Compare commits
8 Commits
c8-stream-
...
i8-stream-
| Author | SHA1 | Date |
|---|---|---|
MSVSphere Packaging Team
|
9fc9e58bf0
|
2 months ago |
|
Arkady L. Shane
|
bf36d0b933
|
4 months ago |
|
MSVSphere Packaging Team
|
a1eca0c55f | 5 months ago |
|
MSVSphere Packaging Team
|
4b5d965444 | 11 months ago |
|
MSVSphere Packaging Team
|
dd92ea54ea | 11 months ago |
|
MSVSphere Packaging Team
|
77ad275e69 | 11 months ago |
|
MSVSphere Packaging Team
|
4a7a822a29 | 11 months ago |
|
MSVSphere Packaging Team
|
5cd0405711 | 11 months ago |
@ -1 +1 @@
|
||||
SOURCES/Python-3.9.16.tar.xz
|
||||
SOURCES/Python-3.9.19.tar.xz
|
||||
|
||||
@ -1 +1 @@
|
||||
19acd6a341e4f2d7ff97c10c2eada258e9898624 SOURCES/Python-3.9.16.tar.xz
|
||||
57d08ec0b329a78923b486abae906d4fa12fadb7 SOURCES/Python-3.9.19.tar.xz
|
||||
|
||||
@ -0,0 +1,24 @@
|
||||
From bbe6bfca8dcdc9a4fda45a44e0c5d2385745a03b Mon Sep 17 00:00:00 2001
|
||||
From: tigro <tigro@msvsphere-os.ru>
|
||||
Date: Wed, 17 Jul 2024 11:39:29 +0300
|
||||
Subject: [PATCH] Skip test_simple_xml
|
||||
|
||||
---
|
||||
Lib/test/test_xml_etree.py | 1 +
|
||||
1 file changed, 1 insertion(+)
|
||||
|
||||
diff --git a/Lib/test/test_xml_etree.py b/Lib/test/test_xml_etree.py
|
||||
index 7b99148..81da905 100644
|
||||
--- a/Lib/test/test_xml_etree.py
|
||||
+++ b/Lib/test/test_xml_etree.py
|
||||
@@ -1396,6 +1396,7 @@ class XMLPullParserTest(unittest.TestCase):
|
||||
expected)
|
||||
|
||||
def test_simple_xml(self, chunk_size=None, flush=False):
|
||||
+ self.skipTest('Skip')
|
||||
parser = ET.XMLPullParser()
|
||||
self.assert_event_tags(parser, [])
|
||||
self._feed(parser, "<!-- comment -->\n", chunk_size, flush)
|
||||
--
|
||||
2.45.2
|
||||
|
||||
@ -0,0 +1,251 @@
|
||||
From 8b70605b594b3831331a9340ba764ff751871612 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 | 128 ++++++++++++++++++++++++++++++++++++++-
|
||||
3 files changed, 169 insertions(+), 4 deletions(-)
|
||||
|
||||
diff --git a/Lib/tarfile.py b/Lib/tarfile.py
|
||||
index b6ad7dbe2a4..dc7050b2c63 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
|
||||
@@ -2197,6 +2204,41 @@ 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 9041e7aa368..1eb1116cc10 100644
|
||||
--- a/Lib/test/test_shutil.py
|
||||
+++ b/Lib/test/test_shutil.py
|
||||
@@ -1613,7 +1613,8 @@ class TestArchives(BaseTest, unittest.TestCase):
|
||||
def check_unpack_tarball(self, format):
|
||||
self.check_unpack_archive(format, filter='fully_trusted')
|
||||
self.check_unpack_archive(format, filter='data')
|
||||
- with warnings_helper.check_no_warnings(self):
|
||||
+ with warnings_helper.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 a66f7efd2d6..6fd3c384b5c 100644
|
||||
--- a/Lib/test/test_tarfile.py
|
||||
+++ b/Lib/test/test_tarfile.py
|
||||
@@ -2,7 +2,7 @@ import sys
|
||||
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
|
||||
@@ -2929,7 +2929,11 @@ 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)
|
||||
@@ -3592,7 +3596,8 @@ class TestExtractionFilters(unittest.TestCase):
|
||||
"""Ensure the default filter does not warn (like in 3.12)"""
|
||||
with ArchiveMaker() as arc:
|
||||
arc.add('foo')
|
||||
- with warnings_helper.check_no_warnings(self):
|
||||
+ with warnings_helper.check_warnings(
|
||||
+ ('.*CVE-2007-4559', RuntimeWarning)):
|
||||
with self.check_context(arc.open(), None):
|
||||
self.expect_file('foo')
|
||||
|
||||
@@ -3762,6 +3767,123 @@ 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 (
|
||||
+ support.temp_dir(tempdir),
|
||||
+ support.swap_attr(tarfile, '_CONFIG_FILENAME', str(configfile)),
|
||||
+ support.EnvironmentVarGuard() as env,
|
||||
+ arc.open() as tar,
|
||||
+ ):
|
||||
+ 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 (
|
||||
+ warnings_helper.check_warnings(
|
||||
+ ('.*CVE-2007-4559', RuntimeWarning)),
|
||||
+ 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 (
|
||||
+ warnings_helper.check_no_warnings(self),
|
||||
+ ):
|
||||
+ tar.extractall(tempdir / 'outdir')
|
||||
+ self.assertTrue((tempdir / 'outdir/good').exists())
|
||||
+ self.assertEqual((tempdir / 'outdir/ugly').readlink(),
|
||||
+ pathlib.Path('/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)
|
||||
--
|
||||
2.40.1
|
||||
|
||||
@ -0,0 +1,88 @@
|
||||
From 2513477cd909e838824f1766d81fdeff01c0790c Mon Sep 17 00:00:00 2001
|
||||
From: Victor Stinner <vstinner@python.org>
|
||||
Date: Wed, 17 Jan 2024 14:53:23 +0100
|
||||
Subject: [PATCH] bpo-46623: Skip two test_zlib tests on s390x (GH-31096)
|
||||
|
||||
Skip test_pair() and test_speech128() of test_zlib on s390x since
|
||||
they fail if zlib uses the s390x hardware accelerator.
|
||||
---
|
||||
Lib/test/test_zlib.py | 32 +++++++++++++++++++
|
||||
.../2022-02-03-09-45-26.bpo-46623.vxzuhV.rst | 2 ++
|
||||
2 files changed, 34 insertions(+)
|
||||
create mode 100644 Misc/NEWS.d/next/Tests/2022-02-03-09-45-26.bpo-46623.vxzuhV.rst
|
||||
|
||||
diff --git a/Lib/test/test_zlib.py b/Lib/test/test_zlib.py
|
||||
index 02509cd..f3654c9 100644
|
||||
--- a/Lib/test/test_zlib.py
|
||||
+++ b/Lib/test/test_zlib.py
|
||||
@@ -2,6 +2,7 @@ import unittest
|
||||
from test import support
|
||||
import binascii
|
||||
import copy
|
||||
+import os
|
||||
import pickle
|
||||
import random
|
||||
import sys
|
||||
@@ -16,6 +17,35 @@ requires_Decompress_copy = unittest.skipUnless(
|
||||
hasattr(zlib.decompressobj(), "copy"),
|
||||
'requires Decompress.copy()')
|
||||
|
||||
+# bpo-46623: On s390x, when a hardware accelerator is used, using different
|
||||
+# ways to compress data with zlib can produce different compressed data.
|
||||
+# Simplified test_pair() code:
|
||||
+#
|
||||
+# def func1(data):
|
||||
+# return zlib.compress(data)
|
||||
+#
|
||||
+# def func2(data)
|
||||
+# co = zlib.compressobj()
|
||||
+# x1 = co.compress(data)
|
||||
+# x2 = co.flush()
|
||||
+# return x1 + x2
|
||||
+#
|
||||
+# On s390x if zlib uses a hardware accelerator, func1() creates a single
|
||||
+# "final" compressed block whereas func2() produces 3 compressed blocks (the
|
||||
+# last one is a final block). On other platforms with no accelerator, func1()
|
||||
+# and func2() produce the same compressed data made of a single (final)
|
||||
+# compressed block.
|
||||
+#
|
||||
+# Only the compressed data is different, the decompression returns the original
|
||||
+# data:
|
||||
+#
|
||||
+# zlib.decompress(func1(data)) == zlib.decompress(func2(data)) == data
|
||||
+#
|
||||
+# Make the assumption that s390x always has an accelerator to simplify the skip
|
||||
+# condition. Windows doesn't have os.uname() but it doesn't support s390x.
|
||||
+skip_on_s390x = unittest.skipIf(hasattr(os, 'uname') and os.uname().machine == 's390x',
|
||||
+ 'skipped on s390x')
|
||||
+
|
||||
|
||||
class VersionTestCase(unittest.TestCase):
|
||||
|
||||
@@ -174,6 +204,7 @@ class CompressTestCase(BaseCompressTestCase, unittest.TestCase):
|
||||
bufsize=zlib.DEF_BUF_SIZE),
|
||||
HAMLET_SCENE)
|
||||
|
||||
+ @skip_on_s390x
|
||||
def test_speech128(self):
|
||||
# compress more data
|
||||
data = HAMLET_SCENE * 128
|
||||
@@ -225,6 +256,7 @@ class CompressTestCase(BaseCompressTestCase, unittest.TestCase):
|
||||
|
||||
class CompressObjectTestCase(BaseCompressTestCase, unittest.TestCase):
|
||||
# Test compression object
|
||||
+ @skip_on_s390x
|
||||
def test_pair(self):
|
||||
# straightforward compress/decompress objects
|
||||
datasrc = HAMLET_SCENE * 128
|
||||
diff --git a/Misc/NEWS.d/next/Tests/2022-02-03-09-45-26.bpo-46623.vxzuhV.rst b/Misc/NEWS.d/next/Tests/2022-02-03-09-45-26.bpo-46623.vxzuhV.rst
|
||||
new file mode 100644
|
||||
index 0000000..be085c0
|
||||
--- /dev/null
|
||||
+++ b/Misc/NEWS.d/next/Tests/2022-02-03-09-45-26.bpo-46623.vxzuhV.rst
|
||||
@@ -0,0 +1,2 @@
|
||||
+Skip test_pair() and test_speech128() of test_zlib on s390x since they fail
|
||||
+if zlib uses the s390x hardware accelerator. Patch by Victor Stinner.
|
||||
--
|
||||
2.43.0
|
||||
|
||||
@ -0,0 +1,750 @@
|
||||
From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
|
||||
From: Victor Stinner <vstinner@python.org>
|
||||
Date: Fri, 15 Dec 2023 16:10:40 +0100
|
||||
Subject: [PATCH] 00415: [CVE-2023-27043] gh-102988: Reject malformed addresses
|
||||
in email.parseaddr() (#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. Patch by
|
||||
Thomas Dwyer.
|
||||
|
||||
Co-Authored-By: Thomas Dwyer <github@tomd.tel>
|
||||
---
|
||||
Doc/library/email.utils.rst | 19 +-
|
||||
Lib/email/utils.py | 151 ++++++++++++-
|
||||
Lib/test/test_email/test_email.py | 204 +++++++++++++++++-
|
||||
...-10-20-15-28-08.gh-issue-102988.dStNO7.rst | 8 +
|
||||
4 files changed, 361 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 4d0e920eb0..104229e9e5 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 48d30160aa..7ca7a7c886 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 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
|
||||
+
|
||||
+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)
|
||||
+
|
||||
+
|
||||
+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 761ea90b78..0c689643de 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
|
||||
@@ -3263,15 +3264,154 @@ Foo
|
||||
[('Al Person', 'aperson@dom.ain'),
|
||||
('Bud Person', 'bperson@dom.ain')])
|
||||
|
||||
+ 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_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"""
|
||||
@@ -3460,6 +3600,54 @@ 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 0000000000..3d0e9e4078
|
||||
--- /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.
|
||||
|
||||
|
||||
From 4df4fad359c280f2328b98ea9b4414f244624a58 Mon Sep 17 00:00:00 2001
|
||||
From: Lumir Balhar <lbalhar@redhat.com>
|
||||
Date: Mon, 18 Dec 2023 20:15:33 +0100
|
||||
Subject: [PATCH] Make it possible to disable strict parsing in email module
|
||||
|
||||
---
|
||||
Doc/library/email.utils.rst | 26 +++++++++++
|
||||
Lib/email/utils.py | 54 ++++++++++++++++++++++-
|
||||
Lib/test/test_email/test_email.py | 72 ++++++++++++++++++++++++++++++-
|
||||
3 files changed, 149 insertions(+), 3 deletions(-)
|
||||
|
||||
diff --git a/Doc/library/email.utils.rst b/Doc/library/email.utils.rst
|
||||
index d1e1898591..7aef773b5f 100644
|
||||
--- a/Doc/library/email.utils.rst
|
||||
+++ b/Doc/library/email.utils.rst
|
||||
@@ -69,6 +69,19 @@ of the new API.
|
||||
|
||||
If *strict* is true, use a strict parser which rejects malformed inputs.
|
||||
|
||||
+ The default setting for *strict* is set to ``True``, but you can override
|
||||
+ it by setting the environment variable ``PYTHON_EMAIL_DISABLE_STRICT_ADDR_PARSING``
|
||||
+ to non-empty string.
|
||||
+
|
||||
+ Additionally, you can permanently set the default value for *strict* to
|
||||
+ ``False`` by creating the configuration file ``/etc/python/email.cfg``
|
||||
+ with the following content:
|
||||
+
|
||||
+ .. code-block:: ini
|
||||
+
|
||||
+ [email_addr_parsing]
|
||||
+ PYTHON_EMAIL_DISABLE_STRICT_ADDR_PARSING = true
|
||||
+
|
||||
.. versionchanged:: 3.13
|
||||
Add *strict* optional parameter and reject malformed inputs by default.
|
||||
|
||||
@@ -97,6 +110,19 @@ of the new API.
|
||||
|
||||
If *strict* is true, use a strict parser which rejects malformed inputs.
|
||||
|
||||
+ The default setting for *strict* is set to ``True``, but you can override
|
||||
+ it by setting the environment variable ``PYTHON_EMAIL_DISABLE_STRICT_ADDR_PARSING``
|
||||
+ to non-empty string.
|
||||
+
|
||||
+ Additionally, you can permanently set the default value for *strict* to
|
||||
+ ``False`` by creating the configuration file ``/etc/python/email.cfg``
|
||||
+ with the following content:
|
||||
+
|
||||
+ .. code-block:: ini
|
||||
+
|
||||
+ [email_addr_parsing]
|
||||
+ PYTHON_EMAIL_DISABLE_STRICT_ADDR_PARSING = true
|
||||
+
|
||||
Here's a simple example that gets all the recipients of a message::
|
||||
|
||||
from email.utils import getaddresses
|
||||
diff --git a/Lib/email/utils.py b/Lib/email/utils.py
|
||||
index f83b7e5d7e..b8e90ceb8e 100644
|
||||
--- a/Lib/email/utils.py
|
||||
+++ b/Lib/email/utils.py
|
||||
@@ -48,6 +48,46 @@ TICK = "'"
|
||||
specialsre = re.compile(r'[][\\()<>@,:;".]')
|
||||
escapesre = re.compile(r'[\\"]')
|
||||
|
||||
+_EMAIL_CONFIG_FILE = "/etc/python/email.cfg"
|
||||
+_cached_strict_addr_parsing = None
|
||||
+
|
||||
+
|
||||
+def _use_strict_email_parsing():
|
||||
+ """"Cache implementation for _cached_strict_addr_parsing"""
|
||||
+ global _cached_strict_addr_parsing
|
||||
+ if _cached_strict_addr_parsing is None:
|
||||
+ _cached_strict_addr_parsing = _use_strict_email_parsing_impl()
|
||||
+ return _cached_strict_addr_parsing
|
||||
+
|
||||
+
|
||||
+def _use_strict_email_parsing_impl():
|
||||
+ """Returns True if strict email parsing is not disabled by
|
||||
+ config file or env variable.
|
||||
+ """
|
||||
+ disabled = bool(os.environ.get("PYTHON_EMAIL_DISABLE_STRICT_ADDR_PARSING"))
|
||||
+ if disabled:
|
||||
+ return False
|
||||
+
|
||||
+ try:
|
||||
+ file = open(_EMAIL_CONFIG_FILE)
|
||||
+ except FileNotFoundError:
|
||||
+ pass
|
||||
+ else:
|
||||
+ with file:
|
||||
+ import configparser
|
||||
+ config = configparser.ConfigParser(
|
||||
+ interpolation=None,
|
||||
+ comment_prefixes=('#', ),
|
||||
+
|
||||
+ )
|
||||
+ config.read_file(file)
|
||||
+ disabled = config.getboolean('email_addr_parsing', "PYTHON_EMAIL_DISABLE_STRICT_ADDR_PARSING", fallback=None)
|
||||
+
|
||||
+ if disabled:
|
||||
+ return False
|
||||
+
|
||||
+ return True
|
||||
+
|
||||
|
||||
def _has_surrogates(s):
|
||||
"""Return True if s contains surrogate-escaped binary data."""
|
||||
@@ -149,7 +189,7 @@ def _strip_quoted_realnames(addr):
|
||||
|
||||
supports_strict_parsing = True
|
||||
|
||||
-def getaddresses(fieldvalues, *, strict=True):
|
||||
+def getaddresses(fieldvalues, *, strict=None):
|
||||
"""Return a list of (REALNAME, EMAIL) or ('','') for each fieldvalue.
|
||||
|
||||
When parsing fails for a fieldvalue, a 2-tuple of ('', '') is returned in
|
||||
@@ -158,6 +198,11 @@ def getaddresses(fieldvalues, *, strict=True):
|
||||
If strict is true, use a strict parser which rejects malformed inputs.
|
||||
"""
|
||||
|
||||
+ # If default is used, it's True unless disabled
|
||||
+ # by env variable or config file.
|
||||
+ if strict == None:
|
||||
+ strict = _use_strict_email_parsing()
|
||||
+
|
||||
# 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 [('',
|
||||
@@ -330,7 +375,7 @@ def parsedate_to_datetime(data):
|
||||
tzinfo=datetime.timezone(datetime.timedelta(seconds=tz)))
|
||||
|
||||
|
||||
-def parseaddr(addr, *, strict=True):
|
||||
+def parseaddr(addr, *, strict=None):
|
||||
"""
|
||||
Parse addr into its constituent realname and email address parts.
|
||||
|
||||
@@ -339,6 +384,11 @@ def parseaddr(addr, *, strict=True):
|
||||
|
||||
If strict is True, use a strict parser which rejects malformed inputs.
|
||||
"""
|
||||
+ # If default is used, it's True unless disabled
|
||||
+ # by env variable or config file.
|
||||
+ if strict == None:
|
||||
+ strict = _use_strict_email_parsing()
|
||||
+
|
||||
if not strict:
|
||||
addrs = _AddressList(addr).addresslist
|
||||
if not addrs:
|
||||
diff --git a/Lib/test/test_email/test_email.py b/Lib/test/test_email/test_email.py
|
||||
index ce36efc1b1..05ea201b68 100644
|
||||
--- a/Lib/test/test_email/test_email.py
|
||||
+++ b/Lib/test/test_email/test_email.py
|
||||
@@ -7,6 +7,9 @@ import time
|
||||
import base64
|
||||
import unittest
|
||||
import textwrap
|
||||
+import contextlib
|
||||
+import tempfile
|
||||
+import os
|
||||
|
||||
from io import StringIO, BytesIO
|
||||
from itertools import chain
|
||||
@@ -41,7 +44,7 @@ from email import iterators
|
||||
from email import base64mime
|
||||
from email import quoprimime
|
||||
|
||||
-from test.support import unlink, start_threads
|
||||
+from test.support import unlink, start_threads, EnvironmentVarGuard, swap_attr
|
||||
from test.test_email import openfile, TestEmailBase
|
||||
|
||||
# These imports are documented to work, but we are testing them using a
|
||||
@@ -3313,6 +3316,73 @@ Foo
|
||||
# Test email.utils.supports_strict_parsing attribute
|
||||
self.assertEqual(email.utils.supports_strict_parsing, True)
|
||||
|
||||
+ def test_parsing_errors_strict_set_via_env_var(self):
|
||||
+ address = 'alice@example.org )Alice('
|
||||
+ empty = ('', '')
|
||||
+
|
||||
+ # Reset cached default value to make the function
|
||||
+ # reload the config file provided below.
|
||||
+ utils._cached_strict_addr_parsing = None
|
||||
+
|
||||
+ # Strict disabled via env variable, old behavior expected
|
||||
+ with EnvironmentVarGuard() as environ:
|
||||
+ environ["PYTHON_EMAIL_DISABLE_STRICT_ADDR_PARSING"] = "1"
|
||||
+
|
||||
+ self.assertEqual(utils.getaddresses([address]),
|
||||
+ [('', 'alice@example.org'), ('', ''), ('', 'Alice')])
|
||||
+ self.assertEqual(utils.parseaddr([address]), ('', address))
|
||||
+
|
||||
+ # Clear cache again
|
||||
+ utils._cached_strict_addr_parsing = None
|
||||
+
|
||||
+ # Default strict=True, empty result expected
|
||||
+ self.assertEqual(utils.getaddresses([address]), [empty])
|
||||
+ self.assertEqual(utils.parseaddr([address]), empty)
|
||||
+
|
||||
+ # Clear cache again
|
||||
+ utils._cached_strict_addr_parsing = None
|
||||
+
|
||||
+ # Empty string in env variable = strict parsing enabled (default)
|
||||
+ with EnvironmentVarGuard() as environ:
|
||||
+ environ["PYTHON_EMAIL_DISABLE_STRICT_ADDR_PARSING"] = ""
|
||||
+
|
||||
+ # Default strict=True, empty result expected
|
||||
+ self.assertEqual(utils.getaddresses([address]), [empty])
|
||||
+ self.assertEqual(utils.parseaddr([address]), empty)
|
||||
+
|
||||
+ @contextlib.contextmanager
|
||||
+ def _email_strict_parsing_conf(self):
|
||||
+ """Context for the given email strict parsing configured in config file"""
|
||||
+ with tempfile.TemporaryDirectory() as tmpdirname:
|
||||
+ filename = os.path.join(tmpdirname, 'conf.cfg')
|
||||
+ with swap_attr(utils, "_EMAIL_CONFIG_FILE", filename):
|
||||
+ with open(filename, 'w') as file:
|
||||
+ file.write('[email_addr_parsing]\n')
|
||||
+ file.write('PYTHON_EMAIL_DISABLE_STRICT_ADDR_PARSING = true')
|
||||
+ utils._EMAIL_CONFIG_FILE = filename
|
||||
+ yield
|
||||
+
|
||||
+ def test_parsing_errors_strict_disabled_via_config_file(self):
|
||||
+ address = 'alice@example.org )Alice('
|
||||
+ empty = ('', '')
|
||||
+
|
||||
+ # Reset cached default value to make the function
|
||||
+ # reload the config file provided below.
|
||||
+ utils._cached_strict_addr_parsing = None
|
||||
+
|
||||
+ # Strict disabled via config file, old results expected
|
||||
+ with self._email_strict_parsing_conf():
|
||||
+ self.assertEqual(utils.getaddresses([address]),
|
||||
+ [('', 'alice@example.org'), ('', ''), ('', 'Alice')])
|
||||
+ self.assertEqual(utils.parseaddr([address]), ('', address))
|
||||
+
|
||||
+ # Clear cache again
|
||||
+ utils._cached_strict_addr_parsing = None
|
||||
+
|
||||
+ # Default strict=True, empty result expected
|
||||
+ self.assertEqual(utils.getaddresses([address]), [empty])
|
||||
+ self.assertEqual(utils.parseaddr([address]), empty)
|
||||
+
|
||||
def test_getaddresses_nasty(self):
|
||||
for addresses, expected in (
|
||||
(['"Sürname, Firstname" <to@example.com>'],
|
||||
--
|
||||
2.43.0
|
||||
|
||||
@ -0,0 +1,63 @@
|
||||
From 60d40d7095983e0bc23a103b2050adc519dc7fe3 Mon Sep 17 00:00:00 2001
|
||||
From: Lumir Balhar <lbalhar@redhat.com>
|
||||
Date: Fri, 3 May 2024 14:17:48 +0200
|
||||
Subject: [PATCH] Expect failures in tests not working properly with expat with
|
||||
a fixed CVE in RHEL
|
||||
|
||||
---
|
||||
Lib/test/test_pyexpat.py | 1 +
|
||||
Lib/test/test_sax.py | 1 +
|
||||
Lib/test/test_xml_etree.py | 3 +++
|
||||
3 files changed, 5 insertions(+)
|
||||
|
||||
diff --git a/Lib/test/test_pyexpat.py b/Lib/test/test_pyexpat.py
|
||||
index 43cbd27..27b1502 100644
|
||||
--- a/Lib/test/test_pyexpat.py
|
||||
+++ b/Lib/test/test_pyexpat.py
|
||||
@@ -793,6 +793,7 @@ class ReparseDeferralTest(unittest.TestCase):
|
||||
|
||||
self.assertEqual(started, ['doc'])
|
||||
|
||||
+ @unittest.expectedFailure
|
||||
def test_reparse_deferral_disabled(self):
|
||||
started = []
|
||||
|
||||
diff --git a/Lib/test/test_sax.py b/Lib/test/test_sax.py
|
||||
index 9b3014a..646c92d 100644
|
||||
--- a/Lib/test/test_sax.py
|
||||
+++ b/Lib/test/test_sax.py
|
||||
@@ -1240,6 +1240,7 @@ class ExpatReaderTest(XmlTestBase):
|
||||
|
||||
self.assertEqual(result.getvalue(), start + b"<doc></doc>")
|
||||
|
||||
+ @unittest.expectedFailure
|
||||
def test_flush_reparse_deferral_disabled(self):
|
||||
result = BytesIO()
|
||||
xmlgen = XMLGenerator(result)
|
||||
diff --git a/Lib/test/test_xml_etree.py b/Lib/test/test_xml_etree.py
|
||||
index 9c382d1..62f2871 100644
|
||||
--- a/Lib/test/test_xml_etree.py
|
||||
+++ b/Lib/test/test_xml_etree.py
|
||||
@@ -1424,9 +1424,11 @@ class XMLPullParserTest(unittest.TestCase):
|
||||
self.assert_event_tags(parser, [('end', 'root')])
|
||||
self.assertIsNone(parser.close())
|
||||
|
||||
+ @unittest.expectedFailure
|
||||
def test_simple_xml_chunk_1(self):
|
||||
self.test_simple_xml(chunk_size=1, flush=True)
|
||||
|
||||
+ @unittest.expectedFailure
|
||||
def test_simple_xml_chunk_5(self):
|
||||
self.test_simple_xml(chunk_size=5, flush=True)
|
||||
|
||||
@@ -1651,6 +1653,7 @@ class XMLPullParserTest(unittest.TestCase):
|
||||
|
||||
self.assert_event_tags(parser, [('end', 'doc')])
|
||||
|
||||
+ @unittest.expectedFailure
|
||||
def test_flush_reparse_deferral_disabled(self):
|
||||
parser = ET.XMLPullParser(events=('start', 'end'))
|
||||
|
||||
--
|
||||
2.44.0
|
||||
|
||||
@ -0,0 +1,402 @@
|
||||
From f647bd8884bc89767914a5e0dea9ae099a8b50b5 Mon Sep 17 00:00:00 2001
|
||||
From: Petr Viktorin <encukou@gmail.com>
|
||||
Date: Tue, 7 May 2024 11:57:58 +0200
|
||||
Subject: [PATCH] gh-113171: gh-65056: Fix "private" (non-global) IP address
|
||||
ranges (GH-113179) (GH-113186) (GH-118177) (GH-118472)
|
||||
|
||||
The _private_networks variables, used by various is_private
|
||||
implementations, were missing some ranges and at the same time had
|
||||
overly strict ranges (where there are more specific ranges considered
|
||||
globally reachable by the IANA registries).
|
||||
|
||||
This patch updates the ranges with what was missing or otherwise
|
||||
incorrect.
|
||||
|
||||
100.64.0.0/10 is left alone, for now, as it's been made special in [1].
|
||||
|
||||
The _address_exclude_many() call returns 8 networks for IPv4, 121
|
||||
networks for IPv6.
|
||||
|
||||
[1] https://github.com/python/cpython/issues/61602
|
||||
|
||||
In 3.10 and below, is_private checks whether the network and broadcast
|
||||
address are both private.
|
||||
In later versions (where the test wss backported from), it checks
|
||||
whether they both are in the same private network.
|
||||
|
||||
For 0.0.0.0/0, both 0.0.0.0 and 255.225.255.255 are private,
|
||||
but one is in 0.0.0.0/8 ("This network") and the other in
|
||||
255.255.255.255/32 ("Limited broadcast").
|
||||
|
||||
---------
|
||||
|
||||
Co-authored-by: Jakub Stasiak <jakub@stasiak.at>
|
||||
---
|
||||
Doc/library/ipaddress.rst | 43 ++++++++-
|
||||
Doc/tools/susp-ignored.csv | 8 ++
|
||||
Doc/whatsnew/3.9.rst | 9 ++
|
||||
Lib/ipaddress.py | 95 +++++++++++++++----
|
||||
Lib/test/test_ipaddress.py | 52 ++++++++++
|
||||
...-03-14-01-38-44.gh-issue-113171.VFnObz.rst | 9 ++
|
||||
6 files changed, 195 insertions(+), 21 deletions(-)
|
||||
create mode 100644 Misc/NEWS.d/next/Library/2024-03-14-01-38-44.gh-issue-113171.VFnObz.rst
|
||||
|
||||
diff --git a/Doc/library/ipaddress.rst b/Doc/library/ipaddress.rst
|
||||
index 9c2dff5..f9c1ebf 100644
|
||||
--- a/Doc/library/ipaddress.rst
|
||||
+++ b/Doc/library/ipaddress.rst
|
||||
@@ -188,18 +188,53 @@ write code that handles both IP versions correctly. Address objects are
|
||||
|
||||
.. attribute:: is_private
|
||||
|
||||
- ``True`` if the address is allocated for private networks. See
|
||||
+ ``True`` if the address is defined as not globally reachable by
|
||||
iana-ipv4-special-registry_ (for IPv4) or iana-ipv6-special-registry_
|
||||
- (for IPv6).
|
||||
+ (for IPv6) with the following exceptions:
|
||||
+
|
||||
+ * ``is_private`` is ``False`` for the shared address space (``100.64.0.0/10``)
|
||||
+ * For IPv4-mapped IPv6-addresses the ``is_private`` value is determined by the
|
||||
+ semantics of the underlying IPv4 addresses and the following condition holds
|
||||
+ (see :attr:`IPv6Address.ipv4_mapped`)::
|
||||
+
|
||||
+ address.is_private == address.ipv4_mapped.is_private
|
||||
+
|
||||
+ ``is_private`` has value opposite to :attr:`is_global`, except for the shared address space
|
||||
+ (``100.64.0.0/10`` range) where they are both ``False``.
|
||||
+
|
||||
+ .. versionchanged:: 3.9.20
|
||||
+
|
||||
+ Fixed some false positives and false negatives.
|
||||
+
|
||||
+ * ``192.0.0.0/24`` is considered private with the exception of ``192.0.0.9/32`` and
|
||||
+ ``192.0.0.10/32`` (previously: only the ``192.0.0.0/29`` sub-range was considered private).
|
||||
+ * ``64:ff9b:1::/48`` is considered private.
|
||||
+ * ``2002::/16`` is considered private.
|
||||
+ * There are exceptions within ``2001::/23`` (otherwise considered private): ``2001:1::1/128``,
|
||||
+ ``2001:1::2/128``, ``2001:3::/32``, ``2001:4:112::/48``, ``2001:20::/28``, ``2001:30::/28``.
|
||||
+ The exceptions are not considered private.
|
||||
|
||||
.. attribute:: is_global
|
||||
|
||||
- ``True`` if the address is allocated for public networks. See
|
||||
+ ``True`` if the address is defined as globally reachable by
|
||||
iana-ipv4-special-registry_ (for IPv4) or iana-ipv6-special-registry_
|
||||
- (for IPv6).
|
||||
+ (for IPv6) with the following exception:
|
||||
+
|
||||
+ For IPv4-mapped IPv6-addresses the ``is_private`` value is determined by the
|
||||
+ semantics of the underlying IPv4 addresses and the following condition holds
|
||||
+ (see :attr:`IPv6Address.ipv4_mapped`)::
|
||||
+
|
||||
+ address.is_global == address.ipv4_mapped.is_global
|
||||
+
|
||||
+ ``is_global`` has value opposite to :attr:`is_private`, except for the shared address space
|
||||
+ (``100.64.0.0/10`` range) where they are both ``False``.
|
||||
|
||||
.. versionadded:: 3.4
|
||||
|
||||
+ .. versionchanged:: 3.9.20
|
||||
+
|
||||
+ Fixed some false positives and false negatives, see :attr:`is_private` for details.
|
||||
+
|
||||
.. attribute:: is_unspecified
|
||||
|
||||
``True`` if the address is unspecified. See :RFC:`5735` (for IPv4)
|
||||
diff --git a/Doc/tools/susp-ignored.csv b/Doc/tools/susp-ignored.csv
|
||||
index 3eb3d79..de91a50 100644
|
||||
--- a/Doc/tools/susp-ignored.csv
|
||||
+++ b/Doc/tools/susp-ignored.csv
|
||||
@@ -169,6 +169,14 @@ library/ipaddress,,:db00,2001:db00::0/24
|
||||
library/ipaddress,,::,2001:db00::0/24
|
||||
library/ipaddress,,:db00,2001:db00::0/ffff:ff00::
|
||||
library/ipaddress,,::,2001:db00::0/ffff:ff00::
|
||||
+library/ipaddress,,:ff9b,64:ff9b:1::/48
|
||||
+library/ipaddress,,::,64:ff9b:1::/48
|
||||
+library/ipaddress,,::,2001::
|
||||
+library/ipaddress,,::,2001:1::
|
||||
+library/ipaddress,,::,2001:3::
|
||||
+library/ipaddress,,::,2001:4:112::
|
||||
+library/ipaddress,,::,2001:20::
|
||||
+library/ipaddress,,::,2001:30::
|
||||
library/itertools,,:step,elements from seq[start:stop:step]
|
||||
library/itertools,,:stop,elements from seq[start:stop:step]
|
||||
library/itertools,,::,kernel = tuple(kernel)[::-1]
|
||||
diff --git a/Doc/whatsnew/3.9.rst b/Doc/whatsnew/3.9.rst
|
||||
index 0064e07..1756a37 100644
|
||||
--- a/Doc/whatsnew/3.9.rst
|
||||
+++ b/Doc/whatsnew/3.9.rst
|
||||
@@ -1616,3 +1616,12 @@ tarfile
|
||||
:exc:`DeprecationWarning`.
|
||||
In Python 3.14, the default will switch to ``'data'``.
|
||||
(Contributed by Petr Viktorin in :pep:`706`.)
|
||||
+
|
||||
+Notable changes in 3.9.20
|
||||
+=========================
|
||||
+
|
||||
+ipaddress
|
||||
+---------
|
||||
+
|
||||
+* Fixed ``is_global`` and ``is_private`` behavior in ``IPv4Address``,
|
||||
+ ``IPv6Address``, ``IPv4Network`` and ``IPv6Network``.
|
||||
diff --git a/Lib/ipaddress.py b/Lib/ipaddress.py
|
||||
index 25f373a..9b35340 100644
|
||||
--- a/Lib/ipaddress.py
|
||||
+++ b/Lib/ipaddress.py
|
||||
@@ -1322,18 +1322,41 @@ class IPv4Address(_BaseV4, _BaseAddress):
|
||||
@property
|
||||
@functools.lru_cache()
|
||||
def is_private(self):
|
||||
- """Test if this address is allocated for private networks.
|
||||
+ """``True`` if the address is defined as not globally reachable by
|
||||
+ iana-ipv4-special-registry_ (for IPv4) or iana-ipv6-special-registry_
|
||||
+ (for IPv6) with the following exceptions:
|
||||
|
||||
- Returns:
|
||||
- A boolean, True if the address is reserved per
|
||||
- iana-ipv4-special-registry.
|
||||
+ * ``is_private`` is ``False`` for ``100.64.0.0/10``
|
||||
+ * For IPv4-mapped IPv6-addresses the ``is_private`` value is determined by the
|
||||
+ semantics of the underlying IPv4 addresses and the following condition holds
|
||||
+ (see :attr:`IPv6Address.ipv4_mapped`)::
|
||||
+
|
||||
+ address.is_private == address.ipv4_mapped.is_private
|
||||
|
||||
+ ``is_private`` has value opposite to :attr:`is_global`, except for the ``100.64.0.0/10``
|
||||
+ IPv4 range where they are both ``False``.
|
||||
"""
|
||||
- return any(self in net for net in self._constants._private_networks)
|
||||
+ return (
|
||||
+ any(self in net for net in self._constants._private_networks)
|
||||
+ and all(self not in net for net in self._constants._private_networks_exceptions)
|
||||
+ )
|
||||
|
||||
@property
|
||||
@functools.lru_cache()
|
||||
def is_global(self):
|
||||
+ """``True`` if the address is defined as globally reachable by
|
||||
+ iana-ipv4-special-registry_ (for IPv4) or iana-ipv6-special-registry_
|
||||
+ (for IPv6) with the following exception:
|
||||
+
|
||||
+ For IPv4-mapped IPv6-addresses the ``is_private`` value is determined by the
|
||||
+ semantics of the underlying IPv4 addresses and the following condition holds
|
||||
+ (see :attr:`IPv6Address.ipv4_mapped`)::
|
||||
+
|
||||
+ address.is_global == address.ipv4_mapped.is_global
|
||||
+
|
||||
+ ``is_global`` has value opposite to :attr:`is_private`, except for the ``100.64.0.0/10``
|
||||
+ IPv4 range where they are both ``False``.
|
||||
+ """
|
||||
return self not in self._constants._public_network and not self.is_private
|
||||
|
||||
@property
|
||||
@@ -1537,13 +1560,15 @@ class _IPv4Constants:
|
||||
|
||||
_public_network = IPv4Network('100.64.0.0/10')
|
||||
|
||||
+ # Not globally reachable address blocks listed on
|
||||
+ # https://www.iana.org/assignments/iana-ipv4-special-registry/iana-ipv4-special-registry.xhtml
|
||||
_private_networks = [
|
||||
IPv4Network('0.0.0.0/8'),
|
||||
IPv4Network('10.0.0.0/8'),
|
||||
IPv4Network('127.0.0.0/8'),
|
||||
IPv4Network('169.254.0.0/16'),
|
||||
IPv4Network('172.16.0.0/12'),
|
||||
- IPv4Network('192.0.0.0/29'),
|
||||
+ IPv4Network('192.0.0.0/24'),
|
||||
IPv4Network('192.0.0.170/31'),
|
||||
IPv4Network('192.0.2.0/24'),
|
||||
IPv4Network('192.168.0.0/16'),
|
||||
@@ -1554,6 +1579,11 @@ class _IPv4Constants:
|
||||
IPv4Network('255.255.255.255/32'),
|
||||
]
|
||||
|
||||
+ _private_networks_exceptions = [
|
||||
+ IPv4Network('192.0.0.9/32'),
|
||||
+ IPv4Network('192.0.0.10/32'),
|
||||
+ ]
|
||||
+
|
||||
_reserved_network = IPv4Network('240.0.0.0/4')
|
||||
|
||||
_unspecified_address = IPv4Address('0.0.0.0')
|
||||
@@ -1995,23 +2025,42 @@ class IPv6Address(_BaseV6, _BaseAddress):
|
||||
@property
|
||||
@functools.lru_cache()
|
||||
def is_private(self):
|
||||
- """Test if this address is allocated for private networks.
|
||||
+ """``True`` if the address is defined as not globally reachable by
|
||||
+ iana-ipv4-special-registry_ (for IPv4) or iana-ipv6-special-registry_
|
||||
+ (for IPv6) with the following exceptions:
|
||||
|
||||
- Returns:
|
||||
- A boolean, True if the address is reserved per
|
||||
- iana-ipv6-special-registry.
|
||||
+ * ``is_private`` is ``False`` for ``100.64.0.0/10``
|
||||
+ * For IPv4-mapped IPv6-addresses the ``is_private`` value is determined by the
|
||||
+ semantics of the underlying IPv4 addresses and the following condition holds
|
||||
+ (see :attr:`IPv6Address.ipv4_mapped`)::
|
||||
+
|
||||
+ address.is_private == address.ipv4_mapped.is_private
|
||||
|
||||
+ ``is_private`` has value opposite to :attr:`is_global`, except for the ``100.64.0.0/10``
|
||||
+ IPv4 range where they are both ``False``.
|
||||
"""
|
||||
- return any(self in net for net in self._constants._private_networks)
|
||||
+ ipv4_mapped = self.ipv4_mapped
|
||||
+ if ipv4_mapped is not None:
|
||||
+ return ipv4_mapped.is_private
|
||||
+ return (
|
||||
+ any(self in net for net in self._constants._private_networks)
|
||||
+ and all(self not in net for net in self._constants._private_networks_exceptions)
|
||||
+ )
|
||||
|
||||
@property
|
||||
def is_global(self):
|
||||
- """Test if this address is allocated for public networks.
|
||||
+ """``True`` if the address is defined as globally reachable by
|
||||
+ iana-ipv4-special-registry_ (for IPv4) or iana-ipv6-special-registry_
|
||||
+ (for IPv6) with the following exception:
|
||||
|
||||
- Returns:
|
||||
- A boolean, true if the address is not reserved per
|
||||
- iana-ipv6-special-registry.
|
||||
+ For IPv4-mapped IPv6-addresses the ``is_private`` value is determined by the
|
||||
+ semantics of the underlying IPv4 addresses and the following condition holds
|
||||
+ (see :attr:`IPv6Address.ipv4_mapped`)::
|
||||
+
|
||||
+ address.is_global == address.ipv4_mapped.is_global
|
||||
|
||||
+ ``is_global`` has value opposite to :attr:`is_private`, except for the ``100.64.0.0/10``
|
||||
+ IPv4 range where they are both ``False``.
|
||||
"""
|
||||
return not self.is_private
|
||||
|
||||
@@ -2252,19 +2301,31 @@ class _IPv6Constants:
|
||||
|
||||
_multicast_network = IPv6Network('ff00::/8')
|
||||
|
||||
+ # Not globally reachable address blocks listed on
|
||||
+ # https://www.iana.org/assignments/iana-ipv6-special-registry/iana-ipv6-special-registry.xhtml
|
||||
_private_networks = [
|
||||
IPv6Network('::1/128'),
|
||||
IPv6Network('::/128'),
|
||||
IPv6Network('::ffff:0:0/96'),
|
||||
+ IPv6Network('64:ff9b:1::/48'),
|
||||
IPv6Network('100::/64'),
|
||||
IPv6Network('2001::/23'),
|
||||
- IPv6Network('2001:2::/48'),
|
||||
IPv6Network('2001:db8::/32'),
|
||||
- IPv6Network('2001:10::/28'),
|
||||
+ # IANA says N/A, let's consider it not globally reachable to be safe
|
||||
+ IPv6Network('2002::/16'),
|
||||
IPv6Network('fc00::/7'),
|
||||
IPv6Network('fe80::/10'),
|
||||
]
|
||||
|
||||
+ _private_networks_exceptions = [
|
||||
+ IPv6Network('2001:1::1/128'),
|
||||
+ IPv6Network('2001:1::2/128'),
|
||||
+ IPv6Network('2001:3::/32'),
|
||||
+ IPv6Network('2001:4:112::/48'),
|
||||
+ IPv6Network('2001:20::/28'),
|
||||
+ IPv6Network('2001:30::/28'),
|
||||
+ ]
|
||||
+
|
||||
_reserved_networks = [
|
||||
IPv6Network('::/8'), IPv6Network('100::/8'),
|
||||
IPv6Network('200::/7'), IPv6Network('400::/6'),
|
||||
diff --git a/Lib/test/test_ipaddress.py b/Lib/test/test_ipaddress.py
|
||||
index 90897f6..bd14f04 100644
|
||||
--- a/Lib/test/test_ipaddress.py
|
||||
+++ b/Lib/test/test_ipaddress.py
|
||||
@@ -2263,6 +2263,10 @@ class IpaddrUnitTest(unittest.TestCase):
|
||||
self.assertEqual(True, ipaddress.ip_address(
|
||||
'172.31.255.255').is_private)
|
||||
self.assertEqual(False, ipaddress.ip_address('172.32.0.0').is_private)
|
||||
+ self.assertFalse(ipaddress.ip_address('192.0.0.0').is_global)
|
||||
+ self.assertTrue(ipaddress.ip_address('192.0.0.9').is_global)
|
||||
+ self.assertTrue(ipaddress.ip_address('192.0.0.10').is_global)
|
||||
+ self.assertFalse(ipaddress.ip_address('192.0.0.255').is_global)
|
||||
|
||||
self.assertEqual(True,
|
||||
ipaddress.ip_address('169.254.100.200').is_link_local)
|
||||
@@ -2278,6 +2282,40 @@ class IpaddrUnitTest(unittest.TestCase):
|
||||
self.assertEqual(False, ipaddress.ip_address('128.0.0.0').is_loopback)
|
||||
self.assertEqual(True, ipaddress.ip_network('0.0.0.0').is_unspecified)
|
||||
|
||||
+ def testPrivateNetworks(self):
|
||||
+ self.assertEqual(True, ipaddress.ip_network("0.0.0.0/0").is_private)
|
||||
+ self.assertEqual(False, ipaddress.ip_network("1.0.0.0/8").is_private)
|
||||
+
|
||||
+ self.assertEqual(True, ipaddress.ip_network("0.0.0.0/8").is_private)
|
||||
+ self.assertEqual(True, ipaddress.ip_network("10.0.0.0/8").is_private)
|
||||
+ self.assertEqual(True, ipaddress.ip_network("127.0.0.0/8").is_private)
|
||||
+ self.assertEqual(True, ipaddress.ip_network("169.254.0.0/16").is_private)
|
||||
+ self.assertEqual(True, ipaddress.ip_network("172.16.0.0/12").is_private)
|
||||
+ self.assertEqual(True, ipaddress.ip_network("192.0.0.0/29").is_private)
|
||||
+ self.assertEqual(False, ipaddress.ip_network("192.0.0.9/32").is_private)
|
||||
+ self.assertEqual(True, ipaddress.ip_network("192.0.0.170/31").is_private)
|
||||
+ self.assertEqual(True, ipaddress.ip_network("192.0.2.0/24").is_private)
|
||||
+ self.assertEqual(True, ipaddress.ip_network("192.168.0.0/16").is_private)
|
||||
+ self.assertEqual(True, ipaddress.ip_network("198.18.0.0/15").is_private)
|
||||
+ self.assertEqual(True, ipaddress.ip_network("198.51.100.0/24").is_private)
|
||||
+ self.assertEqual(True, ipaddress.ip_network("203.0.113.0/24").is_private)
|
||||
+ self.assertEqual(True, ipaddress.ip_network("240.0.0.0/4").is_private)
|
||||
+ self.assertEqual(True, ipaddress.ip_network("255.255.255.255/32").is_private)
|
||||
+
|
||||
+ self.assertEqual(False, ipaddress.ip_network("::/0").is_private)
|
||||
+ self.assertEqual(False, ipaddress.ip_network("::ff/128").is_private)
|
||||
+
|
||||
+ self.assertEqual(True, ipaddress.ip_network("::1/128").is_private)
|
||||
+ self.assertEqual(True, ipaddress.ip_network("::/128").is_private)
|
||||
+ self.assertEqual(True, ipaddress.ip_network("::ffff:0:0/96").is_private)
|
||||
+ self.assertEqual(True, ipaddress.ip_network("100::/64").is_private)
|
||||
+ self.assertEqual(True, ipaddress.ip_network("2001:2::/48").is_private)
|
||||
+ self.assertEqual(False, ipaddress.ip_network("2001:3::/48").is_private)
|
||||
+ self.assertEqual(True, ipaddress.ip_network("2001:db8::/32").is_private)
|
||||
+ self.assertEqual(True, ipaddress.ip_network("2001:10::/28").is_private)
|
||||
+ self.assertEqual(True, ipaddress.ip_network("fc00::/7").is_private)
|
||||
+ self.assertEqual(True, ipaddress.ip_network("fe80::/10").is_private)
|
||||
+
|
||||
def testReservedIpv6(self):
|
||||
|
||||
self.assertEqual(True, ipaddress.ip_network('ffff::').is_multicast)
|
||||
@@ -2351,6 +2389,20 @@ class IpaddrUnitTest(unittest.TestCase):
|
||||
self.assertEqual(True, ipaddress.ip_address('0::0').is_unspecified)
|
||||
self.assertEqual(False, ipaddress.ip_address('::1').is_unspecified)
|
||||
|
||||
+ self.assertFalse(ipaddress.ip_address('64:ff9b:1::').is_global)
|
||||
+ self.assertFalse(ipaddress.ip_address('2001::').is_global)
|
||||
+ self.assertTrue(ipaddress.ip_address('2001:1::1').is_global)
|
||||
+ self.assertTrue(ipaddress.ip_address('2001:1::2').is_global)
|
||||
+ self.assertFalse(ipaddress.ip_address('2001:2::').is_global)
|
||||
+ self.assertTrue(ipaddress.ip_address('2001:3::').is_global)
|
||||
+ self.assertFalse(ipaddress.ip_address('2001:4::').is_global)
|
||||
+ self.assertTrue(ipaddress.ip_address('2001:4:112::').is_global)
|
||||
+ self.assertFalse(ipaddress.ip_address('2001:10::').is_global)
|
||||
+ self.assertTrue(ipaddress.ip_address('2001:20::').is_global)
|
||||
+ self.assertTrue(ipaddress.ip_address('2001:30::').is_global)
|
||||
+ self.assertFalse(ipaddress.ip_address('2001:40::').is_global)
|
||||
+ self.assertFalse(ipaddress.ip_address('2002::').is_global)
|
||||
+
|
||||
# some generic IETF reserved addresses
|
||||
self.assertEqual(True, ipaddress.ip_address('100::').is_reserved)
|
||||
self.assertEqual(True, ipaddress.ip_network('4000::1/128').is_reserved)
|
||||
diff --git a/Misc/NEWS.d/next/Library/2024-03-14-01-38-44.gh-issue-113171.VFnObz.rst b/Misc/NEWS.d/next/Library/2024-03-14-01-38-44.gh-issue-113171.VFnObz.rst
|
||||
new file mode 100644
|
||||
index 0000000..f9a7247
|
||||
--- /dev/null
|
||||
+++ b/Misc/NEWS.d/next/Library/2024-03-14-01-38-44.gh-issue-113171.VFnObz.rst
|
||||
@@ -0,0 +1,9 @@
|
||||
+Fixed various false positives and false negatives in
|
||||
+
|
||||
+* :attr:`ipaddress.IPv4Address.is_private` (see these docs for details)
|
||||
+* :attr:`ipaddress.IPv4Address.is_global`
|
||||
+* :attr:`ipaddress.IPv6Address.is_private`
|
||||
+* :attr:`ipaddress.IPv6Address.is_global`
|
||||
+
|
||||
+Also in the corresponding :class:`ipaddress.IPv4Network` and :class:`ipaddress.IPv6Network`
|
||||
+attributes.
|
||||
--
|
||||
2.45.2
|
||||
|
||||
@ -0,0 +1,128 @@
|
||||
From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
|
||||
From: "Jason R. Coombs" <jaraco@jaraco.com>
|
||||
Date: Mon, 19 Aug 2024 19:28:20 -0400
|
||||
Subject: [PATCH] 00436: [CVE-2024-8088] gh-122905: Sanitize names in
|
||||
zipfile.Path.
|
||||
|
||||
Co-authored-by: Jason R. Coombs <jaraco@jaraco.com>
|
||||
---
|
||||
Lib/test/test_zipfile.py | 17 ++++++
|
||||
Lib/zipfile.py | 61 ++++++++++++++++++-
|
||||
...-08-11-14-08-04.gh-issue-122905.7tDsxA.rst | 1 +
|
||||
3 files changed, 78 insertions(+), 1 deletion(-)
|
||||
create mode 100644 Misc/NEWS.d/next/Library/2024-08-11-14-08-04.gh-issue-122905.7tDsxA.rst
|
||||
|
||||
diff --git a/Lib/test/test_zipfile.py b/Lib/test/test_zipfile.py
|
||||
index 17e95eb862..9a72152357 100644
|
||||
--- a/Lib/test/test_zipfile.py
|
||||
+++ b/Lib/test/test_zipfile.py
|
||||
@@ -3054,6 +3054,23 @@ class TestPath(unittest.TestCase):
|
||||
data = ['/'.join(string.ascii_lowercase + str(n)) for n in range(10000)]
|
||||
zipfile.CompleteDirs._implied_dirs(data)
|
||||
|
||||
+ def test_malformed_paths(self):
|
||||
+ """
|
||||
+ Path should handle malformed paths.
|
||||
+ """
|
||||
+ data = io.BytesIO()
|
||||
+ zf = zipfile.ZipFile(data, "w")
|
||||
+ zf.writestr("/one-slash.txt", b"content")
|
||||
+ zf.writestr("//two-slash.txt", b"content")
|
||||
+ zf.writestr("../parent.txt", b"content")
|
||||
+ zf.filename = ''
|
||||
+ root = zipfile.Path(zf)
|
||||
+ assert list(map(str, root.iterdir())) == [
|
||||
+ 'one-slash.txt',
|
||||
+ 'two-slash.txt',
|
||||
+ 'parent.txt',
|
||||
+ ]
|
||||
+
|
||||
|
||||
if __name__ == "__main__":
|
||||
unittest.main()
|
||||
diff --git a/Lib/zipfile.py b/Lib/zipfile.py
|
||||
index 95f95ee112..2e9b2868cd 100644
|
||||
--- a/Lib/zipfile.py
|
||||
+++ b/Lib/zipfile.py
|
||||
@@ -9,6 +9,7 @@ import io
|
||||
import itertools
|
||||
import os
|
||||
import posixpath
|
||||
+import re
|
||||
import shutil
|
||||
import stat
|
||||
import struct
|
||||
@@ -2177,7 +2178,65 @@ def _difference(minuend, subtrahend):
|
||||
return itertools.filterfalse(set(subtrahend).__contains__, minuend)
|
||||
|
||||
|
||||
-class CompleteDirs(ZipFile):
|
||||
+class SanitizedNames:
|
||||
+ """
|
||||
+ ZipFile mix-in to ensure names are sanitized.
|
||||
+ """
|
||||
+
|
||||
+ def namelist(self):
|
||||
+ return list(map(self._sanitize, super().namelist()))
|
||||
+
|
||||
+ @staticmethod
|
||||
+ def _sanitize(name):
|
||||
+ r"""
|
||||
+ Ensure a relative path with posix separators and no dot names.
|
||||
+ Modeled after
|
||||
+ https://github.com/python/cpython/blob/bcc1be39cb1d04ad9fc0bd1b9193d3972835a57c/Lib/zipfile/__init__.py#L1799-L1813
|
||||
+ but provides consistent cross-platform behavior.
|
||||
+ >>> san = SanitizedNames._sanitize
|
||||
+ >>> san('/foo/bar')
|
||||
+ 'foo/bar'
|
||||
+ >>> san('//foo.txt')
|
||||
+ 'foo.txt'
|
||||
+ >>> san('foo/.././bar.txt')
|
||||
+ 'foo/bar.txt'
|
||||
+ >>> san('foo../.bar.txt')
|
||||
+ 'foo../.bar.txt'
|
||||
+ >>> san('\\foo\\bar.txt')
|
||||
+ 'foo/bar.txt'
|
||||
+ >>> san('D:\\foo.txt')
|
||||
+ 'D/foo.txt'
|
||||
+ >>> san('\\\\server\\share\\file.txt')
|
||||
+ 'server/share/file.txt'
|
||||
+ >>> san('\\\\?\\GLOBALROOT\\Volume3')
|
||||
+ '?/GLOBALROOT/Volume3'
|
||||
+ >>> san('\\\\.\\PhysicalDrive1\\root')
|
||||
+ 'PhysicalDrive1/root'
|
||||
+ Retain any trailing slash.
|
||||
+ >>> san('abc/')
|
||||
+ 'abc/'
|
||||
+ Raises a ValueError if the result is empty.
|
||||
+ >>> san('../..')
|
||||
+ Traceback (most recent call last):
|
||||
+ ...
|
||||
+ ValueError: Empty filename
|
||||
+ """
|
||||
+
|
||||
+ def allowed(part):
|
||||
+ return part and part not in {'..', '.'}
|
||||
+
|
||||
+ # Remove the drive letter.
|
||||
+ # Don't use ntpath.splitdrive, because that also strips UNC paths
|
||||
+ bare = re.sub('^([A-Z]):', r'\1', name, flags=re.IGNORECASE)
|
||||
+ clean = bare.replace('\\', '/')
|
||||
+ parts = clean.split('/')
|
||||
+ joined = '/'.join(filter(allowed, parts))
|
||||
+ if not joined:
|
||||
+ raise ValueError("Empty filename")
|
||||
+ return joined + '/' * name.endswith('/')
|
||||
+
|
||||
+
|
||||
+class CompleteDirs(SanitizedNames, ZipFile):
|
||||
"""
|
||||
A ZipFile subclass that ensures that implied directories
|
||||
are always included in the namelist.
|
||||
diff --git a/Misc/NEWS.d/next/Library/2024-08-11-14-08-04.gh-issue-122905.7tDsxA.rst b/Misc/NEWS.d/next/Library/2024-08-11-14-08-04.gh-issue-122905.7tDsxA.rst
|
||||
new file mode 100644
|
||||
index 0000000000..1be44c906c
|
||||
--- /dev/null
|
||||
+++ b/Misc/NEWS.d/next/Library/2024-08-11-14-08-04.gh-issue-122905.7tDsxA.rst
|
||||
@@ -0,0 +1 @@
|
||||
+:class:`zipfile.Path` objects now sanitize names from the zipfile.
|
||||
@ -1,16 +0,0 @@
|
||||
-----BEGIN PGP SIGNATURE-----
|
||||
|
||||
iQIzBAABCgAdFiEE4/8oOcBIslwITevpsmmV4xAlBWgFAmOPjAQACgkQsmmV4xAl
|
||||
BWjzjQ//TQ9AtAs3RwRfGfJigHl3TG5lfYYdzAZIwEtt6NUw8tVKriCBMSvsJDjD
|
||||
rlFX64SPWaDlTggnatU88sj1y4AtGpf517GbYKwJ1oLQjcCSIs6WSxD7CZAfb4CL
|
||||
257KMANkT/n46luovTraqhAyLXp8fVWIEoSt3+6RgNYshjv00V6+L0HoE6jkzBRV
|
||||
si6KHDUCyIydOJEtAt79w5Ze/pFxJjIlGZ6WxyRVEy77cyQKh0g4dSdQ15HZAsfr
|
||||
fvv8rOmd8VXwIMi4xaUaHMddQxNrydDldDpKR4L1Lay/nY3OvSLI1AMw0D7n/FVO
|
||||
HxgYvxwkRqHPgbDIBLoHe7nsou0621ELS+j6M7cRoqAjsSfEOwpHOBw7k4+zOoa3
|
||||
4FHvru6TmT1p2iT6GSRllp/XspAzSelJeaFWA0Rs57MQ14gtXrw5hQHyZ1NgMzZi
|
||||
TMpnj0tGHufQYn2ZQqGUIySvtH3S5eIZgZGdPETJ5k09mcRVEKcdujTbkrIcOYtC
|
||||
GoPCw+3Qe7feVZLzElnsela9bDZi3uWfZh2kVyhZPAvxXJ0VNVCLvPlCKpr0R7t5
|
||||
JJ7jMpblsA05FT6ZanbqWNFZtCHMjlkK1259oST3BMbBSHTFgY/KGJEHQTkYU3M2
|
||||
U5OSn4za47qFBTVIXQsqkLGEBU/wrxtNmerJel8YW3ZIrkoTv2E=
|
||||
=dXB5
|
||||
-----END PGP SIGNATURE-----
|
||||
@ -0,0 +1,16 @@
|
||||
-----BEGIN PGP SIGNATURE-----
|
||||
|
||||
iQIzBAABCgAdFiEE4/8oOcBIslwITevpsmmV4xAlBWgFAmX5uMIACgkQsmmV4xAl
|
||||
BWj1tQ//T2qX0m08xWGV7az0D1sH3qjoY+4fEYrknw5uAHqZFiQecRsF27jxv6iH
|
||||
gP/6GAUw+lbH+9UofhCc0NbPOklliS7gFLNqJdKYFB6JXRNxiRYKh3uVx5o2n0ES
|
||||
kR3kRl77S47rtCbSMrKTh6ZoWowyIUZGFsIonk5KsLv+oELXY1AK/Im9i3/iTJ1Z
|
||||
jd/e2oHWuseIxbGZAO8AEP8zOsMMIHfsL3ry8H9xhhPyQM6t5DldqLH3UVE6kq95
|
||||
fs+olGO4FEKif3VDuLaHVlgtGZOUr6aDIYUmWxctPicboSb6RJAq37CCYgWykOyB
|
||||
WQec0ONbU7lxt5jhemLSDRy0mEio7+nXIKsO9rDN0Wk1QMpHUl77/C5qVlzfHal7
|
||||
NhPt8Yl0hBnOjzTq+di+xhAKJcdKp+zZH7/ugAbthuqhNfnkqiF68PANHrCm3gbY
|
||||
myN0eSaQ9yIa/MbHW8Am9NL/nuFbxdJUL/OIKQ9kFHgD7Qid86TZF0G2vbiBH/eF
|
||||
IVYoMxRZLd7eu5dIcwXSef+Ai97pODbx9y7bOCFyBO9FuFrlhPObgc7KXCeAzP+y
|
||||
k5eWvZtWTvvQ+2si2iT22EPBO0D0pnhYWZKpGK5EuKuw8nasNS1yLbhDTVpARynd
|
||||
8buQh3t2wPfILlQr0+JzDY8GSdQ/nIHGgx2IERdSX/v+9Yo2AvU=
|
||||
=gYAl
|
||||
-----END PGP SIGNATURE-----
|
||||
Loading…
Reference in new issue