Compare commits

...

No commits in common. "factory" and "devel" have entirely different histories.

16 changed files with 1422 additions and 591 deletions

View File

@ -0,0 +1,461 @@
---
Doc/library/email.utils.rst | 19 -
Lib/email/utils.py | 151 +++++++-
Lib/test/test_email/test_email.py | 187 +++++++++-
Misc/NEWS.d/next/Library/2023-10-20-15-28-08.gh-issue-102988.dStNO7.rst | 8
4 files changed, 344 insertions(+), 21 deletions(-)
--- 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)
--- a/Lib/email/utils.py
+++ b/Lib/email/utils.py
@@ -48,6 +48,7 @@ TICK = "'"
specialsre = re.compile(r'[][\\()<>@,:;".]')
escapesre = re.compile(r'[\\"]')
+
def _has_surrogates(s):
"""Return True if s contains surrogate-escaped binary data."""
# This check is based on the fact that unless there are surrogates, utf8
@@ -106,12 +107,127 @@ def formataddr(pair, charset='utf-8'):
return address
+def _iter_escaped_chars(addr):
+ pos = 0
+ escape = False
+ for pos, ch in enumerate(addr):
+ if escape:
+ yield (pos, '\\' + ch)
+ escape = False
+ elif ch == '\\':
+ escape = True
+ else:
+ yield (pos, ch)
+ if escape:
+ yield (pos, '\\')
+
+
+def _strip_quoted_realnames(addr):
+ """Strip real names between quotes."""
+ if '"' not in addr:
+ # Fast path
+ return addr
+
+ start = 0
+ open_pos = None
+ result = []
+ for pos, ch in _iter_escaped_chars(addr):
+ if ch == '"':
+ if open_pos is None:
+ open_pos = pos
+ else:
+ if start != open_pos:
+ result.append(addr[start:open_pos])
+ start = pos + 1
+ open_pos = None
-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 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):
@@ -205,16 +321,33 @@ 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]
--- 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.generator import Generator, DecodedGenerator, BytesGenerator
@@ -3288,15 +3289,137 @@ Foo
[('Al Person', 'aperson@dom.ain'),
('Bud Person', 'bperson@dom.ain')])
+ 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"""
@@ -3485,6 +3608,54 @@ 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):
--- /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.

View File

@ -45,7 +45,7 @@
def test_simple_xml_chunk_5(self):
self.test_simple_xml(chunk_size=5, flush=True)
@@ -1647,6 +1651,9 @@ class XMLPullParserTest(unittest.TestCas
@@ -1648,6 +1652,9 @@ class XMLPullParserTest(unittest.TestCas
self.assert_event_tags(parser, [('end', 'doc')])

View File

@ -0,0 +1,376 @@
From 0740166e60b8cdae9448220beb28721f0126ee03 Mon Sep 17 00:00:00 2001
From: Petr Viktorin <encukou@gmail.com>
Date: Wed, 24 Apr 2024 14:29:30 +0200
Subject: [PATCH 1/2] gh-113171: gh-65056: Fix "private" (non-global) IP
address ranges (GH-113179) (GH-113186) (GH-118177)
* GH-113171: Fix "private" (non-global) IP address ranges (GH-113179)
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
* GH-65056: Improve the IP address' is_global/is_private documentation (GH-113186)
It wasn't clear what the semantics of is_global/is_private are and, when
one gets to the bottom of it, it's not quite so simple (hence the
exceptions listed).
(cherry picked from commit 2a4cbf17af19a01d942f9579342f77c39fbd23c4)
(cherry picked from commit 40d75c2b7f5c67e254d0a025e0f2e2c7ada7f69f)
---------
(cherry picked from commit f86b17ac511e68192ba71f27e752321a3252cee3)
Co-authored-by: Jakub Stasiak <jakub@stasiak.at>
---
Doc/library/ipaddress.rst | 43 +++-
Doc/whatsnew/3.10.rst | 9
Lib/ipaddress.py | 99 +++++++---
Lib/test/test_ipaddress.py | 52 +++++
Misc/NEWS.d/next/Library/2024-03-14-01-38-44.gh-issue-113171.VFnObz.rst | 9
5 files changed, 187 insertions(+), 25 deletions(-)
create mode 100644 Misc/NEWS.d/next/Library/2024-03-14-01-38-44.gh-issue-113171.VFnObz.rst
--- a/Doc/library/ipaddress.rst
+++ b/Doc/library/ipaddress.rst
@@ -188,18 +188,53 @@ write code that handles both IP versions
.. 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:: 3.10.15
+
+ 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:: 3.10.15
+
+ 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)
--- a/Doc/whatsnew/3.10.rst
+++ b/Doc/whatsnew/3.10.rst
@@ -2348,3 +2348,12 @@ tarfile
:exc:`DeprecationWarning`.
In Python 3.14, the default will switch to ``'data'``.
(Contributed by Petr Viktorin in :pep:`706`.)
+
+Notable changes in 3.10.15
+==========================
+
+ipaddress
+---------
+
+* Fixed ``is_global`` and ``is_private`` behavior in ``IPv4Address``,
+ ``IPv6Address``, ``IPv4Network`` and ``IPv6Network``.
--- a/Lib/ipaddress.py
+++ b/Lib/ipaddress.py
@@ -1323,18 +1323,41 @@ class IPv4Address(_BaseV4, _BaseAddress)
@property
@functools.lru_cache()
def is_private(self):
- """Test if this address is allocated for private networks.
-
- Returns:
- A boolean, True if the address is reserved per
- iana-ipv4-special-registry.
-
- """
- return any(self in net for net in self._constants._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:
+
+ * ``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)
+ 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
@@ -1538,13 +1561,15 @@ 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'),
@@ -1555,6 +1580,11 @@ 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')
@@ -1996,27 +2026,42 @@ 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:
+
+ * ``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`)::
- 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.
+ 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:
+
+ 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`)::
- Returns:
- A boolean, true if the address is not reserved per
- iana-ipv6-special-registry.
+ 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
@@ -2257,19 +2302,31 @@ 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'),
--- 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)
--- /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.

View File

@ -0,0 +1,335 @@
From ff3629b3cedf5e50a7a5f567283778fe5539a11e Mon Sep 17 00:00:00 2001
From: Petr Viktorin <encukou@gmail.com>
Date: Wed, 31 Jul 2024 00:19:48 +0200
Subject: [PATCH] [3.10] 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 | 6
Doc/library/email.policy.rst | 18 ++
Doc/whatsnew/3.10.rst | 12 +
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 ++++
Misc/NEWS.d/next/Library/2024-07-27-16-10-41.gh-issue-121650.nf6oc9.rst | 5
10 files changed, 162 insertions(+), 4 deletions(-)
create mode 100644 Misc/NEWS.d/next/Library/2024-07-27-16-10-41.gh-issue-121650.nf6oc9.rst
--- a/Doc/library/email.errors.rst
+++ b/Doc/library/email.errors.rst
@@ -59,6 +59,12 @@ The following exception classes are defi
:class:`~email.mime.image.MIMEImage`).
+.. exception:: HeaderWriteError()
+
+ Raised when an error occurs when the :mod:`~email.generator` outputs
+ headers.
+
+
Here is the list of the defects that the :class:`~email.parser.FeedParser`
can find while parsing messages. Note that the defects are added to the message
where the problem was found, so for example, if a message nested inside a
--- a/Doc/library/email.policy.rst
+++ b/Doc/library/email.policy.rst
@@ -229,6 +229,24 @@ 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:: 3.10.15
+
+
The following :class:`Policy` method is intended to be called by code using
the email library to create policy instances with custom settings:
--- a/Doc/whatsnew/3.10.rst
+++ b/Doc/whatsnew/3.10.rst
@@ -2357,3 +2357,15 @@ 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`.)
--- a/Lib/email/_header_value_parser.py
+++ b/Lib/email/_header_value_parser.py
@@ -92,6 +92,8 @@ TOKEN_ENDS = TSPECIALS | WSP
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'\"')+'"'
@@ -2778,9 +2780,13 @@ def _refold_parse_tree(parse_tree, *, po
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
--- a/Lib/email/_policybase.py
+++ b/Lib/email/_policybase.py
@@ -157,6 +157,13 @@ class Policy(_PolicyBase, metaclass=abc.
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.
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.
--- 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."""
--- a/Lib/email/generator.py
+++ b/Lib/email/generator.py
@@ -14,12 +14,14 @@ import random
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]')
@@ -223,7 +225,16 @@ class Generator:
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)
--- a/Lib/test/test_email/test_generator.py
+++ b/Lib/test/test_email/test_generator.py
@@ -6,6 +6,7 @@ from email.message import EmailMessage
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 @@ class TestGeneratorBase:
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, T
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):
--- 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.
@@ -277,6 +278,31 @@ class PolicyAPITests(unittest.TestCase):
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).
--- /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`.)

View File

@ -0,0 +1,136 @@
---
Lib/test/test_zipfile.py | 75 ++++++++++
Lib/zipfile.py | 10 +
Misc/NEWS.d/next/Library/2024-08-11-14-08-04.gh-issue-122905.7tDsxA.rst | 1
Misc/NEWS.d/next/Library/2024-08-26-13-45-20.gh-issue-123270.gXHvNJ.rst | 3
4 files changed, 87 insertions(+), 2 deletions(-)
--- a/Lib/test/test_zipfile.py
+++ b/Lib/test/test_zipfile.py
@@ -3280,6 +3280,81 @@ with zipfile.ZipFile(io.BytesIO(), "w")
zipfile.Path(zf)
zf.extractall(source_path.parent)
+ def test_malformed_paths(self):
+ """
+ Path should handle malformed paths gracefully.
+
+ Paths with leading slashes are not visible.
+
+ Paths with dots are treated like regular files.
+ """
+ data = io.BytesIO()
+ zf = zipfile.ZipFile(data, "w")
+ zf.writestr("../parent.txt", b"content")
+ zf.filename = ''
+ root = zipfile.Path(zf)
+ assert list(map(str, root.iterdir())) == ['../']
+ assert root.joinpath('..').joinpath('parent.txt').read_bytes() == b'content'
+
+ def test_unsupported_names(self):
+ """
+ Path segments with special characters are readable.
+
+ On some platforms or file systems, characters like
+ ``:`` and ``?`` are not allowed, but they are valid
+ in the zip file.
+ """
+ data = io.BytesIO()
+ zf = zipfile.ZipFile(data, "w")
+ zf.writestr("path?", b"content")
+ zf.writestr("V: NMS.flac", b"fLaC...")
+ zf.filename = ''
+ root = zipfile.Path(zf)
+ contents = root.iterdir()
+ assert next(contents).name == 'path?'
+ assert next(contents).name == 'V: NMS.flac'
+ assert root.joinpath('V: NMS.flac').read_bytes() == b"fLaC..."
+
+ def test_backslash_not_separator(self):
+ """
+ In a zip file, backslashes are not separators.
+ """
+ data = io.BytesIO()
+ zf = zipfile.ZipFile(data, "w")
+ zf.writestr(DirtyZipInfo.for_name("foo\\bar", zf), b"content")
+ zf.filename = ''
+ root = zipfile.Path(zf)
+ (first,) = root.iterdir()
+ assert not first.is_dir()
+ assert first.name == 'foo\\bar'
+
+
+class DirtyZipInfo(zipfile.ZipInfo):
+ """
+ Bypass name sanitization.
+ """
+
+ def __init__(self, filename, *args, **kwargs):
+ super().__init__(filename, *args, **kwargs)
+ self.filename = filename
+
+ @classmethod
+ def for_name(cls, name, archive):
+ """
+ Construct the same way that ZipFile.writestr does.
+
+ TODO: extract this functionality and re-use
+ """
+ self = cls(filename=name, date_time=time.localtime(time.time())[:6])
+ self.compress_type = archive.compression
+ self.compress_level = archive.compresslevel
+ if self.filename.endswith('/'): # pragma: no cover
+ self.external_attr = 0o40775 << 16 # drwxrwxr-x
+ self.external_attr |= 0x10 # MS-DOS directory flag
+ else:
+ self.external_attr = 0o600 << 16 # ?rw-------
+ return self
+
class StripExtraTests(unittest.TestCase):
# Note: all of the "z" characters are technically invalid, but up
--- 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
@@ -2151,7 +2152,7 @@ def _parents(path):
def _ancestry(path):
"""
Given a path with elements separated by
- posixpath.sep, generate all elements of that path
+ posixpath.sep, generate all elements of that path.
>>> list(_ancestry('b/d'))
['b/d', 'b']
@@ -2163,9 +2164,14 @@ def _ancestry(path):
['b']
>>> list(_ancestry(''))
[]
+
+ Multiple separators are treated like a single.
+
+ >>> list(_ancestry('//b//d///f//'))
+ ['//b//d///f', '//b//d', '//b']
"""
path = path.rstrip(posixpath.sep)
- while path and path != posixpath.sep:
+ while path.rstrip(posixpath.sep):
yield path
path, tail = posixpath.split(path)
--- /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.
--- /dev/null
+++ b/Misc/NEWS.d/next/Library/2024-08-26-13-45-20.gh-issue-123270.gXHvNJ.rst
@@ -0,0 +1,3 @@
+Applied a more surgical fix for malformed payloads in :class:`zipfile.Path`
+causing infinite loops (gh-122905) without breaking contents using
+legitimate characters.

View File

@ -1,296 +0,0 @@
From 21139b45039a72e8346bdc32d498345ef174ba92 Mon Sep 17 00:00:00 2001
From: Victor Stinner <vstinner@python.org>
Date: Fri, 1 Nov 2024 14:11:47 +0100
Subject: [PATCH] [3.11] gh-124651: Quote template strings in `venv` activation
scripts (GH-124712) (GH-126185) (#126269)
(cherry picked from commit ae961ae94bf19c8f8c7fbea3d1c25cc55ce8ae97)
---
Lib/test/test_venv.py | 81 ++++++++++
Lib/venv/__init__.py | 42 ++++-
Lib/venv/scripts/common/activate | 8
Lib/venv/scripts/nt/activate.bat | 6
Lib/venv/scripts/posix/activate.csh | 8
Lib/venv/scripts/posix/activate.fish | 8
Misc/NEWS.d/next/Library/2024-09-28-02-03-04.gh-issue-124651.bLBGtH.rst | 1
7 files changed, 134 insertions(+), 20 deletions(-)
create mode 100644 Misc/NEWS.d/next/Library/2024-09-28-02-03-04.gh-issue-124651.bLBGtH.rst
--- a/Lib/test/test_venv.py
+++ b/Lib/test/test_venv.py
@@ -15,6 +15,7 @@ import struct
import subprocess
import sys
import tempfile
+import shlex
from test.support import (captured_stdout, captured_stderr, requires_zlib,
skip_if_broken_multiprocessing_synchronize)
from test.support.os_helper import (can_symlink, EnvironmentVarGuard, rmtree)
@@ -85,6 +86,10 @@ class BaseTest(unittest.TestCase):
result = f.read()
return result
+ def assertEndsWith(self, string, tail):
+ if not string.endswith(tail):
+ self.fail(f"String {string!r} does not end with {tail!r}")
+
class BasicTest(BaseTest):
"""Test venv module functionality."""
@@ -342,6 +347,82 @@ class BasicTest(BaseTest):
'import sys; print(sys.executable)'])
self.assertEqual(out.strip(), envpy.encode())
+ # gh-124651: test quoted strings
+ @unittest.skipIf(os.name == 'nt', 'contains invalid characters on Windows')
+ def test_special_chars_bash(self):
+ """
+ Test that the template strings are quoted properly (bash)
+ """
+ rmtree(self.env_dir)
+ bash = shutil.which('bash')
+ if bash is None:
+ self.skipTest('bash required for this test')
+ env_name = '"\';&&$e|\'"'
+ env_dir = os.path.join(os.path.realpath(self.env_dir), env_name)
+ builder = venv.EnvBuilder(clear=True)
+ builder.create(env_dir)
+ activate = os.path.join(env_dir, self.bindir, 'activate')
+ test_script = os.path.join(self.env_dir, 'test_special_chars.sh')
+ with open(test_script, "w") as f:
+ f.write(f'source {shlex.quote(activate)}\n'
+ 'python -c \'import sys; print(sys.executable)\'\n'
+ 'python -c \'import os; print(os.environ["VIRTUAL_ENV"])\'\n'
+ 'deactivate\n')
+ out, err = check_output([bash, test_script])
+ lines = out.splitlines()
+ self.assertTrue(env_name.encode() in lines[0])
+ self.assertEndsWith(lines[1], env_name.encode())
+
+ # gh-124651: test quoted strings
+ @unittest.skipIf(os.name == 'nt', 'contains invalid characters on Windows')
+ def test_special_chars_csh(self):
+ """
+ Test that the template strings are quoted properly (csh)
+ """
+ rmtree(self.env_dir)
+ csh = shutil.which('tcsh') or shutil.which('csh')
+ if csh is None:
+ self.skipTest('csh required for this test')
+ env_name = '"\';&&$e|\'"'
+ env_dir = os.path.join(os.path.realpath(self.env_dir), env_name)
+ builder = venv.EnvBuilder(clear=True)
+ builder.create(env_dir)
+ activate = os.path.join(env_dir, self.bindir, 'activate.csh')
+ test_script = os.path.join(self.env_dir, 'test_special_chars.csh')
+ with open(test_script, "w") as f:
+ f.write(f'source {shlex.quote(activate)}\n'
+ 'python -c \'import sys; print(sys.executable)\'\n'
+ 'python -c \'import os; print(os.environ["VIRTUAL_ENV"])\'\n'
+ 'deactivate\n')
+ out, err = check_output([csh, test_script])
+ lines = out.splitlines()
+ self.assertTrue(env_name.encode() in lines[0])
+ self.assertEndsWith(lines[1], env_name.encode())
+
+ # gh-124651: test quoted strings on Windows
+ @unittest.skipUnless(os.name == 'nt', 'only relevant on Windows')
+ def test_special_chars_windows(self):
+ """
+ Test that the template strings are quoted properly on Windows
+ """
+ rmtree(self.env_dir)
+ env_name = "'&&^$e"
+ env_dir = os.path.join(os.path.realpath(self.env_dir), env_name)
+ builder = venv.EnvBuilder(clear=True)
+ builder.create(env_dir)
+ activate = os.path.join(env_dir, self.bindir, 'activate.bat')
+ test_batch = os.path.join(self.env_dir, 'test_special_chars.bat')
+ with open(test_batch, "w") as f:
+ f.write('@echo off\n'
+ f'"{activate}" & '
+ f'{self.exe} -c "import sys; print(sys.executable)" & '
+ f'{self.exe} -c "import os; print(os.environ[\'VIRTUAL_ENV\'])" & '
+ 'deactivate')
+ out, err = check_output([test_batch])
+ lines = out.splitlines()
+ self.assertTrue(env_name.encode() in lines[0])
+ self.assertEndsWith(lines[1], env_name.encode())
+
@unittest.skipUnless(os.name == 'nt', 'only relevant on Windows')
def test_unicode_in_batch_file(self):
"""
--- a/Lib/venv/__init__.py
+++ b/Lib/venv/__init__.py
@@ -11,6 +11,7 @@ import subprocess
import sys
import sysconfig
import types
+import shlex
CORE_VENV_DEPS = ('pip', 'setuptools')
@@ -364,11 +365,41 @@ class EnvBuilder:
:param context: The information for the environment creation request
being processed.
"""
- text = text.replace('__VENV_DIR__', context.env_dir)
- text = text.replace('__VENV_NAME__', context.env_name)
- text = text.replace('__VENV_PROMPT__', context.prompt)
- text = text.replace('__VENV_BIN_NAME__', context.bin_name)
- text = text.replace('__VENV_PYTHON__', context.env_exe)
+ replacements = {
+ '__VENV_DIR__': context.env_dir,
+ '__VENV_NAME__': context.env_name,
+ '__VENV_PROMPT__': context.prompt,
+ '__VENV_BIN_NAME__': context.bin_name,
+ '__VENV_PYTHON__': context.env_exe,
+ }
+
+ def quote_ps1(s):
+ """
+ This should satisfy PowerShell quoting rules [1], unless the quoted
+ string is passed directly to Windows native commands [2].
+ [1]: https://learn.microsoft.com/en-us/powershell/module/microsoft.powershell.core/about/about_quoting_rules
+ [2]: https://learn.microsoft.com/en-us/powershell/module/microsoft.powershell.core/about/about_parsing#passing-arguments-that-contain-quote-characters
+ """
+ s = s.replace("'", "''")
+ return f"'{s}'"
+
+ def quote_bat(s):
+ return s
+
+ # gh-124651: need to quote the template strings properly
+ quote = shlex.quote
+ script_path = context.script_path
+ if script_path.endswith('.ps1'):
+ quote = quote_ps1
+ elif script_path.endswith('.bat'):
+ quote = quote_bat
+ else:
+ # fallbacks to POSIX shell compliant quote
+ quote = shlex.quote
+
+ replacements = {key: quote(s) for key, s in replacements.items()}
+ for key, quoted in replacements.items():
+ text = text.replace(key, quoted)
return text
def install_scripts(self, context, path):
@@ -408,6 +439,7 @@ class EnvBuilder:
with open(srcfile, 'rb') as f:
data = f.read()
if not srcfile.endswith(('.exe', '.pdb')):
+ context.script_path = srcfile
try:
data = data.decode('utf-8')
data = self.replace_variables(data, context)
--- a/Lib/venv/scripts/common/activate
+++ b/Lib/venv/scripts/common/activate
@@ -38,11 +38,11 @@ deactivate () {
# unset irrelevant variables
deactivate nondestructive
-VIRTUAL_ENV="__VENV_DIR__"
+VIRTUAL_ENV=__VENV_DIR__
export VIRTUAL_ENV
_OLD_VIRTUAL_PATH="$PATH"
-PATH="$VIRTUAL_ENV/__VENV_BIN_NAME__:$PATH"
+PATH="$VIRTUAL_ENV/"__VENV_BIN_NAME__":$PATH"
export PATH
# unset PYTHONHOME if set
@@ -55,9 +55,9 @@ fi
if [ -z "${VIRTUAL_ENV_DISABLE_PROMPT:-}" ] ; then
_OLD_VIRTUAL_PS1="${PS1:-}"
- PS1="__VENV_PROMPT__${PS1:-}"
+ PS1=__VENV_PROMPT__"${PS1:-}"
export PS1
- VIRTUAL_ENV_PROMPT="__VENV_PROMPT__"
+ VIRTUAL_ENV_PROMPT=__VENV_PROMPT__
export VIRTUAL_ENV_PROMPT
fi
--- a/Lib/venv/scripts/nt/activate.bat
+++ b/Lib/venv/scripts/nt/activate.bat
@@ -8,7 +8,7 @@ if defined _OLD_CODEPAGE (
"%SystemRoot%\System32\chcp.com" 65001 > nul
)
-set VIRTUAL_ENV=__VENV_DIR__
+set "VIRTUAL_ENV=__VENV_DIR__"
if not defined PROMPT set PROMPT=$P$G
@@ -24,8 +24,8 @@ set PYTHONHOME=
if defined _OLD_VIRTUAL_PATH set PATH=%_OLD_VIRTUAL_PATH%
if not defined _OLD_VIRTUAL_PATH set _OLD_VIRTUAL_PATH=%PATH%
-set PATH=%VIRTUAL_ENV%\__VENV_BIN_NAME__;%PATH%
-set VIRTUAL_ENV_PROMPT=__VENV_PROMPT__
+set "PATH=%VIRTUAL_ENV%\__VENV_BIN_NAME__;%PATH%"
+set "VIRTUAL_ENV_PROMPT=__VENV_PROMPT__"
:END
if defined _OLD_CODEPAGE (
--- a/Lib/venv/scripts/posix/activate.csh
+++ b/Lib/venv/scripts/posix/activate.csh
@@ -8,17 +8,17 @@ alias deactivate 'test $?_OLD_VIRTUAL_PA
# Unset irrelevant variables.
deactivate nondestructive
-setenv VIRTUAL_ENV "__VENV_DIR__"
+setenv VIRTUAL_ENV __VENV_DIR__
set _OLD_VIRTUAL_PATH="$PATH"
-setenv PATH "$VIRTUAL_ENV/__VENV_BIN_NAME__:$PATH"
+setenv PATH "$VIRTUAL_ENV/"__VENV_BIN_NAME__":$PATH"
set _OLD_VIRTUAL_PROMPT="$prompt"
if (! "$?VIRTUAL_ENV_DISABLE_PROMPT") then
- set prompt = "__VENV_PROMPT__$prompt"
- setenv VIRTUAL_ENV_PROMPT "__VENV_PROMPT__"
+ set prompt = __VENV_PROMPT__"$prompt"
+ setenv VIRTUAL_ENV_PROMPT __VENV_PROMPT__
endif
alias pydoc python -m pydoc
--- a/Lib/venv/scripts/posix/activate.fish
+++ b/Lib/venv/scripts/posix/activate.fish
@@ -33,10 +33,10 @@ end
# Unset irrelevant variables.
deactivate nondestructive
-set -gx VIRTUAL_ENV "__VENV_DIR__"
+set -gx VIRTUAL_ENV __VENV_DIR__
set -gx _OLD_VIRTUAL_PATH $PATH
-set -gx PATH "$VIRTUAL_ENV/__VENV_BIN_NAME__" $PATH
+set -gx PATH "$VIRTUAL_ENV/"__VENV_BIN_NAME__ $PATH
# Unset PYTHONHOME if set.
if set -q PYTHONHOME
@@ -56,7 +56,7 @@ if test -z "$VIRTUAL_ENV_DISABLE_PROMPT"
set -l old_status $status
# Output the venv prompt; color taken from the blue of the Python logo.
- printf "%s%s%s" (set_color 4B8BBE) "__VENV_PROMPT__" (set_color normal)
+ printf "%s%s%s" (set_color 4B8BBE) __VENV_PROMPT__ (set_color normal)
# Restore the return status of the previous command.
echo "exit $old_status" | .
@@ -65,5 +65,5 @@ if test -z "$VIRTUAL_ENV_DISABLE_PROMPT"
end
set -gx _OLD_FISH_PROMPT_OVERRIDE "$VIRTUAL_ENV"
- set -gx VIRTUAL_ENV_PROMPT "__VENV_PROMPT__"
+ set -gx VIRTUAL_ENV_PROMPT __VENV_PROMPT__
end
--- /dev/null
+++ b/Misc/NEWS.d/next/Library/2024-09-28-02-03-04.gh-issue-124651.bLBGtH.rst
@@ -0,0 +1 @@
+Properly quote template strings in :mod:`venv` activation scripts.

3
Python-3.10.14.tar.xz Normal file
View File

@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9c50481faa8c2832329ba0fc8868d0a606a680fc4f60ec48d26ce8e076751fda
size 19600188

16
Python-3.10.14.tar.xz.asc Normal file
View File

@ -0,0 +1,16 @@
-----BEGIN PGP SIGNATURE-----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=1PBR
-----END PGP SIGNATURE-----

View File

@ -1,3 +0,0 @@
version https://git-lfs.github.com/spec/v1
oid sha256:aab0950817735172601879872d937c1e4928a57c409ae02369ec3d91dccebe79
size 19596540

View File

@ -1,16 +0,0 @@
-----BEGIN PGP SIGNATURE-----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=f/SR
-----END PGP SIGNATURE-----

View File

@ -35,7 +35,6 @@
Doc/library/copy.rst | 2
Doc/library/copyreg.rst | 4
Doc/library/dis.rst | 2
Doc/library/email.compat32-message.rst | 1
Doc/library/exceptions.rst | 10 +-
Doc/library/fnmatch.rst | 4
Doc/library/functions.rst | 10 +-
@ -55,15 +54,15 @@
Doc/library/shelve.rst | 6 -
Doc/library/site.rst | 6 -
Doc/library/socket.rst | 4
Doc/library/stdtypes.rst | 146 +++++++++++++++----------------
Doc/library/stdtypes.rst | 146 ++++++++++++++++----------------
Doc/library/sys.rst | 2
Doc/library/traceback.rst | 2
Doc/library/types.rst | 2
Doc/reference/compound_stmts.rst | 90 +++++++++----------
Doc/reference/datamodel.rst | 154 ++++++++++++++++-----------------
Doc/reference/datamodel.rst | 154 +++++++++++++++++-----------------
Doc/reference/executionmodel.rst | 2
Doc/reference/expressions.rst | 134 ++++++++++++++--------------
Doc/reference/simple_stmts.rst | 74 +++++++--------
Doc/reference/expressions.rst | 134 ++++++++++++++---------------
Doc/reference/simple_stmts.rst | 74 ++++++++--------
Doc/reference/toplevel_components.rst | 10 +-
Doc/tools/extensions/pyspecific.py | 25 +++++
Doc/tutorial/classes.rst | 2
@ -71,7 +70,7 @@
Doc/tutorial/inputoutput.rst | 6 -
Doc/tutorial/modules.rst | 4
Doc/tutorial/stdlib.rst | 2
72 files changed, 458 insertions(+), 427 deletions(-)
71 files changed, 457 insertions(+), 427 deletions(-)
--- a/Doc/c-api/bytearray.rst
+++ b/Doc/c-api/bytearray.rst
@ -728,16 +727,6 @@
Pushes a slice object on the stack. *argc* must be 2 or 3. If it is 2,
``slice(TOS1, TOS)`` is pushed; if it is 3, ``slice(TOS2, TOS1, TOS)`` is
--- a/Doc/library/email.compat32-message.rst
+++ b/Doc/library/email.compat32-message.rst
@@ -7,6 +7,7 @@
:synopsis: The base class representing email messages in a fashion
backward compatible with Python 3.2
:noindex:
+ :no-index:
The :class:`Message` class is very similar to the
--- a/Doc/library/exceptions.rst
+++ b/Doc/library/exceptions.rst
@@ -4,8 +4,8 @@ Built-in Exceptions
@ -926,7 +915,7 @@
Open a new pseudo-terminal pair. Return a pair of file descriptors
``(master, slave)`` for the pty and the tty, respectively. The new file
@@ -2644,7 +2644,7 @@ features:
@@ -2637,7 +2637,7 @@ features:
possible and call :func:`lstat` on the result. This does not apply to
dangling symlinks or junction points, which will raise the usual exceptions.

View File

@ -29,7 +29,7 @@
Create a Python.framework rather than a traditional Unix install. Optional
--- a/Misc/NEWS
+++ b/Misc/NEWS
@@ -3810,7 +3810,7 @@ C API
@@ -3731,7 +3731,7 @@ C API
-----
- bpo-43795: The list in :ref:`stable-abi-list` now shows the public name

View File

@ -1,35 +0,0 @@
From 1b3f6523a5c83323cdc44031b33a1c062e5dc698 Mon Sep 17 00:00:00 2001
From: Xi Ruoyao <xry111@xry111.site>
Date: Fri, 7 Jun 2024 23:51:32 +0800
Subject: [PATCH] gh-120226: Fix
test_sendfile_close_peer_in_the_middle_of_receiving on Linux >= 6.10
(GH-120227)
The worst case is that the kernel buffers 17 pages with a page size of 64k.
(cherry picked from commit a7584245661102a5768c643fbd7db8395fd3c90e)
Co-authored-by: Xi Ruoyao <xry111@xry111.site>
---
Lib/test/test_asyncio/test_sendfile.py | 11 ++++-------
1 file changed, 4 insertions(+), 7 deletions(-)
--- a/Lib/test/test_asyncio/test_sendfile.py
+++ b/Lib/test/test_asyncio/test_sendfile.py
@@ -93,13 +93,10 @@ class MyProto(asyncio.Protocol):
class SendfileBase:
- # 256 KiB plus small unaligned to buffer chunk
- # Newer versions of Windows seems to have increased its internal
- # buffer and tries to send as much of the data as it can as it
- # has some form of buffering for this which is less than 256KiB
- # on newer server versions and Windows 11.
- # So DATA should be larger than 256 KiB to make this test reliable.
- DATA = b"x" * (1024 * 256 + 1)
+ # Linux >= 6.10 seems buffering up to 17 pages of data.
+ # So DATA should be large enough to make this test reliable even with a
+ # 64 KiB page configuration.
+ DATA = b"x" * (1024 * 17 * 64 + 1)
# Reduce socket buffer size to test on relative small data sets.
BUF_SIZE = 4 * 1024 # 4 KiB

View File

@ -1,118 +1,3 @@
-------------------------------------------------------------------
Mon Nov 4 21:49:20 UTC 2024 - Matej Cepl <mcepl@cepl.eu>
- Update sphinx-72.patch to include renaming :noindex: option to
:no-index: in Sphinx 7.2 (bsc#1232750).
- While renaming drop fix-sphinx-72.patch.
-------------------------------------------------------------------
Fri Nov 1 21:38:45 UTC 2024 - Matej Cepl <mcepl@cepl.eu>
- Update CVE-2024-9287-venv_path_unquoted.patch according to the
upstream PR gh#python/cpython!126301.
-------------------------------------------------------------------
Thu Oct 24 16:09:00 UTC 2024 - Matej Cepl <mcepl@cepl.eu>
- Add CVE-2024-9287-venv_path_unquoted.patch to properly quote
path names provided when creating a virtual environment
(bsc#1232241, CVE-2024-9287)
-------------------------------------------------------------------
Wed Oct 2 16:18:29 UTC 2024 - Matej Cepl <mcepl@cepl.eu>
- Drop .pyc files from docdir for reproducible builds
(bsc#1230906).
-------------------------------------------------------------------
Mon Sep 9 13:41:07 UTC 2024 - Matej Cepl <mcepl@cepl.eu>
- Update to 3.10.15:
- Tests
- gh-112769: The tests now correctly compare zlib version
when :const:`zlib.ZLIB_RUNTIME_VERSION` contains
non-integer suffixes. For example zlib-ng defines the
version as ``1.3.0.zlib-ng``.
- gh-117187: Fix XML tests for vanilla Expat <2.6.0.
- gh-100454: Fix SSL tests CI for OpenSSL 3.1+
- Security
- gh-123678: Upgrade libexpat to 2.6.3
- gh-121957: Fixed missing audit events around interactive
use of Python, now also properly firing for ``python -i``,
as well as for ``python -m asyncio``. The event in question
is ``cpython.run_stdin``.
- gh-122133: Authenticate the socket connection for the
``socket.socketpair()`` fallback on platforms where
``AF_UNIX`` is not available like Windows. Patch by
Gregory P. Smith <greg@krypto.org> and Seth Larson
<seth@python.org>. Reported by Ellie <el@horse64.org>
- gh-121285: Remove backtracking from tarfile header
parsing for ``hdrcharset``, PAX, and GNU sparse headers
(bsc#1230227, CVE-2024-6232).
- gh-118486: :func:`os.mkdir` on Windows now accepts
*mode* of ``0o700`` to restrict the new directory to
the current user. This fixes CVE-2024-4030 affecting
:func:`tempfile.mkdtemp` in scenarios where the base
temporary directory is more permissive than the default.
- gh-116741: Update bundled libexpat to 2.6.2
- Library
- gh-123693: Use platform-agnostic behavior when computing
``zipfile.Path.name``.
- gh-123270: Applied a more surgical fix for malformed
payloads in :class:`zipfile.Path` causing infinite loops
(gh-122905) without breaking contents using legitimate
characters (bsc#1229704, CVE-2024-8088).
- gh-123067: Fix quadratic complexity in parsing ``"``-quoted
cookie values with backslashes by :mod:`http.cookies`
(bsc#1229596, CVE-2024-7592).
- gh-122905: :class:`zipfile.Path` objects now sanitize names
from the zipfile.
- gh-121650: :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.; CVE-2024-6923, bsc#1228780).
- gh-113171: 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.
Fixes bsc#1226448 (CVE-2024-4032).
- gh-102988: :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 (bsc#1210638).
- gh-67693: Fix :func:`urllib.parse.urlunparse` and
:func:`urllib.parse.urlunsplit` for URIs with path starting with multiple
slashes and no authority. Based on patch by Ashwin Ramaswami.
- Core and Builtins
- gh-112275: A deadlock involving ``pystate.c``'s
``HEAD_LOCK`` in ``posixmodule.c`` at fork is now
fixed. Patch by ChuBoning based on previous Python 3.12 fix
by Victor Stinner.
- Remove upstreamed patches:
- CVE-2023-27043-email-parsing-errors.patch
- CVE-2024-4032-private-IP-addrs.patch
- CVE-2024-6923-email-hdr-inject.patch
- CVE-2024-8088-inf-loop-zipfile_Path.patch
- Add sphinx-802.patch to overcome working both with the most
recent and older Sphinx versions.
-------------------------------------------------------------------
Mon Sep 2 09:44:26 UTC 2024 - Matej Cepl <mcepl@cepl.eu>
- Add gh120226-fix-sendfile-test-kernel-610.patch to avoid
failing test_sendfile_close_peer_in_the_middle_of_receiving
tests on Linux >= 6.10 (GH-120227).
-------------------------------------------------------------------
Wed Aug 28 16:54:34 UTC 2024 - Matej Cepl <mcepl@cepl.eu>

View File

@ -108,7 +108,7 @@ Obsoletes: python39%{?1:-%{1}}
# _md5.cpython-38m-x86_64-linux-gnu.so
%define dynlib() %{sitedir}/lib-dynload/%{1}.cpython-%{abi_tag}-%{archname}-%{_os}%{?_gnu}%{?armsuffix}.so
Name: %{python_pkg_name}%{psuffix}
Version: 3.10.15
Version: 3.10.14
Release: 0
Summary: Python 3 Interpreter
License: Python-2.0
@ -178,6 +178,11 @@ Patch18: bpo-37596-make-set-marshalling.patch
# PATCH-FIX-UPSTREAM gh-78214-marshal_stabilize_FLAG_REF.patch bsc#1213463 mcepl@suse.com
# marshal: Stabilize FLAG_REF usage
Patch19: gh-78214-marshal_stabilize_FLAG_REF.patch
# PATCH-FIX-UPSTREAM CVE-2023-27043-email-parsing-errors.patch bsc#1210638 mcepl@suse.com
# Detect email address parsing errors and return empty tuple to
# indicate the parsing error (old API), from gh#python/cpython!105127
# Patch carries a REGRESSION (gh#python/cpython#106669), so it has been also partially REVERTED
Patch20: CVE-2023-27043-email-parsing-errors.patch
# PATCH-FIX-UPSTREAM fix-sphinx-72.patch gh#python/cpython#97950
# This is a patch with a lot of PR combined to make the doc work with
# sphinx 7.2
@ -191,22 +196,22 @@ Patch19: gh-78214-marshal_stabilize_FLAG_REF.patch
# * gh#python/cpython#104163
# * gh#python/cpython#104221
# * gh#python/cpython#107246
Patch21: sphinx-72.patch
Patch21: fix-sphinx-72.patch
# PATCH-FIX-UPSTREAM CVE-2023-52425-libexpat-2.6.0-backport.patch gh#python/cpython#117187 mcepl@suse.com
# Make the test suite work with libexpat < 2.6.0
Patch22: CVE-2023-52425-libexpat-2.6.0-backport.patch
# PATCH-FIX-UPSTREAM CVE-2024-4032-private-IP-addrs.patch bsc#1226448 mcepl@suse.com
# rearrange definition of private v global IP addresses
Patch23: CVE-2024-4032-private-IP-addrs.patch
# PATCH-FIX-UPSTREAM bso1227999-reproducible-builds.patch bsc#1227999 mcepl@suse.com
# reproducibility patches
Patch24: bso1227999-reproducible-builds.patch
# PATCH-FIX-UPSTREAM gh120226-fix-sendfile-test-kernel-610.patch gh#python/cpython#120226 mcepl@suse.com
# Fix test_sendfile_close_peer_in_the_middle_of_receiving on Linux >= 6.10 (GH-120227)
Patch27: gh120226-fix-sendfile-test-kernel-610.patch
# PATCH-FIX-UPSTREAM sphinx-802.patch mcepl@suse.com
# status_iterator method moved between the Sphinx versions
Patch28: sphinx-802.patch
# PATCH-FIX-UPSTREAM CVE-2024-9287-venv_path_unquoted.patch gh#python/cpython#124651 mcepl@suse.com
# venv should properly quote path names provided when creating a venv
Patch29: CVE-2024-9287-venv_path_unquoted.patch
# PATCH-FIX-UPSTREAM CVE-2024-6923-email-hdr-inject.patch bsc#1228780 mcepl@suse.com
# prevent email header injection, patch from gh#python/cpython!122608
Patch25: CVE-2024-6923-email-hdr-inject.patch
# PATCH-FIX-UPSTREAM CVE-2024-8088-inf-loop-zipfile_Path.patch bsc#1229704 mcepl@suse.com
# avoid denial of service in zipfile
Patch26: CVE-2024-8088-inf-loop-zipfile_Path.patch
BuildRequires: autoconf-archive
BuildRequires: automake
BuildRequires: fdupes
@ -481,12 +486,13 @@ other applications.
%patch -p1 -P 17
%patch -p1 -P 18
%patch -p1 -P 19
%patch -p1 -P 20
%patch -p1 -P 21
%patch -p1 -P 22
%patch -p1 -P 23
%patch -p1 -P 24
%patch -p1 -P 27
%patch -p1 -P 28
%patch -p1 -P 29
%patch -p1 -P 25
%patch -p1 -P 26
# drop Autoconf version requirement
sed -i 's/^AC_PREREQ/dnl AC_PREREQ/' configure.ac
@ -823,11 +829,6 @@ LD_LIBRARY_PATH=. ./python -O -c "from py_compile import compile; compile('$FAIL
echo %{sitedir}/_import_failed > %{buildroot}/%{sitedir}/site-packages/zzzz-import-failed-hooks.pth
%endif
# For the purposes of reproducibility, it is necessary to eliminate any *.pyc files inside documentation dirs
if [ -d %{buildroot}%{_defaultdocdir} ] ; then
find %{buildroot}%{_defaultdocdir} -type f -name \*.pyc -ls -exec rm -vf '{}' \;
fi
%if %{with general}
%files -n %{python_pkg_name}-tk
%{sitedir}/tkinter

View File

@ -1,21 +0,0 @@
---
Doc/tools/extensions/pyspecific.py | 8 +++++++-
1 file changed, 7 insertions(+), 1 deletion(-)
--- a/Doc/tools/extensions/pyspecific.py
+++ b/Doc/tools/extensions/pyspecific.py
@@ -27,7 +27,13 @@ try:
except ImportError:
from sphinx.environment import NoUri
from sphinx.locale import _ as sphinx_gettext
-from sphinx.util import status_iterator, logging
+try:
+ from sphinx.util.display import status_iterator
+except ImportError:
+ # This method was moved into sphinx.util.display in Sphinx 6.1.0. Before
+ # that it resided in sphinx.util.
+ from sphinx.util import status_iterator
+from sphinx.util import logging
from sphinx.util.nodes import split_explicit_title
from sphinx.writers.text import TextWriter, TextTranslator
from sphinx.writers.latex import LaTeXTranslator