
- super().__init__(f'{tarinfo.name!r} is a symlink to an absolute path')
+ super().__init__(f'{tarinfo.name!r} is a link to an absolute path')
class LinkOutsideDestinationError(FilterError):
def __init__(self, tarinfo, path):
@@ -810,7 +810,14 @@ 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 f1aed04..a3db33d 100644
--- a/Lib/test/test_tarfile.py
+++ b/Lib/test/test_tarfile.py
@@ -2984,10 +2984,12 @@ class ArchiveMaker:
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:
@@ -3060,7 +3062,8 @@ class TestExtractionFilters(unittest.TestCase):
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
@@ -3094,6 +3097,8 @@ class TestExtractionFilters(unittest.TestCase):
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)
@@ -3139,8 +3144,15 @@ class TestExtractionFilters(unittest.TestCase):
# Test interplaying symlinks
# Inspired by 'dirsymlink2a' in jwilk/traversal-archives
with ArchiveMaker() as arc:
+
+ # `current` links to `.` which is both:
+ # - the destination directory
+ # - `current` itself
arc.add('current', symlink_to='.')
+
+ # effectively points to ./../
arc.add('parent', symlink_to='current/..')
+
arc.add('parent/evil')
if support.can_symlink():
@@ -3181,9 +3193,46 @@ class TestExtractionFilters(unittest.TestCase):
def test_parent_symlink2(self):
# Test interplaying symlinks
# Inspired by 'dirsymlink2b' in jwilk/traversal-archives
+
+ # Posix and Windows have different pathname resolution:
+ # either symlink or a '..' component resolve first.
+ # Let's see which we are on.
+ if support.can_symlink():
+ testpath = os.path.join(TEMPDIR, 'resolution_test')
+ os.mkdir(testpath)
+
+ # testpath/current links to `.` which is all of:
+ # - `testpath`
+ # - `testpath/current`
+ # - `testpath/current/current`
+ # - etc.
+ os.symlink('.', os.path.join(testpath, 'current'))
+
+ # we'll test where `testpath/current/../file` ends up
+ with open(os.path.join(testpath, 'current', '..', 'file'), 'w'):
+ pass
+
+ if os.path.exists(os.path.join(testpath, 'file')):
+ # Windows collapses 'current\..' to '.' first, leaving
+ # 'testpath\file'
+ dotdot_resolves_early = True
+ elif os.path.exists(os.path.join(testpath, '..', 'file')):
+ # Posix resolves 'current' to '.' first, leaving
+ # 'testpath/../file'
+ dotdot_resolves_early = False
+ else:
+ raise AssertionError('Could not determine link resolution')
+
with ArchiveMaker() as arc:
+
+ # `current` links to `.` which is both the destination directory
+ # and `current` itself
arc.add('current', symlink_to='.')
+
+ # `current/parent` is also available as `./parent`,
+ # and effectively points to `./../`
arc.add('current/parent', symlink_to='..')
+
arc.add('parent/evil')
with self.check_context(arc.open(), 'fully_trusted'):
@@ -3197,6 +3246,7 @@ class TestExtractionFilters(unittest.TestCase):
with self.check_context(arc.open(), 'tar'):
if support.can_symlink():
+ # Fail when extracting a file outside destination
self.expect_exception(
tarfile.OutsideDestinationError,
"'parent/evil' would be extracted to "
@@ -3207,10 +3257,24 @@ class TestExtractionFilters(unittest.TestCase):
self.expect_file('parent/evil')
with self.check_context(arc.open(), 'data'):
- self.expect_exception(
- tarfile.LinkOutsideDestinationError,
- """'current/parent' would link to ['"].*['"], """
- + "which is outside the destination")
+ if support.can_symlink():
+ if dotdot_resolves_early:
+ # Fail when extracting a file outside destination
+ self.expect_exception(
+ tarfile.OutsideDestinationError,
+ "'parent/evil' would be extracted to "
+ + """['"].*evil['"], which is outside """
+ + "the destination")
+ else:
+ # Fail as soon as we have a symlink outside the destination
+ self.expect_exception(
+ tarfile.LinkOutsideDestinationError,
+ "'current/parent' would link to "
+ + """['"].*outerdir['"], which is outside """
+ + "the destination")
+ else:
+ self.expect_file('current/')
+ self.expect_file('parent/evil')
def test_absolute_symlink(self):
# Test symlink to an absolute path
@@ -3239,11 +3303,29 @@ class TestExtractionFilters(unittest.TestCase):
with self.check_context(arc.open(), 'data'):
self.expect_exception(
tarfile.AbsoluteLinkError,
- "'parent' is a symlink to an absolute path")
+ "'parent' is a link to an absolute path")
+
+ def test_absolute_hardlink(self):
+ # Test hardlink to an absolute path
+ # Inspired by 'dirsymlink' in https://github.com/jwilk/traversal-archives
+ with ArchiveMaker() as arc:
+ arc.add('parent', hardlink_to=self.outerdir / 'foo')
+
+ with self.check_context(arc.open(), 'fully_trusted'):
+ self.expect_exception(KeyError, ".*foo. not found")
+
+ with self.check_context(arc.open(), 'tar'):
+ self.expect_exception(KeyError, ".*foo. not found")
+
+ with self.check_context(arc.open(), 'data'):
+ self.expect_exception(
+ tarfile.AbsoluteLinkError,
+ "'parent' is a link to an absolute path")
def test_sly_relative0(self):
# Inspired by 'relative0' in jwilk/traversal-archives
with ArchiveMaker() as arc:
+ # points to `../../tmp/moo`
arc.add('../moo', symlink_to='..//tmp/moo')
try:
@@ -3293,6 +3375,54 @@ class TestExtractionFilters(unittest.TestCase):
+ """['"].*moo['"], which is outside the """
+ "destination")
+ def test_deep_symlink(self):
+ # Test that symlinks and hardlinks inside a directory
+ # point to the correct file (`target` of size 3).
+ # If links aren't supported we get a copy of the file.
+ with ArchiveMaker() as arc:
+ arc.add('targetdir/target', size=3)
+ # a hardlink's linkname is relative to the archive
+ arc.add('linkdir/hardlink', hardlink_to=os.path.join(
+ 'targetdir', 'target'))
+ # a symlink's linkname is relative to the link's directory
+ arc.add('linkdir/symlink', symlink_to=os.path.join(
+ '..', '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_chains(self):
+ # Test chaining of symlinks/hardlinks.
+ # Symlinks are created before the files they point to.
+ with ArchiveMaker() as arc:
+ arc.add('linkdir/symlink', symlink_to='hardlink')
+ arc.add('symlink2', symlink_to=os.path.join(
+ 'linkdir', 'hardlink2'))
+ arc.add('targetdir/target', size=3)
+ arc.add('linkdir/hardlink', hardlink_to='targetdir/target')
+ arc.add('linkdir/hardlink2', hardlink_to='linkdir/symlink')
+
+ 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)
+ self.expect_file('linkdir/hardlink2', size=3)
+ if support.can_symlink():
+ self.expect_file('linkdir/symlink', size=3,
+ symlink_to='hardlink')
+ self.expect_file('symlink2', size=3,
+ symlink_to='linkdir/hardlink2')
+ else:
+ self.expect_file('linkdir/symlink', size=3)
+ self.expect_file('symlink2', size=3)
+
def test_modes(self):
# Test how file modes are extracted
# (Note that the modes are ignored on platforms without working chmod)
diff --git a/Misc/NEWS.d/next/Library/2023-08-10-17-36-22.gh-issue-107845.dABiMJ.rst b/Misc/NEWS.d/next/Library/2023-08-10-17-36-22.gh-issue-107845.dABiMJ.rst
new file mode 100644
index 0000000..32c1fb9
--- /dev/null
+++ b/Misc/NEWS.d/next/Library/2023-08-10-17-36-22.gh-issue-107845.dABiMJ.rst
@@ -0,0 +1,3 @@
+:func:`tarfile.data_filter` now takes the location of symlinks into account
+when determining their target, so it will no longer reject some valid
+tarballs with ``LinkOutsideDestinationError``.
--
2.33.0

33
backport-3.7-gh-115133-Fix-test_xml_etree-error-with-expat-ve.patch Normal file
View File

@ -0,0 +1,33 @@
From b6a790412ccacd9b90486fdb86e29f2e49c8fa6c Mon Sep 17 00:00:00 2001
From: wangshuo <wangshuo@kylinos.cn>
Date: Fri, 25 Oct 2024 10:13:37 +0800
Subject: [PATCH 3/3] [3.7] gh-115133: Fix test_xml_etree error with expat
versions that fix CVE-2023-52425
Feeding the parser by too small chunks defers parsing to prevent CVE-2023-52425.
According to the upstream solution, chunk_size=22 is the smallest value
that can pass the tests.
See https://github.com/python/cpython/issues/115133
---
Lib/test/test_xml_etree.py | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/Lib/test/test_xml_etree.py b/Lib/test/test_xml_etree.py
index 5ba0de8..7b225ad 100644
--- a/Lib/test/test_xml_etree.py
+++ b/Lib/test/test_xml_etree.py
@@ -1060,7 +1060,9 @@ class XMLPullParserTest(unittest.TestCase):
expected)
def test_simple_xml(self):
- for chunk_size in (None, 1, 5):
+ # Feeding the parser by too small chunks defers parsing to prevent CVE-2023-52425.
+ # See https://github.com/python/cpython/issues/115133
+ for chunk_size in (None, 22, 25):
with self.subTest(chunk_size=chunk_size):
parser = ET.XMLPullParser()
self.assert_event_tags(parser, [])
--
2.33.0

300
backport-3.7-gh-124651-CVE-2024-9287.patch Normal file
View File

@ -0,0 +1,300 @@
From c2ca86f086de75333051bff50b0e7d886302553f Mon Sep 17 00:00:00 2001
From: Victor Stinner <vstinner@python.org>
Date: Wed, 19 Dec 2024 11:23:56 +0800
Subject: [PATCH] [3.7] gh-124651: Quote template strings in `venv` activation
scripts (GH-124712) (GH-126185) (GH-126269) (GH-126301)
Fix CVE-2024-9287, backported to version 3.7 by wangshuo@kylinos.cn
Refer to:
https://github.com/python/cpython/issues/124651
https://github.com/python/cpython/pull/126301
https://github.com/python/cpython/commit/633555735a023d3e4d92ba31da35b1205f9ecbd7
---
Lib/test/test_venv.py | 81 +++++++++++++++++++
Lib/venv/__init__.py | 42 ++++++++--
Lib/venv/scripts/common/activate | 8 +-
Lib/venv/scripts/nt/activate.bat | 4 +-
Lib/venv/scripts/posix/activate.csh | 4 +-
Lib/venv/scripts/posix/activate.fish | 6 +-
...-09-28-02-03-04.gh-issue-124651.bLBGtH.rst | 1 +
7 files changed, 130 insertions(+), 16 deletions(-)
create mode 100644 Misc/NEWS.d/next/Library/2024-09-28-02-03-04.gh-issue-124651.bLBGtH.rst
diff --git a/Lib/test/test_venv.py b/Lib/test/test_venv.py
index a1fc675..2945907 100644
--- a/Lib/test/test_venv.py
+++ b/Lib/test/test_venv.py
@@ -14,6 +14,7 @@ import struct
import subprocess
import sys
import tempfile
+import shlex
from test.support import (captured_stdout, captured_stderr, requires_zlib,
can_symlink, EnvironmentVarGuard, rmtree)
import threading
@@ -83,6 +84,10 @@ class BaseTest(unittest.TestCase):
result = f.read()
return result
+ def assertEndsWith(self, string, tail):
+ if not string.endswith(tail):
+ self.fail(f"String {string!r} does not end with {tail!r}")
+
class BasicTest(BaseTest):
"""Test venv module functionality."""
@@ -293,6 +298,82 @@ class BasicTest(BaseTest):
'import sys; print(sys.executable)'])
self.assertEqual(out.strip(), envpy.encode())
+ # gh-124651: test quoted strings
+ @unittest.skipIf(os.name == 'nt', 'contains invalid characters on Windows')
+ def test_special_chars_bash(self):
+ """
+ Test that the template strings are quoted properly (bash)
+ """
+ rmtree(self.env_dir)
+ bash = shutil.which('bash')
+ if bash is None:
+ self.skipTest('bash required for this test')
+ env_name = '"\';&&$e|\'"'
+ env_dir = os.path.join(os.path.realpath(self.env_dir), env_name)
+ builder = venv.EnvBuilder(clear=True)
+ builder.create(env_dir)
+ activate = os.path.join(env_dir, self.bindir, 'activate')
+ test_script = os.path.join(self.env_dir, 'test_special_chars.sh')
+ with open(test_script, "w") as f:
+ f.write(f'source {shlex.quote(activate)}\n'
+ 'python -c \'import sys; print(sys.executable)\'\n'
+ 'python -c \'import os; print(os.environ["VIRTUAL_ENV"])\'\n'
+ 'deactivate\n')
+ out, err = check_output([bash, test_script])
+ lines = out.splitlines()
+ self.assertTrue(env_name.encode() in lines[0])
+ self.assertEndsWith(lines[1], env_name.encode())
+
+ # gh-124651: test quoted strings
+ @unittest.skipIf(os.name == 'nt', 'contains invalid characters on Windows')
+ def test_special_chars_csh(self):
+ """
+ Test that the template strings are quoted properly (csh)
+ """
+ rmtree(self.env_dir)
+ csh = shutil.which('tcsh') or shutil.which('csh')
+ if csh is None:
+ self.skipTest('csh required for this test')
+ env_name = '"\';&&$e|\'"'
+ env_dir = os.path.join(os.path.realpath(self.env_dir), env_name)
+ builder = venv.EnvBuilder(clear=True)
+ builder.create(env_dir)
+ activate = os.path.join(env_dir, self.bindir, 'activate.csh')
+ test_script = os.path.join(self.env_dir, 'test_special_chars.csh')
+ with open(test_script, "w") as f:
+ f.write(f'source {shlex.quote(activate)}\n'
+ 'python -c \'import sys; print(sys.executable)\'\n'
+ 'python -c \'import os; print(os.environ["VIRTUAL_ENV"])\'\n'
+ 'deactivate\n')
+ out, err = check_output([csh, test_script])
+ lines = out.splitlines()
+ self.assertTrue(env_name.encode() in lines[0])
+ self.assertEndsWith(lines[1], env_name.encode())
+
+ # gh-124651: test quoted strings on Windows
+ @unittest.skipUnless(os.name == 'nt', 'only relevant on Windows')
+ def test_special_chars_windows(self):
+ """
+ Test that the template strings are quoted properly on Windows
+ """
+ rmtree(self.env_dir)
+ env_name = "'&&^$e"
+ env_dir = os.path.join(os.path.realpath(self.env_dir), env_name)
+ builder = venv.EnvBuilder(clear=True)
+ builder.create(env_dir)
+ activate = os.path.join(env_dir, self.bindir, 'activate.bat')
+ test_batch = os.path.join(self.env_dir, 'test_special_chars.bat')
+ with open(test_batch, "w") as f:
+ f.write('@echo off\n'
+ f'"{activate}" & '
+ f'{self.exe} -c "import sys; print(sys.executable)" & '
+ f'{self.exe} -c "import os; print(os.environ[\'VIRTUAL_ENV\'])" & '
+ 'deactivate')
+ out, err = check_output([test_batch])
+ lines = out.splitlines()
+ self.assertTrue(env_name.encode() in lines[0])
+ self.assertEndsWith(lines[1], env_name.encode())
+
@unittest.skipUnless(os.name == 'nt', 'only relevant on Windows')
def test_unicode_in_batch_file(self):
"""
diff --git a/Lib/venv/__init__.py b/Lib/venv/__init__.py
index c454082..de4d3eb 100644
--- a/Lib/venv/__init__.py
+++ b/Lib/venv/__init__.py
@@ -11,6 +11,7 @@ import subprocess
import sys
import sysconfig
import types
+import shlex
logger = logging.getLogger(__name__)
@@ -323,11 +324,41 @@ class EnvBuilder:
:param context: The information for the environment creation request
being processed.
"""
- text = text.replace('__VENV_DIR__', context.env_dir)
- text = text.replace('__VENV_NAME__', context.env_name)
- text = text.replace('__VENV_PROMPT__', context.prompt)
- text = text.replace('__VENV_BIN_NAME__', context.bin_name)
- text = text.replace('__VENV_PYTHON__', context.env_exe)
+ replacements = {
+ '__VENV_DIR__': context.env_dir,
+ '__VENV_NAME__': context.env_name,
+ '__VENV_PROMPT__': context.prompt,
+ '__VENV_BIN_NAME__': context.bin_name,
+ '__VENV_PYTHON__': context.env_exe,
+ }
+
+ def quote_ps1(s):
+ """
+ This should satisfy PowerShell quoting rules [1], unless the quoted
+ string is passed directly to Windows native commands [2].
+ [1]: https://learn.microsoft.com/en-us/powershell/module/microsoft.powershell.core/about/about_quoting_rules
+ [2]: https://learn.microsoft.com/en-us/powershell/module/microsoft.powershell.core/about/about_parsing#passing-arguments-that-contain-quote-characters
+ """
+ s = s.replace("'", "''")
+ return f"'{s}'"
+
+ def quote_bat(s):
+ return s
+
+ # gh-124651: need to quote the template strings properly
+ quote = shlex.quote
+ script_path = context.script_path
+ if script_path.endswith('.ps1'):
+ quote = quote_ps1
+ elif script_path.endswith('.bat'):
+ quote = quote_bat
+ else:
+ # fallbacks to POSIX shell compliant quote
+ quote = shlex.quote
+
+ replacements = {key: quote(s) for key, s in replacements.items()}
+ for key, quoted in replacements.items():
+ text = text.replace(key, quoted)
return text
def install_scripts(self, context, path):
@@ -367,6 +398,7 @@ class EnvBuilder:
with open(srcfile, 'rb') as f:
data = f.read()
if not srcfile.endswith(('.exe', '.pdb')):
+ context.script_path = srcfile
try:
data = data.decode('utf-8')
data = self.replace_variables(data, context)
diff --git a/Lib/venv/scripts/common/activate b/Lib/venv/scripts/common/activate
index b9d498f..a002005 100644
--- a/Lib/venv/scripts/common/activate
+++ b/Lib/venv/scripts/common/activate
@@ -37,11 +37,11 @@ deactivate () {
# unset irrelevant variables
deactivate nondestructive
-VIRTUAL_ENV="__VENV_DIR__"
+VIRTUAL_ENV=__VENV_DIR__
export VIRTUAL_ENV
_OLD_VIRTUAL_PATH="$PATH"
-PATH="$VIRTUAL_ENV/__VENV_BIN_NAME__:$PATH"
+PATH="$VIRTUAL_ENV/"__VENV_BIN_NAME__":$PATH"
export PATH
# unset PYTHONHOME if set
@@ -54,8 +54,8 @@ fi
if [ -z "${VIRTUAL_ENV_DISABLE_PROMPT:-}" ] ; then
_OLD_VIRTUAL_PS1="${PS1:-}"
- if [ "x__VENV_PROMPT__" != x ] ; then
- PS1="__VENV_PROMPT__${PS1:-}"
+ if [ x__VENV_PROMPT__ != x ] ; then
+ PS1=__VENV_PROMPT__"${PS1:-}"
else
if [ "`basename \"$VIRTUAL_ENV\"`" = "__" ] ; then
# special case for Aspen magic directories
diff --git a/Lib/venv/scripts/nt/activate.bat b/Lib/venv/scripts/nt/activate.bat
index f61413e..11210c7 100644
--- a/Lib/venv/scripts/nt/activate.bat
+++ b/Lib/venv/scripts/nt/activate.bat
@@ -8,7 +8,7 @@ if defined _OLD_CODEPAGE (
"%SystemRoot%\System32\chcp.com" 65001 > nul
)
-set VIRTUAL_ENV=__VENV_DIR__
+set "VIRTUAL_ENV=__VENV_DIR__"
if not defined PROMPT set PROMPT=$P$G
@@ -24,7 +24,7 @@ set PYTHONHOME=
if defined _OLD_VIRTUAL_PATH set PATH=%_OLD_VIRTUAL_PATH%
if not defined _OLD_VIRTUAL_PATH set _OLD_VIRTUAL_PATH=%PATH%
-set PATH=%VIRTUAL_ENV%\__VENV_BIN_NAME__;%PATH%
+set "PATH=%VIRTUAL_ENV%\__VENV_BIN_NAME__;%PATH%"
:END
if defined _OLD_CODEPAGE (
diff --git a/Lib/venv/scripts/posix/activate.csh b/Lib/venv/scripts/posix/activate.csh
index b0c7028..ad53fd3 100644
--- a/Lib/venv/scripts/posix/activate.csh
+++ b/Lib/venv/scripts/posix/activate.csh
@@ -8,10 +8,10 @@ alias deactivate 'test $?_OLD_VIRTUAL_PATH != 0 && setenv PATH "$_OLD_VIRTUAL_PA
# Unset irrelevant variables.
deactivate nondestructive
-setenv VIRTUAL_ENV "__VENV_DIR__"
+setenv VIRTUAL_ENV __VENV_DIR__
set _OLD_VIRTUAL_PATH="$PATH"
-setenv PATH "$VIRTUAL_ENV/__VENV_BIN_NAME__:$PATH"
+setenv PATH "$VIRTUAL_ENV/"__VENV_BIN_NAME__":$PATH"
set _OLD_VIRTUAL_PROMPT="$prompt"
diff --git a/Lib/venv/scripts/posix/activate.fish b/Lib/venv/scripts/posix/activate.fish
index b401058..16723a2 100644
--- a/Lib/venv/scripts/posix/activate.fish
+++ b/Lib/venv/scripts/posix/activate.fish
@@ -29,10 +29,10 @@ end
# unset irrelevant variables
deactivate nondestructive
-set -gx VIRTUAL_ENV "__VENV_DIR__"
+set -gx VIRTUAL_ENV __VENV_DIR__
set -gx _OLD_VIRTUAL_PATH $PATH
-set -gx PATH "$VIRTUAL_ENV/__VENV_BIN_NAME__" $PATH
+set -gx PATH "$VIRTUAL_ENV/"__VENV_BIN_NAME__ $PATH
# unset PYTHONHOME if set
if set -q PYTHONHOME
@@ -53,7 +53,7 @@ if test -z "$VIRTUAL_ENV_DISABLE_PROMPT"
# Prompt override?
if test -n "__VENV_PROMPT__"
- printf "%s%s" "__VENV_PROMPT__" (set_color normal)
+ printf "%s%s" __VENV_PROMPT__ (set_color normal)
else
# ...Otherwise, prepend env
set -l _checkbase (basename "$VIRTUAL_ENV")
diff --git a/Misc/NEWS.d/next/Library/2024-09-28-02-03-04.gh-issue-124651.bLBGtH.rst b/Misc/NEWS.d/next/Library/2024-09-28-02-03-04.gh-issue-124651.bLBGtH.rst
new file mode 100644
index 0000000..17fc917
--- /dev/null
+++ b/Misc/NEWS.d/next/Library/2024-09-28-02-03-04.gh-issue-124651.bLBGtH.rst
@@ -0,0 +1 @@
+Properly quote template strings in :mod:`venv` activation scripts.
--
2.27.0

89
backport-3.7-gh-99889-Fix-directory-traversal-security-flaw-i.patch Normal file
View File

@ -0,0 +1,89 @@
From 1ce801b81ce63867ce382f6e9f56873a844c2bc6 Mon Sep 17 00:00:00 2001
From: "Miss Islington (bot)"
<31488909+miss-islington@users.noreply.github.com>
Date: Sat, 27 May 2023 00:04:28 -0700
Subject: [PATCH] [3.7] gh-99889: Fix directory traversal security flaw in
uu.decode() (GH-104333)
(cherry picked from commit 0aeda297931820436a50b78f4f7f0597274b5df4)
Co-authored-by: Sam Carroll <70000253+samcarroll42@users.noreply.github.com>
---
Lib/test/test_uu.py | 28 +++++++++++++++++++
Lib/uu.py | 9 +++++-
...3-05-02-17-56-32.gh-issue-99889.l664SU.rst | 2 ++
3 files changed, 38 insertions(+), 1 deletion(-)
mode change 100755 => 100644 Lib/uu.py
create mode 100644 Misc/NEWS.d/next/Security/2023-05-02-17-56-32.gh-issue-99889.l664SU.rst
diff --git a/Lib/test/test_uu.py b/Lib/test/test_uu.py
index c8709f7a0d6..e5d93d6cd1c 100644
--- a/Lib/test/test_uu.py
+++ b/Lib/test/test_uu.py
@@ -145,6 +145,34 @@ class UUTest(unittest.TestCase):
uu.encode(inp, out, filename)
self.assertIn(safefilename, out.getvalue())
+ def test_no_directory_traversal(self):
+ relative_bad = b"""\
+begin 644 ../../../../../../../../tmp/test1
+$86)C"@``
+`
+end
+"""
+ with self.assertRaisesRegex(uu.Error, 'directory'):
+ uu.decode(io.BytesIO(relative_bad))
+ if os.altsep:
+ relative_bad_bs = relative_bad.replace(b'/', b'\\')
+ with self.assertRaisesRegex(uu.Error, 'directory'):
+ uu.decode(io.BytesIO(relative_bad_bs))
+
+ absolute_bad = b"""\
+begin 644 /tmp/test2
+$86)C"@``
+`
+end
+"""
+ with self.assertRaisesRegex(uu.Error, 'directory'):
+ uu.decode(io.BytesIO(absolute_bad))
+ if os.altsep:
+ absolute_bad_bs = absolute_bad.replace(b'/', b'\\')
+ with self.assertRaisesRegex(uu.Error, 'directory'):
+ uu.decode(io.BytesIO(absolute_bad_bs))
+
+
class UUStdIOTest(unittest.TestCase):
def setUp(self):
diff --git a/Lib/uu.py b/Lib/uu.py
old mode 100755
new mode 100644
index 9f1f37f1a64..9fe252a639e
--- a/Lib/uu.py
+++ b/Lib/uu.py
@@ -130,7 +130,14 @@ def decode(in_file, out_file=None, mode=None, quiet=False):
# If the filename isn't ASCII, what's up with that?!?
out_file = hdrfields[2].rstrip(b' \t\r\n\f').decode("ascii")
if os.path.exists(out_file):
- raise Error('Cannot overwrite existing file: %s' % out_file)
+ raise Error(f'Cannot overwrite existing file: {out_file}')
+ if (out_file.startswith(os.sep) or
+ f'..{os.sep}' in out_file or (
+ os.altsep and
+ (out_file.startswith(os.altsep) or
+ f'..{os.altsep}' in out_file))
+ ):
+ raise Error(f'Refusing to write to {out_file} due to directory traversal')
if mode is None:
mode = int(hdrfields[1], 8)
#
diff --git a/Misc/NEWS.d/next/Security/2023-05-02-17-56-32.gh-issue-99889.l664SU.rst b/Misc/NEWS.d/next/Security/2023-05-02-17-56-32.gh-issue-99889.l664SU.rst
new file mode 100644
index 00000000000..b7002e81b6b
--- /dev/null
+++ b/Misc/NEWS.d/next/Security/2023-05-02-17-56-32.gh-issue-99889.l664SU.rst
@@ -0,0 +1,2 @@
+Fixed a security in flaw in :func:`uu.decode` that could allow for
+directory traversal based on the input if no ``out_file`` was specified.
--
2.25.1

489
backport-CVE-2023-27043.patch Normal file
View File

@ -0,0 +1,489 @@
From 213a9208f830980b5241a9f24a79778cb699b2c7 Mon Sep 17 00:00:00 2001
From: GuoCe <guoce@kylinos.cn>
Date: Tue, 5 Mar 2024 16:47:59 +0800
Subject: [PATCH 3/3] Subject: [PATCH] [Backport] CVE-2023-27043 Reject
malformed addresses in email.parseaddr()
Reference: https://github.com/python/cpython/pull/111116
Detect email address parsing errors and return empty tuple to
indicate the parsing error (old API). Add an optional 'strict'
parameter to getaddresses() and parseaddr() functions.
Offering: CloudBu CMP
CVE: CVE-2023-27043
---
Doc/library/email.utils.rst | 19 +-
Lib/email/utils.py | 151 +++++++++++++-
Lib/test/test_email/test_email.py | 187 +++++++++++++++++-
...-10-20-15-28-08.gh-issue-102988.dStNO7.rst | 8 +
4 files changed, 344 insertions(+), 21 deletions(-)
create mode 100644 Misc/NEWS.d/next/Library/2023-10-20-15-28-08.gh-issue-102988.dStNO7.rst
diff --git a/Doc/library/email.utils.rst b/Doc/library/email.utils.rst
index 4d0e920..104229e 100644
--- a/Doc/library/email.utils.rst
+++ b/Doc/library/email.utils.rst
@@ -60,13 +60,18 @@ of the new API.
begins with angle brackets, they are stripped off.
-.. function:: parseaddr(address)
+.. function:: parseaddr(address, *, strict=True)
Parse address -- which should be the value of some address-containing field such
as :mailheader:`To` or :mailheader:`Cc` -- into its constituent *realname* and
*email address* parts. Returns a tuple of that information, unless the parse
fails, in which case a 2-tuple of ``('', '')`` is returned.
+ If *strict* is true, use a strict parser which rejects malformed inputs.
+
+ .. versionchanged:: 3.13
+ Add *strict* optional parameter and reject malformed inputs by default.
+
.. function:: formataddr(pair, charset='utf-8')
@@ -84,12 +89,15 @@ of the new API.
Added the *charset* option.
-.. function:: getaddresses(fieldvalues)
+.. function:: getaddresses(fieldvalues, *, strict=True)
This method returns a list of 2-tuples of the form returned by ``parseaddr()``.
*fieldvalues* is a sequence of header field values as might be returned by
- :meth:`Message.get_all <email.message.Message.get_all>`. Here's a simple
- example that gets all the recipients of a message::
+ :meth:`Message.get_all <email.message.Message.get_all>`.
+
+ If *strict* is true, use a strict parser which rejects malformed inputs.
+
+ Here's a simple example that gets all the recipients of a message::
from email.utils import getaddresses
@@ -99,6 +107,9 @@ of the new API.
resent_ccs = msg.get_all('resent-cc', [])
all_recipients = getaddresses(tos + ccs + resent_tos + resent_ccs)
+ .. versionchanged:: 3.13
+ Add *strict* optional parameter and reject malformed inputs by default.
+
.. function:: parsedate(date)
diff --git a/Lib/email/utils.py b/Lib/email/utils.py
index e7a4149..14f73ea 100644
--- a/Lib/email/utils.py
+++ b/Lib/email/utils.py
@@ -48,6 +48,7 @@ TICK = "'"
specialsre = re.compile(r'[][\\()<>@,:;".]')
escapesre = re.compile(r'[\\"]')
+
def _has_surrogates(s):
"""Return True if s contains surrogate-escaped binary data."""
# This check is based on the fact that unless there are surrogates, utf8
@@ -106,12 +107,127 @@ def formataddr(pair, charset='utf-8'):
return address
+def _iter_escaped_chars(addr):
+ pos = 0
+ escape = False
+ for pos, ch in enumerate(addr):
+ if escape:
+ yield (pos, '\\' + ch)
+ escape = False
+ elif ch == '\\':
+ escape = True
+ else:
+ yield (pos, ch)
+ if escape:
+ yield (pos, '\\')
+
+
+def _strip_quoted_realnames(addr):
+ """Strip real names between quotes."""
+ if '"' not in addr:
+ # Fast path
+ return addr
+
+ start = 0
+ open_pos = None
+ result = []
+ for pos, ch in _iter_escaped_chars(addr):
+ if ch == '"':
+ if open_pos is None:
+ open_pos = pos
+ else:
+ if start != open_pos:
+ result.append(addr[start:open_pos])
+ start = pos + 1
+ open_pos = None
+
+ if start < len(addr):
+ result.append(addr[start:])
+
+ return ''.join(result)
-def getaddresses(fieldvalues):
- """Return a list of (REALNAME, EMAIL) for each fieldvalue."""
- all = COMMASPACE.join(str(v) for v in fieldvalues)
- a = _AddressList(all)
- return a.addresslist
+
+supports_strict_parsing = True
+
+def getaddresses(fieldvalues, *, strict=True):
+ """Return a list of (REALNAME, EMAIL) or ('','') for each fieldvalue.
+
+ When parsing fails for a fieldvalue, a 2-tuple of ('', '') is returned in
+ its place.
+
+ If strict is true, use a strict parser which rejects malformed inputs.
+ """
+
+ # If strict is true, if the resulting list of parsed addresses is greater
+ # than the number of fieldvalues in the input list, a parsing error has
+ # occurred and consequently a list containing a single empty 2-tuple [('',
+ # '')] is returned in its place. This is done to avoid invalid output.
+ #
+ # Malformed input: getaddresses(['alice@example.com <bob@example.com>'])
+ # Invalid output: [('', 'alice@example.com'), ('', 'bob@example.com')]
+ # Safe output: [('', '')]
+
+ if not strict:
+ all = COMMASPACE.join(str(v) for v in fieldvalues)
+ a = _AddressList(all)
+ return a.addresslist
+
+ fieldvalues = [str(v) for v in fieldvalues]
+ fieldvalues = _pre_parse_validation(fieldvalues)
+ addr = COMMASPACE.join(fieldvalues)
+ a = _AddressList(addr)
+ result = _post_parse_validation(a.addresslist)
+
+ # Treat output as invalid if the number of addresses is not equal to the
+ # expected number of addresses.
+ n = 0
+ for v in fieldvalues:
+ # When a comma is used in the Real Name part it is not a deliminator.
+ # So strip those out before counting the commas.
+ v = _strip_quoted_realnames(v)
+ # Expected number of addresses: 1 + number of commas
+ n += 1 + v.count(',')
+ if len(result) != n:
+ return [('', '')]
+
+ return result
+
+
+def _check_parenthesis(addr):
+ # Ignore parenthesis in quoted real names.
+ addr = _strip_quoted_realnames(addr)
+
+ opens = 0
+ for pos, ch in _iter_escaped_chars(addr):
+ if ch == '(':
+ opens += 1
+ elif ch == ')':
+ opens -= 1
+ if opens < 0:
+ return False
+ return (opens == 0)
+
+
+def _pre_parse_validation(email_header_fields):
+ accepted_values = []
+ for v in email_header_fields:
+ if not _check_parenthesis(v):
+ v = "('', '')"
+ accepted_values.append(v)
+
+ return accepted_values
+
+
+def _post_parse_validation(parsed_email_header_tuples):
+ accepted_values = []
+ # The parser would have parsed a correctly formatted domain-literal
+ # The existence of an [ after parsing indicates a parsing failure
+ for v in parsed_email_header_tuples:
+ if '[' in v[1]:
+ v = ('', '')
+ accepted_values.append(v)
+
+ return accepted_values
def _format_timetuple_and_zone(timetuple, zone):
@@ -202,16 +318,33 @@ def parsedate_to_datetime(data):
tzinfo=datetime.timezone(datetime.timedelta(seconds=tz)))
-def parseaddr(addr):
+def parseaddr(addr, *, strict=True):
"""
Parse addr into its constituent realname and email address parts.
Return a tuple of realname and email address, unless the parse fails, in
which case return a 2-tuple of ('', '').
+
+ If strict is True, use a strict parser which rejects malformed inputs.
"""
- addrs = _AddressList(addr).addresslist
- if not addrs:
- return '', ''
+ if not strict:
+ addrs = _AddressList(addr).addresslist
+ if not addrs:
+ return ('', '')
+ return addrs[0]
+
+ if isinstance(addr, list):
+ addr = addr[0]
+
+ if not isinstance(addr, str):
+ return ('', '')
+
+ addr = _pre_parse_validation([addr])[0]
+ addrs = _post_parse_validation(_AddressList(addr).addresslist)
+
+ if not addrs or len(addrs) > 1:
+ return ('', '')
+
return addrs[0]
diff --git a/Lib/test/test_email/test_email.py b/Lib/test/test_email/test_email.py
index 66aaee1..56a8063 100644
--- a/Lib/test/test_email/test_email.py
+++ b/Lib/test/test_email/test_email.py
@@ -16,6 +16,7 @@ from unittest.mock import patch
import email
import email.policy
+import email.utils
from email.charset import Charset
from email.header import Header, decode_header, make_header
@@ -3230,15 +3231,137 @@ Foo
],
)
+ def test_parsing_errors(self):
+ """Test for parsing errors from CVE-2023-27043 and CVE-2019-16056"""
+ alice = 'alice@example.org'
+ bob = 'bob@example.com'
+ empty = ('', '')
+
+ # Test utils.getaddresses() and utils.parseaddr() on malformed email
+ # addresses: default behavior (strict=True) rejects malformed address,
+ # and strict=False which tolerates malformed address.
+ for invalid_separator, expected_non_strict in (
+ ('(', [(f'<{bob}>', alice)]),
+ (')', [('', alice), empty, ('', bob)]),
+ ('<', [('', alice), empty, ('', bob), empty]),
+ ('>', [('', alice), empty, ('', bob)]),
+ ('[', [('', f'{alice}[<{bob}>]')]),
+ (']', [('', alice), empty, ('', bob)]),
+ ('@', [empty, empty, ('', bob)]),
+ (';', [('', alice), empty, ('', bob)]),
+ (':', [('', alice), ('', bob)]),
+ ('.', [('', alice + '.'), ('', bob)]),
+ ('"', [('', alice), ('', f'<{bob}>')]),
+ ):
+ address = f'{alice}{invalid_separator}<{bob}>'
+ with self.subTest(address=address):
+ self.assertEqual(utils.getaddresses([address]),
+ [empty])
+ self.assertEqual(utils.getaddresses([address], strict=False),
+ expected_non_strict)
+
+ self.assertEqual(utils.parseaddr([address]),
+ empty)
+ self.assertEqual(utils.parseaddr([address], strict=False),
+ ('', address))
+
+ # Comma (',') is treated differently depending on strict parameter.
+ # Comma without quotes.
+ address = f'{alice},<{bob}>'
+ self.assertEqual(utils.getaddresses([address]),
+ [('', alice), ('', bob)])
+ self.assertEqual(utils.getaddresses([address], strict=False),
+ [('', alice), ('', bob)])
+ self.assertEqual(utils.parseaddr([address]),
+ empty)
+ self.assertEqual(utils.parseaddr([address], strict=False),
+ ('', address))
+
+ # Real name between quotes containing comma.
+ address = '"Alice, alice@example.org" <bob@example.com>'
+ expected_strict = ('Alice, alice@example.org', 'bob@example.com')
+ self.assertEqual(utils.getaddresses([address]), [expected_strict])
+ self.assertEqual(utils.getaddresses([address], strict=False), [expected_strict])
+ self.assertEqual(utils.parseaddr([address]), expected_strict)
+ self.assertEqual(utils.parseaddr([address], strict=False),
+ ('', address))
+
+ # Valid parenthesis in comments.
+ address = 'alice@example.org (Alice)'
+ expected_strict = ('Alice', 'alice@example.org')
+ self.assertEqual(utils.getaddresses([address]), [expected_strict])
+ self.assertEqual(utils.getaddresses([address], strict=False), [expected_strict])
+ self.assertEqual(utils.parseaddr([address]), expected_strict)
+ self.assertEqual(utils.parseaddr([address], strict=False),
+ ('', address))
+
+ # Invalid parenthesis in comments.
+ address = 'alice@example.org )Alice('
+ self.assertEqual(utils.getaddresses([address]), [empty])
+ self.assertEqual(utils.getaddresses([address], strict=False),
+ [('', 'alice@example.org'), ('', ''), ('', 'Alice')])
+ self.assertEqual(utils.parseaddr([address]), empty)
+ self.assertEqual(utils.parseaddr([address], strict=False),
+ ('', address))
+
+ # Two addresses with quotes separated by comma.
+ address = '"Jane Doe" <jane@example.net>, "John Doe" <john@example.net>'
+ self.assertEqual(utils.getaddresses([address]),
+ [('Jane Doe', 'jane@example.net'),
+ ('John Doe', 'john@example.net')])
+ self.assertEqual(utils.getaddresses([address], strict=False),
+ [('Jane Doe', 'jane@example.net'),
+ ('John Doe', 'john@example.net')])
+ self.assertEqual(utils.parseaddr([address]), empty)
+ self.assertEqual(utils.parseaddr([address], strict=False),
+ ('', address))
+
+ # Test email.utils.supports_strict_parsing attribute
+ self.assertEqual(email.utils.supports_strict_parsing, True)
+
def test_getaddresses_nasty(self):
- eq = self.assertEqual
- eq(utils.getaddresses(['foo: ;']), [('', '')])
- eq(utils.getaddresses(
- ['[]*-- =~$']),
- [('', ''), ('', ''), ('', '*--')])
- eq(utils.getaddresses(
- ['foo: ;', '"Jason R. Mastaler" <jason@dom.ain>']),
- [('', ''), ('Jason R. Mastaler', 'jason@dom.ain')])
+ for addresses, expected in (
+ (['"Sürname, Firstname" <to@example.com>'],
+ [('Sürname, Firstname', 'to@example.com')]),
+
+ (['foo: ;'],
+ [('', '')]),
+
+ (['foo: ;', '"Jason R. Mastaler" <jason@dom.ain>'],
+ [('', ''), ('Jason R. Mastaler', 'jason@dom.ain')]),
+
+ ([r'Pete(A nice \) chap) <pete(his account)@silly.test(his host)>'],
+ [('Pete (A nice ) chap his account his host)', 'pete@silly.test')]),
+
+ (['(Empty list)(start)Undisclosed recipients :(nobody(I know))'],
+ [('', '')]),
+
+ (['Mary <@machine.tld:mary@example.net>, , jdoe@test . example'],
+ [('Mary', 'mary@example.net'), ('', ''), ('', 'jdoe@test.example')]),
+
+ (['John Doe <jdoe@machine(comment). example>'],
+ [('John Doe (comment)', 'jdoe@machine.example')]),
+
+ (['"Mary Smith: Personal Account" <smith@home.example>'],
+ [('Mary Smith: Personal Account', 'smith@home.example')]),
+
+ (['Undisclosed recipients:;'],
+ [('', '')]),
+
+ ([r'<boss@nil.test>, "Giant; \"Big\" Box" <bob@example.net>'],
+ [('', 'boss@nil.test'), ('Giant; "Big" Box', 'bob@example.net')]),
+ ):
+ with self.subTest(addresses=addresses):
+ self.assertEqual(utils.getaddresses(addresses),
+ expected)
+ self.assertEqual(utils.getaddresses(addresses, strict=False),
+ expected)
+
+ addresses = ['[]*-- =~$']
+ self.assertEqual(utils.getaddresses(addresses),
+ [('', '')])
+ self.assertEqual(utils.getaddresses(addresses, strict=False),
+ [('', ''), ('', ''), ('', '*--')])
def test_getaddresses_embedded_comment(self):
"""Test proper handling of a nested comment"""
@@ -3422,6 +3545,54 @@ multipart/report
m = cls(*constructor, policy=email.policy.default)
self.assertIs(m.policy, email.policy.default)
+ def test_iter_escaped_chars(self):
+ self.assertEqual(list(utils._iter_escaped_chars(r'a\\b\"c\\"d')),
+ [(0, 'a'),
+ (2, '\\\\'),
+ (3, 'b'),
+ (5, '\\"'),
+ (6, 'c'),
+ (8, '\\\\'),
+ (9, '"'),
+ (10, 'd')])
+ self.assertEqual(list(utils._iter_escaped_chars('a\\')),
+ [(0, 'a'), (1, '\\')])
+
+ def test_strip_quoted_realnames(self):
+ def check(addr, expected):
+ self.assertEqual(utils._strip_quoted_realnames(addr), expected)
+
+ check('"Jane Doe" <jane@example.net>, "John Doe" <john@example.net>',
+ ' <jane@example.net>, <john@example.net>')
+ check(r'"Jane \"Doe\"." <jane@example.net>',
+ ' <jane@example.net>')
+
+ # special cases
+ check(r'before"name"after', 'beforeafter')
+ check(r'before"name"', 'before')
+ check(r'b"name"', 'b') # single char
+ check(r'"name"after', 'after')
+ check(r'"name"a', 'a') # single char
+ check(r'"name"', '')
+
+ # no change
+ for addr in (
+ 'Jane Doe <jane@example.net>, John Doe <john@example.net>',
+ 'lone " quote',
+ ):
+ self.assertEqual(utils._strip_quoted_realnames(addr), addr)
+
+
+ def test_check_parenthesis(self):
+ addr = 'alice@example.net'
+ self.assertTrue(utils._check_parenthesis(f'{addr} (Alice)'))
+ self.assertFalse(utils._check_parenthesis(f'{addr} )Alice('))
+ self.assertFalse(utils._check_parenthesis(f'{addr} (Alice))'))
+ self.assertFalse(utils._check_parenthesis(f'{addr} ((Alice)'))
+
+ # Ignore real name between quotes
+ self.assertTrue(utils._check_parenthesis(f'")Alice((" {addr}'))
+
# Test the iterator/generators
class TestIterators(TestEmailBase):
diff --git a/Misc/NEWS.d/next/Library/2023-10-20-15-28-08.gh-issue-102988.dStNO7.rst b/Misc/NEWS.d/next/Library/2023-10-20-15-28-08.gh-issue-102988.dStNO7.rst
new file mode 100644
index 0000000..3d0e9e4
--- /dev/null
+++ b/Misc/NEWS.d/next/Library/2023-10-20-15-28-08.gh-issue-102988.dStNO7.rst
@@ -0,0 +1,8 @@
+:func:`email.utils.getaddresses` and :func:`email.utils.parseaddr` now
+return ``('', '')`` 2-tuples in more situations where invalid email
+addresses are encountered instead of potentially inaccurate values. Add
+optional *strict* parameter to these two functions: use ``strict=False`` to
+get the old behavior, accept malformed inputs.
+``getattr(email.utils, 'supports_strict_parsing', False)`` can be use to check
+if the *strict* paramater is available. Patch by Thomas Dwyer and Victor
+Stinner to improve the CVE-2023-27043 fix.
--
2.27.0

267
backport-Fix-parsing-errors-in-email-_parseaddr.py.patch Normal file
View File

@ -0,0 +1,267 @@
From 42fe8d3b828bbea6c530225a6369eda8ad86c9f3 Mon Sep 17 00:00:00 2001
From: GuoCe <guoce@kylinos.cn>
Date: Tue, 5 Mar 2024 15:33:14 +0800
Subject: [PATCH 1/3] Subject: [PATCH] [Backport] Fix parsing errors in
email/_parseaddr.py
Reference: https://github.com/python/cpython/issues/102988
The e-mail module of Python 0 - 2.7.18, 3.x - 3.11 incorrectly parses e-mail addresses which contain a special character. This vulnerability allows attackers to send messages from e-mail addresses that would otherwise be rejected.
Offering: CloudBu CMP
CVE: CVE-2023-27043
---
Doc/library/email.utils.rst | 26 +++++-
Lib/email/utils.py | 63 +++++++++++++--
Lib/test/test_email/test_email.py | 81 ++++++++++++++++++-
...-06-13-20-52-24.gh-issue-102988.Kei7Vf.rst | 4 +
4 files changed, 164 insertions(+), 10 deletions(-)
create mode 100644 Misc/NEWS.d/next/Security/2023-06-13-20-52-24.gh-issue-102988.Kei7Vf.rst
diff --git a/Doc/library/email.utils.rst b/Doc/library/email.utils.rst
index 4d0e920..97df962 100644
--- a/Doc/library/email.utils.rst
+++ b/Doc/library/email.utils.rst
@@ -67,6 +67,11 @@ of the new API.
*email address* parts. Returns a tuple of that information, unless the parse
fails, in which case a 2-tuple of ``('', '')`` is returned.
+ .. versionchanged:: 3.12
+ For security reasons, addresses that were ambiguous and could parse into
+ multiple different addresses now cause ``('', '')`` to be returned
+ instead of only one of the *potential* addresses.
+
.. function:: formataddr(pair, charset='utf-8')
@@ -89,7 +94,7 @@ of the new API.
This method returns a list of 2-tuples of the form returned by ``parseaddr()``.
*fieldvalues* is a sequence of header field values as might be returned by
:meth:`Message.get_all <email.message.Message.get_all>`. Here's a simple
- example that gets all the recipients of a message::
+ example that gets all the recipients of a message:
from email.utils import getaddresses
@@ -99,6 +104,25 @@ of the new API.
resent_ccs = msg.get_all('resent-cc', [])
all_recipients = getaddresses(tos + ccs + resent_tos + resent_ccs)
+ When parsing fails for a single fieldvalue, a 2-tuple of ``('', '')``
+ is returned in its place. Other errors in parsing the list of
+ addresses such as a fieldvalue seemingly parsing into multiple
+ addresses may result in a list containing a single empty 2-tuple
+ ``[('', '')]`` being returned rather than returning potentially
+ invalid output.
+
+ Example malformed input parsing:
+
+ .. doctest::
+
+ >>> from email.utils import getaddresses
+ >>> getaddresses(['alice@example.com <bob@example.com>', 'me@example.com'])
+ [('', '')]
+
+ .. versionchanged:: 3.12
+ The 2-tuple of ``('', '')`` in the returned values when parsing
+ fails were added as to address a security issue.
+
.. function:: parsedate(date)
diff --git a/Lib/email/utils.py b/Lib/email/utils.py
index 858f620..8b1d4d1 100644
--- a/Lib/email/utils.py
+++ b/Lib/email/utils.py
@@ -106,12 +106,54 @@ def formataddr(pair, charset='utf-8'):
return address
+def _pre_parse_validation(email_header_fields):
+ accepted_values = []
+ for v in email_header_fields:
+ s = v.replace('\\(', '').replace('\\)', '')
+ if s.count('(') != s.count(')'):
+ v = "('', '')"
+ accepted_values.append(v)
+
+ return accepted_values
+
+
+def _post_parse_validation(parsed_email_header_tuples):
+ accepted_values = []
+ # The parser would have parsed a correctly formatted domain-literal
+ # The existence of an [ after parsing indicates a parsing failure
+ for v in parsed_email_header_tuples:
+ if '[' in v[1]:
+ v = ('', '')
+ accepted_values.append(v)
+
+ return accepted_values
+
def getaddresses(fieldvalues):
- """Return a list of (REALNAME, EMAIL) for each fieldvalue."""
- all = COMMASPACE.join(fieldvalues)
+ """Return a list of (REALNAME, EMAIL) or ('','') for each fieldvalue.
+
+ When parsing fails for a fieldvalue, a 2-tuple of ('', '') is returned in
+ its place.
+
+ If the resulting list of parsed address is not the same as the number of
+ fieldvalues in the input list a parsing error has occurred. A list
+ containing a single empty 2-tuple [('', '')] is returned in its place.
+ This is done to avoid invalid output.
+ """
+ fieldvalues = [str(v) for v in fieldvalues]
+ fieldvalues = _pre_parse_validation(fieldvalues)
+ all = COMMASPACE.join(v for v in fieldvalues)
a = _AddressList(all)
- return a.addresslist
+ result = _post_parse_validation(a.addresslist)
+
+ n = 0
+ for v in fieldvalues:
+ n += v.count(',') + 1
+
+ if len(result) != n:
+ return [('', '')]
+
+ return result
def _format_timetuple_and_zone(timetuple, zone):
@@ -209,9 +251,18 @@ def parseaddr(addr):
Return a tuple of realname and email address, unless the parse fails, in
which case return a 2-tuple of ('', '').
"""
- addrs = _AddressList(addr).addresslist
- if not addrs:
- return '', ''
+ if isinstance(addr, list):
+ addr = addr[0]
+
+ if not isinstance(addr, str):
+ return ('', '')
+
+ addr = _pre_parse_validation([addr])[0]
+ addrs = _post_parse_validation(_AddressList(addr).addresslist)
+
+ if not addrs or len(addrs) > 1:
+ return ('', '')
+
return addrs[0]
diff --git a/Lib/test/test_email/test_email.py b/Lib/test/test_email/test_email.py
index 64bcdcc..8b5c9c1 100644
--- a/Lib/test/test_email/test_email.py
+++ b/Lib/test/test_email/test_email.py
@@ -3213,15 +3213,90 @@ Foo
[('Al Person', 'aperson@dom.ain'),
('Bud Person', 'bperson@dom.ain')])
+ def test_getaddresses_parsing_errors(self):
+ """Test for parsing errors from CVE-2023-27043"""
+ eq = self.assertEqual
+ eq(utils.getaddresses(['alice@example.org(<bob@example.com>']),
+ [('', '')])
+ eq(utils.getaddresses(['alice@example.org)<bob@example.com>']),
+ [('', '')])
+ eq(utils.getaddresses(['alice@example.org<<bob@example.com>']),
+ [('', '')])
+ eq(utils.getaddresses(['alice@example.org><bob@example.com>']),
+ [('', '')])
+ eq(utils.getaddresses(['alice@example.org@<bob@example.com>']),
+ [('', '')])
+ eq(utils.getaddresses(['alice@example.org,<bob@example.com>']),
+ [('', 'alice@example.org'), ('', 'bob@example.com')])
+ eq(utils.getaddresses(['alice@example.org;<bob@example.com>']),
+ [('', '')])
+ eq(utils.getaddresses(['alice@example.org:<bob@example.com>']),
+ [('', '')])
+ eq(utils.getaddresses(['alice@example.org.<bob@example.com>']),
+ [('', '')])
+ eq(utils.getaddresses(['alice@example.org"<bob@example.com>']),
+ [('', '')])
+ eq(utils.getaddresses(['alice@example.org[<bob@example.com>']),
+ [('', '')])
+ eq(utils.getaddresses(['alice@example.org]<bob@example.com>']),
+ [('', '')])
+
+ def test_parseaddr_parsing_errors(self):
+ """Test for parsing errors from CVE-2023-27043"""
+ eq = self.assertEqual
+ eq(utils.parseaddr(['alice@example.org(<bob@example.com>']),
+ ('', ''))
+ eq(utils.parseaddr(['alice@example.org)<bob@example.com>']),
+ ('', ''))
+ eq(utils.parseaddr(['alice@example.org<<bob@example.com>']),
+ ('', ''))
+ eq(utils.parseaddr(['alice@example.org><bob@example.com>']),
+ ('', ''))
+ eq(utils.parseaddr(['alice@example.org@<bob@example.com>']),
+ ('', ''))
+ eq(utils.parseaddr(['alice@example.org,<bob@example.com>']),
+ ('', ''))
+ eq(utils.parseaddr(['alice@example.org;<bob@example.com>']),
+ ('', ''))
+ eq(utils.parseaddr(['alice@example.org:<bob@example.com>']),
+ ('', ''))
+ eq(utils.parseaddr(['alice@example.org.<bob@example.com>']),
+ ('', ''))
+ eq(utils.parseaddr(['alice@example.org"<bob@example.com>']),
+ ('', ''))
+ eq(utils.parseaddr(['alice@example.org[<bob@example.com>']),
+ ('', ''))
+ eq(utils.parseaddr(['alice@example.org]<bob@example.com>']),
+ ('', ''))
+
def test_getaddresses_nasty(self):
eq = self.assertEqual
eq(utils.getaddresses(['foo: ;']), [('', '')])
- eq(utils.getaddresses(
- ['[]*-- =~$']),
- [('', ''), ('', ''), ('', '*--')])
+ eq(utils.getaddresses(['[]*-- =~$']), [('', '')])
eq(utils.getaddresses(
['foo: ;', '"Jason R. Mastaler" <jason@dom.ain>']),
[('', ''), ('Jason R. Mastaler', 'jason@dom.ain')])
+ eq(utils.getaddresses(
+ [r'Pete(A nice \) chap) <pete(his account)@silly.test(his host)>']),
+ [('Pete (A nice ) chap his account his host)', 'pete@silly.test')])
+ eq(utils.getaddresses(
+ ['(Empty list)(start)Undisclosed recipients :(nobody(I know))']),
+ [('', '')])
+ eq(utils.getaddresses(
+ ['Mary <@machine.tld:mary@example.net>, , jdoe@test . example']),
+ [('Mary', 'mary@example.net'), ('', ''), ('', 'jdoe@test.example')])
+ eq(utils.getaddresses(
+ ['John Doe <jdoe@machine(comment). example>']),
+ [('John Doe (comment)', 'jdoe@machine.example')])
+ eq(utils.getaddresses(
+ ['"Mary Smith: Personal Account" <smith@home.example>']),
+ [('Mary Smith: Personal Account', 'smith@home.example')])
+ eq(utils.getaddresses(
+ ['Undisclosed recipients:;']),
+ [('', '')])
+ eq(utils.getaddresses(
+ [r'<boss@nil.test>, "Giant; \"Big\" Box" <bob@example.net>']),
+ [('', 'boss@nil.test'), ('Giant; "Big" Box', 'bob@example.net')])
def test_getaddresses_embedded_comment(self):
"""Test proper handling of a nested comment"""
diff --git a/Misc/NEWS.d/next/Security/2023-06-13-20-52-24.gh-issue-102988.Kei7Vf.rst b/Misc/NEWS.d/next/Security/2023-06-13-20-52-24.gh-issue-102988.Kei7Vf.rst
new file mode 100644
index 0000000..e0434cc
--- /dev/null
+++ b/Misc/NEWS.d/next/Security/2023-06-13-20-52-24.gh-issue-102988.Kei7Vf.rst
@@ -0,0 +1,4 @@
+CVE-2023-27043: Prevent :func:`email.utils.parseaddr`
+and :func:`email.utils.getaddresses` from returning the realname portion of an
+invalid RFC2822 email header in the email address portion of the 2-tuple
+returned after being parsed by :class:`email._parseaddr.AddressList`.
--
2.27.0

286
backport-Revert-fixes-for-CVE-2023-27043.patch Normal file
View File

@ -0,0 +1,286 @@
From 2c367ef26f6cb9897a862f5871047703fe0af31e Mon Sep 17 00:00:00 2001
From: GuoCe <guoce@kylinos.cn>
Date: Tue, 5 Mar 2024 16:03:17 +0800
Subject: [PATCH 2/3] Subject: [PATCH] [Backport] Revert fixes for
CVE-2023-27043
Reference: https://github.com/python/cpython/pull/106733
Revert "gh-102988: Detect email address parsing errors and return empty tuple to indicate the parsing error (old API) (#105127)"
This reverts commit and adds the regression test suggested in the issue.
Offering: CloudBu CMP
CVE: CVE-2023-27043
---
Doc/library/email.utils.rst | 26 +----
Lib/email/utils.py | 63 ++----------
Lib/test/test_email/test_email.py | 96 ++++---------------
...-06-13-20-52-24.gh-issue-102988.Kei7Vf.rst | 8 +-
4 files changed, 30 insertions(+), 163 deletions(-)
diff --git a/Doc/library/email.utils.rst b/Doc/library/email.utils.rst
index 97df962..4d0e920 100644
--- a/Doc/library/email.utils.rst
+++ b/Doc/library/email.utils.rst
@@ -67,11 +67,6 @@ of the new API.
*email address* parts. Returns a tuple of that information, unless the parse
fails, in which case a 2-tuple of ``('', '')`` is returned.
- .. versionchanged:: 3.12
- For security reasons, addresses that were ambiguous and could parse into
- multiple different addresses now cause ``('', '')`` to be returned
- instead of only one of the *potential* addresses.
-
.. function:: formataddr(pair, charset='utf-8')
@@ -94,7 +89,7 @@ of the new API.
This method returns a list of 2-tuples of the form returned by ``parseaddr()``.
*fieldvalues* is a sequence of header field values as might be returned by
:meth:`Message.get_all <email.message.Message.get_all>`. Here's a simple
- example that gets all the recipients of a message:
+ example that gets all the recipients of a message::
from email.utils import getaddresses
@@ -104,25 +99,6 @@ of the new API.
resent_ccs = msg.get_all('resent-cc', [])
all_recipients = getaddresses(tos + ccs + resent_tos + resent_ccs)
- When parsing fails for a single fieldvalue, a 2-tuple of ``('', '')``
- is returned in its place. Other errors in parsing the list of
- addresses such as a fieldvalue seemingly parsing into multiple
- addresses may result in a list containing a single empty 2-tuple
- ``[('', '')]`` being returned rather than returning potentially
- invalid output.
-
- Example malformed input parsing:
-
- .. doctest::
-
- >>> from email.utils import getaddresses
- >>> getaddresses(['alice@example.com <bob@example.com>', 'me@example.com'])
- [('', '')]
-
- .. versionchanged:: 3.12
- The 2-tuple of ``('', '')`` in the returned values when parsing
- fails were added as to address a security issue.
-
.. function:: parsedate(date)
diff --git a/Lib/email/utils.py b/Lib/email/utils.py
index 8b1d4d1..e7a4149 100644
--- a/Lib/email/utils.py
+++ b/Lib/email/utils.py
@@ -106,54 +106,12 @@ def formataddr(pair, charset='utf-8'):
return address
-def _pre_parse_validation(email_header_fields):
- accepted_values = []
- for v in email_header_fields:
- s = v.replace('\\(', '').replace('\\)', '')
- if s.count('(') != s.count(')'):
- v = "('', '')"
- accepted_values.append(v)
-
- return accepted_values
-
-
-def _post_parse_validation(parsed_email_header_tuples):
- accepted_values = []
- # The parser would have parsed a correctly formatted domain-literal
- # The existence of an [ after parsing indicates a parsing failure
- for v in parsed_email_header_tuples:
- if '[' in v[1]:
- v = ('', '')
- accepted_values.append(v)
-
- return accepted_values
-
def getaddresses(fieldvalues):
- """Return a list of (REALNAME, EMAIL) or ('','') for each fieldvalue.
-
- When parsing fails for a fieldvalue, a 2-tuple of ('', '') is returned in
- its place.
-
- If the resulting list of parsed address is not the same as the number of
- fieldvalues in the input list a parsing error has occurred. A list
- containing a single empty 2-tuple [('', '')] is returned in its place.
- This is done to avoid invalid output.
- """
- fieldvalues = [str(v) for v in fieldvalues]
- fieldvalues = _pre_parse_validation(fieldvalues)
- all = COMMASPACE.join(v for v in fieldvalues)
+ """Return a list of (REALNAME, EMAIL) for each fieldvalue."""
+ all = COMMASPACE.join(str(v) for v in fieldvalues)
a = _AddressList(all)
- result = _post_parse_validation(a.addresslist)
-
- n = 0
- for v in fieldvalues:
- n += v.count(',') + 1
-
- if len(result) != n:
- return [('', '')]
-
- return result
+ return a.addresslist
def _format_timetuple_and_zone(timetuple, zone):
@@ -251,18 +209,9 @@ def parseaddr(addr):
Return a tuple of realname and email address, unless the parse fails, in
which case return a 2-tuple of ('', '').
"""
- if isinstance(addr, list):
- addr = addr[0]
-
- if not isinstance(addr, str):
- return ('', '')
-
- addr = _pre_parse_validation([addr])[0]
- addrs = _post_parse_validation(_AddressList(addr).addresslist)
-
- if not addrs or len(addrs) > 1:
- return ('', '')
-
+ addrs = _AddressList(addr).addresslist
+ if not addrs:
+ return '', ''
return addrs[0]
diff --git a/Lib/test/test_email/test_email.py b/Lib/test/test_email/test_email.py
index 8b5c9c1..66aaee1 100644
--- a/Lib/test/test_email/test_email.py
+++ b/Lib/test/test_email/test_email.py
@@ -3213,90 +3213,32 @@ Foo
[('Al Person', 'aperson@dom.ain'),
('Bud Person', 'bperson@dom.ain')])
- def test_getaddresses_parsing_errors(self):
- """Test for parsing errors from CVE-2023-27043"""
- eq = self.assertEqual
- eq(utils.getaddresses(['alice@example.org(<bob@example.com>']),
- [('', '')])
- eq(utils.getaddresses(['alice@example.org)<bob@example.com>']),
- [('', '')])
- eq(utils.getaddresses(['alice@example.org<<bob@example.com>']),
- [('', '')])
- eq(utils.getaddresses(['alice@example.org><bob@example.com>']),
- [('', '')])
- eq(utils.getaddresses(['alice@example.org@<bob@example.com>']),
- [('', '')])
- eq(utils.getaddresses(['alice@example.org,<bob@example.com>']),
- [('', 'alice@example.org'), ('', 'bob@example.com')])
- eq(utils.getaddresses(['alice@example.org;<bob@example.com>']),
- [('', '')])
- eq(utils.getaddresses(['alice@example.org:<bob@example.com>']),
- [('', '')])
- eq(utils.getaddresses(['alice@example.org.<bob@example.com>']),
- [('', '')])
- eq(utils.getaddresses(['alice@example.org"<bob@example.com>']),
- [('', '')])
- eq(utils.getaddresses(['alice@example.org[<bob@example.com>']),
- [('', '')])
- eq(utils.getaddresses(['alice@example.org]<bob@example.com>']),
- [('', '')])
-
- def test_parseaddr_parsing_errors(self):
- """Test for parsing errors from CVE-2023-27043"""
- eq = self.assertEqual
- eq(utils.parseaddr(['alice@example.org(<bob@example.com>']),
- ('', ''))
- eq(utils.parseaddr(['alice@example.org)<bob@example.com>']),
- ('', ''))
- eq(utils.parseaddr(['alice@example.org<<bob@example.com>']),
- ('', ''))
- eq(utils.parseaddr(['alice@example.org><bob@example.com>']),
- ('', ''))
- eq(utils.parseaddr(['alice@example.org@<bob@example.com>']),
- ('', ''))
- eq(utils.parseaddr(['alice@example.org,<bob@example.com>']),
- ('', ''))
- eq(utils.parseaddr(['alice@example.org;<bob@example.com>']),
- ('', ''))
- eq(utils.parseaddr(['alice@example.org:<bob@example.com>']),
- ('', ''))
- eq(utils.parseaddr(['alice@example.org.<bob@example.com>']),
- ('', ''))
- eq(utils.parseaddr(['alice@example.org"<bob@example.com>']),
- ('', ''))
- eq(utils.parseaddr(['alice@example.org[<bob@example.com>']),
- ('', ''))
- eq(utils.parseaddr(['alice@example.org]<bob@example.com>']),
- ('', ''))
+ def test_getaddresses_comma_in_name(self):
+ """GH-106669 regression test."""
+ self.assertEqual(
+ utils.getaddresses(
+ [
+ '"Bud, Person" <bperson@dom.ain>',
+ 'aperson@dom.ain (Al Person)',
+ '"Mariusz Felisiak" <to@example.com>',
+ ]
+ ),
+ [
+ ('Bud, Person', 'bperson@dom.ain'),
+ ('Al Person', 'aperson@dom.ain'),
+ ('Mariusz Felisiak', 'to@example.com'),
+ ],
+ )
def test_getaddresses_nasty(self):
eq = self.assertEqual
eq(utils.getaddresses(['foo: ;']), [('', '')])
- eq(utils.getaddresses(['[]*-- =~$']), [('', '')])
+ eq(utils.getaddresses(
+ ['[]*-- =~$']),
+ [('', ''), ('', ''), ('', '*--')])
eq(utils.getaddresses(
['foo: ;', '"Jason R. Mastaler" <jason@dom.ain>']),
[('', ''), ('Jason R. Mastaler', 'jason@dom.ain')])
- eq(utils.getaddresses(
- [r'Pete(A nice \) chap) <pete(his account)@silly.test(his host)>']),
- [('Pete (A nice ) chap his account his host)', 'pete@silly.test')])
- eq(utils.getaddresses(
- ['(Empty list)(start)Undisclosed recipients :(nobody(I know))']),
- [('', '')])
- eq(utils.getaddresses(
- ['Mary <@machine.tld:mary@example.net>, , jdoe@test . example']),
- [('Mary', 'mary@example.net'), ('', ''), ('', 'jdoe@test.example')])
- eq(utils.getaddresses(
- ['John Doe <jdoe@machine(comment). example>']),
- [('John Doe (comment)', 'jdoe@machine.example')])
- eq(utils.getaddresses(
- ['"Mary Smith: Personal Account" <smith@home.example>']),
- [('Mary Smith: Personal Account', 'smith@home.example')])
- eq(utils.getaddresses(
- ['Undisclosed recipients:;']),
- [('', '')])
- eq(utils.getaddresses(
- [r'<boss@nil.test>, "Giant; \"Big\" Box" <bob@example.net>']),
- [('', 'boss@nil.test'), ('Giant; "Big" Box', 'bob@example.net')])
def test_getaddresses_embedded_comment(self):
"""Test proper handling of a nested comment"""
diff --git a/Misc/NEWS.d/next/Security/2023-06-13-20-52-24.gh-issue-102988.Kei7Vf.rst b/Misc/NEWS.d/next/Security/2023-06-13-20-52-24.gh-issue-102988.Kei7Vf.rst
index e0434cc..c67ec45 100644
--- a/Misc/NEWS.d/next/Security/2023-06-13-20-52-24.gh-issue-102988.Kei7Vf.rst
+++ b/Misc/NEWS.d/next/Security/2023-06-13-20-52-24.gh-issue-102988.Kei7Vf.rst
@@ -1,4 +1,4 @@
-CVE-2023-27043: Prevent :func:`email.utils.parseaddr`
-and :func:`email.utils.getaddresses` from returning the realname portion of an
-invalid RFC2822 email header in the email address portion of the 2-tuple
-returned after being parsed by :class:`email._parseaddr.AddressList`.
+Reverted the :mod:`email.utils` security improvement change released in
+3.12beta4 that unintentionally caused :mod:`email.utils.getaddresses` to fail
+to parse email addresses with a comma in the quoted name field.
+See :gh:`106669`.
--
2.27.0

81
python3.spec
View File

@ -3,7 +3,7 @@ Summary: Interpreter of the Python3 programming language
URL: https://www.python.org/
Version: 3.7.9
Release: 37
Release: 43
License: Python-2.0
%global branchversion 3.7
@ -73,7 +73,9 @@ BuildRequires: tcl-devel
BuildRequires: tix-devel
BuildRequires: tk-devel
%ifnarch loongarch64
BuildRequires: valgrind-devel
%endif
BuildRequires: xz-devel
BuildRequires: zlib-devel
@ -176,6 +178,22 @@ Patch6065: backport-0003-CVE-2023-40217.patch
patch9000: Don-t-override-PYTHONPATH-which-is-already-set.patch
patch9001: add-the-sm3-method-for-obtaining-the-salt-value.patch
Patch9002: fix-CVE-2023-24329.patch
Patch9003: backport-Fix-parsing-errors-in-email-_parseaddr.py.patch
Patch9004: backport-Revert-fixes-for-CVE-2023-27043.patch
Patch9005: backport-CVE-2023-27043.patch
Patch9006: Add-loongarch-support.patch
# fix CVE-2007-4559
Patch9007: backport-3.7-gh-102950-Implement-PEP-706-Filter-for-tarfile.e.patch
Patch9008: backport-3.7-gh-107845-Fix-symlink-handling-for-tarfile.data_.patch
# fix test error
Patch9009: backport-3.7-gh-115133-Fix-test_xml_etree-error-with-expat-ve.patch
Patch9010: backport-3.7-gh-104049-do-not-expose-on-disk-location-from-Si.patch
Patch9011: backport-3.7-gh-99889-Fix-directory-traversal-security-flaw-i.patch
Patch9012: 0001-expected_algs-list-to-include-TLS_SM4.patch
Patch9013: backport-3.7-gh-124651-CVE-2024-9287.patch
Provides: python%{branchversion} = %{version}-%{release}
Provides: python(abi) = %{branchversion}
@ -336,6 +354,19 @@ rm Lib/ensurepip/_bundled/*.whl
%patch9000 -p1
%patch9001 -p1
%patch9002 -p1
%patch9003 -p1
%patch9004 -p1
%patch9005 -p1
%patch9006 -p1
%patch9007 -p1
%patch9008 -p1
%patch9009 -p1
%patch9010 -p1
%patch9011 -p1
%patch9012 -p1
%patch9013 -p1
sed -i "s/generic_os/%{_vendor}/g" Lib/platform.py
rm configure pyconfig.h.in
@ -381,7 +412,9 @@ pushd ${DebugBuildDir}
--enable-loadable-sqlite-extensions \
--with-dtrace \
--with-ssl-default-suites=openssl \
%ifnarch loongarch64
--with-valgrind \
%endif
--without-ensurepip \
--with-pydebug
@ -405,7 +438,9 @@ pushd ${OptimizedBuildDir}
--enable-loadable-sqlite-extensions \
--with-dtrace \
--with-ssl-default-suites=openssl \
%ifnarch loongarch64
--with-valgrind \
%endif
--without-ensurepip \
%{optimizations_flag}
@ -937,14 +972,54 @@ export BEP_GTDLIST="$BEP_GTDLIST_TMP"
%{_mandir}/*/*
%changelog
* Fri Mar 01 GuoCe <guoce@kylinos.cn> - 3.7.9-37
* Thu Dec 19 2024 wangshuo <wangshuo@kylinos.cn> - 3.7.9-43
- Type:CVE
- CVE:CVE-2024-9287
- SUG:NA
- DESC:fix CVE-2024-9287
- gh-124651: Quote template strings in `venv` activation scripts
* Wed Dec 11 2024 wangshuo <wangshuo@kylinos.cn> - 3.7.9-42
- Type:update
- ID:NA
- SUG:NA
- DESC:support TLS_SM4
* Tue Oct 29 2024 wangshuo <wangshuo@kylinos.cn> - 3.7.9-41
- Type:bugfix
- ID:NA
- SUG:NA
- DESC:backport upstream patches
- gh-104049: do not expose on-disk location from SimpleHTTPRequestHandler
- gh-99889: Fix directory traversal security flaw in uu.decode()
* Fri Oct 25 2024 wangshuo <wangshuo@kylinos.cn> - 3.7.9-40
- Type:CVE
- CVE:CVE-2007-4559
- SUG:NA
- DESC:Patch9007-9008, fix CVE-2007-4559
- Patch9009, fix test_xml_etree error with expat versions that fix CVE-2023-52425
* Wed Mar 06 2024 GuoCe <guoce@kylinos.cn> - 3.7.9-39
- Type:bugfix
- CVE:NA
- SUG:NA
- DESC: add loongarch64 support and disable valgrind-devel for loongarch64
* Tue Mar 05 2024 GuoCe <guoce@kylinos.cn> - 3.7.9-38
- Type:CVE
- CVE:CVE-2023-27043
- SUG:NA
- DESC:fix CVE-2023-27043
* Fri Mar 01 2024 GuoCe <guoce@kylinos.cn> - 3.7.9-37
- Type:bugfix
- CVE:NA
- SUG:NA
- DESC:Modify the spec file to synchronize the version information of
CHANGLOG and VERSION.
* Tue Sep 19 zhuofeng <zhuofeng2@huawei.com> - 3.7.9-36
* Tue Sep 19 2023 zhuofeng <zhuofeng2@huawei.com> - 3.7.9-36
- Type:CVE
- CVE:CVE-2023-40217
- SUG:NA