Compare commits
No commits in common. 'i9' and 'c9-beta' have entirely different histories.
@ -1,2 +1 @@
|
||||
SOURCES/Python-3.11.2.tar.xz
|
||||
SOURCES/pgp_keys.asc
|
||||
SOURCES/Python-3.11.9.tar.xz
|
||||
|
||||
@ -1,2 +1 @@
|
||||
ae1c199ecb7a969588b15354e19e7b60cb65d1b9 SOURCES/Python-3.11.2.tar.xz
|
||||
befe131eceffa73877ba3adceca3b7b1da1d2319 SOURCES/pgp_keys.asc
|
||||
926cd6a577b2e8dcbb17671b30eda04019328ada SOURCES/Python-3.11.9.tar.xz
|
||||
|
||||
@ -0,0 +1,250 @@
|
||||
From 0181d677dd7fd11bc19a211b3eb735ac3ad3d7fb Mon Sep 17 00:00:00 2001
|
||||
From: Petr Viktorin <encukou@gmail.com>
|
||||
Date: Mon, 6 Mar 2023 17:24:24 +0100
|
||||
Subject: [PATCH] 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 | 127 ++++++++++++++++++++++++++++++++++++++-
|
||||
3 files changed, 168 insertions(+), 4 deletions(-)
|
||||
|
||||
diff --git a/Lib/tarfile.py b/Lib/tarfile.py
|
||||
index 612217b..dc59fc6 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
|
||||
@@ -2219,6 +2226,41 @@ 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 6728d30..2338b63 100644
|
||||
--- a/Lib/test/test_shutil.py
|
||||
+++ b/Lib/test/test_shutil.py
|
||||
@@ -1774,7 +1774,8 @@ 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 389da7b..5a43f9d 100644
|
||||
--- a/Lib/test/test_tarfile.py
|
||||
+++ b/Lib/test/test_tarfile.py
|
||||
@@ -3,7 +3,7 @@ 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
|
||||
@@ -3049,7 +3049,11 @@ 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)
|
||||
@@ -3868,7 +3872,8 @@ 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')
|
||||
|
||||
@@ -4037,6 +4042,122 @@ class TestExtractionFilters(unittest.TestCase):
|
||||
with self.check_context(arc.open(errorlevel='boo!'), filtererror_filter):
|
||||
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 (
|
||||
+ os_helper.temp_dir(tempdir),
|
||||
+ support.swap_attr(tarfile, '_CONFIG_FILENAME', str(configfile)),
|
||||
+ os_helper.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)
|
||||
+
|
||||
|
||||
class OverwriteTests(archiver_tests.OverwriteTests, unittest.TestCase):
|
||||
testdir = os.path.join(TEMPDIR, "testoverwrite")
|
||||
--
|
||||
2.44.0
|
||||
|
||||
@ -0,0 +1,748 @@
|
||||
From 642f28679e04c7b4ec7731f0c8872103f21a76f8 Mon Sep 17 00:00:00 2001
|
||||
From: Victor Stinner <vstinner@python.org>
|
||||
Date: Fri, 15 Dec 2023 16:10:40 +0100
|
||||
Subject: [PATCH 1/2] 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 | 150 ++++++++++++-
|
||||
Lib/test/test_email/test_email.py | 204 +++++++++++++++++-
|
||||
...-10-20-15-28-08.gh-issue-102988.dStNO7.rst | 8 +
|
||||
4 files changed, 360 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 0e266b6..6723dc4 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 8993858..41bb3c9 100644
|
||||
--- a/Lib/email/utils.py
|
||||
+++ b/Lib/email/utils.py
|
||||
@@ -106,12 +106,127 @@ 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)
|
||||
+
|
||||
+
|
||||
+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.
|
||||
|
||||
-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
|
||||
+ 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):
|
||||
@@ -205,16 +320,33 @@ 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 785696e..ad60ed3 100644
|
||||
--- a/Lib/test/test_email/test_email.py
|
||||
+++ b/Lib/test/test_email/test_email.py
|
||||
@@ -17,6 +17,7 @@ from unittest.mock import patch
|
||||
|
||||
import email
|
||||
import email.policy
|
||||
+import email.utils
|
||||
|
||||
from email.charset import Charset
|
||||
from email.generator import Generator, DecodedGenerator, BytesGenerator
|
||||
@@ -3336,15 +3337,154 @@ 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"""
|
||||
@@ -3535,6 +3675,54 @@ 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.
|
||||
--
|
||||
2.44.0
|
||||
|
||||
|
||||
From d371679e7c485551c10380ac11e5039a9fb4515b Mon Sep 17 00:00:00 2001
|
||||
From: Lumir Balhar <lbalhar@redhat.com>
|
||||
Date: Wed, 10 Jan 2024 08:53:53 +0100
|
||||
Subject: [PATCH 2/2] Make it possible to disable strict parsing in email
|
||||
module
|
||||
|
||||
---
|
||||
Doc/library/email.utils.rst | 26 +++++++++++
|
||||
Lib/email/utils.py | 55 ++++++++++++++++++++++-
|
||||
Lib/test/test_email/test_email.py | 74 ++++++++++++++++++++++++++++++-
|
||||
3 files changed, 151 insertions(+), 4 deletions(-)
|
||||
|
||||
diff --git a/Doc/library/email.utils.rst b/Doc/library/email.utils.rst
|
||||
index 6723dc4..c89602d 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 41bb3c9..09a414c 100644
|
||||
--- a/Lib/email/utils.py
|
||||
+++ b/Lib/email/utils.py
|
||||
@@ -48,6 +48,47 @@ 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 may contain surrogate-escaped binary data."""
|
||||
# This check is based on the fact that unless there are surrogates, utf8
|
||||
@@ -148,7 +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
|
||||
@@ -157,6 +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 [('',
|
||||
@@ -320,7 +366,7 @@ 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.
|
||||
|
||||
@@ -329,6 +375,11 @@ 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 ad60ed3..f85da56 100644
|
||||
--- a/Lib/test/test_email/test_email.py
|
||||
+++ b/Lib/test/test_email/test_email.py
|
||||
@@ -8,6 +8,9 @@ import base64
|
||||
import unittest
|
||||
import textwrap
|
||||
import warnings
|
||||
+import contextlib
|
||||
+import tempfile
|
||||
+import os
|
||||
|
||||
from io import StringIO, BytesIO
|
||||
from itertools import chain
|
||||
@@ -41,8 +44,8 @@ from email import quoprimime
|
||||
from email import utils
|
||||
|
||||
from test import support
|
||||
-from test.support import threading_helper
|
||||
-from test.support.os_helper import unlink
|
||||
+from test.support import threading_helper, swap_attr
|
||||
+from test.support.os_helper import unlink, EnvironmentVarGuard
|
||||
from test.test_email import openfile, TestEmailBase
|
||||
|
||||
# These imports are documented to work, but we are testing them using a
|
||||
@@ -3442,6 +3445,73 @@ 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>'],
|
||||
--
|
||||
2.44.0
|
||||
|
||||
@ -0,0 +1,75 @@
|
||||
From 670984c96eea60488c5355b4cf535c1ee3cf081a Mon Sep 17 00:00:00 2001
|
||||
From: rpm-build <rpm-build>
|
||||
Date: Wed, 24 Apr 2024 04:24:16 +0200
|
||||
Subject: [PATCH] Fix xml tests
|
||||
|
||||
---
|
||||
Lib/test/test_pyexpat.py | 3 +++
|
||||
Lib/test/test_sax.py | 2 ++
|
||||
Lib/test/test_xml_etree.py | 6 ++++++
|
||||
3 files changed, 11 insertions(+)
|
||||
|
||||
diff --git a/Lib/test/test_pyexpat.py b/Lib/test/test_pyexpat.py
|
||||
index 44bd1de..5976fa0 100644
|
||||
--- a/Lib/test/test_pyexpat.py
|
||||
+++ b/Lib/test/test_pyexpat.py
|
||||
@@ -3,6 +3,7 @@
|
||||
|
||||
import os
|
||||
import platform
|
||||
+import pyexpat
|
||||
import sys
|
||||
import sysconfig
|
||||
import unittest
|
||||
@@ -793,6 +794,8 @@ class ReparseDeferralTest(unittest.TestCase):
|
||||
|
||||
self.assertEqual(started, ['doc'])
|
||||
|
||||
+ @unittest.skipIf(pyexpat.version_info < (2, 6, 0),
|
||||
+ "Reparse deferral not defined for libexpat < 2.6.0")
|
||||
def test_reparse_deferral_disabled(self):
|
||||
started = []
|
||||
|
||||
diff --git a/Lib/test/test_sax.py b/Lib/test/test_sax.py
|
||||
index 9b3014a..5960de1 100644
|
||||
--- a/Lib/test/test_sax.py
|
||||
+++ b/Lib/test/test_sax.py
|
||||
@@ -1240,6 +1240,8 @@ class ExpatReaderTest(XmlTestBase):
|
||||
|
||||
self.assertEqual(result.getvalue(), start + b"<doc></doc>")
|
||||
|
||||
+ @unittest.skipIf(pyexpat.version_info < (2, 6, 0),
|
||||
+ "Reparse deferral not defined for libexpat < 2.6.0")
|
||||
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 8becafb..5e9b6b5 100644
|
||||
--- a/Lib/test/test_xml_etree.py
|
||||
+++ b/Lib/test/test_xml_etree.py
|
||||
@@ -1424,9 +1424,13 @@ class XMLPullParserTest(unittest.TestCase):
|
||||
self.assert_event_tags(parser, [('end', 'root')])
|
||||
self.assertIsNone(parser.close())
|
||||
|
||||
+ @unittest.skipIf(pyexpat.version_info < (2, 6, 0),
|
||||
+ "test not compatible with the latest expat security release")
|
||||
def test_simple_xml_chunk_1(self):
|
||||
self.test_simple_xml(chunk_size=1, flush=True)
|
||||
|
||||
+ @unittest.skipIf(pyexpat.version_info < (2, 6, 0),
|
||||
+ "test not compatible with the latest expat security release")
|
||||
def test_simple_xml_chunk_5(self):
|
||||
self.test_simple_xml(chunk_size=5, flush=True)
|
||||
|
||||
@@ -1651,6 +1655,8 @@ class XMLPullParserTest(unittest.TestCase):
|
||||
|
||||
self.assert_event_tags(parser, [('end', 'doc')])
|
||||
|
||||
+ @unittest.skipIf(pyexpat.version_info < (2, 6, 0),
|
||||
+ "Reparse deferral not defined for libexpat < 2.6.0")
|
||||
def test_flush_reparse_deferral_disabled(self):
|
||||
parser = ET.XMLPullParser(events=('start', 'end'))
|
||||
|
||||
--
|
||||
2.44.0
|
||||
|
||||
@ -0,0 +1,346 @@
|
||||
From 2963bbab04546f5aef6a37a3b027ae7a484deec1 Mon Sep 17 00:00:00 2001
|
||||
From: Petr Viktorin <encukou@gmail.com>
|
||||
Date: Thu, 25 Apr 2024 14:45:48 +0200
|
||||
Subject: [PATCH] gh-113171: gh-65056: Fix "private" (non-global) IP address
|
||||
ranges (GH-113179) (GH-113186) (GH-118177) (#118227)
|
||||
|
||||
---
|
||||
Doc/library/ipaddress.rst | 43 +++++++-
|
||||
Doc/whatsnew/3.11.rst | 9 ++
|
||||
Lib/ipaddress.py | 99 +++++++++++++++----
|
||||
Lib/test/test_ipaddress.py | 21 +++-
|
||||
...-03-14-01-38-44.gh-issue-113171.VFnObz.rst | 9 ++
|
||||
5 files changed, 157 insertions(+), 24 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 03dc956..f57fa15 100644
|
||||
--- a/Doc/library/ipaddress.rst
|
||||
+++ b/Doc/library/ipaddress.rst
|
||||
@@ -178,18 +178,53 @@ 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:: 3.11.10
|
||||
+
|
||||
+ 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:: 3.11.10
|
||||
+
|
||||
+ 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/whatsnew/3.11.rst b/Doc/whatsnew/3.11.rst
|
||||
index f670fa1..42b61c7 100644
|
||||
--- a/Doc/whatsnew/3.11.rst
|
||||
+++ b/Doc/whatsnew/3.11.rst
|
||||
@@ -2727,3 +2727,12 @@ OpenSSL
|
||||
* Windows builds and macOS installers from python.org now use OpenSSL 3.0.
|
||||
|
||||
.. _libb2: https://www.blake2.net/
|
||||
+
|
||||
+Notable changes in 3.11.10
|
||||
+==========================
|
||||
+
|
||||
+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 16ba16c..567beb3 100644
|
||||
--- a/Lib/ipaddress.py
|
||||
+++ b/Lib/ipaddress.py
|
||||
@@ -1086,7 +1086,11 @@ class _BaseNetwork(_IPAddressBase):
|
||||
"""
|
||||
return any(self.network_address in priv_network and
|
||||
self.broadcast_address in priv_network
|
||||
- for priv_network in self._constants._private_networks)
|
||||
+ for priv_network in self._constants._private_networks) and all(
|
||||
+ self.network_address not in network and
|
||||
+ self.broadcast_address not in network
|
||||
+ for network in self._constants._private_networks_exceptions
|
||||
+ )
|
||||
|
||||
@property
|
||||
def is_global(self):
|
||||
@@ -1333,18 +1337,41 @@ 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
|
||||
@@ -1548,13 +1575,15 @@ 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'),
|
||||
@@ -1565,6 +1594,11 @@ 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')
|
||||
@@ -2010,27 +2044,42 @@ 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, or is ipv4_mapped and is
|
||||
- reserved in the 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``.
|
||||
"""
|
||||
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)
|
||||
+ 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
|
||||
|
||||
@@ -2271,19 +2320,31 @@ 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 fc27628..16c3416 100644
|
||||
--- a/Lib/test/test_ipaddress.py
|
||||
+++ b/Lib/test/test_ipaddress.py
|
||||
@@ -2269,6 +2269,10 @@ 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)
|
||||
@@ -2294,6 +2298,7 @@ class IpaddrUnitTest(unittest.TestCase):
|
||||
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)
|
||||
@@ -2310,8 +2315,8 @@ class IpaddrUnitTest(unittest.TestCase):
|
||||
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::/23").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)
|
||||
@@ -2390,6 +2395,20 @@ 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 +1,365 @@
|
||||
From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
|
||||
From: Petr Viktorin <encukou@gmail.com>
|
||||
Date: Wed, 31 Jul 2024 00:19:48 +0200
|
||||
Subject: [PATCH] 00435: gh-121650: Encode newlines in headers, and verify
|
||||
headers are sound (GH-122233)
|
||||
|
||||
Per RFC 2047:
|
||||
|
||||
> [...] these encoding schemes allow the
|
||||
> encoding of arbitrary octet values, mail readers that implement this
|
||||
> decoding should also ensure that display of the decoded data on the
|
||||
> recipient's terminal will not cause unwanted side-effects
|
||||
|
||||
It seems that the "quoted-word" scheme is a valid way to include
|
||||
a newline character in a header value, just like we already allow
|
||||
undecodable bytes or control characters.
|
||||
They do need to be properly quoted when serialized to text, though.
|
||||
|
||||
This should fail for custom fold() implementations that aren't careful
|
||||
about newlines.
|
||||
|
||||
(cherry picked from commit 097633981879b3c9de9a1dd120d3aa585ecc2384)
|
||||
|
||||
Co-authored-by: Petr Viktorin <encukou@gmail.com>
|
||||
Co-authored-by: Bas Bloemsaat <bas@bloemsaat.org>
|
||||
Co-authored-by: Serhiy Storchaka <storchaka@gmail.com>
|
||||
---
|
||||
Doc/library/email.errors.rst | 7 +++
|
||||
Doc/library/email.policy.rst | 18 ++++++
|
||||
Doc/whatsnew/3.11.rst | 13 ++++
|
||||
Lib/email/_header_value_parser.py | 12 +++-
|
||||
Lib/email/_policybase.py | 8 +++
|
||||
Lib/email/errors.py | 4 ++
|
||||
Lib/email/generator.py | 13 +++-
|
||||
Lib/test/test_email/test_generator.py | 62 +++++++++++++++++++
|
||||
Lib/test/test_email/test_policy.py | 26 ++++++++
|
||||
...-07-27-16-10-41.gh-issue-121650.nf6oc9.rst | 5 ++
|
||||
10 files changed, 164 insertions(+), 4 deletions(-)
|
||||
create mode 100644 Misc/NEWS.d/next/Library/2024-07-27-16-10-41.gh-issue-121650.nf6oc9.rst
|
||||
|
||||
diff --git a/Doc/library/email.errors.rst b/Doc/library/email.errors.rst
|
||||
index 56aea6598b..27b0481a85 100644
|
||||
--- a/Doc/library/email.errors.rst
|
||||
+++ b/Doc/library/email.errors.rst
|
||||
@@ -58,6 +58,13 @@ The following exception classes are defined in the :mod:`email.errors` module:
|
||||
:class:`~email.mime.nonmultipart.MIMENonMultipart` (e.g.
|
||||
:class:`~email.mime.image.MIMEImage`).
|
||||
|
||||
+
|
||||
+.. exception:: HeaderWriteError()
|
||||
+
|
||||
+ Raised when an error occurs when the :mod:`~email.generator` outputs
|
||||
+ headers.
|
||||
+
|
||||
+
|
||||
.. exception:: MessageDefect()
|
||||
|
||||
This is the base class for all defects found when parsing email messages.
|
||||
diff --git a/Doc/library/email.policy.rst b/Doc/library/email.policy.rst
|
||||
index bb406c5a56..3edba4028b 100644
|
||||
--- a/Doc/library/email.policy.rst
|
||||
+++ b/Doc/library/email.policy.rst
|
||||
@@ -228,6 +228,24 @@ added matters. To illustrate::
|
||||
|
||||
.. versionadded:: 3.6
|
||||
|
||||
+
|
||||
+ .. attribute:: verify_generated_headers
|
||||
+
|
||||
+ If ``True`` (the default), the generator will raise
|
||||
+ :exc:`~email.errors.HeaderWriteError` instead of writing a header
|
||||
+ that is improperly folded or delimited, such that it would
|
||||
+ be parsed as multiple headers or joined with adjacent data.
|
||||
+ Such headers can be generated by custom header classes or bugs
|
||||
+ in the ``email`` module.
|
||||
+
|
||||
+ As it's a security feature, this defaults to ``True`` even in the
|
||||
+ :class:`~email.policy.Compat32` policy.
|
||||
+ For backwards compatible, but unsafe, behavior, it must be set to
|
||||
+ ``False`` explicitly.
|
||||
+
|
||||
+ .. versionadded:: 3.11.10
|
||||
+
|
||||
+
|
||||
The following :class:`Policy` method is intended to be called by code using
|
||||
the email library to create policy instances with custom settings:
|
||||
|
||||
diff --git a/Doc/whatsnew/3.11.rst b/Doc/whatsnew/3.11.rst
|
||||
index 42b61c75c7..f12c871998 100644
|
||||
--- a/Doc/whatsnew/3.11.rst
|
||||
+++ b/Doc/whatsnew/3.11.rst
|
||||
@@ -2728,6 +2728,7 @@ OpenSSL
|
||||
|
||||
.. _libb2: https://www.blake2.net/
|
||||
|
||||
+
|
||||
Notable changes in 3.11.10
|
||||
==========================
|
||||
|
||||
@@ -2736,3 +2737,15 @@ ipaddress
|
||||
|
||||
* Fixed ``is_global`` and ``is_private`` behavior in ``IPv4Address``,
|
||||
``IPv6Address``, ``IPv4Network`` and ``IPv6Network``.
|
||||
+
|
||||
+email
|
||||
+-----
|
||||
+
|
||||
+* Headers with embedded newlines are now quoted on output.
|
||||
+
|
||||
+ The :mod:`~email.generator` will now refuse to serialize (write) headers
|
||||
+ that are improperly folded or delimited, such that they would be parsed as
|
||||
+ multiple headers or joined with adjacent data.
|
||||
+ If you need to turn this safety feature off,
|
||||
+ set :attr:`~email.policy.Policy.verify_generated_headers`.
|
||||
+ (Contributed by Bas Bloemsaat and Petr Viktorin in :gh:`121650`.)
|
||||
diff --git a/Lib/email/_header_value_parser.py b/Lib/email/_header_value_parser.py
|
||||
index 8cb8852cf0..255a953092 100644
|
||||
--- a/Lib/email/_header_value_parser.py
|
||||
+++ b/Lib/email/_header_value_parser.py
|
||||
@@ -92,6 +92,8 @@
|
||||
ASPECIALS = TSPECIALS | set("*'%")
|
||||
ATTRIBUTE_ENDS = ASPECIALS | WSP
|
||||
EXTENDED_ATTRIBUTE_ENDS = ATTRIBUTE_ENDS - set('%')
|
||||
+NLSET = {'\n', '\r'}
|
||||
+SPECIALSNL = SPECIALS | NLSET
|
||||
|
||||
def quote_string(value):
|
||||
return '"'+str(value).replace('\\', '\\\\').replace('"', r'\"')+'"'
|
||||
@@ -2780,9 +2782,13 @@ def _refold_parse_tree(parse_tree, *, policy):
|
||||
wrap_as_ew_blocked -= 1
|
||||
continue
|
||||
tstr = str(part)
|
||||
- if part.token_type == 'ptext' and set(tstr) & SPECIALS:
|
||||
- # Encode if tstr contains special characters.
|
||||
- want_encoding = True
|
||||
+ if not want_encoding:
|
||||
+ if part.token_type == 'ptext':
|
||||
+ # Encode if tstr contains special characters.
|
||||
+ want_encoding = not SPECIALSNL.isdisjoint(tstr)
|
||||
+ else:
|
||||
+ # Encode if tstr contains newlines.
|
||||
+ want_encoding = not NLSET.isdisjoint(tstr)
|
||||
try:
|
||||
tstr.encode(encoding)
|
||||
charset = encoding
|
||||
diff --git a/Lib/email/_policybase.py b/Lib/email/_policybase.py
|
||||
index c9cbadd2a8..d1f48211f9 100644
|
||||
--- a/Lib/email/_policybase.py
|
||||
+++ b/Lib/email/_policybase.py
|
||||
@@ -157,6 +157,13 @@ class Policy(_PolicyBase, metaclass=abc.ABCMeta):
|
||||
message_factory -- the class to use to create new message objects.
|
||||
If the value is None, the default is Message.
|
||||
|
||||
+ verify_generated_headers
|
||||
+ -- if true, the generator verifies that each header
|
||||
+ they are properly folded, so that a parser won't
|
||||
+ treat it as multiple headers, start-of-body, or
|
||||
+ part of another header.
|
||||
+ This is a check against custom Header & fold()
|
||||
+ implementations.
|
||||
"""
|
||||
|
||||
raise_on_defect = False
|
||||
@@ -165,6 +172,7 @@ class Policy(_PolicyBase, metaclass=abc.ABCMeta):
|
||||
max_line_length = 78
|
||||
mangle_from_ = False
|
||||
message_factory = None
|
||||
+ verify_generated_headers = True
|
||||
|
||||
def handle_defect(self, obj, defect):
|
||||
"""Based on policy, either raise defect or call register_defect.
|
||||
diff --git a/Lib/email/errors.py b/Lib/email/errors.py
|
||||
index 3ad0056554..02aa5eced6 100644
|
||||
--- a/Lib/email/errors.py
|
||||
+++ b/Lib/email/errors.py
|
||||
@@ -29,6 +29,10 @@ class CharsetError(MessageError):
|
||||
"""An illegal charset was given."""
|
||||
|
||||
|
||||
+class HeaderWriteError(MessageError):
|
||||
+ """Error while writing headers."""
|
||||
+
|
||||
+
|
||||
# These are parsing defects which the parser was able to work around.
|
||||
class MessageDefect(ValueError):
|
||||
"""Base class for a message defect."""
|
||||
diff --git a/Lib/email/generator.py b/Lib/email/generator.py
|
||||
index eb597de76d..563ca17072 100644
|
||||
--- a/Lib/email/generator.py
|
||||
+++ b/Lib/email/generator.py
|
||||
@@ -14,12 +14,14 @@
|
||||
from copy import deepcopy
|
||||
from io import StringIO, BytesIO
|
||||
from email.utils import _has_surrogates
|
||||
+from email.errors import HeaderWriteError
|
||||
|
||||
UNDERSCORE = '_'
|
||||
NL = '\n' # XXX: no longer used by the code below.
|
||||
|
||||
NLCRE = re.compile(r'\r\n|\r|\n')
|
||||
fcre = re.compile(r'^From ', re.MULTILINE)
|
||||
+NEWLINE_WITHOUT_FWSP = re.compile(r'\r\n[^ \t]|\r[^ \n\t]|\n[^ \t]')
|
||||
|
||||
|
||||
class Generator:
|
||||
@@ -222,7 +224,16 @@ def _dispatch(self, msg):
|
||||
|
||||
def _write_headers(self, msg):
|
||||
for h, v in msg.raw_items():
|
||||
- self.write(self.policy.fold(h, v))
|
||||
+ folded = self.policy.fold(h, v)
|
||||
+ if self.policy.verify_generated_headers:
|
||||
+ linesep = self.policy.linesep
|
||||
+ if not folded.endswith(self.policy.linesep):
|
||||
+ raise HeaderWriteError(
|
||||
+ f'folded header does not end with {linesep!r}: {folded!r}')
|
||||
+ if NEWLINE_WITHOUT_FWSP.search(folded.removesuffix(linesep)):
|
||||
+ raise HeaderWriteError(
|
||||
+ f'folded header contains newline: {folded!r}')
|
||||
+ self.write(folded)
|
||||
# A blank line always separates headers from body
|
||||
self.write(self._NL)
|
||||
|
||||
diff --git a/Lib/test/test_email/test_generator.py b/Lib/test/test_email/test_generator.py
|
||||
index 89e7edeb63..d29400f0ed 100644
|
||||
--- a/Lib/test/test_email/test_generator.py
|
||||
+++ b/Lib/test/test_email/test_generator.py
|
||||
@@ -6,6 +6,7 @@
|
||||
from email.generator import Generator, BytesGenerator
|
||||
from email.headerregistry import Address
|
||||
from email import policy
|
||||
+import email.errors
|
||||
from test.test_email import TestEmailBase, parameterize
|
||||
|
||||
|
||||
@@ -216,6 +217,44 @@ def test_rfc2231_wrapping_switches_to_default_len_if_too_narrow(self):
|
||||
g.flatten(msg)
|
||||
self.assertEqual(s.getvalue(), self.typ(expected))
|
||||
|
||||
+ def test_keep_encoded_newlines(self):
|
||||
+ msg = self.msgmaker(self.typ(textwrap.dedent("""\
|
||||
+ To: nobody
|
||||
+ Subject: Bad subject=?UTF-8?Q?=0A?=Bcc: injection@example.com
|
||||
+
|
||||
+ None
|
||||
+ """)))
|
||||
+ expected = textwrap.dedent("""\
|
||||
+ To: nobody
|
||||
+ Subject: Bad subject=?UTF-8?Q?=0A?=Bcc: injection@example.com
|
||||
+
|
||||
+ None
|
||||
+ """)
|
||||
+ s = self.ioclass()
|
||||
+ g = self.genclass(s, policy=self.policy.clone(max_line_length=80))
|
||||
+ g.flatten(msg)
|
||||
+ self.assertEqual(s.getvalue(), self.typ(expected))
|
||||
+
|
||||
+ def test_keep_long_encoded_newlines(self):
|
||||
+ msg = self.msgmaker(self.typ(textwrap.dedent("""\
|
||||
+ To: nobody
|
||||
+ Subject: Bad subject=?UTF-8?Q?=0A?=Bcc: injection@example.com
|
||||
+
|
||||
+ None
|
||||
+ """)))
|
||||
+ expected = textwrap.dedent("""\
|
||||
+ To: nobody
|
||||
+ Subject: Bad subject
|
||||
+ =?utf-8?q?=0A?=Bcc:
|
||||
+ injection@example.com
|
||||
+
|
||||
+ None
|
||||
+ """)
|
||||
+ s = self.ioclass()
|
||||
+ g = self.genclass(s, policy=self.policy.clone(max_line_length=30))
|
||||
+ g.flatten(msg)
|
||||
+ self.assertEqual(s.getvalue(), self.typ(expected))
|
||||
+
|
||||
|
||||
class TestGenerator(TestGeneratorBase, TestEmailBase):
|
||||
|
||||
@@ -224,6 +263,29 @@ class TestGenerator(TestGeneratorBase, TestEmailBase):
|
||||
ioclass = io.StringIO
|
||||
typ = str
|
||||
|
||||
+ def test_verify_generated_headers(self):
|
||||
+ """gh-121650: by default the generator prevents header injection"""
|
||||
+ class LiteralHeader(str):
|
||||
+ name = 'Header'
|
||||
+ def fold(self, **kwargs):
|
||||
+ return self
|
||||
+
|
||||
+ for text in (
|
||||
+ 'Value\r\nBad Injection\r\n',
|
||||
+ 'NoNewLine'
|
||||
+ ):
|
||||
+ with self.subTest(text=text):
|
||||
+ message = message_from_string(
|
||||
+ "Header: Value\r\n\r\nBody",
|
||||
+ policy=self.policy,
|
||||
+ )
|
||||
+
|
||||
+ del message['Header']
|
||||
+ message['Header'] = LiteralHeader(text)
|
||||
+
|
||||
+ with self.assertRaises(email.errors.HeaderWriteError):
|
||||
+ message.as_string()
|
||||
+
|
||||
|
||||
class TestBytesGenerator(TestGeneratorBase, TestEmailBase):
|
||||
|
||||
diff --git a/Lib/test/test_email/test_policy.py b/Lib/test/test_email/test_policy.py
|
||||
index c6b9c80efe..baa35fd68e 100644
|
||||
--- a/Lib/test/test_email/test_policy.py
|
||||
+++ b/Lib/test/test_email/test_policy.py
|
||||
@@ -26,6 +26,7 @@ class PolicyAPITests(unittest.TestCase):
|
||||
'raise_on_defect': False,
|
||||
'mangle_from_': True,
|
||||
'message_factory': None,
|
||||
+ 'verify_generated_headers': True,
|
||||
}
|
||||
# These default values are the ones set on email.policy.default.
|
||||
# If any of these defaults change, the docs must be updated.
|
||||
@@ -294,6 +295,31 @@ def test_short_maxlen_error(self):
|
||||
with self.assertRaises(email.errors.HeaderParseError):
|
||||
policy.fold("Subject", subject)
|
||||
|
||||
+ def test_verify_generated_headers(self):
|
||||
+ """Turning protection off allows header injection"""
|
||||
+ policy = email.policy.default.clone(verify_generated_headers=False)
|
||||
+ for text in (
|
||||
+ 'Header: Value\r\nBad: Injection\r\n',
|
||||
+ 'Header: NoNewLine'
|
||||
+ ):
|
||||
+ with self.subTest(text=text):
|
||||
+ message = email.message_from_string(
|
||||
+ "Header: Value\r\n\r\nBody",
|
||||
+ policy=policy,
|
||||
+ )
|
||||
+ class LiteralHeader(str):
|
||||
+ name = 'Header'
|
||||
+ def fold(self, **kwargs):
|
||||
+ return self
|
||||
+
|
||||
+ del message['Header']
|
||||
+ message['Header'] = LiteralHeader(text)
|
||||
+
|
||||
+ self.assertEqual(
|
||||
+ message.as_string(),
|
||||
+ f"{text}\nBody",
|
||||
+ )
|
||||
+
|
||||
# XXX: Need subclassing tests.
|
||||
# For adding subclassed objects, make sure the usual rules apply (subclass
|
||||
# wins), but that the order still works (right overrides left).
|
||||
diff --git a/Misc/NEWS.d/next/Library/2024-07-27-16-10-41.gh-issue-121650.nf6oc9.rst b/Misc/NEWS.d/next/Library/2024-07-27-16-10-41.gh-issue-121650.nf6oc9.rst
|
||||
new file mode 100644
|
||||
index 0000000000..83dd28d4ac
|
||||
--- /dev/null
|
||||
+++ b/Misc/NEWS.d/next/Library/2024-07-27-16-10-41.gh-issue-121650.nf6oc9.rst
|
||||
@@ -0,0 +1,5 @@
|
||||
+:mod:`email` headers with embedded newlines are now quoted on output. The
|
||||
+:mod:`~email.generator` will now refuse to serialize (write) headers that
|
||||
+are unsafely folded or delimited; see
|
||||
+:attr:`~email.policy.Policy.verify_generated_headers`. (Contributed by Bas
|
||||
+Bloemsaat and Petr Viktorin in :gh:`121650`.)
|
||||
@ -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 4de6f379a4..8bdc7a1b7d 100644
|
||||
--- a/Lib/test/test_zipfile.py
|
||||
+++ b/Lib/test/test_zipfile.py
|
||||
@@ -3651,6 +3651,23 @@ def test_extract_orig_with_implied_dirs(self, alpharep):
|
||||
zipfile.Path(zf)
|
||||
zf.extractall(source_path.parent)
|
||||
|
||||
+ 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',
|
||||
+ ]
|
||||
+
|
||||
|
||||
class EncodedMetadataTests(unittest.TestCase):
|
||||
file_names = ['\u4e00', '\u4e8c', '\u4e09'] # Han 'one', 'two', 'three'
|
||||
diff --git a/Lib/zipfile.py b/Lib/zipfile.py
|
||||
index 86829abce4..b7bf9ef7e3 100644
|
||||
--- a/Lib/zipfile.py
|
||||
+++ b/Lib/zipfile.py
|
||||
@@ -9,6 +9,7 @@
|
||||
import itertools
|
||||
import os
|
||||
import posixpath
|
||||
+import re
|
||||
import shutil
|
||||
import stat
|
||||
import struct
|
||||
@@ -2243,7 +2244,65 @@ 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-----
|
||||
|
||||
iQIzBAABCAAdFiEEz9yiRbEEPPKl+Xhl/+h0BBaL2EcFAmPiV84ACgkQ/+h0BBaL
|
||||
2EeZ1xAAwBi0AEjUlZ9oeC54VuqC/XLuVwc3xWf+Irw/5mJA2/weJHoQqG9aEDkB
|
||||
ph1pDJ6G/vDyKdjh8NZKkKftIL9pggRpAcA4mQ3XcDMKI/J+EQe5P/BwsTGClLhK
|
||||
cZg6IcQKZvo9djfyRz48w9wfKs34NasBgoFQP+hOzmU10UMrcR7gUSB2ZgMVMDID
|
||||
0rK1w2aPmZmDLUltBhf6Xb2voUYo+3jINLHWmQC6tdDOBxtxv222dhxS1mvpV7Zu
|
||||
Xw8do9OsQxonc+owkpciMKDLcFoVmkdQPz9bmvHJKovMXT2RY7FEam9H7ukr35fC
|
||||
xA6BKnyMgvWIWQVTwjBhcz3C85adzAz/ypHNTbJOuPxp1ZP8qO3D6vPlhZIFyTeJ
|
||||
7LhagUBUkIKKtbz7u3ERJgvA6tn3UVyLOXM1DnaKkXQ1FgSymgWPRU7BsxanQ8FD
|
||||
QkfTjC8fatZLCewNfGInkeAdLue+rMwZc8Q6vw2CAmcVdOKsQ98Db/FLF5sC+Kjz
|
||||
D3brUESEX1ELcVk7vumUI0/z+MECF11dpv5hPOZ4cZDoInsNu846TfU0rzOeVe7H
|
||||
gGO6Ae/Lu5gG09TNqepbFGA/dWR8V3zdLs5ZShTT4FsNFrHh7GDAEAMZSwT3AsVZ
|
||||
TjOdU3+xEGsEfrYWRXOkhVIQdJtuovwv9+me5YWeyC4Puzp0Zwk=
|
||||
=8/cW
|
||||
-----END PGP SIGNATURE-----
|
||||
@ -0,0 +1,16 @@
|
||||
-----BEGIN PGP SIGNATURE-----
|
||||
|
||||
iQIzBAABCAAdFiEEz9yiRbEEPPKl+Xhl/+h0BBaL2EcFAmYNMEcACgkQ/+h0BBaL
|
||||
2EeHhxAAuuIM9bl0dgAWOjbgRjCeXR8aFdfcI4dkO7bZrUy8eKbM+XCvPUUvloRJ
|
||||
vzGkxYyTmI4kcNPOHfscUwH7AVVij8nGv7WeaXBUZGIXNwfHwvqOxvYvSsNNNFnr
|
||||
70yJB7Df8/2s0XqFx3X1aWcnyMDerWKpfJ/VI/NPmCVxkYXGshuTTSFcCMTSFBQB
|
||||
sNrIb5NWAsBF4R85uRQDlCg1AoyaKOdJNQkPo1Nrjol1ExJ+MHE7+E+QL9pQkUWG
|
||||
SBISPUhJySBAegxolw6YR5dz1L4nukueQDJz3NizUeQGDvH7h1ImY8cypRi44U61
|
||||
SUUHhBfmUBiC2dS/tTQawySULWcgbkV4GJ6cJZfDd95uffd4S/GDJCa2wCE2UTlA
|
||||
XzQHwbcnIeoL064gX7ruBuFHJ6n/Oz7nZkFqbH2aqLTAWgLiUq31xH3HY734sL6X
|
||||
zIJQRbcK1EM7cnNjKMVPlnHpAeKbsbHbU6yzWwZ7reIoyWlZ7vEGrfXO7Kmul93K
|
||||
wVaWu0AiOY566ugekdDx4cKV+FQN6oppAN63yTfPJ2Ddcmxs4KNrtozw9OAgDTPE
|
||||
GTPFD6V1CMuyQj/jOpAmbj+4bRD4Mx3u2PSittvrIeopxrXPsGGSZ5kdl62Xa2+A
|
||||
DzKyYNXzcmxqS9lGdFb+OWCTyAIXxwZrdz1Q61g5xDvR9z/wZiI=
|
||||
=Br9/
|
||||
-----END PGP SIGNATURE-----
|
||||
@ -0,0 +1,109 @@
|
||||
-----BEGIN PGP PUBLIC KEY BLOCK-----
|
||||
|
||||
mQINBFq+ToQBEADRYvIVtbK6owynD3j3nxwpW2KEk/p+aDvtXmc2SR2dBcZ8sFW2
|
||||
R5vEsG8d3/D3wgv5pcL3KfNNXQYUnXVbobrFUUWQYc79qIsE3MgiPf5NVOtwKPUR
|
||||
i5g9YJgKvpBxkQfqp3LYGm9ZBtwo3DVLA3yn7KsazCmAgTNFJYw7ku1XxgmIzY6K
|
||||
5J30DfbJiqDqj4f9GslCCCCH3qiPnuLG/HUyVLHMpbWlaiy9NI0GcaLxjJewHj9w
|
||||
W2D2lydkxe5JGo7egUkV3ILcuLVSVKA35SKY27dYqfuyqp9tAzaRbjDYjsYdHA6G
|
||||
BqrNrKBn/GwlFDPrVdcvN3ZSY2wMLTxWE3Axc/FweuHxFnou/80FwX7F3JD+oEQ6
|
||||
rofmcxOBCC7J98I7HZAhP9jBn88XIS2hztbLq8d6rZJZRtcz0k61VR0ddO+TrFmf
|
||||
9rMYCPgCckRtVxeFIVIabrN1IzKynLFeo040h8hSGswd6YKDOVwjJY6Oa6EmVefZ
|
||||
a8QSt4+M65RSzH6SEPY008F3nJUAK6MEkzTak+tFltZNrVWu8p2xd1j9nmxAwEhZ
|
||||
/lgbxLqzYgaUWmfyHeZ8yVA0MhHzdiAL8nVUEdG3KecIq0RWCJLGLWWIjd6KAJl1
|
||||
yAmhRYKK/sjPDsL3elHsFACfZbyx3o5GGQNlas1FYoPLWbaNGaJtgFTF2QARAQAB
|
||||
tCtQYWJsbyBHYWxpbmRvIFNhbGdhZG8gPHBhYmxvZ3NhbEBnbWFpbC5jb20+iQJO
|
||||
BBMBCgA4FiEEoDXIwZIZuoIezqhrZOYo+NaEaW0FAlq+ToQCGwMFCwkIBwMFFQoJ
|
||||
CAsFFgIDAQACHgECF4AACgkQZOYo+NaEaW2bmA/+PXIap2udLoUVOHxnsIBdqYwp
|
||||
sv1Aj5lfIJmNhmxPbHShwp1Jg+w4urxe+2Dj5ofKVlIo1i83bQkvnKJMDXDVuc/K
|
||||
P6zqhBJ3rT4Q3qx2mzX8bIfQoJ2JHuH4lkP+I7doDcHHRyeNASyk72VdQmU4twNw
|
||||
Ibn8nSNV6ThKHdoPYzVnO2rZUFcGIqH5HNsvR+B7cc1MBCHsgURYwSVhSePIFGlZ
|
||||
iasdBD6QQkDSe4QWi7AcJFWFElw4kbOKJWxAWsrEk+tMXJVGRjnmL289EmPCx/vx
|
||||
BqKy7Mse0yWCSRR3vB+O6TB1S5SgEyEgqlYsfGNv1qf/rfRD4KkyCbNU3LhY1Aim
|
||||
vJP4pDW+KFxTk2Ks8vrx8gOSd2aFqPeO/pFDrpsF7PD62XwsfoXu4xc5V0Giw7r1
|
||||
Nai0nax7kOrldNF8TbbtRjW0jmoC7wLIDujAkwDIOroZ0CXA3N4HVHdSbrHm/urX
|
||||
nyxJXupXAQNwGx64JCBcbF2fp3Kvu1VAXBEFnd01KaopthHcbG5pA50Kl2Vhe+98
|
||||
OdezUX42fHkQpQkB7HgtXfm6W1bw6YRBamrNvs1OoHBYmUjlECpe566IIu25Hc8s
|
||||
x3qA+6eca7iqizyLG+WyMT8ZIYTWGAS59jxwR4esqGczbbZPSAPHFwLbGv7Wr0Rd
|
||||
TPu5B0FcKpDkTd4IxQW5Ag0EWr5O2gEQAMjLe4CtbSfofmJrz5wfNkMVsZ81Gbqe
|
||||
MoYd3dtkJnQYERUj8flzBj3ucaxGJ+Cuf7ybh3naPopKvEI1q0vkcgCDqrEgXK//
|
||||
jKJbP28uPSMGhOG28q4PbamG55gy5FtM3ezzAxPWWKe9qBpV65GMmFy7eBQx2iJs
|
||||
yiDIOOQQ4kraS+cTqNFimEXAGLCOQRNLcwIZzwAAHoW7HEpNUfVwaBD9kMlbo1ND
|
||||
I60IKcNrNcmcmRxhJqfxjj8YBMwcKHO6GBE3AVpaE/+UO9zyr4TH+0YuQUgxKlPW
|
||||
Dkg5XlkDo0S1GyLY5e9ckIDIlkTdDa2pOkoE2yB5MQCEga3YiHrKUVTTWaxn9XVJ
|
||||
6x5ZjUF6bgSWGkrG5dUqSYoO1iDMuNVjtiujNyf/rvfj5cNxS7/lgxchhQKZHZXL
|
||||
WVqxlneeVJ6s0P4+ROVG9ga2Sve7aUJ6wXIewZwulBcV2sE/W/DgxHgLBi53CUQt
|
||||
vEzFzKvo48GnDqL5VYjA7l0HMYHd4GksCLi8E8U6Cgj+imXiM8voL7pHRZfs8mY8
|
||||
udR+UT4e1Scl2MYP2qBJ9/17B/X52B3s1EZdqI/r+hfOyqrhPs+dbAN0mtMPn68+
|
||||
nrvY1+nscvrSYEP6ZBlc9Hp2mgJdb6IcTvINXBEeLRjgc3pjViva443pkiFp9Axm
|
||||
ecOckMKP3uSlABEBAAGJBGwEGAEKACAWIQSgNcjBkhm6gh7OqGtk5ij41oRpbQUC
|
||||
Wr5O2gIbAgJACRBk5ij41oRpbcF0IAQZAQoAHRYhBM/cokWxBDzypfl4Zf/odAQW
|
||||
i9hHBQJavk7aAAoJEP/odAQWi9hHr7YP/RCLre1CmOoWYpAtoa1yVCeYMDV6eQgL
|
||||
B488/BEZHQE1zbrYy16XkhORob3JF/kUMjmJW7XaFF8FrWvRcdj/xaUGbOOEulKg
|
||||
v+8zWfswYQRiZ4/JlwER4vRLi6fTE89MVER6Fkj2ASD4D2cifY+EztD4flV3sq3s
|
||||
vIogGFaN9IvdrdeptOVGXs1RmAyoTsiS2mKQ6xsGh8B9ZAm55W8fBOGiSzLX21Xk
|
||||
Ofdw53BrFQxn3cu/JgIKpdeZxgukcvEAI62B6X+YL6Na4j0eqEGLzsNtU1+xeJlo
|
||||
WtVvmRwnRHGSxF6fzIZ3mk/p/aFiXAEq/xITCTY6tDv7x7pFE/RpdlJZyNJ+R5Y4
|
||||
SQiuDsylxNCa/4G5EB6q+7iVYtbEQ9MnZg2phowEE42tlj0rz8/rvDK3LH3xibot
|
||||
KHIodCWKlWByxH99u2PuHUQ0c1oCVBUE1KkruMpvI236DpU/dvdq4JLSg/fWrys/
|
||||
VIjqLZgsIE5g/KO9XqngWHkLcBLh4CNAmHJ8Iia+s+/rfgsejQWB5uJb6eYg2JjB
|
||||
4WP1EI0rULM6fdrCNB+MJ36wE2Lnb4bfT0phOMgjjH5/Ki7ZCbkxkOsBs4SRjiS+
|
||||
weCsmpAtMqodWY/Cnw9pWSA/qLSRD5/mKeb9SO6OZ/OPfAatwnGHsvZ2sAueC6rR
|
||||
04W5BfXZWrnJUXQP/id/EKE1Ksp5fKoxSCbkKTCig+Sf5Afwe36yFN+niZBqzn5b
|
||||
BgL/HIKaZM97oDHersPPANeEgS+JVlBf95iKIYnQbZP43FLVbvOuaINhBIVtFO54
|
||||
2Y7EYwl41kP7ILDElVy36KAmdQyBAfrjnZiRA70xShOxApLug1L0lxhR3YfmLwNi
|
||||
RJ0V6KnYDKf0pfdhO9VFyFFWUojX1usn2SmSsXNizsNtvRqHXzPnX0rbJzZ9+N4O
|
||||
9k1nxygYFG/2R/jGonVmTjRzcAHrAkNJETMWXMA7/8wRMDwluz8j+cCldey9x8Vk
|
||||
JwgLGnZSbQtVpcFAnm5r/36Gt+9wc1VWMyrUrVr6Z679aqAbG7PMaeR5h5ygMj1k
|
||||
VqRTYAUPSk1f8bZKRssQkQwEbp9dVIjm9SsR8VT7/tB+UuB85dABxgHfv3psJRT+
|
||||
tL8g9V7kSZqQfcLNGmvEVvr2Zl9NtxwXtsFM2OBprxCenwb+e9Ppm1LjfJG/NE72
|
||||
mAnOERfDaiLt4bqNo36Ei5sGCJ4Fx61phzNBXzkdRNM47i8J5UZRKFkE91c99BVM
|
||||
HKUaY61NRK24fR0zP98ftDU82YFw0VRFJpTeBrO5ivN1MlQxUPzUWxKxMxO+20wa
|
||||
UOXroEw11Tb4SRLGOla1pCl6lCUPJRy9IzadPDgTr/OTMkob/snt/XLdnV5/uQIN
|
||||
BFq+TvoBEAC8Oy1g6pPWBbrCMhIq7VWY2fjylJ1fwg5BPXkOKVK1dsGYO4QD7oW9
|
||||
L0aSqcFSNFGF9Cl0Ri4TFXZC3hnG4HeSXUWApuKdBLn21H3jba36Ay1oGcGfdm0v
|
||||
Zght4c6BlMVBpGCw2wIkJbUNEy6InMM+O8CCbbaH3iJkJ4141P7pODHignx5AmZI
|
||||
conMui4YOhC+IXQXynVEv1Juk7erB1Nh1RcRvsA4lb44HWx49lIwe85ejOmoZ0O3
|
||||
6f9NJRer6bV0+rHWmg4IV5Q9h/Gn4IhEDZxA0DZl1RQI7dMgaMbIFbXGq7Kgzstz
|
||||
EUnOoy29hXodxVmwIsMrAiQUYtwJ9hW+ESsw47+W2iPHVgviGWl7r/SgcgMYmf6m
|
||||
5kiTBtwU7BQPS9G3zwwP2Rm3AA/6g39Q+tQKjOwi1I8+GZsY2On44Zly7BreBNg5
|
||||
4gJgdAGcMOYU9etr050clH3UpTYcAEtX++ahtOKhJgLIPNcIAQNlnifqvU0VYpgw
|
||||
R4YpZ7hgg+AVDzC73PIM0lFI0XiDuqChbxE+K1jmLXWe5iJF0dzgVTwP+PmsifNZ
|
||||
Wg3+YxSsS+hDMPQ2xPiQN49gT4JJDHcDuyhHyCGYgyMiVJCsku9KrkubbfVRivyN
|
||||
ZF2Zfo3f+nbrRxsftz0yjAq8byCvb0V0XOpt4pJ/ddlug9ytRxALNwARAQABiQI2
|
||||
BBgBCgAgFiEEoDXIwZIZuoIezqhrZOYo+NaEaW0FAlq+TvoCGwwACgkQZOYo+NaE
|
||||
aW3urA//UQ/cKQ7HvWjcLphzQOZc+6m5YL0wxvZkSjemU7mqjZdpacteIvRAoers
|
||||
EqXHc208liIBtNfRzoreXdcXNzie65xXkrRnWoHVH/fTWy4lOnHr2CMXLeHjUgg/
|
||||
M6PYi8+sARm05YFB8nsYhlhx3IdLhcfeVVbJedQKO0yL3CK1okT30DUVq5Lq6X/K
|
||||
DC6AxuJR3D6UMSoT0WLaoX8qbhAp88qLynInfBVL18d97h916WPLTPeP0eHwhwND
|
||||
bYtKDCMDuKQ9XX5+QsNH0RmbxlX274LHrUMMvkLKxcfCBvP+iuqrBeIuoeVzXYJZ
|
||||
j7ZJtEH79bW44eecl/CY/STFYgSQ2XGTp2BI2q60wAmtKlNhwxY5ena0FgyFl6Tm
|
||||
5OBHW/Pwo+ndQJGfbrCyWkTgRay9c8er3gl3GQYIBH6X0kCiG7h/Epj0b5CHOPU5
|
||||
hCw0kEB8MB4poTIjeiY+Q01472/lQ68CL3DX158hR5d3XaPSIxAN+qFsfB1o316p
|
||||
yjxhfK1MD/IfrOgjlggPPnc/KmLkCzpgdwKcZwLCdZq9hYBvF1Zs34HbaVMYbWTK
|
||||
uxLowtXGU43vatCXXqmPOvl4/g4tZD6rysJDgOrHQnEHzT+Napn07s0BRC0IbbNn
|
||||
FynUrkr5KMSuRz7Hg7xMApENOrb0nqdHSUJ914ZpuMIS6RhJgGu5Ag0EWr5PIAEQ
|
||||
ALfh9vPD2B+miHDTMADI8aRZ7g9tnzynZYkk3+2sCiiusetsQQ+HIPJ/ASEJB7On
|
||||
ane9dyT/LTRhrK9qaxgVMimk2COXB/xyh7Mnw7nJgFU0aRSbtX0vbvQz2suSzrQ6
|
||||
9mPKzan28JGoClqB0bw1vwf3VjjxHV2dgD57CmqFPv7kAC/2a56dE+etzXattZAL
|
||||
+2JWTpmfQ0ePRRadtBm0VahQhnU8x0+jvAVrEawqpVW83ozYFyW/0WInM2J7jHgQ
|
||||
16OosY4lj5L/DxpVxaArhRFoRfWPXfC37iE8Mou/I95isvPQIhp1wTo4jG0KM02B
|
||||
oIVbp/QRNBQ6WtpOzvJs1gqQiJJTfqbKJXQ3NDEY9crpVS83HJ+Zv99PNsyNkFjG
|
||||
QpU84U3ZhsI4ygjdY45mpZueqI1RVcRQdu8Hgvoo/78Q/Sir6gMGop3mVdVo2guI
|
||||
kFcJrXh0Xk3ech4aVqrmKx/mPXGwOAQU0DAul4RW3fKg1QxQE7Tlw3+95Ee/+q5j
|
||||
HARL0uDbCJpRO8Sl8NDEuL32n/2Ot6kQeCSHrU7KJRYAkTxkKvr8zNow7hFhHFPE
|
||||
SnHvTnskI6noh0VY6NwMhmLvhm0wKkRxZPzUNc3sgLvbK1NymIZ9aKCZamzhZrmG
|
||||
vnblEz/OSLwGUua465H3hM1vvBQiartj7+6ZqWIkSmBPABEBAAGJAjYEGAEKACAW
|
||||
IQSgNcjBkhm6gh7OqGtk5ij41oRpbQUCWr5PIAIbIAAKCRBk5ij41oRpbWmeEACG
|
||||
+axtDC8UoNp9ORiYwEWLzZWDuugE+ah7DYYGD4Vs633FXVZW3SgM/bFtJ/0Lg8CF
|
||||
74jI4LMHyIjDzEjcoItwnhBLix+kUoJTvrY58GPydwekLuw1p4KXLqtRs4fsZbNQ
|
||||
YTknl4jYtRWoxO98x7tun7Gq2gqmJkIB2uj630fKz5cBk6p6oDFKjzyrHe+V7BiK
|
||||
3okQPaD4x7hq8OnTy7lOy92ZZAqztS4tNEb4DkYW1MpuwsJ7hbBZitc1siI+FVVb
|
||||
GjVVGZz6ssXoW67Tz8+VxdWJxNLXlv27eMcj4sme5S0th/YYNA5fRRv6zuzqZAru
|
||||
YNGLpYYU7JLvZJ+3lCwa5j5ycOGBF0GvsGs6gj6h+CHkjR/BgzAgWC+GgUgslt6q
|
||||
aH04rWtV6rVz+Y91LcrX5P6OM4anmXD3Gp3kl35AypXb4KyASF19+11RUziD4Z7q
|
||||
wQEWfbwOltNyZv2lD8s2jPr7P02axWRQUbZAEhxRmvOQev/FZPyCF6gqUo/HxRbQ
|
||||
y3bzmnipyHSv1DlXNfCFCHvN8kGyZnRWARqIKRg+j9ediJgOUqlLhg6KmrTVxd5v
|
||||
3Dfv52PW2UODDTM20s3cQGuX/UswzMRwPI/+P44iCMwEKdm7duM/5oisZT9Vhy7g
|
||||
P15MreFZLcZvUVgjqgy0u57cstyGK1Bo9e2sFcK2fA==
|
||||
=6Zb4
|
||||
-----END PGP PUBLIC KEY BLOCK-----
|
||||
Loading…
Reference in new issue