Compare commits

..

No commits in common. 'c8' and 'c9-beta' have entirely different histories.
c8 ... c9-beta

2
.gitignore vendored

@ -1 +1 @@
SOURCES/Python-3.11.10.tar.xz
SOURCES/Python-3.11.9.tar.xz

@ -1 +1 @@
eb0ee5c84407445809a556592008cfc1867a39bc SOURCES/Python-3.11.10.tar.xz
926cd6a577b2e8dcbb17671b30eda04019328ada SOURCES/Python-3.11.9.tar.xz

@ -1,47 +0,0 @@
From db083095e3bdb93e4f8170d814664c482b1e94da Mon Sep 17 00:00:00 2001
From: rpm-build <rpm-build>
Date: Tue, 14 Jun 2022 06:38:43 +0200
Subject: [PATCH] Fix test suite for Expat >= 2.4.5
---
Lib/test/test_minidom.py | 17 +++++------------
1 file changed, 5 insertions(+), 12 deletions(-)
diff --git a/Lib/test/test_minidom.py b/Lib/test/test_minidom.py
index 9762025..5f52ed1 100644
--- a/Lib/test/test_minidom.py
+++ b/Lib/test/test_minidom.py
@@ -1149,14 +1149,10 @@ class MinidomTest(unittest.TestCase):
# Verify that character decoding errors raise exceptions instead
# of crashing
- if pyexpat.version_info >= (2, 4, 5):
- self.assertRaises(ExpatError, parseString,
- b'<fran\xe7ais></fran\xe7ais>')
- self.assertRaises(ExpatError, parseString,
- b'<franais>Comment \xe7a va ? Tr\xe8s bien ?</franais>')
- else:
- self.assertRaises(UnicodeDecodeError, parseString,
- b'<fran\xe7ais>Comment \xe7a va ? Tr\xe8s bien ?</fran\xe7ais>')
+ self.assertRaises(ExpatError, parseString,
+ b'<fran\xe7ais></fran\xe7ais>')
+ self.assertRaises(ExpatError, parseString,
+ b'<franais>Comment \xe7a va ? Tr\xe8s bien ?</franais>')
doc.unlink()
@@ -1617,10 +1613,7 @@ class MinidomTest(unittest.TestCase):
self.confirm(doc2.namespaceURI == xml.dom.EMPTY_NAMESPACE)
def testExceptionOnSpacesInXMLNSValue(self):
- if pyexpat.version_info >= (2, 4, 5):
- context = self.assertRaisesRegex(ExpatError, 'syntax error')
- else:
- context = self.assertRaisesRegex(ValueError, 'Unsupported syntax')
+ context = self.assertRaisesRegex(ExpatError, 'syntax error')
with context:
parseString('<element xmlns:abc="http:abc.com/de f g/hi/j k"><abc:foo /></element>')
--
2.35.3

@ -1,16 +1,513 @@
From 3f01ced0b5051798516fc65f5fac10ffd15dbce6 Mon Sep 17 00:00:00 2001
From 642f28679e04c7b4ec7731f0c8872103f21a76f8 Mon Sep 17 00:00:00 2001
From: Victor Stinner <vstinner@python.org>
Date: Fri, 15 Dec 2023 16:10:40 +0100
Subject: [PATCH 1/2] 00415: [CVE-2023-27043] gh-102988: Reject malformed
addresses in email.parseaddr() (#111116)
Detect email address parsing errors and return empty tuple to
indicate the parsing error (old API). Add an optional 'strict'
parameter to getaddresses() and parseaddr() functions. Patch by
Thomas Dwyer.
Co-Authored-By: Thomas Dwyer <github@tomd.tel>
---
Doc/library/email.utils.rst | 19 +-
Lib/email/utils.py | 150 ++++++++++++-
Lib/test/test_email/test_email.py | 204 +++++++++++++++++-
...-10-20-15-28-08.gh-issue-102988.dStNO7.rst | 8 +
4 files changed, 360 insertions(+), 21 deletions(-)
create mode 100644 Misc/NEWS.d/next/Library/2023-10-20-15-28-08.gh-issue-102988.dStNO7.rst
diff --git a/Doc/library/email.utils.rst b/Doc/library/email.utils.rst
index 0e266b6..6723dc4 100644
--- a/Doc/library/email.utils.rst
+++ b/Doc/library/email.utils.rst
@@ -60,13 +60,18 @@ of the new API.
begins with angle brackets, they are stripped off.
-.. function:: parseaddr(address)
+.. function:: parseaddr(address, *, strict=True)
Parse address -- which should be the value of some address-containing field such
as :mailheader:`To` or :mailheader:`Cc` -- into its constituent *realname* and
*email address* parts. Returns a tuple of that information, unless the parse
fails, in which case a 2-tuple of ``('', '')`` is returned.
+ If *strict* is true, use a strict parser which rejects malformed inputs.
+
+ .. versionchanged:: 3.13
+ Add *strict* optional parameter and reject malformed inputs by default.
+
.. function:: formataddr(pair, charset='utf-8')
@@ -84,12 +89,15 @@ of the new API.
Added the *charset* option.
-.. function:: getaddresses(fieldvalues)
+.. function:: getaddresses(fieldvalues, *, strict=True)
This method returns a list of 2-tuples of the form returned by ``parseaddr()``.
*fieldvalues* is a sequence of header field values as might be returned by
- :meth:`Message.get_all <email.message.Message.get_all>`. Here's a simple
- example that gets all the recipients of a message::
+ :meth:`Message.get_all <email.message.Message.get_all>`.
+
+ If *strict* is true, use a strict parser which rejects malformed inputs.
+
+ Here's a simple example that gets all the recipients of a message::
from email.utils import getaddresses
@@ -99,6 +107,9 @@ of the new API.
resent_ccs = msg.get_all('resent-cc', [])
all_recipients = getaddresses(tos + ccs + resent_tos + resent_ccs)
+ .. versionchanged:: 3.13
+ Add *strict* optional parameter and reject malformed inputs by default.
+
.. function:: parsedate(date)
diff --git a/Lib/email/utils.py b/Lib/email/utils.py
index 8993858..41bb3c9 100644
--- a/Lib/email/utils.py
+++ b/Lib/email/utils.py
@@ -106,12 +106,127 @@ def formataddr(pair, charset='utf-8'):
return address
+def _iter_escaped_chars(addr):
+ pos = 0
+ escape = False
+ for pos, ch in enumerate(addr):
+ if escape:
+ yield (pos, '\\' + ch)
+ escape = False
+ elif ch == '\\':
+ escape = True
+ else:
+ yield (pos, ch)
+ if escape:
+ yield (pos, '\\')
+
+
+def _strip_quoted_realnames(addr):
+ """Strip real names between quotes."""
+ if '"' not in addr:
+ # Fast path
+ return addr
+
+ start = 0
+ open_pos = None
+ result = []
+ for pos, ch in _iter_escaped_chars(addr):
+ if ch == '"':
+ if open_pos is None:
+ open_pos = pos
+ else:
+ if start != open_pos:
+ result.append(addr[start:open_pos])
+ start = pos + 1
+ open_pos = None
+
+ if start < len(addr):
+ result.append(addr[start:])
+
+ return ''.join(result)
+
+
+supports_strict_parsing = True
+
+def getaddresses(fieldvalues, *, strict=True):
+ """Return a list of (REALNAME, EMAIL) or ('','') for each fieldvalue.
+
+ When parsing fails for a fieldvalue, a 2-tuple of ('', '') is returned in
+ its place.
-def getaddresses(fieldvalues):
- """Return a list of (REALNAME, EMAIL) for each fieldvalue."""
- all = COMMASPACE.join(str(v) for v in fieldvalues)
- a = _AddressList(all)
- return a.addresslist
+ If strict is true, use a strict parser which rejects malformed inputs.
+ """
+
+ # If strict is true, if the resulting list of parsed addresses is greater
+ # than the number of fieldvalues in the input list, a parsing error has
+ # occurred and consequently a list containing a single empty 2-tuple [('',
+ # '')] is returned in its place. This is done to avoid invalid output.
+ #
+ # Malformed input: getaddresses(['alice@example.com <bob@example.com>'])
+ # Invalid output: [('', 'alice@example.com'), ('', 'bob@example.com')]
+ # Safe output: [('', '')]
+
+ if not strict:
+ all = COMMASPACE.join(str(v) for v in fieldvalues)
+ a = _AddressList(all)
+ return a.addresslist
+
+ fieldvalues = [str(v) for v in fieldvalues]
+ fieldvalues = _pre_parse_validation(fieldvalues)
+ addr = COMMASPACE.join(fieldvalues)
+ a = _AddressList(addr)
+ result = _post_parse_validation(a.addresslist)
+
+ # Treat output as invalid if the number of addresses is not equal to the
+ # expected number of addresses.
+ n = 0
+ for v in fieldvalues:
+ # When a comma is used in the Real Name part it is not a deliminator.
+ # So strip those out before counting the commas.
+ v = _strip_quoted_realnames(v)
+ # Expected number of addresses: 1 + number of commas
+ n += 1 + v.count(',')
+ if len(result) != n:
+ return [('', '')]
+
+ return result
+
+
+def _check_parenthesis(addr):
+ # Ignore parenthesis in quoted real names.
+ addr = _strip_quoted_realnames(addr)
+
+ opens = 0
+ for pos, ch in _iter_escaped_chars(addr):
+ if ch == '(':
+ opens += 1
+ elif ch == ')':
+ opens -= 1
+ if opens < 0:
+ return False
+ return (opens == 0)
+
+
+def _pre_parse_validation(email_header_fields):
+ accepted_values = []
+ for v in email_header_fields:
+ if not _check_parenthesis(v):
+ v = "('', '')"
+ accepted_values.append(v)
+
+ return accepted_values
+
+
+def _post_parse_validation(parsed_email_header_tuples):
+ accepted_values = []
+ # The parser would have parsed a correctly formatted domain-literal
+ # The existence of an [ after parsing indicates a parsing failure
+ for v in parsed_email_header_tuples:
+ if '[' in v[1]:
+ v = ('', '')
+ accepted_values.append(v)
+
+ return accepted_values
def _format_timetuple_and_zone(timetuple, zone):
@@ -205,16 +320,33 @@ def parsedate_to_datetime(data):
tzinfo=datetime.timezone(datetime.timedelta(seconds=tz)))
-def parseaddr(addr):
+def parseaddr(addr, *, strict=True):
"""
Parse addr into its constituent realname and email address parts.
Return a tuple of realname and email address, unless the parse fails, in
which case return a 2-tuple of ('', '').
+
+ If strict is True, use a strict parser which rejects malformed inputs.
"""
- addrs = _AddressList(addr).addresslist
- if not addrs:
- return '', ''
+ if not strict:
+ addrs = _AddressList(addr).addresslist
+ if not addrs:
+ return ('', '')
+ return addrs[0]
+
+ if isinstance(addr, list):
+ addr = addr[0]
+
+ if not isinstance(addr, str):
+ return ('', '')
+
+ addr = _pre_parse_validation([addr])[0]
+ addrs = _post_parse_validation(_AddressList(addr).addresslist)
+
+ if not addrs or len(addrs) > 1:
+ return ('', '')
+
return addrs[0]
diff --git a/Lib/test/test_email/test_email.py b/Lib/test/test_email/test_email.py
index 785696e..ad60ed3 100644
--- a/Lib/test/test_email/test_email.py
+++ b/Lib/test/test_email/test_email.py
@@ -17,6 +17,7 @@ from unittest.mock import patch
import email
import email.policy
+import email.utils
from email.charset import Charset
from email.generator import Generator, DecodedGenerator, BytesGenerator
@@ -3336,15 +3337,154 @@ Foo
[('Al Person', 'aperson@dom.ain'),
('Bud Person', 'bperson@dom.ain')])
+ def test_getaddresses_comma_in_name(self):
+ """GH-106669 regression test."""
+ self.assertEqual(
+ utils.getaddresses(
+ [
+ '"Bud, Person" <bperson@dom.ain>',
+ 'aperson@dom.ain (Al Person)',
+ '"Mariusz Felisiak" <to@example.com>',
+ ]
+ ),
+ [
+ ('Bud, Person', 'bperson@dom.ain'),
+ ('Al Person', 'aperson@dom.ain'),
+ ('Mariusz Felisiak', 'to@example.com'),
+ ],
+ )
+
+ def test_parsing_errors(self):
+ """Test for parsing errors from CVE-2023-27043 and CVE-2019-16056"""
+ alice = 'alice@example.org'
+ bob = 'bob@example.com'
+ empty = ('', '')
+
+ # Test utils.getaddresses() and utils.parseaddr() on malformed email
+ # addresses: default behavior (strict=True) rejects malformed address,
+ # and strict=False which tolerates malformed address.
+ for invalid_separator, expected_non_strict in (
+ ('(', [(f'<{bob}>', alice)]),
+ (')', [('', alice), empty, ('', bob)]),
+ ('<', [('', alice), empty, ('', bob), empty]),
+ ('>', [('', alice), empty, ('', bob)]),
+ ('[', [('', f'{alice}[<{bob}>]')]),
+ (']', [('', alice), empty, ('', bob)]),
+ ('@', [empty, empty, ('', bob)]),
+ (';', [('', alice), empty, ('', bob)]),
+ (':', [('', alice), ('', bob)]),
+ ('.', [('', alice + '.'), ('', bob)]),
+ ('"', [('', alice), ('', f'<{bob}>')]),
+ ):
+ address = f'{alice}{invalid_separator}<{bob}>'
+ with self.subTest(address=address):
+ self.assertEqual(utils.getaddresses([address]),
+ [empty])
+ self.assertEqual(utils.getaddresses([address], strict=False),
+ expected_non_strict)
+
+ self.assertEqual(utils.parseaddr([address]),
+ empty)
+ self.assertEqual(utils.parseaddr([address], strict=False),
+ ('', address))
+
+ # Comma (',') is treated differently depending on strict parameter.
+ # Comma without quotes.
+ address = f'{alice},<{bob}>'
+ self.assertEqual(utils.getaddresses([address]),
+ [('', alice), ('', bob)])
+ self.assertEqual(utils.getaddresses([address], strict=False),
+ [('', alice), ('', bob)])
+ self.assertEqual(utils.parseaddr([address]),
+ empty)
+ self.assertEqual(utils.parseaddr([address], strict=False),
+ ('', address))
+
+ # Real name between quotes containing comma.
+ address = '"Alice, alice@example.org" <bob@example.com>'
+ expected_strict = ('Alice, alice@example.org', 'bob@example.com')
+ self.assertEqual(utils.getaddresses([address]), [expected_strict])
+ self.assertEqual(utils.getaddresses([address], strict=False), [expected_strict])
+ self.assertEqual(utils.parseaddr([address]), expected_strict)
+ self.assertEqual(utils.parseaddr([address], strict=False),
+ ('', address))
+
+ # Valid parenthesis in comments.
+ address = 'alice@example.org (Alice)'
+ expected_strict = ('Alice', 'alice@example.org')
+ self.assertEqual(utils.getaddresses([address]), [expected_strict])
+ self.assertEqual(utils.getaddresses([address], strict=False), [expected_strict])
+ self.assertEqual(utils.parseaddr([address]), expected_strict)
+ self.assertEqual(utils.parseaddr([address], strict=False),
+ ('', address))
+
+ # Invalid parenthesis in comments.
+ address = 'alice@example.org )Alice('
+ self.assertEqual(utils.getaddresses([address]), [empty])
+ self.assertEqual(utils.getaddresses([address], strict=False),
+ [('', 'alice@example.org'), ('', ''), ('', 'Alice')])
+ self.assertEqual(utils.parseaddr([address]), empty)
+ self.assertEqual(utils.parseaddr([address], strict=False),
+ ('', address))
+
+ # Two addresses with quotes separated by comma.
+ address = '"Jane Doe" <jane@example.net>, "John Doe" <john@example.net>'
+ self.assertEqual(utils.getaddresses([address]),
+ [('Jane Doe', 'jane@example.net'),
+ ('John Doe', 'john@example.net')])
+ self.assertEqual(utils.getaddresses([address], strict=False),
+ [('Jane Doe', 'jane@example.net'),
+ ('John Doe', 'john@example.net')])
+ self.assertEqual(utils.parseaddr([address]), empty)
+ self.assertEqual(utils.parseaddr([address], strict=False),
+ ('', address))
+
+ # Test email.utils.supports_strict_parsing attribute
+ self.assertEqual(email.utils.supports_strict_parsing, True)
+
def test_getaddresses_nasty(self):
- eq = self.assertEqual
- eq(utils.getaddresses(['foo: ;']), [('', '')])
- eq(utils.getaddresses(
- ['[]*-- =~$']),
- [('', ''), ('', ''), ('', '*--')])
- eq(utils.getaddresses(
- ['foo: ;', '"Jason R. Mastaler" <jason@dom.ain>']),
- [('', ''), ('Jason R. Mastaler', 'jason@dom.ain')])
+ for addresses, expected in (
+ (['"Sürname, Firstname" <to@example.com>'],
+ [('Sürname, Firstname', 'to@example.com')]),
+
+ (['foo: ;'],
+ [('', '')]),
+
+ (['foo: ;', '"Jason R. Mastaler" <jason@dom.ain>'],
+ [('', ''), ('Jason R. Mastaler', 'jason@dom.ain')]),
+
+ ([r'Pete(A nice \) chap) <pete(his account)@silly.test(his host)>'],
+ [('Pete (A nice ) chap his account his host)', 'pete@silly.test')]),
+
+ (['(Empty list)(start)Undisclosed recipients :(nobody(I know))'],
+ [('', '')]),
+
+ (['Mary <@machine.tld:mary@example.net>, , jdoe@test . example'],
+ [('Mary', 'mary@example.net'), ('', ''), ('', 'jdoe@test.example')]),
+
+ (['John Doe <jdoe@machine(comment). example>'],
+ [('John Doe (comment)', 'jdoe@machine.example')]),
+
+ (['"Mary Smith: Personal Account" <smith@home.example>'],
+ [('Mary Smith: Personal Account', 'smith@home.example')]),
+
+ (['Undisclosed recipients:;'],
+ [('', '')]),
+
+ ([r'<boss@nil.test>, "Giant; \"Big\" Box" <bob@example.net>'],
+ [('', 'boss@nil.test'), ('Giant; "Big" Box', 'bob@example.net')]),
+ ):
+ with self.subTest(addresses=addresses):
+ self.assertEqual(utils.getaddresses(addresses),
+ expected)
+ self.assertEqual(utils.getaddresses(addresses, strict=False),
+ expected)
+
+ addresses = ['[]*-- =~$']
+ self.assertEqual(utils.getaddresses(addresses),
+ [('', '')])
+ self.assertEqual(utils.getaddresses(addresses, strict=False),
+ [('', ''), ('', ''), ('', '*--')])
def test_getaddresses_embedded_comment(self):
"""Test proper handling of a nested comment"""
@@ -3535,6 +3675,54 @@ multipart/report
m = cls(*constructor, policy=email.policy.default)
self.assertIs(m.policy, email.policy.default)
+ def test_iter_escaped_chars(self):
+ self.assertEqual(list(utils._iter_escaped_chars(r'a\\b\"c\\"d')),
+ [(0, 'a'),
+ (2, '\\\\'),
+ (3, 'b'),
+ (5, '\\"'),
+ (6, 'c'),
+ (8, '\\\\'),
+ (9, '"'),
+ (10, 'd')])
+ self.assertEqual(list(utils._iter_escaped_chars('a\\')),
+ [(0, 'a'), (1, '\\')])
+
+ def test_strip_quoted_realnames(self):
+ def check(addr, expected):
+ self.assertEqual(utils._strip_quoted_realnames(addr), expected)
+
+ check('"Jane Doe" <jane@example.net>, "John Doe" <john@example.net>',
+ ' <jane@example.net>, <john@example.net>')
+ check(r'"Jane \"Doe\"." <jane@example.net>',
+ ' <jane@example.net>')
+
+ # special cases
+ check(r'before"name"after', 'beforeafter')
+ check(r'before"name"', 'before')
+ check(r'b"name"', 'b') # single char
+ check(r'"name"after', 'after')
+ check(r'"name"a', 'a') # single char
+ check(r'"name"', '')
+
+ # no change
+ for addr in (
+ 'Jane Doe <jane@example.net>, John Doe <john@example.net>',
+ 'lone " quote',
+ ):
+ self.assertEqual(utils._strip_quoted_realnames(addr), addr)
+
+
+ def test_check_parenthesis(self):
+ addr = 'alice@example.net'
+ self.assertTrue(utils._check_parenthesis(f'{addr} (Alice)'))
+ self.assertFalse(utils._check_parenthesis(f'{addr} )Alice('))
+ self.assertFalse(utils._check_parenthesis(f'{addr} (Alice))'))
+ self.assertFalse(utils._check_parenthesis(f'{addr} ((Alice)'))
+
+ # Ignore real name between quotes
+ self.assertTrue(utils._check_parenthesis(f'")Alice((" {addr}'))
+
# Test the iterator/generators
class TestIterators(TestEmailBase):
diff --git a/Misc/NEWS.d/next/Library/2023-10-20-15-28-08.gh-issue-102988.dStNO7.rst b/Misc/NEWS.d/next/Library/2023-10-20-15-28-08.gh-issue-102988.dStNO7.rst
new file mode 100644
index 0000000..3d0e9e4
--- /dev/null
+++ b/Misc/NEWS.d/next/Library/2023-10-20-15-28-08.gh-issue-102988.dStNO7.rst
@@ -0,0 +1,8 @@
+:func:`email.utils.getaddresses` and :func:`email.utils.parseaddr` now
+return ``('', '')`` 2-tuples in more situations where invalid email
+addresses are encountered instead of potentially inaccurate values. Add
+optional *strict* parameter to these two functions: use ``strict=False`` to
+get the old behavior, accept malformed inputs.
+``getattr(email.utils, 'supports_strict_parsing', False)`` can be use to check
+if the *strict* paramater is available. Patch by Thomas Dwyer and Victor
+Stinner to improve the CVE-2023-27043 fix.
--
2.44.0
From d371679e7c485551c10380ac11e5039a9fb4515b Mon Sep 17 00:00:00 2001
From: Lumir Balhar <lbalhar@redhat.com>
Date: Wed, 10 Jan 2024 08:53:53 +0100
Subject: [PATCH] Make it possible to disable strict parsing in email module
Subject: [PATCH 2/2] Make it possible to disable strict parsing in email
module
---
Doc/library/email.utils.rst | 26 +++++++++++
Lib/email/utils.py | 54 +++++++++++++++++++++-
Lib/email/utils.py | 55 ++++++++++++++++++++++-
Lib/test/test_email/test_email.py | 74 ++++++++++++++++++++++++++++++-
3 files changed, 150 insertions(+), 4 deletions(-)
3 files changed, 151 insertions(+), 4 deletions(-)
diff --git a/Doc/library/email.utils.rst b/Doc/library/email.utils.rst
index 97ddf49..0c9bf53 100644
index 6723dc4..c89602d 100644
--- a/Doc/library/email.utils.rst
+++ b/Doc/library/email.utils.rst
@@ -69,6 +69,19 @@ of the new API.
@ -30,7 +527,7 @@ index 97ddf49..0c9bf53 100644
+ [email_addr_parsing]
+ PYTHON_EMAIL_DISABLE_STRICT_ADDR_PARSING = true
+
.. versionchanged:: 3.11.10
.. versionchanged:: 3.13
Add *strict* optional parameter and reject malformed inputs by default.
@@ -97,6 +110,19 @@ of the new API.
@ -54,10 +551,10 @@ index 97ddf49..0c9bf53 100644
from email.utils import getaddresses
diff --git a/Lib/email/utils.py b/Lib/email/utils.py
index 94ead0e..09a414c 100644
index 41bb3c9..09a414c 100644
--- a/Lib/email/utils.py
+++ b/Lib/email/utils.py
@@ -48,6 +48,46 @@ TICK = "'"
@@ -48,6 +48,47 @@ TICK = "'"
specialsre = re.compile(r'[][\\()<>@,:;".]')
escapesre = re.compile(r'[\\"]')
@ -101,10 +598,11 @@ index 94ead0e..09a414c 100644
+
+ return True
+
+
def _has_surrogates(s):
"""Return True if s may contain surrogate-escaped binary data."""
@@ -149,7 +189,7 @@ def _strip_quoted_realnames(addr):
# This check is based on the fact that unless there are surrogates, utf8
@@ -148,7 +189,7 @@ def _strip_quoted_realnames(addr):
supports_strict_parsing = True
@ -113,7 +611,7 @@ index 94ead0e..09a414c 100644
"""Return a list of (REALNAME, EMAIL) or ('','') for each fieldvalue.
When parsing fails for a fieldvalue, a 2-tuple of ('', '') is returned in
@@ -158,6 +198,11 @@ def getaddresses(fieldvalues, *, strict=True):
@@ -157,6 +198,11 @@ def getaddresses(fieldvalues, *, strict=True):
If strict is true, use a strict parser which rejects malformed inputs.
"""
@ -125,7 +623,7 @@ index 94ead0e..09a414c 100644
# 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 [('',
@@ -321,7 +366,7 @@ def parsedate_to_datetime(data):
@@ -320,7 +366,7 @@ def parsedate_to_datetime(data):
tzinfo=datetime.timezone(datetime.timedelta(seconds=tz)))
@ -134,7 +632,7 @@ index 94ead0e..09a414c 100644
"""
Parse addr into its constituent realname and email address parts.
@@ -330,6 +375,11 @@ def parseaddr(addr, *, strict=True):
@@ -329,6 +375,11 @@ def parseaddr(addr, *, strict=True):
If strict is True, use a strict parser which rejects malformed inputs.
"""
@ -246,5 +744,5 @@ index ad60ed3..f85da56 100644
for addresses, expected in (
(['"Sürname, Firstname" <to@example.com>'],
--
2.46.0
2.44.0

@ -0,0 +1,346 @@
From 2963bbab04546f5aef6a37a3b027ae7a484deec1 Mon Sep 17 00:00:00 2001
From: Petr Viktorin <encukou@gmail.com>
Date: Thu, 25 Apr 2024 14:45:48 +0200
Subject: [PATCH] gh-113171: gh-65056: Fix "private" (non-global) IP address
ranges (GH-113179) (GH-113186) (GH-118177) (#118227)
---
Doc/library/ipaddress.rst | 43 +++++++-
Doc/whatsnew/3.11.rst | 9 ++
Lib/ipaddress.py | 99 +++++++++++++++----
Lib/test/test_ipaddress.py | 21 +++-
...-03-14-01-38-44.gh-issue-113171.VFnObz.rst | 9 ++
5 files changed, 157 insertions(+), 24 deletions(-)
create mode 100644 Misc/NEWS.d/next/Library/2024-03-14-01-38-44.gh-issue-113171.VFnObz.rst
diff --git a/Doc/library/ipaddress.rst b/Doc/library/ipaddress.rst
index 03dc956..f57fa15 100644
--- a/Doc/library/ipaddress.rst
+++ b/Doc/library/ipaddress.rst
@@ -178,18 +178,53 @@ write code that handles both IP versions correctly. Address objects are
.. attribute:: is_private
- ``True`` if the address is allocated for private networks. See
+ ``True`` if the address is defined as not globally reachable by
iana-ipv4-special-registry_ (for IPv4) or iana-ipv6-special-registry_
- (for IPv6).
+ (for IPv6) with the following exceptions:
+
+ * ``is_private`` is ``False`` for the shared address space (``100.64.0.0/10``)
+ * For IPv4-mapped IPv6-addresses the ``is_private`` value is determined by the
+ semantics of the underlying IPv4 addresses and the following condition holds
+ (see :attr:`IPv6Address.ipv4_mapped`)::
+
+ address.is_private == address.ipv4_mapped.is_private
+
+ ``is_private`` has value opposite to :attr:`is_global`, except for the shared address space
+ (``100.64.0.0/10`` range) where they are both ``False``.
+
+ .. versionchanged:: 3.11.10
+
+ Fixed some false positives and false negatives.
+
+ * ``192.0.0.0/24`` is considered private with the exception of ``192.0.0.9/32`` and
+ ``192.0.0.10/32`` (previously: only the ``192.0.0.0/29`` sub-range was considered private).
+ * ``64:ff9b:1::/48`` is considered private.
+ * ``2002::/16`` is considered private.
+ * There are exceptions within ``2001::/23`` (otherwise considered private): ``2001:1::1/128``,
+ ``2001:1::2/128``, ``2001:3::/32``, ``2001:4:112::/48``, ``2001:20::/28``, ``2001:30::/28``.
+ The exceptions are not considered private.
.. attribute:: is_global
- ``True`` if the address is allocated for public networks. See
+ ``True`` if the address is defined as globally reachable by
iana-ipv4-special-registry_ (for IPv4) or iana-ipv6-special-registry_
- (for IPv6).
+ (for IPv6) with the following exception:
+
+ For IPv4-mapped IPv6-addresses the ``is_private`` value is determined by the
+ semantics of the underlying IPv4 addresses and the following condition holds
+ (see :attr:`IPv6Address.ipv4_mapped`)::
+
+ address.is_global == address.ipv4_mapped.is_global
+
+ ``is_global`` has value opposite to :attr:`is_private`, except for the shared address space
+ (``100.64.0.0/10`` range) where they are both ``False``.
.. versionadded:: 3.4
+ .. versionchanged:: 3.11.10
+
+ Fixed some false positives and false negatives, see :attr:`is_private` for details.
+
.. attribute:: is_unspecified
``True`` if the address is unspecified. See :RFC:`5735` (for IPv4)
diff --git a/Doc/whatsnew/3.11.rst b/Doc/whatsnew/3.11.rst
index f670fa1..42b61c7 100644
--- a/Doc/whatsnew/3.11.rst
+++ b/Doc/whatsnew/3.11.rst
@@ -2727,3 +2727,12 @@ OpenSSL
* Windows builds and macOS installers from python.org now use OpenSSL 3.0.
.. _libb2: https://www.blake2.net/
+
+Notable changes in 3.11.10
+==========================
+
+ipaddress
+---------
+
+* Fixed ``is_global`` and ``is_private`` behavior in ``IPv4Address``,
+ ``IPv6Address``, ``IPv4Network`` and ``IPv6Network``.
diff --git a/Lib/ipaddress.py b/Lib/ipaddress.py
index 16ba16c..567beb3 100644
--- a/Lib/ipaddress.py
+++ b/Lib/ipaddress.py
@@ -1086,7 +1086,11 @@ class _BaseNetwork(_IPAddressBase):
"""
return any(self.network_address in priv_network and
self.broadcast_address in priv_network
- for priv_network in self._constants._private_networks)
+ for priv_network in self._constants._private_networks) and all(
+ self.network_address not in network and
+ self.broadcast_address not in network
+ for network in self._constants._private_networks_exceptions
+ )
@property
def is_global(self):
@@ -1333,18 +1337,41 @@ class IPv4Address(_BaseV4, _BaseAddress):
@property
@functools.lru_cache()
def is_private(self):
- """Test if this address is allocated for private networks.
+ """``True`` if the address is defined as not globally reachable by
+ iana-ipv4-special-registry_ (for IPv4) or iana-ipv6-special-registry_
+ (for IPv6) with the following exceptions:
- Returns:
- A boolean, True if the address is reserved per
- iana-ipv4-special-registry.
+ * ``is_private`` is ``False`` for ``100.64.0.0/10``
+ * For IPv4-mapped IPv6-addresses the ``is_private`` value is determined by the
+ semantics of the underlying IPv4 addresses and the following condition holds
+ (see :attr:`IPv6Address.ipv4_mapped`)::
+ address.is_private == address.ipv4_mapped.is_private
+
+ ``is_private`` has value opposite to :attr:`is_global`, except for the ``100.64.0.0/10``
+ IPv4 range where they are both ``False``.
"""
- return any(self in net for net in self._constants._private_networks)
+ return (
+ any(self in net for net in self._constants._private_networks)
+ and all(self not in net for net in self._constants._private_networks_exceptions)
+ )
@property
@functools.lru_cache()
def is_global(self):
+ """``True`` if the address is defined as globally reachable by
+ iana-ipv4-special-registry_ (for IPv4) or iana-ipv6-special-registry_
+ (for IPv6) with the following exception:
+
+ For IPv4-mapped IPv6-addresses the ``is_private`` value is determined by the
+ semantics of the underlying IPv4 addresses and the following condition holds
+ (see :attr:`IPv6Address.ipv4_mapped`)::
+
+ address.is_global == address.ipv4_mapped.is_global
+
+ ``is_global`` has value opposite to :attr:`is_private`, except for the ``100.64.0.0/10``
+ IPv4 range where they are both ``False``.
+ """
return self not in self._constants._public_network and not self.is_private
@property
@@ -1548,13 +1575,15 @@ class _IPv4Constants:
_public_network = IPv4Network('100.64.0.0/10')
+ # Not globally reachable address blocks listed on
+ # https://www.iana.org/assignments/iana-ipv4-special-registry/iana-ipv4-special-registry.xhtml
_private_networks = [
IPv4Network('0.0.0.0/8'),
IPv4Network('10.0.0.0/8'),
IPv4Network('127.0.0.0/8'),
IPv4Network('169.254.0.0/16'),
IPv4Network('172.16.0.0/12'),
- IPv4Network('192.0.0.0/29'),
+ IPv4Network('192.0.0.0/24'),
IPv4Network('192.0.0.170/31'),
IPv4Network('192.0.2.0/24'),
IPv4Network('192.168.0.0/16'),
@@ -1565,6 +1594,11 @@ class _IPv4Constants:
IPv4Network('255.255.255.255/32'),
]
+ _private_networks_exceptions = [
+ IPv4Network('192.0.0.9/32'),
+ IPv4Network('192.0.0.10/32'),
+ ]
+
_reserved_network = IPv4Network('240.0.0.0/4')
_unspecified_address = IPv4Address('0.0.0.0')
@@ -2010,27 +2044,42 @@ class IPv6Address(_BaseV6, _BaseAddress):
@property
@functools.lru_cache()
def is_private(self):
- """Test if this address is allocated for private networks.
+ """``True`` if the address is defined as not globally reachable by
+ iana-ipv4-special-registry_ (for IPv4) or iana-ipv6-special-registry_
+ (for IPv6) with the following exceptions:
- Returns:
- A boolean, True if the address is reserved per
- iana-ipv6-special-registry, or is ipv4_mapped and is
- reserved in the iana-ipv4-special-registry.
+ * ``is_private`` is ``False`` for ``100.64.0.0/10``
+ * For IPv4-mapped IPv6-addresses the ``is_private`` value is determined by the
+ semantics of the underlying IPv4 addresses and the following condition holds
+ (see :attr:`IPv6Address.ipv4_mapped`)::
+ address.is_private == address.ipv4_mapped.is_private
+
+ ``is_private`` has value opposite to :attr:`is_global`, except for the ``100.64.0.0/10``
+ IPv4 range where they are both ``False``.
"""
ipv4_mapped = self.ipv4_mapped
if ipv4_mapped is not None:
return ipv4_mapped.is_private
- return any(self in net for net in self._constants._private_networks)
+ return (
+ any(self in net for net in self._constants._private_networks)
+ and all(self not in net for net in self._constants._private_networks_exceptions)
+ )
@property
def is_global(self):
- """Test if this address is allocated for public networks.
+ """``True`` if the address is defined as globally reachable by
+ iana-ipv4-special-registry_ (for IPv4) or iana-ipv6-special-registry_
+ (for IPv6) with the following exception:
- Returns:
- A boolean, true if the address is not reserved per
- iana-ipv6-special-registry.
+ For IPv4-mapped IPv6-addresses the ``is_private`` value is determined by the
+ semantics of the underlying IPv4 addresses and the following condition holds
+ (see :attr:`IPv6Address.ipv4_mapped`)::
+
+ address.is_global == address.ipv4_mapped.is_global
+ ``is_global`` has value opposite to :attr:`is_private`, except for the ``100.64.0.0/10``
+ IPv4 range where they are both ``False``.
"""
return not self.is_private
@@ -2271,19 +2320,31 @@ class _IPv6Constants:
_multicast_network = IPv6Network('ff00::/8')
+ # Not globally reachable address blocks listed on
+ # https://www.iana.org/assignments/iana-ipv6-special-registry/iana-ipv6-special-registry.xhtml
_private_networks = [
IPv6Network('::1/128'),
IPv6Network('::/128'),
IPv6Network('::ffff:0:0/96'),
+ IPv6Network('64:ff9b:1::/48'),
IPv6Network('100::/64'),
IPv6Network('2001::/23'),
- IPv6Network('2001:2::/48'),
IPv6Network('2001:db8::/32'),
- IPv6Network('2001:10::/28'),
+ # IANA says N/A, let's consider it not globally reachable to be safe
+ IPv6Network('2002::/16'),
IPv6Network('fc00::/7'),
IPv6Network('fe80::/10'),
]
+ _private_networks_exceptions = [
+ IPv6Network('2001:1::1/128'),
+ IPv6Network('2001:1::2/128'),
+ IPv6Network('2001:3::/32'),
+ IPv6Network('2001:4:112::/48'),
+ IPv6Network('2001:20::/28'),
+ IPv6Network('2001:30::/28'),
+ ]
+
_reserved_networks = [
IPv6Network('::/8'), IPv6Network('100::/8'),
IPv6Network('200::/7'), IPv6Network('400::/6'),
diff --git a/Lib/test/test_ipaddress.py b/Lib/test/test_ipaddress.py
index fc27628..16c3416 100644
--- a/Lib/test/test_ipaddress.py
+++ b/Lib/test/test_ipaddress.py
@@ -2269,6 +2269,10 @@ class IpaddrUnitTest(unittest.TestCase):
self.assertEqual(True, ipaddress.ip_address(
'172.31.255.255').is_private)
self.assertEqual(False, ipaddress.ip_address('172.32.0.0').is_private)
+ self.assertFalse(ipaddress.ip_address('192.0.0.0').is_global)
+ self.assertTrue(ipaddress.ip_address('192.0.0.9').is_global)
+ self.assertTrue(ipaddress.ip_address('192.0.0.10').is_global)
+ self.assertFalse(ipaddress.ip_address('192.0.0.255').is_global)
self.assertEqual(True,
ipaddress.ip_address('169.254.100.200').is_link_local)
@@ -2294,6 +2298,7 @@ class IpaddrUnitTest(unittest.TestCase):
self.assertEqual(True, ipaddress.ip_network("169.254.0.0/16").is_private)
self.assertEqual(True, ipaddress.ip_network("172.16.0.0/12").is_private)
self.assertEqual(True, ipaddress.ip_network("192.0.0.0/29").is_private)
+ self.assertEqual(False, ipaddress.ip_network("192.0.0.9/32").is_private)
self.assertEqual(True, ipaddress.ip_network("192.0.0.170/31").is_private)
self.assertEqual(True, ipaddress.ip_network("192.0.2.0/24").is_private)
self.assertEqual(True, ipaddress.ip_network("192.168.0.0/16").is_private)
@@ -2310,8 +2315,8 @@ class IpaddrUnitTest(unittest.TestCase):
self.assertEqual(True, ipaddress.ip_network("::/128").is_private)
self.assertEqual(True, ipaddress.ip_network("::ffff:0:0/96").is_private)
self.assertEqual(True, ipaddress.ip_network("100::/64").is_private)
- self.assertEqual(True, ipaddress.ip_network("2001::/23").is_private)
self.assertEqual(True, ipaddress.ip_network("2001:2::/48").is_private)
+ self.assertEqual(False, ipaddress.ip_network("2001:3::/48").is_private)
self.assertEqual(True, ipaddress.ip_network("2001:db8::/32").is_private)
self.assertEqual(True, ipaddress.ip_network("2001:10::/28").is_private)
self.assertEqual(True, ipaddress.ip_network("fc00::/7").is_private)
@@ -2390,6 +2395,20 @@ class IpaddrUnitTest(unittest.TestCase):
self.assertEqual(True, ipaddress.ip_address('0::0').is_unspecified)
self.assertEqual(False, ipaddress.ip_address('::1').is_unspecified)
+ self.assertFalse(ipaddress.ip_address('64:ff9b:1::').is_global)
+ self.assertFalse(ipaddress.ip_address('2001::').is_global)
+ self.assertTrue(ipaddress.ip_address('2001:1::1').is_global)
+ self.assertTrue(ipaddress.ip_address('2001:1::2').is_global)
+ self.assertFalse(ipaddress.ip_address('2001:2::').is_global)
+ self.assertTrue(ipaddress.ip_address('2001:3::').is_global)
+ self.assertFalse(ipaddress.ip_address('2001:4::').is_global)
+ self.assertTrue(ipaddress.ip_address('2001:4:112::').is_global)
+ self.assertFalse(ipaddress.ip_address('2001:10::').is_global)
+ self.assertTrue(ipaddress.ip_address('2001:20::').is_global)
+ self.assertTrue(ipaddress.ip_address('2001:30::').is_global)
+ self.assertFalse(ipaddress.ip_address('2001:40::').is_global)
+ self.assertFalse(ipaddress.ip_address('2002::').is_global)
+
# some generic IETF reserved addresses
self.assertEqual(True, ipaddress.ip_address('100::').is_reserved)
self.assertEqual(True, ipaddress.ip_network('4000::1/128').is_reserved)
diff --git a/Misc/NEWS.d/next/Library/2024-03-14-01-38-44.gh-issue-113171.VFnObz.rst b/Misc/NEWS.d/next/Library/2024-03-14-01-38-44.gh-issue-113171.VFnObz.rst
new file mode 100644
index 0000000..f9a7247
--- /dev/null
+++ b/Misc/NEWS.d/next/Library/2024-03-14-01-38-44.gh-issue-113171.VFnObz.rst
@@ -0,0 +1,9 @@
+Fixed various false positives and false negatives in
+
+* :attr:`ipaddress.IPv4Address.is_private` (see these docs for details)
+* :attr:`ipaddress.IPv4Address.is_global`
+* :attr:`ipaddress.IPv6Address.is_private`
+* :attr:`ipaddress.IPv6Address.is_global`
+
+Also in the corresponding :class:`ipaddress.IPv4Network` and :class:`ipaddress.IPv6Network`
+attributes.
--
2.45.2

@ -0,0 +1,365 @@
From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
From: Petr Viktorin <encukou@gmail.com>
Date: Wed, 31 Jul 2024 00:19:48 +0200
Subject: [PATCH] 00435: gh-121650: Encode newlines in headers, and verify
headers are sound (GH-122233)
Per RFC 2047:
> [...] these encoding schemes allow the
> encoding of arbitrary octet values, mail readers that implement this
> decoding should also ensure that display of the decoded data on the
> recipient's terminal will not cause unwanted side-effects
It seems that the "quoted-word" scheme is a valid way to include
a newline character in a header value, just like we already allow
undecodable bytes or control characters.
They do need to be properly quoted when serialized to text, though.
This should fail for custom fold() implementations that aren't careful
about newlines.
(cherry picked from commit 097633981879b3c9de9a1dd120d3aa585ecc2384)
Co-authored-by: Petr Viktorin <encukou@gmail.com>
Co-authored-by: Bas Bloemsaat <bas@bloemsaat.org>
Co-authored-by: Serhiy Storchaka <storchaka@gmail.com>
---
Doc/library/email.errors.rst | 7 +++
Doc/library/email.policy.rst | 18 ++++++
Doc/whatsnew/3.11.rst | 13 ++++
Lib/email/_header_value_parser.py | 12 +++-
Lib/email/_policybase.py | 8 +++
Lib/email/errors.py | 4 ++
Lib/email/generator.py | 13 +++-
Lib/test/test_email/test_generator.py | 62 +++++++++++++++++++
Lib/test/test_email/test_policy.py | 26 ++++++++
...-07-27-16-10-41.gh-issue-121650.nf6oc9.rst | 5 ++
10 files changed, 164 insertions(+), 4 deletions(-)
create mode 100644 Misc/NEWS.d/next/Library/2024-07-27-16-10-41.gh-issue-121650.nf6oc9.rst
diff --git a/Doc/library/email.errors.rst b/Doc/library/email.errors.rst
index 56aea6598b..27b0481a85 100644
--- a/Doc/library/email.errors.rst
+++ b/Doc/library/email.errors.rst
@@ -58,6 +58,13 @@ The following exception classes are defined in the :mod:`email.errors` module:
:class:`~email.mime.nonmultipart.MIMENonMultipart` (e.g.
:class:`~email.mime.image.MIMEImage`).
+
+.. exception:: HeaderWriteError()
+
+ Raised when an error occurs when the :mod:`~email.generator` outputs
+ headers.
+
+
.. exception:: MessageDefect()
This is the base class for all defects found when parsing email messages.
diff --git a/Doc/library/email.policy.rst b/Doc/library/email.policy.rst
index bb406c5a56..3edba4028b 100644
--- a/Doc/library/email.policy.rst
+++ b/Doc/library/email.policy.rst
@@ -228,6 +228,24 @@ added matters. To illustrate::
.. versionadded:: 3.6
+
+ .. attribute:: verify_generated_headers
+
+ If ``True`` (the default), the generator will raise
+ :exc:`~email.errors.HeaderWriteError` instead of writing a header
+ that is improperly folded or delimited, such that it would
+ be parsed as multiple headers or joined with adjacent data.
+ Such headers can be generated by custom header classes or bugs
+ in the ``email`` module.
+
+ As it's a security feature, this defaults to ``True`` even in the
+ :class:`~email.policy.Compat32` policy.
+ For backwards compatible, but unsafe, behavior, it must be set to
+ ``False`` explicitly.
+
+ .. versionadded:: 3.11.10
+
+
The following :class:`Policy` method is intended to be called by code using
the email library to create policy instances with custom settings:
diff --git a/Doc/whatsnew/3.11.rst b/Doc/whatsnew/3.11.rst
index 42b61c75c7..f12c871998 100644
--- a/Doc/whatsnew/3.11.rst
+++ b/Doc/whatsnew/3.11.rst
@@ -2728,6 +2728,7 @@ OpenSSL
.. _libb2: https://www.blake2.net/
+
Notable changes in 3.11.10
==========================
@@ -2736,3 +2737,15 @@ ipaddress
* Fixed ``is_global`` and ``is_private`` behavior in ``IPv4Address``,
``IPv6Address``, ``IPv4Network`` and ``IPv6Network``.
+
+email
+-----
+
+* Headers with embedded newlines are now quoted on output.
+
+ The :mod:`~email.generator` will now refuse to serialize (write) headers
+ that are improperly folded or delimited, such that they would be parsed as
+ multiple headers or joined with adjacent data.
+ If you need to turn this safety feature off,
+ set :attr:`~email.policy.Policy.verify_generated_headers`.
+ (Contributed by Bas Bloemsaat and Petr Viktorin in :gh:`121650`.)
diff --git a/Lib/email/_header_value_parser.py b/Lib/email/_header_value_parser.py
index 8cb8852cf0..255a953092 100644
--- a/Lib/email/_header_value_parser.py
+++ b/Lib/email/_header_value_parser.py
@@ -92,6 +92,8 @@
ASPECIALS = TSPECIALS | set("*'%")
ATTRIBUTE_ENDS = ASPECIALS | WSP
EXTENDED_ATTRIBUTE_ENDS = ATTRIBUTE_ENDS - set('%')
+NLSET = {'\n', '\r'}
+SPECIALSNL = SPECIALS | NLSET
def quote_string(value):
return '"'+str(value).replace('\\', '\\\\').replace('"', r'\"')+'"'
@@ -2780,9 +2782,13 @@ def _refold_parse_tree(parse_tree, *, policy):
wrap_as_ew_blocked -= 1
continue
tstr = str(part)
- if part.token_type == 'ptext' and set(tstr) & SPECIALS:
- # Encode if tstr contains special characters.
- want_encoding = True
+ if not want_encoding:
+ if part.token_type == 'ptext':
+ # Encode if tstr contains special characters.
+ want_encoding = not SPECIALSNL.isdisjoint(tstr)
+ else:
+ # Encode if tstr contains newlines.
+ want_encoding = not NLSET.isdisjoint(tstr)
try:
tstr.encode(encoding)
charset = encoding
diff --git a/Lib/email/_policybase.py b/Lib/email/_policybase.py
index c9cbadd2a8..d1f48211f9 100644
--- a/Lib/email/_policybase.py
+++ b/Lib/email/_policybase.py
@@ -157,6 +157,13 @@ class Policy(_PolicyBase, metaclass=abc.ABCMeta):
message_factory -- the class to use to create new message objects.
If the value is None, the default is Message.
+ verify_generated_headers
+ -- if true, the generator verifies that each header
+ they are properly folded, so that a parser won't
+ treat it as multiple headers, start-of-body, or
+ part of another header.
+ This is a check against custom Header & fold()
+ implementations.
"""
raise_on_defect = False
@@ -165,6 +172,7 @@ class Policy(_PolicyBase, metaclass=abc.ABCMeta):
max_line_length = 78
mangle_from_ = False
message_factory = None
+ verify_generated_headers = True
def handle_defect(self, obj, defect):
"""Based on policy, either raise defect or call register_defect.
diff --git a/Lib/email/errors.py b/Lib/email/errors.py
index 3ad0056554..02aa5eced6 100644
--- a/Lib/email/errors.py
+++ b/Lib/email/errors.py
@@ -29,6 +29,10 @@ class CharsetError(MessageError):
"""An illegal charset was given."""
+class HeaderWriteError(MessageError):
+ """Error while writing headers."""
+
+
# These are parsing defects which the parser was able to work around.
class MessageDefect(ValueError):
"""Base class for a message defect."""
diff --git a/Lib/email/generator.py b/Lib/email/generator.py
index eb597de76d..563ca17072 100644
--- a/Lib/email/generator.py
+++ b/Lib/email/generator.py
@@ -14,12 +14,14 @@
from copy import deepcopy
from io import StringIO, BytesIO
from email.utils import _has_surrogates
+from email.errors import HeaderWriteError
UNDERSCORE = '_'
NL = '\n' # XXX: no longer used by the code below.
NLCRE = re.compile(r'\r\n|\r|\n')
fcre = re.compile(r'^From ', re.MULTILINE)
+NEWLINE_WITHOUT_FWSP = re.compile(r'\r\n[^ \t]|\r[^ \n\t]|\n[^ \t]')
class Generator:
@@ -222,7 +224,16 @@ def _dispatch(self, msg):
def _write_headers(self, msg):
for h, v in msg.raw_items():
- self.write(self.policy.fold(h, v))
+ folded = self.policy.fold(h, v)
+ if self.policy.verify_generated_headers:
+ linesep = self.policy.linesep
+ if not folded.endswith(self.policy.linesep):
+ raise HeaderWriteError(
+ f'folded header does not end with {linesep!r}: {folded!r}')
+ if NEWLINE_WITHOUT_FWSP.search(folded.removesuffix(linesep)):
+ raise HeaderWriteError(
+ f'folded header contains newline: {folded!r}')
+ self.write(folded)
# A blank line always separates headers from body
self.write(self._NL)
diff --git a/Lib/test/test_email/test_generator.py b/Lib/test/test_email/test_generator.py
index 89e7edeb63..d29400f0ed 100644
--- a/Lib/test/test_email/test_generator.py
+++ b/Lib/test/test_email/test_generator.py
@@ -6,6 +6,7 @@
from email.generator import Generator, BytesGenerator
from email.headerregistry import Address
from email import policy
+import email.errors
from test.test_email import TestEmailBase, parameterize
@@ -216,6 +217,44 @@ def test_rfc2231_wrapping_switches_to_default_len_if_too_narrow(self):
g.flatten(msg)
self.assertEqual(s.getvalue(), self.typ(expected))
+ def test_keep_encoded_newlines(self):
+ msg = self.msgmaker(self.typ(textwrap.dedent("""\
+ To: nobody
+ Subject: Bad subject=?UTF-8?Q?=0A?=Bcc: injection@example.com
+
+ None
+ """)))
+ expected = textwrap.dedent("""\
+ To: nobody
+ Subject: Bad subject=?UTF-8?Q?=0A?=Bcc: injection@example.com
+
+ None
+ """)
+ s = self.ioclass()
+ g = self.genclass(s, policy=self.policy.clone(max_line_length=80))
+ g.flatten(msg)
+ self.assertEqual(s.getvalue(), self.typ(expected))
+
+ def test_keep_long_encoded_newlines(self):
+ msg = self.msgmaker(self.typ(textwrap.dedent("""\
+ To: nobody
+ Subject: Bad subject=?UTF-8?Q?=0A?=Bcc: injection@example.com
+
+ None
+ """)))
+ expected = textwrap.dedent("""\
+ To: nobody
+ Subject: Bad subject
+ =?utf-8?q?=0A?=Bcc:
+ injection@example.com
+
+ None
+ """)
+ s = self.ioclass()
+ g = self.genclass(s, policy=self.policy.clone(max_line_length=30))
+ g.flatten(msg)
+ self.assertEqual(s.getvalue(), self.typ(expected))
+
class TestGenerator(TestGeneratorBase, TestEmailBase):
@@ -224,6 +263,29 @@ class TestGenerator(TestGeneratorBase, TestEmailBase):
ioclass = io.StringIO
typ = str
+ def test_verify_generated_headers(self):
+ """gh-121650: by default the generator prevents header injection"""
+ class LiteralHeader(str):
+ name = 'Header'
+ def fold(self, **kwargs):
+ return self
+
+ for text in (
+ 'Value\r\nBad Injection\r\n',
+ 'NoNewLine'
+ ):
+ with self.subTest(text=text):
+ message = message_from_string(
+ "Header: Value\r\n\r\nBody",
+ policy=self.policy,
+ )
+
+ del message['Header']
+ message['Header'] = LiteralHeader(text)
+
+ with self.assertRaises(email.errors.HeaderWriteError):
+ message.as_string()
+
class TestBytesGenerator(TestGeneratorBase, TestEmailBase):
diff --git a/Lib/test/test_email/test_policy.py b/Lib/test/test_email/test_policy.py
index c6b9c80efe..baa35fd68e 100644
--- a/Lib/test/test_email/test_policy.py
+++ b/Lib/test/test_email/test_policy.py
@@ -26,6 +26,7 @@ class PolicyAPITests(unittest.TestCase):
'raise_on_defect': False,
'mangle_from_': True,
'message_factory': None,
+ 'verify_generated_headers': True,
}
# These default values are the ones set on email.policy.default.
# If any of these defaults change, the docs must be updated.
@@ -294,6 +295,31 @@ def test_short_maxlen_error(self):
with self.assertRaises(email.errors.HeaderParseError):
policy.fold("Subject", subject)
+ def test_verify_generated_headers(self):
+ """Turning protection off allows header injection"""
+ policy = email.policy.default.clone(verify_generated_headers=False)
+ for text in (
+ 'Header: Value\r\nBad: Injection\r\n',
+ 'Header: NoNewLine'
+ ):
+ with self.subTest(text=text):
+ message = email.message_from_string(
+ "Header: Value\r\n\r\nBody",
+ policy=policy,
+ )
+ class LiteralHeader(str):
+ name = 'Header'
+ def fold(self, **kwargs):
+ return self
+
+ del message['Header']
+ message['Header'] = LiteralHeader(text)
+
+ self.assertEqual(
+ message.as_string(),
+ f"{text}\nBody",
+ )
+
# XXX: Need subclassing tests.
# For adding subclassed objects, make sure the usual rules apply (subclass
# wins), but that the order still works (right overrides left).
diff --git a/Misc/NEWS.d/next/Library/2024-07-27-16-10-41.gh-issue-121650.nf6oc9.rst b/Misc/NEWS.d/next/Library/2024-07-27-16-10-41.gh-issue-121650.nf6oc9.rst
new file mode 100644
index 0000000000..83dd28d4ac
--- /dev/null
+++ b/Misc/NEWS.d/next/Library/2024-07-27-16-10-41.gh-issue-121650.nf6oc9.rst
@@ -0,0 +1,5 @@
+:mod:`email` headers with embedded newlines are now quoted on output. The
+:mod:`~email.generator` will now refuse to serialize (write) headers that
+are unsafely folded or delimited; see
+:attr:`~email.policy.Policy.verify_generated_headers`. (Contributed by Bas
+Bloemsaat and Petr Viktorin in :gh:`121650`.)

@ -0,0 +1,128 @@
From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
From: "Jason R. Coombs" <jaraco@jaraco.com>
Date: Mon, 19 Aug 2024 19:28:20 -0400
Subject: [PATCH] 00436: [CVE-2024-8088] gh-122905: Sanitize names in
zipfile.Path.
Co-authored-by: Jason R. Coombs <jaraco@jaraco.com>
---
Lib/test/test_zipfile.py | 17 ++++++
Lib/zipfile.py | 61 ++++++++++++++++++-
...-08-11-14-08-04.gh-issue-122905.7tDsxA.rst | 1 +
3 files changed, 78 insertions(+), 1 deletion(-)
create mode 100644 Misc/NEWS.d/next/Library/2024-08-11-14-08-04.gh-issue-122905.7tDsxA.rst
diff --git a/Lib/test/test_zipfile.py b/Lib/test/test_zipfile.py
index 4de6f379a4..8bdc7a1b7d 100644
--- a/Lib/test/test_zipfile.py
+++ b/Lib/test/test_zipfile.py
@@ -3651,6 +3651,23 @@ def test_extract_orig_with_implied_dirs(self, alpharep):
zipfile.Path(zf)
zf.extractall(source_path.parent)
+ def test_malformed_paths(self):
+ """
+ Path should handle malformed paths.
+ """
+ data = io.BytesIO()
+ zf = zipfile.ZipFile(data, "w")
+ zf.writestr("/one-slash.txt", b"content")
+ zf.writestr("//two-slash.txt", b"content")
+ zf.writestr("../parent.txt", b"content")
+ zf.filename = ''
+ root = zipfile.Path(zf)
+ assert list(map(str, root.iterdir())) == [
+ 'one-slash.txt',
+ 'two-slash.txt',
+ 'parent.txt',
+ ]
+
class EncodedMetadataTests(unittest.TestCase):
file_names = ['\u4e00', '\u4e8c', '\u4e09'] # Han 'one', 'two', 'three'
diff --git a/Lib/zipfile.py b/Lib/zipfile.py
index 86829abce4..b7bf9ef7e3 100644
--- a/Lib/zipfile.py
+++ b/Lib/zipfile.py
@@ -9,6 +9,7 @@
import itertools
import os
import posixpath
+import re
import shutil
import stat
import struct
@@ -2243,7 +2244,65 @@ def _difference(minuend, subtrahend):
return itertools.filterfalse(set(subtrahend).__contains__, minuend)
-class CompleteDirs(ZipFile):
+class SanitizedNames:
+ """
+ ZipFile mix-in to ensure names are sanitized.
+ """
+
+ def namelist(self):
+ return list(map(self._sanitize, super().namelist()))
+
+ @staticmethod
+ def _sanitize(name):
+ r"""
+ Ensure a relative path with posix separators and no dot names.
+ Modeled after
+ https://github.com/python/cpython/blob/bcc1be39cb1d04ad9fc0bd1b9193d3972835a57c/Lib/zipfile/__init__.py#L1799-L1813
+ but provides consistent cross-platform behavior.
+ >>> san = SanitizedNames._sanitize
+ >>> san('/foo/bar')
+ 'foo/bar'
+ >>> san('//foo.txt')
+ 'foo.txt'
+ >>> san('foo/.././bar.txt')
+ 'foo/bar.txt'
+ >>> san('foo../.bar.txt')
+ 'foo../.bar.txt'
+ >>> san('\\foo\\bar.txt')
+ 'foo/bar.txt'
+ >>> san('D:\\foo.txt')
+ 'D/foo.txt'
+ >>> san('\\\\server\\share\\file.txt')
+ 'server/share/file.txt'
+ >>> san('\\\\?\\GLOBALROOT\\Volume3')
+ '?/GLOBALROOT/Volume3'
+ >>> san('\\\\.\\PhysicalDrive1\\root')
+ 'PhysicalDrive1/root'
+ Retain any trailing slash.
+ >>> san('abc/')
+ 'abc/'
+ Raises a ValueError if the result is empty.
+ >>> san('../..')
+ Traceback (most recent call last):
+ ...
+ ValueError: Empty filename
+ """
+
+ def allowed(part):
+ return part and part not in {'..', '.'}
+
+ # Remove the drive letter.
+ # Don't use ntpath.splitdrive, because that also strips UNC paths
+ bare = re.sub('^([A-Z]):', r'\1', name, flags=re.IGNORECASE)
+ clean = bare.replace('\\', '/')
+ parts = clean.split('/')
+ joined = '/'.join(filter(allowed, parts))
+ if not joined:
+ raise ValueError("Empty filename")
+ return joined + '/' * name.endswith('/')
+
+
+class CompleteDirs(SanitizedNames, ZipFile):
"""
A ZipFile subclass that ensures that implied directories
are always included in the namelist.
diff --git a/Misc/NEWS.d/next/Library/2024-08-11-14-08-04.gh-issue-122905.7tDsxA.rst b/Misc/NEWS.d/next/Library/2024-08-11-14-08-04.gh-issue-122905.7tDsxA.rst
new file mode 100644
index 0000000000..1be44c906c
--- /dev/null
+++ b/Misc/NEWS.d/next/Library/2024-08-11-14-08-04.gh-issue-122905.7tDsxA.rst
@@ -0,0 +1 @@
+:class:`zipfile.Path` objects now sanitize names from the zipfile.

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

@ -0,0 +1,16 @@
-----BEGIN PGP SIGNATURE-----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=Br9/
-----END PGP SIGNATURE-----

@ -16,7 +16,6 @@ LEVELS = (None, 1, 2)
# list of globs of test and other files that we expect not to have bytecode
not_compiled = [
'/usr/bin/*',
'/usr/lib/rpm/redhat/*',
'*/test/*/bad_coding.py',
'*/test/*/bad_coding2.py',
'*/test/*/badsyntax_*.py',

@ -1,171 +0,0 @@
'''Script to perform import of each module given to %%py_check_import
'''
import argparse
import importlib
import fnmatch
import os
import re
import site
import sys
from contextlib import contextmanager
from pathlib import Path
def read_modules_files(file_paths):
'''Read module names from the files (modules must be newline separated).
Return the module names list or, if no files were provided, an empty list.
'''
if not file_paths:
return []
modules = []
for file in file_paths:
file_contents = file.read_text()
modules.extend(file_contents.split())
return modules
def read_modules_from_cli(argv):
'''Read module names from command-line arguments (space or comma separated).
Return the module names list.
'''
if not argv:
return []
# %%py3_check_import allows to separate module list with comma or whitespace,
# we need to unify the output to a list of particular elements
modules_as_str = ' '.join(argv)
modules = re.split(r'[\s,]+', modules_as_str)
# Because of shell expansion in some less typical cases it may happen
# that a trailing space will occur at the end of the list.
# Remove the empty items from the list before passing it further
modules = [m for m in modules if m]
return modules
def filter_top_level_modules_only(modules):
'''Filter out entries with nested modules (containing dot) ie. 'foo.bar'.
Return the list of top-level modules.
'''
return [module for module in modules if '.' not in module]
def any_match(text, globs):
'''Return True if any of given globs fnmatchcase's the given text.'''
return any(fnmatch.fnmatchcase(text, g) for g in globs)
def exclude_unwanted_module_globs(globs, modules):
'''Filter out entries which match the either of the globs given as argv.
Return the list of filtered modules.
'''
return [m for m in modules if not any_match(m, globs)]
def read_modules_from_all_args(args):
'''Return a joined list of modules from all given command-line arguments.
'''
modules = read_modules_files(args.filename)
modules.extend(read_modules_from_cli(args.modules))
if args.exclude:
modules = exclude_unwanted_module_globs(args.exclude, modules)
if args.top_level:
modules = filter_top_level_modules_only(modules)
# Error when someone accidentally managed to filter out everything
if len(modules) == 0:
raise ValueError('No modules to check were left')
return modules
def import_modules(modules):
'''Procedure to perform import check for each module name from the given list of modules.
'''
for module in modules:
print('Check import:', module, file=sys.stderr)
importlib.import_module(module)
def argparser():
parser = argparse.ArgumentParser(
description='Generate list of all importable modules for import check.'
)
parser.add_argument(
'modules', nargs='*',
help=('Add modules to check the import (space or comma separated).'),
)
parser.add_argument(
'-f', '--filename', action='append', type=Path,
help='Add importable module names list from file.',
)
parser.add_argument(
'-t', '--top-level', action='store_true',
help='Check only top-level modules.',
)
parser.add_argument(
'-e', '--exclude', action='append',
help='Provide modules globs to be excluded from the check.',
)
return parser
@contextmanager
def remove_unwanteds_from_sys_path():
'''Remove cwd and this script's parent from sys.path for the import test.
Bring the original contents back after import is done (or failed)
'''
cwd_absolute = Path.cwd().absolute()
this_file_parent = Path(__file__).parent.absolute()
old_sys_path = list(sys.path)
for path in old_sys_path:
if Path(path).absolute() in (cwd_absolute, this_file_parent):
sys.path.remove(path)
try:
yield
finally:
sys.path = old_sys_path
def addsitedirs_from_environ():
'''Load directories from the _PYTHONSITE environment variable (separated by :)
and load the ones already present in sys.path via site.addsitedir()
to handle .pth files in them.
This is needed to properly import old-style namespace packages with nspkg.pth files.
See https://bugzilla.redhat.com/2018551 for a more detailed rationale.'''
for path in os.getenv('_PYTHONSITE', '').split(':'):
if path in sys.path:
site.addsitedir(path)
def main(argv=None):
cli_args = argparser().parse_args(argv)
if not cli_args.modules and not cli_args.filename:
raise ValueError('No modules to check were provided')
modules = read_modules_from_all_args(cli_args)
with remove_unwanteds_from_sys_path():
addsitedirs_from_environ()
import_modules(modules)
if __name__ == '__main__':
main()

@ -1,77 +0,0 @@
%__python3 /usr/bin/python3.11
%python3_pkgversion 3.11
# The following are macros from macros.python3 in Fedora that are newer/different than those in the python3-rpm-macros package in RHEL.
# These macros overwrite/supercede some of the macros in the python3-rpm-macros package in RHEL.
# nb: $RPM_BUILD_ROOT is not set when the macros are expanded (at spec parse time)
# so we set it manually (to empty string), making our Python prefer the correct install scheme location
# platbase/base is explicitly set to %%{_prefix} to support custom values, such as /app for flatpaks
%python3_sitelib %(RPM_BUILD_ROOT= %{__python3} -Ic "import sysconfig; print(sysconfig.get_path('purelib', vars={'platbase': '%{_prefix}', 'base': '%{_prefix}'}))")
%python3_sitearch %(RPM_BUILD_ROOT= %{__python3} -Ic "import sysconfig; print(sysconfig.get_path('platlib', vars={'platbase': '%{_prefix}', 'base': '%{_prefix}'}))")
%python3_version %(RPM_BUILD_ROOT= %{__python3} -Ic "import sys; sys.stdout.write('{0.major}.{0.minor}'.format(sys.version_info))")
%python3_version_nodots %(RPM_BUILD_ROOT= %{__python3} -Ic "import sys; sys.stdout.write('{0.major}{0.minor}'.format(sys.version_info))")
%python3_platform %(RPM_BUILD_ROOT= %{__python3} -Ic "import sysconfig; print(sysconfig.get_platform())")
%python3_platform_triplet %(RPM_BUILD_ROOT= %{__python3} -Ic "import sysconfig; print(sysconfig.get_config_var('MULTIARCH'))")
%python3_ext_suffix %(RPM_BUILD_ROOT= %{__python3} -Ic "import sysconfig; print(sysconfig.get_config_var('EXT_SUFFIX'))")
%python3_cache_tag %(RPM_BUILD_ROOT= %{__python3} -Ic "import sys; print(sys.implementation.cache_tag)")
%_py3_shebang_s s
%_py3_shebang_P %(RPM_BUILD_ROOT= %{__python3} -Ic "import sys; print('P' if hasattr(sys.flags, 'safe_path') else '')")
%py3_shbang_opts -%{?_py3_shebang_s}%{?_py3_shebang_P}
%py3_install() %{expand:\\\
CFLAGS="${CFLAGS:-${RPM_OPT_FLAGS}}" LDFLAGS="${LDFLAGS:-${RPM_LD_FLAGS}}"\\\
%{__python3} %{py_setup} %{?py_setup_args} install -O1 --skip-build --root %{buildroot} --prefix %{_prefix} %{?*}
rm -rfv %{buildroot}%{_bindir}/__pycache__
}
%py3_install_egg() %{expand:\\\
mkdir -p %{buildroot}%{python3_sitelib}
%{__python3} -m easy_install -m --prefix %{buildroot}%{_prefix} -Z dist/*-py%{python3_version}.egg %{?*}
rm -rfv %{buildroot}%{_bindir}/__pycache__
}
%py3_install_wheel() %{expand:\\\
%{__python3} -m pip install -I dist/%{1} --root %{buildroot} --prefix %{_prefix} --no-deps --no-index --no-warn-script-location
rm -rfv %{buildroot}%{_bindir}/__pycache__
for distinfo in %{buildroot}%{python3_sitelib}/*.dist-info %{buildroot}%{python3_sitearch}/*.dist-info; do
if [ -f ${distinfo}/direct_url.json ]; then
rm -fv ${distinfo}/direct_url.json
sed -i '/direct_url.json/d' ${distinfo}/RECORD
fi
done
}
# With $PATH and $PYTHONPATH set to the %%buildroot,
# try to import the Python 3 module(s) given as command-line args or read from file (-f).
# Respect the custom values of %%py3_shebang_flags or set nothing if it's undefined.
# Filter and check import on only top-level modules using -t flag.
# Exclude unwanted modules by passing their globs to -e option.
# Useful as a smoke test in %%check when running tests is not feasible.
# Use spaces or commas as separators if providing list directly.
# Use newlines as separators if providing list in a file.
%py3_check_import(e:tf:) %{expand:\\\
PATH="%{buildroot}%{_bindir}:$PATH"\\\
PYTHONPATH="${PYTHONPATH:-%{buildroot}%{python3_sitearch}:%{buildroot}%{python3_sitelib}}"\\\
_PYTHONSITE="%{buildroot}%{python3_sitearch}:%{buildroot}%{python3_sitelib}"\\\
PYTHONDONTWRITEBYTECODE=1\\\
%{lua:
local command = "%{__python3} "
if rpm.expand("%{?py3_shebang_flags}") ~= "" then
command = command .. "-%{py3_shebang_flags}"
end
command = command .. " %{_rpmconfigdir}/redhat/import_all_modules_py3_11.py "
-- handle multiline arguments correctly, see https://bugzilla.redhat.com/2018809
local args=rpm.expand('%{?**}'):gsub("[%s\\\\]*%s+", " ")
print(command .. args)
}
}
%pytest %{expand:\\\
CFLAGS="${CFLAGS:-${RPM_OPT_FLAGS}}" LDFLAGS="${LDFLAGS:-${RPM_LD_FLAGS}}"\\\
PATH="%{buildroot}%{_bindir}:$PATH"\\\
PYTHONPATH="${PYTHONPATH:-%{buildroot}%{python3_sitearch}:%{buildroot}%{python3_sitelib}}"\\\
PYTHONDONTWRITEBYTECODE=1\\\
%{?__pytest_addopts:PYTEST_ADDOPTS="${PYTEST_ADDOPTS:-} %{__pytest_addopts}"}\\\
%__pytest}

@ -16,11 +16,11 @@ 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}.10
%global general_version %{pybasever}.9
#global prerel ...
%global upstream_version %{general_version}%{?prerel}
Version: %{general_version}%{?prerel:~%{prerel}}
Release: 1%{?dist}
Release: 7%{?dist}
License: Python
@ -260,10 +260,6 @@ Source1: %{url}ftp/python/%{general_version}/Python-%{upstream_version}.tar.xz.a
# The release manager for Python 3.11 is pablogsal
Source2: https://keybase.io/pablogsal/pgp_keys.asc
# Sources for the python3.11-rpm-macros
Source3: macros.python3.11
Source4: import_all_modules_py3_11.py
# A simple script to check timestamps of bytecode files
# Run in check section with Python that is currently being built
# Originally written by bkabrda
@ -343,31 +339,6 @@ Patch329: 00329-fips.patch
# https://github.com/GrahamDumpleton/mod_wsgi/issues/730
Patch371: 00371-revert-bpo-1596321-fix-threading-_shutdown-for-the-main-thread-gh-28549-gh-28589.patch
# 00378 #
# Support expat 2.4.5
#
# Curly brackets were never allowed in namespace URIs
# according to RFC 3986, and so-called namespace-validating
# XML parsers have the right to reject them a invalid URIs.
#
# libexpat >=2.4.5 has become strcter in that regard due to
# related security issues; with ET.XML instantiating a
# namespace-aware parser under the hood, this test has no
# future in CPython.
#
# References:
# - https://datatracker.ietf.org/doc/html/rfc3968
# - https://www.w3.org/TR/xml-names/
#
# Also, test_minidom.py: Support Expat >=2.4.5
#
# The patch has diverged from upstream as the python test
# suite was relying on checking the expat version, whereas
# in RHEL fixes get backported instead of rebasing packages.
#
# Upstream: https://bugs.python.org/issue46811
Patch378: 00378-support-expat-2-4-5.patch
# 00397 #
# Filters for tarfile extraction (CVE-2007-4559, PEP-706)
# First patch fixes determination of symlink targets, which were treated
@ -388,7 +359,7 @@ Patch397: 00397-tarfile-filter.patch
#
# Upstream PR: https://github.com/python/cpython/pull/111116
#
# The patch implements the possibility to restore the old behavior via
# Second patch implmenets the possibility to restore the old behavior via
# config file or environment variable.
Patch415: 00415-cve-2023-27043-gh-102988-reject-malformed-addresses-in-email-parseaddr-111116.patch
@ -398,6 +369,35 @@ Patch415: 00415-cve-2023-27043-gh-102988-reject-malformed-addresses-in-email-par
# Downstream only.
Patch422: 00422-fix-expat-tests.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 # d33a3c90daa3d5d2d7e67f6e9264e5438d9608a0
# 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 # 1acd6db660ad1124ab7ae449a841608dd9d9062d
# [CVE-2024-8088] gh-122905: Sanitize names in zipfile.Path.
Patch436: 00436-cve-2024-8088-gh-122905-sanitize-names-in-zipfile-path.patch
# (New patches go here ^^^)
#
# When adding new patches to "python" and "python3" in Fedora, EL, etc.,
@ -416,14 +416,6 @@ Patch422: 00422-fix-expat-tests.patch
# Descriptions, and metadata for subpackages
# ==========================================
# Require alternatives version that implements the --keep-foreign flag and fixes rhbz#2203820
Requires: alternatives >= 1.19.2-1
Requires(post): alternatives >= 1.19.2-1
Requires(postun): alternatives >= 1.19.2-1
# When the user tries to `yum install python`, yum will list this package among
# the possible alternatives
Provides: alternative-for(python)
%if %{with main_python}
# Description for the python3X SRPM only:
@ -498,7 +490,6 @@ Documentation for Python is provided in the %{pkgname}-docs package.
Packages containing additional libraries for Python are generally named with
the "%{pkgname}-" prefix.
For the unversioned "python" executable, see manual page "unversioned-python".
%if %{with main_python}
# https://fedoraproject.org/wiki/Changes/Move_usr_bin_python_into_separate_package
@ -567,12 +558,9 @@ Requires: %{pkgname}-libs%{?_isa} = %{version}-%{release}
Requires: (python-rpm-macros if rpm-build)
Requires: (python3-rpm-macros if rpm-build)
# Require alternatives version that implements the --keep-foreign flag and fixes rhbz#2203820
Requires(postun): alternatives >= 1.19.2-1
# python3.11 installs the alternatives master symlink to which we attach a slave
Requires(post): %{pkgname}
Requires(postun): %{pkgname}
# We provide the python3.11-rpm-macros here to make it possible to
# BuildRequire them in the same manner as RHEL8.
Provides: %{pkgname}-rpm-macros = %{version}-%{release}
%unversioned_obsoletes_of_python3_X_if_main devel
@ -621,13 +609,6 @@ Provides: idle = %{version}-%{release}
Provides: %{pkgname}-tools = %{version}-%{release}
Provides: %{pkgname}-tools%{?_isa} = %{version}-%{release}
# Require alternatives version that implements the --keep-foreign flag and fixes rhbz#2203820
Requires(postun): alternatives >= 1.19.2-1
# python3.11 installs the alternatives master symlink to which we attach a slave
Requires(post): %{pkgname}
Requires(postun): %{pkgname}
%description -n %{pkgname}-idle
IDLE is Pythons Integrated Development and Learning Environment.
@ -687,13 +668,6 @@ Requires: %{pkgname}-idle%{?_isa} = %{version}-%{release}
%unversioned_obsoletes_of_python3_X_if_main debug
# Require alternatives version that implements the --keep-foreign flag and fixes rhbz#2203820
Requires(postun): alternatives >= 1.19.2-1
# python3.11 installs the alternatives master symlink to which we attach a slave
Requires(post): %{pkgname}
Requires(postun): %{pkgname}
%description -n %{pkgname}-debug
python3-debug provides a version of the Python runtime with numerous debugging
features enabled, aimed at advanced Python users such as developers of Python
@ -711,23 +685,6 @@ The debug runtime additionally supports debug builds of C-API extensions
(with the "d" ABI flag) for debugging issues in those extensions.
%endif # with debug_build
# We package the python3.11-rpm-macros in RHEL8 as to properly set the
# %%__python3 and %%python3_pkgversion macros as well as provide modern
# versions the current base macros.
%package -n %{pkgname}-rpm-macros
Summary: RPM macros for building RPMs with Python %{pybasever}
License: MIT
Provides: python-modular-rpm-macros == %{pybasever}
Conflicts: python-modular-rpm-macros > %{pybasever}
Requires: python3-rpm-macros
BuildArch: noarch
%description -n %{pkgname}-rpm-macros
RPM macros for building RPMs with Python %{pybasever} from the python%{pyshortver} module.
If you want to build an RPM against the python%{pyshortver} module, you need to add:
BuildRequire: %{pkgname}-rpm-macros.
# ======================================================
# The prep phase of the build:
# ======================================================
@ -1140,28 +1097,6 @@ for file in %{buildroot}%{pylibdir}/pydoc_data/topics.py $(grep --include='*.py'
rm ${directory}/{__pycache__/${module}.cpython-%{pyshortver}.opt-?.pyc,${module}.py}
done
# Python RPM macros
mkdir -p %{buildroot}%{rpmmacrodir}/
install -m 644 %{SOURCE3} \
%{buildroot}/%{rpmmacrodir}/
# Add a script that is being used by python3.11-rpm-macros
mkdir -p %{buildroot}%{_rpmconfigdir}/redhat
install -m 644 %{SOURCE4} %{buildroot}%{_rpmconfigdir}/redhat/
# All ghost files controlled by alternatives need to exist for the files
# section check to succeed
# - Don't list /usr/bin/python as a ghost file so `yum install /usr/bin/python`
# doesn't install this package
touch %{buildroot}%{_bindir}/unversioned-python
touch %{buildroot}%{_mandir}/man1/python.1.gz
touch %{buildroot}%{_bindir}/python3
touch %{buildroot}%{_mandir}/man1/python3.1.gz
touch %{buildroot}%{_bindir}/pydoc3
touch %{buildroot}%{_bindir}/pydoc-3
touch %{buildroot}%{_bindir}/idle3
touch %{buildroot}%{_bindir}/python3-config
# ======================================================
# Checks for packaging issues
# ======================================================
@ -1252,118 +1187,9 @@ CheckPython optimized
%endif # with tests
# ======================================================
# Scriptlets for alternatives on rhel8
# ======================================================
%post
# Alternative for /usr/bin/python -> /usr/bin/python3 + man page
alternatives --install %{_bindir}/unversioned-python \
python \
%{_bindir}/python3 \
300 \
--slave %{_bindir}/python \
unversioned-python \
%{_bindir}/python3 \
--slave %{_mandir}/man1/python.1.gz \
unversioned-python-man \
%{_mandir}/man1/python3.1.gz
# Alternative for /usr/bin/python -> /usr/bin/python3.11 + man page
alternatives --install %{_bindir}/unversioned-python \
python \
%{_bindir}/python3.11 \
211 \
--slave %{_bindir}/python \
unversioned-python \
%{_bindir}/python3.11 \
--slave %{_mandir}/man1/python.1.gz \
unversioned-python-man \
%{_mandir}/man1/python3.11.1.gz
# Alternative for /usr/bin/python3 -> /usr/bin/python3.11 + related files
# Create only if it doesn't exist already
EXISTS=`alternatives --display python3 | \
grep -c "^/usr/bin/python3.11 - priority [0-9]*"`
if [ $EXISTS -eq 0 ]; then
alternatives --install %{_bindir}/python3 \
python3 \
%{_bindir}/python3.11 \
31100 \
--slave %{_mandir}/man1/python3.1.gz \
python3-man \
%{_mandir}/man1/python3.11.1.gz \
--slave %{_bindir}/pydoc3 \
pydoc3 \
%{_bindir}/pydoc3.11 \
--slave %{_bindir}/pydoc-3 \
pydoc-3 \
%{_bindir}/pydoc3.11
fi
%postun
# Do this only during uninstall process (not during update)
if [ $1 -eq 0 ]; then
alternatives --keep-foreign --remove python \
%{_bindir}/python3.11
alternatives --keep-foreign --remove python3 \
%{_bindir}/python3.11
# Remove link python → python3 if no other python3.* exists
if ! alternatives --display python3 > /dev/null; then
alternatives --keep-foreign --remove python \
%{_bindir}/python3
fi
fi
%post devel
alternatives --add-slave python3 %{_bindir}/python3.11 \
%{_bindir}/python3-config \
python3-config \
%{_bindir}/python3.11-config
%postun devel
# Do this only during uninstall process (not during update)
if [ $1 -eq 0 ]; then
alternatives --keep-foreign --remove-slave python3 %{_bindir}/python3.11 \
python3-config
fi
%post idle
alternatives --add-slave python3 %{_bindir}/python3.11 \
%{_bindir}/idle3 \
idle3 \
%{_bindir}/idle3.11
%postun idle
# Do this only during uninstall process (not during update)
if [ $1 -eq 0 ]; then
alternatives --keep-foreign --remove-slave python3 %{_bindir}/python3.11 \
idle3
fi
# ======================================================
# Files for each RPM (sub)package
# ======================================================
%files -n %{pkgname}-rpm-macros
%{rpmmacrodir}/macros.python%{pybasever}
%{_rpmconfigdir}/redhat/import_all_modules_py3_11.py
%files -n %{pkgname}
%doc README.rst
# Alternatives
%ghost %{_bindir}/unversioned-python
%ghost %{_mandir}/man1/python.1.gz
%ghost %{_bindir}/python3
%ghost %{_mandir}/man1/python3.1.gz
%ghost %{_bindir}/pydoc3
%ghost %{_bindir}/pydoc-3
%if %{with main_python}
%{_bindir}/pydoc*
%{_bindir}/python3
@ -1653,9 +1479,6 @@ fi
%{_bindir}/python%{pybasever}-config
%{_bindir}/python%{LDVERSION_optimized}-config
%{_bindir}/python%{LDVERSION_optimized}-*-config
# Alternatives
%ghost %{_bindir}/python3-config
%{_libdir}/libpython%{LDVERSION_optimized}.so
%{_libdir}/pkgconfig/python-%{LDVERSION_optimized}.pc
%{_libdir}/pkgconfig/python-%{LDVERSION_optimized}-embed.pc
@ -1668,8 +1491,6 @@ fi
%{_bindir}/idle*
%else
%{_bindir}/idle%{pybasever}
# Alternatives
%ghost %{_bindir}/idle3
%endif
%{pylibdir}/idlelib
@ -1855,17 +1676,13 @@ fi
# ======================================================
%changelog
* Mon Sep 09 2024 Tomáš Hrnčiar <thrnciar@redhat.com> - 3.11.10-1
- Update to 3.11.10
Resolves: RHEL-57400
* Fri Aug 23 2024 Charalampos Stratakis <cstratak@redhat.com> - 3.11.9-7
- Security fix for CVE-2024-8088
Resolves: RHEL-55934
Resolves: RHEL-55959
* Thu Aug 15 2024 Charalampos Stratakis <cstratak@redhat.com> - 3.11.9-6
- Security fix for CVE-2024-6923
Resolves: RHEL-53089
Resolves: RHEL-53038
* Thu Jul 25 2024 Charalampos Stratakis <cstratak@redhat.com> - 3.11.9-5
- Properly propagate the optimization flags to C extensions
@ -1876,34 +1693,30 @@ Resolves: RHEL-53089
* Thu Jul 18 2024 Charalampos Stratakis <cstratak@redhat.com> - 3.11.9-3
- Security fix for CVE-2024-4032
Resolves: RHEL-44067
Resolves: RHEL-44099
* Tue Jun 11 2024 Charalampos Stratakis <cstratak@redhat.com> - 3.11.9-2
- Enable importing of hash-based .pyc files under FIPS mode
Resolves: RHEL-40783
Resolves: RHEL-40779
* Mon Apr 22 2024 Charalampos Stratakis <cstratak@redhat.com> - 3.11.9-1
- Rebase to 3.11.9
- Security fixes for CVE-2023-6597 and CVE-2024-0450
- Fix expat tests for the latest expat security release
Resolves: RHEL-33672, RHEL-33684
Resolves: RHEL-33677, RHEL-33689
* Mon Jan 22 2024 Charalampos Stratakis <cstratak@redhat.com> - 3.11.7-1
- Rebase to 3.11.7
Resolves: RHEL-21915
Resolves: RHEL-20233
* Tue Jan 09 2024 Lumír Balhar <lbalhar@redhat.com> - 3.11.5-2
- Security fix for CVE-2023-27043
Resolves: RHEL-7842
Resolves: RHEL-21325
* Thu Sep 07 2023 Charalampos Stratakis <cstratak@redhat.com> - 3.11.5-1
- Rebase to 3.11.5
- Security fixes for CVE-2023-40217 and CVE-2023-41105
Resolves: RHEL-3047, RHEL-3267
* Thu Aug 10 2023 Tomas Orsava <torsava@redhat.com> - 3.11.4-4
- Add the import_all_modules_py3_11.py file for the python3.11-rpm-macros subpackage
Resolves: rhbz#2207631
Resolves: RHEL-3045, RHEL-3269
* Wed Aug 09 2023 Petr Viktorin <pviktori@redhat.com> - 3.11.4-3
- Fix symlink handling in the fix for CVE-2023-24329
@ -1929,10 +1742,7 @@ Resolves: rhbz#2173917
* Mon Jan 30 2023 Charalampos Stratakis <cstratak@redhat.com> - 3.11.1-3
- Disable bootstrap
- Revert python3.11-rpm-macros requirement
* Mon Jan 30 2023 Charalampos Stratakis <cstratak@redhat.com> - 3.11.1-2
- Fix macros requirements
- Bump release to sync with RHEL8
* Tue Dec 13 2022 Charalampos Stratakis <cstratak@redhat.com> - 3.11.1-1
- Initial package

Loading…
Cancel
Save