From aeede11e2d069ec4da24bbd6f0558d1b5edad277 Mon Sep 17 00:00:00 2001 From: eabdullin Date: Thu, 12 Dec 2024 08:27:17 +0000 Subject: [PATCH] import UBI python3.9-3.9.21-1.el9_5 --- .gitignore | 2 +- .python3.9.metadata | 2 +- SOURCES/00414-skip_test_zlib_s390x.patch | 88 --- ...-addresses-in-email-parseaddr-111116.patch | 504 +----------------- SOURCES/00431-CVE-2024-4032.patch | 402 -------------- ...d-verify-headers-are-sound-gh-122233.patch | 356 ------------- ...22905-sanitize-names-in-zipfile-path.patch | 128 ----- SOURCES/00437-CVE-2024-6232.patch | 245 --------- SOURCES/Python-3.9.19.tar.xz.asc | 16 - SOURCES/Python-3.9.21.tar.xz.asc | 16 + SPECS/python3.9.spec | 50 +- 11 files changed, 27 insertions(+), 1782 deletions(-) delete mode 100644 SOURCES/00414-skip_test_zlib_s390x.patch delete mode 100644 SOURCES/00431-CVE-2024-4032.patch delete mode 100644 SOURCES/00435-gh-121650-encode-newlines-in-headers-and-verify-headers-are-sound-gh-122233.patch delete mode 100644 SOURCES/00436-cve-2024-8088-gh-122905-sanitize-names-in-zipfile-path.patch delete mode 100644 SOURCES/00437-CVE-2024-6232.patch delete mode 100644 SOURCES/Python-3.9.19.tar.xz.asc create mode 100644 SOURCES/Python-3.9.21.tar.xz.asc diff --git a/.gitignore b/.gitignore index aced865..1e7e31b 100644 --- a/.gitignore +++ b/.gitignore @@ -1 +1 @@ -SOURCES/Python-3.9.19.tar.xz +SOURCES/Python-3.9.21.tar.xz diff --git a/.python3.9.metadata b/.python3.9.metadata index 4e88085..1c47439 100644 --- a/.python3.9.metadata +++ b/.python3.9.metadata @@ -1 +1 @@ -57d08ec0b329a78923b486abae906d4fa12fadb7 SOURCES/Python-3.9.19.tar.xz +d968a953f19c6fc3bf54b5ded5c06852197ebddc SOURCES/Python-3.9.21.tar.xz diff --git a/SOURCES/00414-skip_test_zlib_s390x.patch b/SOURCES/00414-skip_test_zlib_s390x.patch deleted file mode 100644 index dac7540..0000000 --- a/SOURCES/00414-skip_test_zlib_s390x.patch +++ /dev/null @@ -1,88 +0,0 @@ -From e5be32d6eb880c9563fde2f23cc31b7e449719ec Mon Sep 17 00:00:00 2001 -From: Victor Stinner -Date: Wed, 24 Jan 2024 18:14:14 +0100 -Subject: [PATCH] bpo-46623: Skip two test_zlib tests on s390x (GH-31096) - -Skip test_pair() and test_speech128() of test_zlib on s390x since -they fail if zlib uses the s390x hardware accelerator. ---- - Lib/test/test_zlib.py | 32 +++++++++++++++++++ - .../2022-02-03-09-45-26.bpo-46623.vxzuhV.rst | 2 ++ - 2 files changed, 34 insertions(+) - create mode 100644 Misc/NEWS.d/next/Tests/2022-02-03-09-45-26.bpo-46623.vxzuhV.rst - -diff --git a/Lib/test/test_zlib.py b/Lib/test/test_zlib.py -index 02509cd..f3654c9 100644 ---- a/Lib/test/test_zlib.py -+++ b/Lib/test/test_zlib.py -@@ -2,6 +2,7 @@ import unittest - from test import support - import binascii - import copy -+import os - import pickle - import random - import sys -@@ -16,6 +17,35 @@ requires_Decompress_copy = unittest.skipUnless( - hasattr(zlib.decompressobj(), "copy"), - 'requires Decompress.copy()') - -+# bpo-46623: On s390x, when a hardware accelerator is used, using different -+# ways to compress data with zlib can produce different compressed data. -+# Simplified test_pair() code: -+# -+# def func1(data): -+# return zlib.compress(data) -+# -+# def func2(data) -+# co = zlib.compressobj() -+# x1 = co.compress(data) -+# x2 = co.flush() -+# return x1 + x2 -+# -+# On s390x if zlib uses a hardware accelerator, func1() creates a single -+# "final" compressed block whereas func2() produces 3 compressed blocks (the -+# last one is a final block). On other platforms with no accelerator, func1() -+# and func2() produce the same compressed data made of a single (final) -+# compressed block. -+# -+# Only the compressed data is different, the decompression returns the original -+# data: -+# -+# zlib.decompress(func1(data)) == zlib.decompress(func2(data)) == data -+# -+# Make the assumption that s390x always has an accelerator to simplify the skip -+# condition. Windows doesn't have os.uname() but it doesn't support s390x. -+skip_on_s390x = unittest.skipIf(hasattr(os, 'uname') and os.uname().machine == 's390x', -+ 'skipped on s390x') -+ - - class VersionTestCase(unittest.TestCase): - -@@ -174,6 +204,7 @@ class CompressTestCase(BaseCompressTestCase, unittest.TestCase): - bufsize=zlib.DEF_BUF_SIZE), - HAMLET_SCENE) - -+ @skip_on_s390x - def test_speech128(self): - # compress more data - data = HAMLET_SCENE * 128 -@@ -225,6 +256,7 @@ class CompressTestCase(BaseCompressTestCase, unittest.TestCase): - - class CompressObjectTestCase(BaseCompressTestCase, unittest.TestCase): - # Test compression object -+ @skip_on_s390x - def test_pair(self): - # straightforward compress/decompress objects - datasrc = HAMLET_SCENE * 128 -diff --git a/Misc/NEWS.d/next/Tests/2022-02-03-09-45-26.bpo-46623.vxzuhV.rst b/Misc/NEWS.d/next/Tests/2022-02-03-09-45-26.bpo-46623.vxzuhV.rst -new file mode 100644 -index 0000000..be085c0 ---- /dev/null -+++ b/Misc/NEWS.d/next/Tests/2022-02-03-09-45-26.bpo-46623.vxzuhV.rst -@@ -0,0 +1,2 @@ -+Skip test_pair() and test_speech128() of test_zlib on s390x since they fail -+if zlib uses the s390x hardware accelerator. Patch by Victor Stinner. --- -2.43.0 - diff --git a/SOURCES/00415-cve-2023-27043-gh-102988-reject-malformed-addresses-in-email-parseaddr-111116.patch b/SOURCES/00415-cve-2023-27043-gh-102988-reject-malformed-addresses-in-email-parseaddr-111116.patch index 145981d..7feac58 100644 --- a/SOURCES/00415-cve-2023-27043-gh-102988-reject-malformed-addresses-in-email-parseaddr-111116.patch +++ b/SOURCES/00415-cve-2023-27043-gh-102988-reject-malformed-addresses-in-email-parseaddr-111116.patch @@ -1,505 +1,3 @@ -From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001 -From: Victor Stinner -Date: Fri, 15 Dec 2023 16:10:40 +0100 -Subject: [PATCH] 00415: [CVE-2023-27043] gh-102988: Reject malformed addresses - in email.parseaddr() (#111116) - -Detect email address parsing errors and return empty tuple to -indicate the parsing error (old API). Add an optional 'strict' -parameter to getaddresses() and parseaddr() functions. Patch by -Thomas Dwyer. - -Co-Authored-By: Thomas Dwyer ---- - Doc/library/email.utils.rst | 19 +- - Lib/email/utils.py | 151 ++++++++++++- - Lib/test/test_email/test_email.py | 204 +++++++++++++++++- - ...-10-20-15-28-08.gh-issue-102988.dStNO7.rst | 8 + - 4 files changed, 361 insertions(+), 21 deletions(-) - create mode 100644 Misc/NEWS.d/next/Library/2023-10-20-15-28-08.gh-issue-102988.dStNO7.rst - -diff --git a/Doc/library/email.utils.rst b/Doc/library/email.utils.rst -index 4d0e920eb0..104229e9e5 100644 ---- a/Doc/library/email.utils.rst -+++ b/Doc/library/email.utils.rst -@@ -60,13 +60,18 @@ of the new API. - begins with angle brackets, they are stripped off. - - --.. function:: parseaddr(address) -+.. function:: parseaddr(address, *, strict=True) - - Parse address -- which should be the value of some address-containing field such - as :mailheader:`To` or :mailheader:`Cc` -- into its constituent *realname* and - *email address* parts. Returns a tuple of that information, unless the parse - fails, in which case a 2-tuple of ``('', '')`` is returned. - -+ If *strict* is true, use a strict parser which rejects malformed inputs. -+ -+ .. versionchanged:: 3.13 -+ Add *strict* optional parameter and reject malformed inputs by default. -+ - - .. function:: formataddr(pair, charset='utf-8') - -@@ -84,12 +89,15 @@ of the new API. - Added the *charset* option. - - --.. function:: getaddresses(fieldvalues) -+.. function:: getaddresses(fieldvalues, *, strict=True) - - This method returns a list of 2-tuples of the form returned by ``parseaddr()``. - *fieldvalues* is a sequence of header field values as might be returned by -- :meth:`Message.get_all `. Here's a simple -- example that gets all the recipients of a message:: -+ :meth:`Message.get_all `. -+ -+ If *strict* is true, use a strict parser which rejects malformed inputs. -+ -+ Here's a simple example that gets all the recipients of a message:: - - from email.utils import getaddresses - -@@ -99,6 +107,9 @@ of the new API. - resent_ccs = msg.get_all('resent-cc', []) - all_recipients = getaddresses(tos + ccs + resent_tos + resent_ccs) - -+ .. versionchanged:: 3.13 -+ Add *strict* optional parameter and reject malformed inputs by default. -+ - - .. function:: parsedate(date) - -diff --git a/Lib/email/utils.py b/Lib/email/utils.py -index 48d30160aa..7ca7a7c886 100644 ---- a/Lib/email/utils.py -+++ b/Lib/email/utils.py -@@ -48,6 +48,7 @@ TICK = "'" - specialsre = re.compile(r'[][\\()<>@,:;".]') - escapesre = re.compile(r'[\\"]') - -+ - def _has_surrogates(s): - """Return True if s contains surrogate-escaped binary data.""" - # This check is based on the fact that unless there are surrogates, utf8 -@@ -106,12 +107,127 @@ def formataddr(pair, charset='utf-8'): - return address - - -+def _iter_escaped_chars(addr): -+ pos = 0 -+ escape = False -+ for pos, ch in enumerate(addr): -+ if escape: -+ yield (pos, '\\' + ch) -+ escape = False -+ elif ch == '\\': -+ escape = True -+ else: -+ yield (pos, ch) -+ if escape: -+ yield (pos, '\\') - --def getaddresses(fieldvalues): -- """Return a list of (REALNAME, EMAIL) for each fieldvalue.""" -- all = COMMASPACE.join(str(v) for v in fieldvalues) -- a = _AddressList(all) -- return a.addresslist -+ -+def _strip_quoted_realnames(addr): -+ """Strip real names between quotes.""" -+ if '"' not in addr: -+ # Fast path -+ return addr -+ -+ start = 0 -+ open_pos = None -+ result = [] -+ for pos, ch in _iter_escaped_chars(addr): -+ if ch == '"': -+ if open_pos is None: -+ open_pos = pos -+ else: -+ if start != open_pos: -+ result.append(addr[start:open_pos]) -+ start = pos + 1 -+ open_pos = None -+ -+ if start < len(addr): -+ result.append(addr[start:]) -+ -+ return ''.join(result) -+ -+ -+supports_strict_parsing = True -+ -+def getaddresses(fieldvalues, *, strict=True): -+ """Return a list of (REALNAME, EMAIL) or ('','') for each fieldvalue. -+ -+ When parsing fails for a fieldvalue, a 2-tuple of ('', '') is returned in -+ its place. -+ -+ If strict is true, use a strict parser which rejects malformed inputs. -+ """ -+ -+ # If strict is true, if the resulting list of parsed addresses is greater -+ # than the number of fieldvalues in the input list, a parsing error has -+ # occurred and consequently a list containing a single empty 2-tuple [('', -+ # '')] is returned in its place. This is done to avoid invalid output. -+ # -+ # Malformed input: getaddresses(['alice@example.com ']) -+ # Invalid output: [('', 'alice@example.com'), ('', 'bob@example.com')] -+ # Safe output: [('', '')] -+ -+ if not strict: -+ all = COMMASPACE.join(str(v) for v in fieldvalues) -+ a = _AddressList(all) -+ return a.addresslist -+ -+ fieldvalues = [str(v) for v in fieldvalues] -+ fieldvalues = _pre_parse_validation(fieldvalues) -+ addr = COMMASPACE.join(fieldvalues) -+ a = _AddressList(addr) -+ result = _post_parse_validation(a.addresslist) -+ -+ # Treat output as invalid if the number of addresses is not equal to the -+ # expected number of addresses. -+ n = 0 -+ for v in fieldvalues: -+ # When a comma is used in the Real Name part it is not a deliminator. -+ # So strip those out before counting the commas. -+ v = _strip_quoted_realnames(v) -+ # Expected number of addresses: 1 + number of commas -+ n += 1 + v.count(',') -+ if len(result) != n: -+ return [('', '')] -+ -+ return result -+ -+ -+def _check_parenthesis(addr): -+ # Ignore parenthesis in quoted real names. -+ addr = _strip_quoted_realnames(addr) -+ -+ opens = 0 -+ for pos, ch in _iter_escaped_chars(addr): -+ if ch == '(': -+ opens += 1 -+ elif ch == ')': -+ opens -= 1 -+ if opens < 0: -+ return False -+ return (opens == 0) -+ -+ -+def _pre_parse_validation(email_header_fields): -+ accepted_values = [] -+ for v in email_header_fields: -+ if not _check_parenthesis(v): -+ v = "('', '')" -+ accepted_values.append(v) -+ -+ return accepted_values -+ -+ -+def _post_parse_validation(parsed_email_header_tuples): -+ accepted_values = [] -+ # The parser would have parsed a correctly formatted domain-literal -+ # The existence of an [ after parsing indicates a parsing failure -+ for v in parsed_email_header_tuples: -+ if '[' in v[1]: -+ v = ('', '') -+ accepted_values.append(v) -+ -+ return accepted_values - - - def _format_timetuple_and_zone(timetuple, zone): -@@ -202,16 +318,33 @@ def parsedate_to_datetime(data): - tzinfo=datetime.timezone(datetime.timedelta(seconds=tz))) - - --def parseaddr(addr): -+def parseaddr(addr, *, strict=True): - """ - Parse addr into its constituent realname and email address parts. - - Return a tuple of realname and email address, unless the parse fails, in - which case return a 2-tuple of ('', ''). -+ -+ If strict is True, use a strict parser which rejects malformed inputs. - """ -- addrs = _AddressList(addr).addresslist -- if not addrs: -- return '', '' -+ if not strict: -+ addrs = _AddressList(addr).addresslist -+ if not addrs: -+ return ('', '') -+ return addrs[0] -+ -+ if isinstance(addr, list): -+ addr = addr[0] -+ -+ if not isinstance(addr, str): -+ return ('', '') -+ -+ addr = _pre_parse_validation([addr])[0] -+ addrs = _post_parse_validation(_AddressList(addr).addresslist) -+ -+ if not addrs or len(addrs) > 1: -+ return ('', '') -+ - return addrs[0] - - -diff --git a/Lib/test/test_email/test_email.py b/Lib/test/test_email/test_email.py -index 761ea90b78..0c689643de 100644 ---- a/Lib/test/test_email/test_email.py -+++ b/Lib/test/test_email/test_email.py -@@ -16,6 +16,7 @@ from unittest.mock import patch - - import email - import email.policy -+import email.utils - - from email.charset import Charset - from email.header import Header, decode_header, make_header -@@ -3263,15 +3264,154 @@ Foo - [('Al Person', 'aperson@dom.ain'), - ('Bud Person', 'bperson@dom.ain')]) - -+ def test_getaddresses_comma_in_name(self): -+ """GH-106669 regression test.""" -+ self.assertEqual( -+ utils.getaddresses( -+ [ -+ '"Bud, Person" ', -+ 'aperson@dom.ain (Al Person)', -+ '"Mariusz Felisiak" ', -+ ] -+ ), -+ [ -+ ('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" ' -+ 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" , "John Doe" ' -+ 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 R. Mastaler', 'jason@dom.ain')]) -+ for addresses, expected in ( -+ (['"Sürname, Firstname" '], -+ [('Sürname, Firstname', 'to@example.com')]), -+ -+ (['foo: ;'], -+ [('', '')]), -+ -+ (['foo: ;', '"Jason R. Mastaler" '], -+ [('', ''), ('Jason R. Mastaler', 'jason@dom.ain')]), -+ -+ ([r'Pete(A nice \) chap) '], -+ [('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 '], -+ [('John Doe (comment)', 'jdoe@machine.example')]), -+ -+ (['"Mary Smith: Personal Account" '], -+ [('Mary Smith: Personal Account', 'smith@home.example')]), -+ -+ (['Undisclosed recipients:;'], -+ [('', '')]), -+ -+ ([r', "Giant; \"Big\" Box" '], -+ [('', 'boss@nil.test'), ('Giant; "Big" Box', 'bob@example.net')]), -+ ): -+ with self.subTest(addresses=addresses): -+ self.assertEqual(utils.getaddresses(addresses), -+ expected) -+ self.assertEqual(utils.getaddresses(addresses, strict=False), -+ expected) -+ -+ addresses = ['[]*-- =~$'] -+ self.assertEqual(utils.getaddresses(addresses), -+ [('', '')]) -+ self.assertEqual(utils.getaddresses(addresses, strict=False), -+ [('', ''), ('', ''), ('', '*--')]) - - def test_getaddresses_embedded_comment(self): - """Test proper handling of a nested comment""" -@@ -3460,6 +3600,54 @@ multipart/report - m = cls(*constructor, policy=email.policy.default) - self.assertIs(m.policy, email.policy.default) - -+ def test_iter_escaped_chars(self): -+ self.assertEqual(list(utils._iter_escaped_chars(r'a\\b\"c\\"d')), -+ [(0, 'a'), -+ (2, '\\\\'), -+ (3, 'b'), -+ (5, '\\"'), -+ (6, 'c'), -+ (8, '\\\\'), -+ (9, '"'), -+ (10, 'd')]) -+ self.assertEqual(list(utils._iter_escaped_chars('a\\')), -+ [(0, 'a'), (1, '\\')]) -+ -+ def test_strip_quoted_realnames(self): -+ def check(addr, expected): -+ self.assertEqual(utils._strip_quoted_realnames(addr), expected) -+ -+ check('"Jane Doe" , "John Doe" ', -+ ' , ') -+ check(r'"Jane \"Doe\"." ', -+ ' ') -+ -+ # 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 , John Doe ', -+ 'lone " quote', -+ ): -+ self.assertEqual(utils._strip_quoted_realnames(addr), addr) -+ -+ -+ def test_check_parenthesis(self): -+ addr = 'alice@example.net' -+ self.assertTrue(utils._check_parenthesis(f'{addr} (Alice)')) -+ self.assertFalse(utils._check_parenthesis(f'{addr} )Alice(')) -+ self.assertFalse(utils._check_parenthesis(f'{addr} (Alice))')) -+ self.assertFalse(utils._check_parenthesis(f'{addr} ((Alice)')) -+ -+ # Ignore real name between quotes -+ self.assertTrue(utils._check_parenthesis(f'")Alice((" {addr}')) -+ - - # Test the iterator/generators - class TestIterators(TestEmailBase): -diff --git a/Misc/NEWS.d/next/Library/2023-10-20-15-28-08.gh-issue-102988.dStNO7.rst b/Misc/NEWS.d/next/Library/2023-10-20-15-28-08.gh-issue-102988.dStNO7.rst -new file mode 100644 -index 0000000000..3d0e9e4078 ---- /dev/null -+++ b/Misc/NEWS.d/next/Library/2023-10-20-15-28-08.gh-issue-102988.dStNO7.rst -@@ -0,0 +1,8 @@ -+:func:`email.utils.getaddresses` and :func:`email.utils.parseaddr` now -+return ``('', '')`` 2-tuples in more situations where invalid email -+addresses are encountered instead of potentially inaccurate values. Add -+optional *strict* parameter to these two functions: use ``strict=False`` to -+get the old behavior, accept malformed inputs. -+``getattr(email.utils, 'supports_strict_parsing', False)`` can be use to check -+if the *strict* paramater is available. Patch by Thomas Dwyer and Victor -+Stinner to improve the CVE-2023-27043 fix. - - From 4df4fad359c280f2328b98ea9b4414f244624a58 Mon Sep 17 00:00:00 2001 From: Lumir Balhar Date: Mon, 18 Dec 2023 20:15:33 +0100 @@ -532,7 +30,7 @@ index d1e1898591..7aef773b5f 100644 + [email_addr_parsing] + PYTHON_EMAIL_DISABLE_STRICT_ADDR_PARSING = true + - .. versionchanged:: 3.13 + .. versionchanged:: 3.9.20 Add *strict* optional parameter and reject malformed inputs by default. @@ -97,6 +110,19 @@ of the new API. diff --git a/SOURCES/00431-CVE-2024-4032.patch b/SOURCES/00431-CVE-2024-4032.patch deleted file mode 100644 index 03bc928..0000000 --- a/SOURCES/00431-CVE-2024-4032.patch +++ /dev/null @@ -1,402 +0,0 @@ -From f647bd8884bc89767914a5e0dea9ae099a8b50b5 Mon Sep 17 00:00:00 2001 -From: Petr Viktorin -Date: Tue, 7 May 2024 11:57:58 +0200 -Subject: [PATCH] gh-113171: gh-65056: Fix "private" (non-global) IP address - ranges (GH-113179) (GH-113186) (GH-118177) (GH-118472) - -The _private_networks variables, used by various is_private -implementations, were missing some ranges and at the same time had -overly strict ranges (where there are more specific ranges considered -globally reachable by the IANA registries). - -This patch updates the ranges with what was missing or otherwise -incorrect. - -100.64.0.0/10 is left alone, for now, as it's been made special in [1]. - -The _address_exclude_many() call returns 8 networks for IPv4, 121 -networks for IPv6. - -[1] https://github.com/python/cpython/issues/61602 - -In 3.10 and below, is_private checks whether the network and broadcast -address are both private. -In later versions (where the test wss backported from), it checks -whether they both are in the same private network. - -For 0.0.0.0/0, both 0.0.0.0 and 255.225.255.255 are private, -but one is in 0.0.0.0/8 ("This network") and the other in -255.255.255.255/32 ("Limited broadcast"). - ---------- - -Co-authored-by: Jakub Stasiak ---- - Doc/library/ipaddress.rst | 43 ++++++++- - Doc/tools/susp-ignored.csv | 8 ++ - Doc/whatsnew/3.9.rst | 9 ++ - Lib/ipaddress.py | 95 +++++++++++++++---- - Lib/test/test_ipaddress.py | 52 ++++++++++ - ...-03-14-01-38-44.gh-issue-113171.VFnObz.rst | 9 ++ - 6 files changed, 195 insertions(+), 21 deletions(-) - create mode 100644 Misc/NEWS.d/next/Library/2024-03-14-01-38-44.gh-issue-113171.VFnObz.rst - -diff --git a/Doc/library/ipaddress.rst b/Doc/library/ipaddress.rst -index 9c2dff5..f9c1ebf 100644 ---- a/Doc/library/ipaddress.rst -+++ b/Doc/library/ipaddress.rst -@@ -188,18 +188,53 @@ write code that handles both IP versions correctly. Address objects are - - .. attribute:: is_private - -- ``True`` if the address is allocated for private networks. See -+ ``True`` if the address is defined as not globally reachable by - iana-ipv4-special-registry_ (for IPv4) or iana-ipv6-special-registry_ -- (for IPv6). -+ (for IPv6) with the following exceptions: -+ -+ * ``is_private`` is ``False`` for the shared address space (``100.64.0.0/10``) -+ * For IPv4-mapped IPv6-addresses the ``is_private`` value is determined by the -+ semantics of the underlying IPv4 addresses and the following condition holds -+ (see :attr:`IPv6Address.ipv4_mapped`):: -+ -+ address.is_private == address.ipv4_mapped.is_private -+ -+ ``is_private`` has value opposite to :attr:`is_global`, except for the shared address space -+ (``100.64.0.0/10`` range) where they are both ``False``. -+ -+ .. versionchanged:: 3.9.20 -+ -+ Fixed some false positives and false negatives. -+ -+ * ``192.0.0.0/24`` is considered private with the exception of ``192.0.0.9/32`` and -+ ``192.0.0.10/32`` (previously: only the ``192.0.0.0/29`` sub-range was considered private). -+ * ``64:ff9b:1::/48`` is considered private. -+ * ``2002::/16`` is considered private. -+ * There are exceptions within ``2001::/23`` (otherwise considered private): ``2001:1::1/128``, -+ ``2001:1::2/128``, ``2001:3::/32``, ``2001:4:112::/48``, ``2001:20::/28``, ``2001:30::/28``. -+ The exceptions are not considered private. - - .. attribute:: is_global - -- ``True`` if the address is allocated for public networks. See -+ ``True`` if the address is defined as globally reachable by - iana-ipv4-special-registry_ (for IPv4) or iana-ipv6-special-registry_ -- (for IPv6). -+ (for IPv6) with the following exception: -+ -+ For IPv4-mapped IPv6-addresses the ``is_private`` value is determined by the -+ semantics of the underlying IPv4 addresses and the following condition holds -+ (see :attr:`IPv6Address.ipv4_mapped`):: -+ -+ address.is_global == address.ipv4_mapped.is_global -+ -+ ``is_global`` has value opposite to :attr:`is_private`, except for the shared address space -+ (``100.64.0.0/10`` range) where they are both ``False``. - - .. versionadded:: 3.4 - -+ .. versionchanged:: 3.9.20 -+ -+ Fixed some false positives and false negatives, see :attr:`is_private` for details. -+ - .. attribute:: is_unspecified - - ``True`` if the address is unspecified. See :RFC:`5735` (for IPv4) -diff --git a/Doc/tools/susp-ignored.csv b/Doc/tools/susp-ignored.csv -index 3eb3d79..de91a50 100644 ---- a/Doc/tools/susp-ignored.csv -+++ b/Doc/tools/susp-ignored.csv -@@ -169,6 +169,14 @@ library/ipaddress,,:db00,2001:db00::0/24 - library/ipaddress,,::,2001:db00::0/24 - library/ipaddress,,:db00,2001:db00::0/ffff:ff00:: - library/ipaddress,,::,2001:db00::0/ffff:ff00:: -+library/ipaddress,,:ff9b,64:ff9b:1::/48 -+library/ipaddress,,::,64:ff9b:1::/48 -+library/ipaddress,,::,2001:: -+library/ipaddress,,::,2001:1:: -+library/ipaddress,,::,2001:3:: -+library/ipaddress,,::,2001:4:112:: -+library/ipaddress,,::,2001:20:: -+library/ipaddress,,::,2001:30:: - library/itertools,,:step,elements from seq[start:stop:step] - library/itertools,,:stop,elements from seq[start:stop:step] - library/itertools,,::,kernel = tuple(kernel)[::-1] -diff --git a/Doc/whatsnew/3.9.rst b/Doc/whatsnew/3.9.rst -index 0064e07..1756a37 100644 ---- a/Doc/whatsnew/3.9.rst -+++ b/Doc/whatsnew/3.9.rst -@@ -1616,3 +1616,12 @@ tarfile - :exc:`DeprecationWarning`. - In Python 3.14, the default will switch to ``'data'``. - (Contributed by Petr Viktorin in :pep:`706`.) -+ -+Notable changes in 3.9.20 -+========================= -+ -+ipaddress -+--------- -+ -+* Fixed ``is_global`` and ``is_private`` behavior in ``IPv4Address``, -+ ``IPv6Address``, ``IPv4Network`` and ``IPv6Network``. -diff --git a/Lib/ipaddress.py b/Lib/ipaddress.py -index 25f373a..9b35340 100644 ---- a/Lib/ipaddress.py -+++ b/Lib/ipaddress.py -@@ -1322,18 +1322,41 @@ class IPv4Address(_BaseV4, _BaseAddress): - @property - @functools.lru_cache() - def is_private(self): -- """Test if this address is allocated for private networks. -+ """``True`` if the address is defined as not globally reachable by -+ iana-ipv4-special-registry_ (for IPv4) or iana-ipv6-special-registry_ -+ (for IPv6) with the following exceptions: - -- Returns: -- A boolean, True if the address is reserved per -- iana-ipv4-special-registry. -+ * ``is_private`` is ``False`` for ``100.64.0.0/10`` -+ * For IPv4-mapped IPv6-addresses the ``is_private`` value is determined by the -+ semantics of the underlying IPv4 addresses and the following condition holds -+ (see :attr:`IPv6Address.ipv4_mapped`):: -+ -+ address.is_private == address.ipv4_mapped.is_private - -+ ``is_private`` has value opposite to :attr:`is_global`, except for the ``100.64.0.0/10`` -+ IPv4 range where they are both ``False``. - """ -- return any(self in net for net in self._constants._private_networks) -+ return ( -+ any(self in net for net in self._constants._private_networks) -+ and all(self not in net for net in self._constants._private_networks_exceptions) -+ ) - - @property - @functools.lru_cache() - def is_global(self): -+ """``True`` if the address is defined as globally reachable by -+ iana-ipv4-special-registry_ (for IPv4) or iana-ipv6-special-registry_ -+ (for IPv6) with the following exception: -+ -+ For IPv4-mapped IPv6-addresses the ``is_private`` value is determined by the -+ semantics of the underlying IPv4 addresses and the following condition holds -+ (see :attr:`IPv6Address.ipv4_mapped`):: -+ -+ address.is_global == address.ipv4_mapped.is_global -+ -+ ``is_global`` has value opposite to :attr:`is_private`, except for the ``100.64.0.0/10`` -+ IPv4 range where they are both ``False``. -+ """ - return self not in self._constants._public_network and not self.is_private - - @property -@@ -1537,13 +1560,15 @@ class _IPv4Constants: - - _public_network = IPv4Network('100.64.0.0/10') - -+ # Not globally reachable address blocks listed on -+ # https://www.iana.org/assignments/iana-ipv4-special-registry/iana-ipv4-special-registry.xhtml - _private_networks = [ - IPv4Network('0.0.0.0/8'), - IPv4Network('10.0.0.0/8'), - IPv4Network('127.0.0.0/8'), - IPv4Network('169.254.0.0/16'), - IPv4Network('172.16.0.0/12'), -- IPv4Network('192.0.0.0/29'), -+ IPv4Network('192.0.0.0/24'), - IPv4Network('192.0.0.170/31'), - IPv4Network('192.0.2.0/24'), - IPv4Network('192.168.0.0/16'), -@@ -1554,6 +1579,11 @@ class _IPv4Constants: - IPv4Network('255.255.255.255/32'), - ] - -+ _private_networks_exceptions = [ -+ IPv4Network('192.0.0.9/32'), -+ IPv4Network('192.0.0.10/32'), -+ ] -+ - _reserved_network = IPv4Network('240.0.0.0/4') - - _unspecified_address = IPv4Address('0.0.0.0') -@@ -1995,23 +2025,42 @@ class IPv6Address(_BaseV6, _BaseAddress): - @property - @functools.lru_cache() - def is_private(self): -- """Test if this address is allocated for private networks. -+ """``True`` if the address is defined as not globally reachable by -+ iana-ipv4-special-registry_ (for IPv4) or iana-ipv6-special-registry_ -+ (for IPv6) with the following exceptions: - -- Returns: -- A boolean, True if the address is reserved per -- iana-ipv6-special-registry. -+ * ``is_private`` is ``False`` for ``100.64.0.0/10`` -+ * For IPv4-mapped IPv6-addresses the ``is_private`` value is determined by the -+ semantics of the underlying IPv4 addresses and the following condition holds -+ (see :attr:`IPv6Address.ipv4_mapped`):: -+ -+ address.is_private == address.ipv4_mapped.is_private - -+ ``is_private`` has value opposite to :attr:`is_global`, except for the ``100.64.0.0/10`` -+ IPv4 range where they are both ``False``. - """ -- return any(self in net for net in self._constants._private_networks) -+ ipv4_mapped = self.ipv4_mapped -+ if ipv4_mapped is not None: -+ return ipv4_mapped.is_private -+ return ( -+ any(self in net for net in self._constants._private_networks) -+ and all(self not in net for net in self._constants._private_networks_exceptions) -+ ) - - @property - def is_global(self): -- """Test if this address is allocated for public networks. -+ """``True`` if the address is defined as globally reachable by -+ iana-ipv4-special-registry_ (for IPv4) or iana-ipv6-special-registry_ -+ (for IPv6) with the following exception: - -- Returns: -- A boolean, true if the address is not reserved per -- iana-ipv6-special-registry. -+ For IPv4-mapped IPv6-addresses the ``is_private`` value is determined by the -+ semantics of the underlying IPv4 addresses and the following condition holds -+ (see :attr:`IPv6Address.ipv4_mapped`):: -+ -+ address.is_global == address.ipv4_mapped.is_global - -+ ``is_global`` has value opposite to :attr:`is_private`, except for the ``100.64.0.0/10`` -+ IPv4 range where they are both ``False``. - """ - return not self.is_private - -@@ -2252,19 +2301,31 @@ class _IPv6Constants: - - _multicast_network = IPv6Network('ff00::/8') - -+ # Not globally reachable address blocks listed on -+ # https://www.iana.org/assignments/iana-ipv6-special-registry/iana-ipv6-special-registry.xhtml - _private_networks = [ - IPv6Network('::1/128'), - IPv6Network('::/128'), - IPv6Network('::ffff:0:0/96'), -+ IPv6Network('64:ff9b:1::/48'), - IPv6Network('100::/64'), - IPv6Network('2001::/23'), -- IPv6Network('2001:2::/48'), - IPv6Network('2001:db8::/32'), -- IPv6Network('2001:10::/28'), -+ # IANA says N/A, let's consider it not globally reachable to be safe -+ IPv6Network('2002::/16'), - IPv6Network('fc00::/7'), - IPv6Network('fe80::/10'), - ] - -+ _private_networks_exceptions = [ -+ IPv6Network('2001:1::1/128'), -+ IPv6Network('2001:1::2/128'), -+ IPv6Network('2001:3::/32'), -+ IPv6Network('2001:4:112::/48'), -+ IPv6Network('2001:20::/28'), -+ IPv6Network('2001:30::/28'), -+ ] -+ - _reserved_networks = [ - IPv6Network('::/8'), IPv6Network('100::/8'), - IPv6Network('200::/7'), IPv6Network('400::/6'), -diff --git a/Lib/test/test_ipaddress.py b/Lib/test/test_ipaddress.py -index 90897f6..bd14f04 100644 ---- a/Lib/test/test_ipaddress.py -+++ b/Lib/test/test_ipaddress.py -@@ -2263,6 +2263,10 @@ class IpaddrUnitTest(unittest.TestCase): - self.assertEqual(True, ipaddress.ip_address( - '172.31.255.255').is_private) - self.assertEqual(False, ipaddress.ip_address('172.32.0.0').is_private) -+ self.assertFalse(ipaddress.ip_address('192.0.0.0').is_global) -+ self.assertTrue(ipaddress.ip_address('192.0.0.9').is_global) -+ self.assertTrue(ipaddress.ip_address('192.0.0.10').is_global) -+ self.assertFalse(ipaddress.ip_address('192.0.0.255').is_global) - - self.assertEqual(True, - ipaddress.ip_address('169.254.100.200').is_link_local) -@@ -2278,6 +2282,40 @@ class IpaddrUnitTest(unittest.TestCase): - self.assertEqual(False, ipaddress.ip_address('128.0.0.0').is_loopback) - self.assertEqual(True, ipaddress.ip_network('0.0.0.0').is_unspecified) - -+ def testPrivateNetworks(self): -+ self.assertEqual(True, ipaddress.ip_network("0.0.0.0/0").is_private) -+ self.assertEqual(False, ipaddress.ip_network("1.0.0.0/8").is_private) -+ -+ self.assertEqual(True, ipaddress.ip_network("0.0.0.0/8").is_private) -+ self.assertEqual(True, ipaddress.ip_network("10.0.0.0/8").is_private) -+ self.assertEqual(True, ipaddress.ip_network("127.0.0.0/8").is_private) -+ self.assertEqual(True, ipaddress.ip_network("169.254.0.0/16").is_private) -+ self.assertEqual(True, ipaddress.ip_network("172.16.0.0/12").is_private) -+ self.assertEqual(True, ipaddress.ip_network("192.0.0.0/29").is_private) -+ self.assertEqual(False, ipaddress.ip_network("192.0.0.9/32").is_private) -+ self.assertEqual(True, ipaddress.ip_network("192.0.0.170/31").is_private) -+ self.assertEqual(True, ipaddress.ip_network("192.0.2.0/24").is_private) -+ self.assertEqual(True, ipaddress.ip_network("192.168.0.0/16").is_private) -+ self.assertEqual(True, ipaddress.ip_network("198.18.0.0/15").is_private) -+ self.assertEqual(True, ipaddress.ip_network("198.51.100.0/24").is_private) -+ self.assertEqual(True, ipaddress.ip_network("203.0.113.0/24").is_private) -+ self.assertEqual(True, ipaddress.ip_network("240.0.0.0/4").is_private) -+ self.assertEqual(True, ipaddress.ip_network("255.255.255.255/32").is_private) -+ -+ self.assertEqual(False, ipaddress.ip_network("::/0").is_private) -+ self.assertEqual(False, ipaddress.ip_network("::ff/128").is_private) -+ -+ self.assertEqual(True, ipaddress.ip_network("::1/128").is_private) -+ self.assertEqual(True, ipaddress.ip_network("::/128").is_private) -+ self.assertEqual(True, ipaddress.ip_network("::ffff:0:0/96").is_private) -+ self.assertEqual(True, ipaddress.ip_network("100::/64").is_private) -+ self.assertEqual(True, ipaddress.ip_network("2001:2::/48").is_private) -+ self.assertEqual(False, ipaddress.ip_network("2001:3::/48").is_private) -+ self.assertEqual(True, ipaddress.ip_network("2001:db8::/32").is_private) -+ self.assertEqual(True, ipaddress.ip_network("2001:10::/28").is_private) -+ self.assertEqual(True, ipaddress.ip_network("fc00::/7").is_private) -+ self.assertEqual(True, ipaddress.ip_network("fe80::/10").is_private) -+ - def testReservedIpv6(self): - - self.assertEqual(True, ipaddress.ip_network('ffff::').is_multicast) -@@ -2351,6 +2389,20 @@ class IpaddrUnitTest(unittest.TestCase): - self.assertEqual(True, ipaddress.ip_address('0::0').is_unspecified) - self.assertEqual(False, ipaddress.ip_address('::1').is_unspecified) - -+ self.assertFalse(ipaddress.ip_address('64:ff9b:1::').is_global) -+ self.assertFalse(ipaddress.ip_address('2001::').is_global) -+ self.assertTrue(ipaddress.ip_address('2001:1::1').is_global) -+ self.assertTrue(ipaddress.ip_address('2001:1::2').is_global) -+ self.assertFalse(ipaddress.ip_address('2001:2::').is_global) -+ self.assertTrue(ipaddress.ip_address('2001:3::').is_global) -+ self.assertFalse(ipaddress.ip_address('2001:4::').is_global) -+ self.assertTrue(ipaddress.ip_address('2001:4:112::').is_global) -+ self.assertFalse(ipaddress.ip_address('2001:10::').is_global) -+ self.assertTrue(ipaddress.ip_address('2001:20::').is_global) -+ self.assertTrue(ipaddress.ip_address('2001:30::').is_global) -+ self.assertFalse(ipaddress.ip_address('2001:40::').is_global) -+ self.assertFalse(ipaddress.ip_address('2002::').is_global) -+ - # some generic IETF reserved addresses - self.assertEqual(True, ipaddress.ip_address('100::').is_reserved) - self.assertEqual(True, ipaddress.ip_network('4000::1/128').is_reserved) -diff --git a/Misc/NEWS.d/next/Library/2024-03-14-01-38-44.gh-issue-113171.VFnObz.rst b/Misc/NEWS.d/next/Library/2024-03-14-01-38-44.gh-issue-113171.VFnObz.rst -new file mode 100644 -index 0000000..f9a7247 ---- /dev/null -+++ b/Misc/NEWS.d/next/Library/2024-03-14-01-38-44.gh-issue-113171.VFnObz.rst -@@ -0,0 +1,9 @@ -+Fixed various false positives and false negatives in -+ -+* :attr:`ipaddress.IPv4Address.is_private` (see these docs for details) -+* :attr:`ipaddress.IPv4Address.is_global` -+* :attr:`ipaddress.IPv6Address.is_private` -+* :attr:`ipaddress.IPv6Address.is_global` -+ -+Also in the corresponding :class:`ipaddress.IPv4Network` and :class:`ipaddress.IPv6Network` -+attributes. --- -2.45.2 - diff --git a/SOURCES/00435-gh-121650-encode-newlines-in-headers-and-verify-headers-are-sound-gh-122233.patch b/SOURCES/00435-gh-121650-encode-newlines-in-headers-and-verify-headers-are-sound-gh-122233.patch deleted file mode 100644 index 432920d..0000000 --- a/SOURCES/00435-gh-121650-encode-newlines-in-headers-and-verify-headers-are-sound-gh-122233.patch +++ /dev/null @@ -1,356 +0,0 @@ -From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001 -From: Petr Viktorin -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 -Co-authored-by: Bas Bloemsaat -Co-authored-by: Serhiy Storchaka ---- - Doc/library/email.errors.rst | 6 ++ - Doc/library/email.policy.rst | 18 ++++++ - Doc/whatsnew/3.9.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 ++++++++ - ...-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 - -diff --git a/Doc/library/email.errors.rst b/Doc/library/email.errors.rst -index f4b9f52509..878c09bb04 100644 ---- a/Doc/library/email.errors.rst -+++ b/Doc/library/email.errors.rst -@@ -59,6 +59,12 @@ The following exception classes are defined in the :mod:`email.errors` module: - :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 -diff --git a/Doc/library/email.policy.rst b/Doc/library/email.policy.rst -index bf53b9520f..57a75ce452 100644 ---- 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:: 3.9.20 -+ -+ - 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/3.9.rst b/Doc/whatsnew/3.9.rst -index 1756a37338..eeda4e6955 100644 ---- a/Doc/whatsnew/3.9.rst -+++ b/Doc/whatsnew/3.9.rst -@@ -1625,3 +1625,15 @@ 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 8a8fb8bc42..e394cfd2e1 100644 ---- 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, *, 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 d28a680010..1a0d5c63e6 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 c9b121624e..89224ae41c 100644 ---- 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) - -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.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, 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 e87c275549..ff1ddf7d7a 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. -@@ -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). -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`.) diff --git a/SOURCES/00436-cve-2024-8088-gh-122905-sanitize-names-in-zipfile-path.patch b/SOURCES/00436-cve-2024-8088-gh-122905-sanitize-names-in-zipfile-path.patch deleted file mode 100644 index fed0497..0000000 --- a/SOURCES/00436-cve-2024-8088-gh-122905-sanitize-names-in-zipfile-path.patch +++ /dev/null @@ -1,128 +0,0 @@ -From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001 -From: "Jason R. Coombs" -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 ---- - Lib/test/test_zipfile.py | 17 ++++++ - Lib/zipfile.py | 61 ++++++++++++++++++- - ...-08-11-14-08-04.gh-issue-122905.7tDsxA.rst | 1 + - 3 files changed, 78 insertions(+), 1 deletion(-) - create mode 100644 Misc/NEWS.d/next/Library/2024-08-11-14-08-04.gh-issue-122905.7tDsxA.rst - -diff --git a/Lib/test/test_zipfile.py b/Lib/test/test_zipfile.py -index 17e95eb862..9a72152357 100644 ---- a/Lib/test/test_zipfile.py -+++ b/Lib/test/test_zipfile.py -@@ -3054,6 +3054,23 @@ class TestPath(unittest.TestCase): - data = ['/'.join(string.ascii_lowercase + str(n)) for n in range(10000)] - zipfile.CompleteDirs._implied_dirs(data) - -+ def test_malformed_paths(self): -+ """ -+ Path should handle malformed paths. -+ """ -+ data = io.BytesIO() -+ zf = zipfile.ZipFile(data, "w") -+ zf.writestr("/one-slash.txt", b"content") -+ zf.writestr("//two-slash.txt", b"content") -+ zf.writestr("../parent.txt", b"content") -+ zf.filename = '' -+ root = zipfile.Path(zf) -+ assert list(map(str, root.iterdir())) == [ -+ 'one-slash.txt', -+ 'two-slash.txt', -+ 'parent.txt', -+ ] -+ - - if __name__ == "__main__": - unittest.main() -diff --git a/Lib/zipfile.py b/Lib/zipfile.py -index 95f95ee112..2e9b2868cd 100644 ---- a/Lib/zipfile.py -+++ b/Lib/zipfile.py -@@ -9,6 +9,7 @@ import io - import itertools - import os - import posixpath -+import re - import shutil - import stat - import struct -@@ -2177,7 +2178,65 @@ def _difference(minuend, subtrahend): - return itertools.filterfalse(set(subtrahend).__contains__, minuend) - - --class CompleteDirs(ZipFile): -+class SanitizedNames: -+ """ -+ ZipFile mix-in to ensure names are sanitized. -+ """ -+ -+ def namelist(self): -+ return list(map(self._sanitize, super().namelist())) -+ -+ @staticmethod -+ def _sanitize(name): -+ r""" -+ Ensure a relative path with posix separators and no dot names. -+ Modeled after -+ https://github.com/python/cpython/blob/bcc1be39cb1d04ad9fc0bd1b9193d3972835a57c/Lib/zipfile/__init__.py#L1799-L1813 -+ but provides consistent cross-platform behavior. -+ >>> san = SanitizedNames._sanitize -+ >>> san('/foo/bar') -+ 'foo/bar' -+ >>> san('//foo.txt') -+ 'foo.txt' -+ >>> san('foo/.././bar.txt') -+ 'foo/bar.txt' -+ >>> san('foo../.bar.txt') -+ 'foo../.bar.txt' -+ >>> san('\\foo\\bar.txt') -+ 'foo/bar.txt' -+ >>> san('D:\\foo.txt') -+ 'D/foo.txt' -+ >>> san('\\\\server\\share\\file.txt') -+ 'server/share/file.txt' -+ >>> san('\\\\?\\GLOBALROOT\\Volume3') -+ '?/GLOBALROOT/Volume3' -+ >>> san('\\\\.\\PhysicalDrive1\\root') -+ 'PhysicalDrive1/root' -+ Retain any trailing slash. -+ >>> san('abc/') -+ 'abc/' -+ Raises a ValueError if the result is empty. -+ >>> san('../..') -+ Traceback (most recent call last): -+ ... -+ ValueError: Empty filename -+ """ -+ -+ def allowed(part): -+ return part and part not in {'..', '.'} -+ -+ # Remove the drive letter. -+ # Don't use ntpath.splitdrive, because that also strips UNC paths -+ bare = re.sub('^([A-Z]):', r'\1', name, flags=re.IGNORECASE) -+ clean = bare.replace('\\', '/') -+ parts = clean.split('/') -+ joined = '/'.join(filter(allowed, parts)) -+ if not joined: -+ raise ValueError("Empty filename") -+ return joined + '/' * name.endswith('/') -+ -+ -+class CompleteDirs(SanitizedNames, ZipFile): - """ - A ZipFile subclass that ensures that implied directories - are always included in the namelist. -diff --git a/Misc/NEWS.d/next/Library/2024-08-11-14-08-04.gh-issue-122905.7tDsxA.rst b/Misc/NEWS.d/next/Library/2024-08-11-14-08-04.gh-issue-122905.7tDsxA.rst -new file mode 100644 -index 0000000000..1be44c906c ---- /dev/null -+++ b/Misc/NEWS.d/next/Library/2024-08-11-14-08-04.gh-issue-122905.7tDsxA.rst -@@ -0,0 +1 @@ -+:class:`zipfile.Path` objects now sanitize names from the zipfile. diff --git a/SOURCES/00437-CVE-2024-6232.patch b/SOURCES/00437-CVE-2024-6232.patch deleted file mode 100644 index 92e7701..0000000 --- a/SOURCES/00437-CVE-2024-6232.patch +++ /dev/null @@ -1,245 +0,0 @@ -From b4225ca91547aa97ed3aca391614afbb255bc877 Mon Sep 17 00:00:00 2001 -From: Seth Michael Larson -Date: Wed, 4 Sep 2024 10:46:01 -0500 -Subject: [PATCH] [3.9] gh-121285: Remove backtracking when parsing tarfile - headers (GH-121286) (#123641) - -* Remove backtracking when parsing tarfile headers -* Rewrite PAX header parsing to be stricter -* Optimize parsing of GNU extended sparse headers v0.0 - -(cherry picked from commit 34ddb64d088dd7ccc321f6103d23153256caa5d4) - -Co-authored-by: Seth Michael Larson -Co-authored-by: Kirill Podoprigora -Co-authored-by: Gregory P. Smith ---- - Lib/tarfile.py | 105 +++++++++++------- - Lib/test/test_tarfile.py | 42 +++++++ - ...-07-02-13-39-20.gh-issue-121285.hrl-yI.rst | 2 + - 3 files changed, 111 insertions(+), 38 deletions(-) - create mode 100644 Misc/NEWS.d/next/Security/2024-07-02-13-39-20.gh-issue-121285.hrl-yI.rst - -diff --git a/Lib/tarfile.py b/Lib/tarfile.py -index 7a6158c2eb9893..d75ba50b6670c7 100755 ---- a/Lib/tarfile.py -+++ b/Lib/tarfile.py -@@ -840,6 +840,9 @@ def data_filter(member, dest_path): - # Sentinel for replace() defaults, meaning "don't change the attribute" - _KEEP = object() - -+# Header length is digits followed by a space. -+_header_length_prefix_re = re.compile(br"([0-9]{1,20}) ") -+ - class TarInfo(object): - """Informational class which holds the details about an - archive member given by a tar header block. -@@ -1399,41 +1402,59 @@ def _proc_pax(self, tarfile): - else: - pax_headers = tarfile.pax_headers.copy() - -- # Check if the pax header contains a hdrcharset field. This tells us -- # the encoding of the path, linkpath, uname and gname fields. Normally, -- # these fields are UTF-8 encoded but since POSIX.1-2008 tar -- # implementations are allowed to store them as raw binary strings if -- # the translation to UTF-8 fails. -- match = re.search(br"\d+ hdrcharset=([^\n]+)\n", buf) -- if match is not None: -- pax_headers["hdrcharset"] = match.group(1).decode("utf-8") -- -- # For the time being, we don't care about anything other than "BINARY". -- # The only other value that is currently allowed by the standard is -- # "ISO-IR 10646 2000 UTF-8" in other words UTF-8. -- hdrcharset = pax_headers.get("hdrcharset") -- if hdrcharset == "BINARY": -- encoding = tarfile.encoding -- else: -- encoding = "utf-8" -- - # Parse pax header information. A record looks like that: - # "%d %s=%s\n" % (length, keyword, value). length is the size - # of the complete record including the length field itself and -- # the newline. keyword and value are both UTF-8 encoded strings. -- regex = re.compile(br"(\d+) ([^=]+)=") -+ # the newline. - pos = 0 -- while True: -- match = regex.match(buf, pos) -- if not match: -- break -+ encoding = None -+ raw_headers = [] -+ while len(buf) > pos and buf[pos] != 0x00: -+ if not (match := _header_length_prefix_re.match(buf, pos)): -+ raise InvalidHeaderError("invalid header") -+ try: -+ length = int(match.group(1)) -+ except ValueError: -+ raise InvalidHeaderError("invalid header") -+ # Headers must be at least 5 bytes, shortest being '5 x=\n'. -+ # Value is allowed to be empty. -+ if length < 5: -+ raise InvalidHeaderError("invalid header") -+ if pos + length > len(buf): -+ raise InvalidHeaderError("invalid header") - -- length, keyword = match.groups() -- length = int(length) -- if length == 0: -+ header_value_end_offset = match.start(1) + length - 1 # Last byte of the header -+ keyword_and_value = buf[match.end(1) + 1:header_value_end_offset] -+ raw_keyword, equals, raw_value = keyword_and_value.partition(b"=") -+ -+ # Check the framing of the header. The last character must be '\n' (0x0A) -+ if not raw_keyword or equals != b"=" or buf[header_value_end_offset] != 0x0A: - raise InvalidHeaderError("invalid header") -- value = buf[match.end(2) + 1:match.start(1) + length - 1] -+ raw_headers.append((length, raw_keyword, raw_value)) -+ -+ # Check if the pax header contains a hdrcharset field. This tells us -+ # the encoding of the path, linkpath, uname and gname fields. Normally, -+ # these fields are UTF-8 encoded but since POSIX.1-2008 tar -+ # implementations are allowed to store them as raw binary strings if -+ # the translation to UTF-8 fails. For the time being, we don't care about -+ # anything other than "BINARY". The only other value that is currently -+ # allowed by the standard is "ISO-IR 10646 2000 UTF-8" in other words UTF-8. -+ # Note that we only follow the initial 'hdrcharset' setting to preserve -+ # the initial behavior of the 'tarfile' module. -+ if raw_keyword == b"hdrcharset" and encoding is None: -+ if raw_value == b"BINARY": -+ encoding = tarfile.encoding -+ else: # This branch ensures only the first 'hdrcharset' header is used. -+ encoding = "utf-8" -+ -+ pos += length - -+ # If no explicit hdrcharset is set, we use UTF-8 as a default. -+ if encoding is None: -+ encoding = "utf-8" -+ -+ # After parsing the raw headers we can decode them to text. -+ for length, raw_keyword, raw_value in raw_headers: - # Normally, we could just use "utf-8" as the encoding and "strict" - # as the error handler, but we better not take the risk. For - # example, GNU tar <= 1.23 is known to store filenames it cannot -@@ -1441,17 +1462,16 @@ def _proc_pax(self, tarfile): - # hdrcharset=BINARY header). - # We first try the strict standard encoding, and if that fails we - # fall back on the user's encoding and error handler. -- keyword = self._decode_pax_field(keyword, "utf-8", "utf-8", -+ keyword = self._decode_pax_field(raw_keyword, "utf-8", "utf-8", - tarfile.errors) - if keyword in PAX_NAME_FIELDS: -- value = self._decode_pax_field(value, encoding, tarfile.encoding, -+ value = self._decode_pax_field(raw_value, encoding, tarfile.encoding, - tarfile.errors) - else: -- value = self._decode_pax_field(value, "utf-8", "utf-8", -+ value = self._decode_pax_field(raw_value, "utf-8", "utf-8", - tarfile.errors) - - pax_headers[keyword] = value -- pos += length - - # Fetch the next header. - try: -@@ -1466,7 +1486,7 @@ def _proc_pax(self, tarfile): - - elif "GNU.sparse.size" in pax_headers: - # GNU extended sparse format version 0.0. -- self._proc_gnusparse_00(next, pax_headers, buf) -+ self._proc_gnusparse_00(next, raw_headers) - - elif pax_headers.get("GNU.sparse.major") == "1" and pax_headers.get("GNU.sparse.minor") == "0": - # GNU extended sparse format version 1.0. -@@ -1488,15 +1508,24 @@ def _proc_pax(self, tarfile): - - return next - -- def _proc_gnusparse_00(self, next, pax_headers, buf): -+ def _proc_gnusparse_00(self, next, raw_headers): - """Process a GNU tar extended sparse header, version 0.0. - """ - offsets = [] -- for match in re.finditer(br"\d+ GNU.sparse.offset=(\d+)\n", buf): -- offsets.append(int(match.group(1))) - numbytes = [] -- for match in re.finditer(br"\d+ GNU.sparse.numbytes=(\d+)\n", buf): -- numbytes.append(int(match.group(1))) -+ for _, keyword, value in raw_headers: -+ if keyword == b"GNU.sparse.offset": -+ try: -+ offsets.append(int(value.decode())) -+ except ValueError: -+ raise InvalidHeaderError("invalid header") -+ -+ elif keyword == b"GNU.sparse.numbytes": -+ try: -+ numbytes.append(int(value.decode())) -+ except ValueError: -+ raise InvalidHeaderError("invalid header") -+ - next.sparse = list(zip(offsets, numbytes)) - - def _proc_gnusparse_01(self, next, pax_headers): -diff --git a/Lib/test/test_tarfile.py b/Lib/test/test_tarfile.py -index 3df64c78032275..2218401e3867be 100644 ---- a/Lib/test/test_tarfile.py -+++ b/Lib/test/test_tarfile.py -@@ -1113,6 +1113,48 @@ def test_pax_number_fields(self): - finally: - tar.close() - -+ def test_pax_header_bad_formats(self): -+ # The fields from the pax header have priority over the -+ # TarInfo. -+ pax_header_replacements = ( -+ b" foo=bar\n", -+ b"0 \n", -+ b"1 \n", -+ b"2 \n", -+ b"3 =\n", -+ b"4 =a\n", -+ b"1000000 foo=bar\n", -+ b"0 foo=bar\n", -+ b"-12 foo=bar\n", -+ b"000000000000000000000000036 foo=bar\n", -+ ) -+ pax_headers = {"foo": "bar"} -+ -+ for replacement in pax_header_replacements: -+ with self.subTest(header=replacement): -+ tar = tarfile.open(tmpname, "w", format=tarfile.PAX_FORMAT, -+ encoding="iso8859-1") -+ try: -+ t = tarfile.TarInfo() -+ t.name = "pax" # non-ASCII -+ t.uid = 1 -+ t.pax_headers = pax_headers -+ tar.addfile(t) -+ finally: -+ tar.close() -+ -+ with open(tmpname, "rb") as f: -+ data = f.read() -+ self.assertIn(b"11 foo=bar\n", data) -+ data = data.replace(b"11 foo=bar\n", replacement) -+ -+ with open(tmpname, "wb") as f: -+ f.truncate() -+ f.write(data) -+ -+ with self.assertRaisesRegex(tarfile.ReadError, r"file could not be opened successfully"): -+ tarfile.open(tmpname, encoding="iso8859-1") -+ - - class WriteTestBase(TarTest): - # Put all write tests in here that are supposed to be tested -diff --git a/Misc/NEWS.d/next/Security/2024-07-02-13-39-20.gh-issue-121285.hrl-yI.rst b/Misc/NEWS.d/next/Security/2024-07-02-13-39-20.gh-issue-121285.hrl-yI.rst -new file mode 100644 -index 00000000000000..81f918bfe2b255 ---- /dev/null -+++ b/Misc/NEWS.d/next/Security/2024-07-02-13-39-20.gh-issue-121285.hrl-yI.rst -@@ -0,0 +1,2 @@ -+Remove backtracking from tarfile header parsing for ``hdrcharset``, PAX, and -+GNU sparse headers. diff --git a/SOURCES/Python-3.9.19.tar.xz.asc b/SOURCES/Python-3.9.19.tar.xz.asc deleted file mode 100644 index 0dbbb22..0000000 --- a/SOURCES/Python-3.9.19.tar.xz.asc +++ /dev/null @@ -1,16 +0,0 @@ ------BEGIN PGP SIGNATURE----- - -iQIzBAABCgAdFiEE4/8oOcBIslwITevpsmmV4xAlBWgFAmX5uMIACgkQsmmV4xAl -BWj1tQ//T2qX0m08xWGV7az0D1sH3qjoY+4fEYrknw5uAHqZFiQecRsF27jxv6iH -gP/6GAUw+lbH+9UofhCc0NbPOklliS7gFLNqJdKYFB6JXRNxiRYKh3uVx5o2n0ES -kR3kRl77S47rtCbSMrKTh6ZoWowyIUZGFsIonk5KsLv+oELXY1AK/Im9i3/iTJ1Z -jd/e2oHWuseIxbGZAO8AEP8zOsMMIHfsL3ry8H9xhhPyQM6t5DldqLH3UVE6kq95 -fs+olGO4FEKif3VDuLaHVlgtGZOUr6aDIYUmWxctPicboSb6RJAq37CCYgWykOyB -WQec0ONbU7lxt5jhemLSDRy0mEio7+nXIKsO9rDN0Wk1QMpHUl77/C5qVlzfHal7 -NhPt8Yl0hBnOjzTq+di+xhAKJcdKp+zZH7/ugAbthuqhNfnkqiF68PANHrCm3gbY -myN0eSaQ9yIa/MbHW8Am9NL/nuFbxdJUL/OIKQ9kFHgD7Qid86TZF0G2vbiBH/eF -IVYoMxRZLd7eu5dIcwXSef+Ai97pODbx9y7bOCFyBO9FuFrlhPObgc7KXCeAzP+y -k5eWvZtWTvvQ+2si2iT22EPBO0D0pnhYWZKpGK5EuKuw8nasNS1yLbhDTVpARynd -8buQh3t2wPfILlQr0+JzDY8GSdQ/nIHGgx2IERdSX/v+9Yo2AvU= -=gYAl ------END PGP SIGNATURE----- diff --git a/SOURCES/Python-3.9.21.tar.xz.asc b/SOURCES/Python-3.9.21.tar.xz.asc new file mode 100644 index 0000000..6e49b13 --- /dev/null +++ b/SOURCES/Python-3.9.21.tar.xz.asc @@ -0,0 +1,16 @@ +-----BEGIN PGP SIGNATURE----- + +iQIzBAABCgAdFiEE4/8oOcBIslwITevpsmmV4xAlBWgFAmdPScsACgkQsmmV4xAl +BWgZtRAAiPehPRc94kRpNn4CuLw9hDFJmucXfG/Pjf9DdQkrmWAMvFS2kpigd9A0 +3QoDbgZPb8k9XtTrbpT4A0j/SYaqnLXOktXE7CEwM1vRTHbUDm62qxRSIa+RXO1d +h/EqhF1Rpgl37I1GL3mAHew6KjIq3K/aNvJVTtKA+1xy8XpF5Dbk3feDeTucqYaM +evtCu2SlwQXRvIbqFciMtRC2bmkNHgRVFpuxInjmp82ED0E6yZ/ecHXjb5Da7lDV +8uRh9aEjMWY4LHTdl2tWaaerLqYZfvHSlz2xY8W5itSgOAzzJNn3dX8P6EKK5ab7 +IV85vqPX1oMcX0seZd3QlVdOxUPf1tKB7Eo7yHz3gV/KgWzFSAHSZFCwiqyfNfj8 +PibYYwtGG0+S7GJ7bZ2iCCgkqrFBoMQ8yOEDxE7Pt36JSXtZ2grtsFB8WAZqhCMa +luIjiibGkOzzBRX/neW5RYT1HLNzi140G7XEZeRv3CXzuud66+ynLdOK7uFEr8jq +W0t/fHbrqcSjyEo9L9VDP4Wd9VU/nwf6tb3Py6nPZKM93ZYqtlJNmzxmOyQOmn30 +bRGEQyzcYmEKMWg6zzO57In/WRytB4BgE7Dj7L876TbnJ8YoR8TVpuQ3sDKoSxwo +gIdNR/6lcqP0HwDFtqBrcwSQ9Dew6wMz0Pp2EwX90EZLwnBvpeI= +=taeu +-----END PGP SIGNATURE----- diff --git a/SPECS/python3.9.spec b/SPECS/python3.9.spec index 565ef0b..5286d56 100644 --- a/SPECS/python3.9.spec +++ b/SPECS/python3.9.spec @@ -13,11 +13,11 @@ URL: https://www.python.org/ # WARNING When rebasing to a new Python version, # remember to update the python3-docs package as well -%global general_version %{pybasever}.19 +%global general_version %{pybasever}.21 #global prerel ... %global upstream_version %{general_version}%{?prerel} Version: %{general_version}%{?prerel:~%{prerel}} -Release: 8%{?dist}.1 +Release: 1%{?dist} License: Python @@ -416,12 +416,6 @@ Patch353: 00353-architecture-names-upstream-downstream.patch # - https://access.redhat.com/articles/7004769 Patch397: 00397-tarfile-filter.patch -# 00414 # -# -# Skip test_pair() and test_speech128() of test_zlib on s390x since -# they fail if zlib uses the s390x hardware accelerator. -Patch414: 00414-skip_test_zlib_s390x.patch - # 00415 # # [CVE-2023-27043] gh-102988: Reject malformed addresses in email.parseaddr() (#111116) # @@ -443,40 +437,6 @@ Patch415: 00415-cve-2023-27043-gh-102988-reject-malformed-addresses-in-email-par # CVE-2023-52425. Future versions of Expat may be more reactive. Patch422: 00422-fix-tests-for-xmlpullparser-with-expat-2-6-0.patch -# 00431 # -# Security fix for CVE-2024-4032: incorrect IPv4 and IPv6 private ranges -# Resolved upstream: https://github.com/python/cpython/issues/113171 -# Tracking bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2292921 -Patch431: 00431-CVE-2024-4032.patch - -# 00435 # f2924d30f4dd44804219c10410a57dd96764d297 -# 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. -Patch435: 00435-gh-121650-encode-newlines-in-headers-and-verify-headers-are-sound-gh-122233.patch - -# 00436 # 506dd77b7132f69ada7185b8bb91eba0e1296aa8 -# [CVE-2024-8088] gh-122905: Sanitize names in zipfile.Path. -Patch436: 00436-cve-2024-8088-gh-122905-sanitize-names-in-zipfile-path.patch - -# 00437 # -# CVE-2024-6232: gh-121285: Remove backtracking when parsing tarfile headers -# Resolved upstream: https://github.com/python/cpython/issues/121285 -Patch437: 00437-CVE-2024-6232.patch - # (New patches go here ^^^) # # When adding new patches to "python" and "python3" in Fedora, EL, etc., @@ -1881,6 +1841,12 @@ CheckPython optimized # ====================================================== %changelog +* Thu Dec 05 2024 Tomáš Hrnčiar - 3.9.21-1 +- Update to 3.9.21 +- Security fix for CVE-2024-11168 and CVE-2024-9287 +Resolves: RHEL-64888 +Resolves: RHEL-67259 + * Wed Sep 11 2024 Lumír Balhar - 3.9.19-8.1 - Security fix for CVE-2024-6232 Resolves: RHEL-57420