parent
62390fcd99
commit
31b2ab84bc
@ -1 +1 @@
|
|||||||
SOURCES/Python-3.11.5.tar.xz
|
SOURCES/Python-3.11.7.tar.xz
|
||||||
|
@ -1 +1 @@
|
|||||||
b13ec58fa6ebf5b0f7178555c5506e135cb7d785 SOURCES/Python-3.11.5.tar.xz
|
f2534d591121f3845388fbdd6a121b96dfe305a6 SOURCES/Python-3.11.7.tar.xz
|
||||||
|
@ -0,0 +1,755 @@
|
|||||||
|
From d8b0fafb202bf884135a3f7f0ce0b086217a2da2 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 | 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 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 cfdfeb3..9522341 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 _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)
|
||||||
|
|
||||||
|
-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
|
||||||
|
+
|
||||||
|
+supports_strict_parsing = True
|
||||||
|
+
|
||||||
|
+def getaddresses(fieldvalues, *, strict=True):
|
||||||
|
+ """Return a list of (REALNAME, EMAIL) or ('','') for each fieldvalue.
|
||||||
|
+
|
||||||
|
+ When parsing fails for a fieldvalue, a 2-tuple of ('', '') is returned in
|
||||||
|
+ its place.
|
||||||
|
+
|
||||||
|
+ If strict is true, use a strict parser which rejects malformed inputs.
|
||||||
|
+ """
|
||||||
|
+
|
||||||
|
+ # If strict is true, if the resulting list of parsed addresses is greater
|
||||||
|
+ # than the number of fieldvalues in the input list, a parsing error has
|
||||||
|
+ # occurred and consequently a list containing a single empty 2-tuple [('',
|
||||||
|
+ # '')] is returned in its place. This is done to avoid invalid output.
|
||||||
|
+ #
|
||||||
|
+ # Malformed input: getaddresses(['alice@example.com <bob@example.com>'])
|
||||||
|
+ # Invalid output: [('', 'alice@example.com'), ('', 'bob@example.com')]
|
||||||
|
+ # Safe output: [('', '')]
|
||||||
|
+
|
||||||
|
+ if not strict:
|
||||||
|
+ all = COMMASPACE.join(str(v) for v in fieldvalues)
|
||||||
|
+ a = _AddressList(all)
|
||||||
|
+ return a.addresslist
|
||||||
|
+
|
||||||
|
+ fieldvalues = [str(v) for v in fieldvalues]
|
||||||
|
+ fieldvalues = _pre_parse_validation(fieldvalues)
|
||||||
|
+ addr = COMMASPACE.join(fieldvalues)
|
||||||
|
+ a = _AddressList(addr)
|
||||||
|
+ result = _post_parse_validation(a.addresslist)
|
||||||
|
+
|
||||||
|
+ # Treat output as invalid if the number of addresses is not equal to the
|
||||||
|
+ # expected number of addresses.
|
||||||
|
+ n = 0
|
||||||
|
+ for v in fieldvalues:
|
||||||
|
+ # When a comma is used in the Real Name part it is not a deliminator.
|
||||||
|
+ # So strip those out before counting the commas.
|
||||||
|
+ v = _strip_quoted_realnames(v)
|
||||||
|
+ # Expected number of addresses: 1 + number of commas
|
||||||
|
+ n += 1 + v.count(',')
|
||||||
|
+ if len(result) != n:
|
||||||
|
+ return [('', '')]
|
||||||
|
+
|
||||||
|
+ return result
|
||||||
|
+
|
||||||
|
+
|
||||||
|
+def _check_parenthesis(addr):
|
||||||
|
+ # Ignore parenthesis in quoted real names.
|
||||||
|
+ addr = _strip_quoted_realnames(addr)
|
||||||
|
+
|
||||||
|
+ opens = 0
|
||||||
|
+ for pos, ch in _iter_escaped_chars(addr):
|
||||||
|
+ if ch == '(':
|
||||||
|
+ opens += 1
|
||||||
|
+ elif ch == ')':
|
||||||
|
+ opens -= 1
|
||||||
|
+ if opens < 0:
|
||||||
|
+ return False
|
||||||
|
+ return (opens == 0)
|
||||||
|
+
|
||||||
|
+
|
||||||
|
+def _pre_parse_validation(email_header_fields):
|
||||||
|
+ accepted_values = []
|
||||||
|
+ for v in email_header_fields:
|
||||||
|
+ if not _check_parenthesis(v):
|
||||||
|
+ v = "('', '')"
|
||||||
|
+ accepted_values.append(v)
|
||||||
|
+
|
||||||
|
+ return accepted_values
|
||||||
|
+
|
||||||
|
+
|
||||||
|
+def _post_parse_validation(parsed_email_header_tuples):
|
||||||
|
+ accepted_values = []
|
||||||
|
+ # The parser would have parsed a correctly formatted domain-literal
|
||||||
|
+ # The existence of an [ after parsing indicates a parsing failure
|
||||||
|
+ for v in parsed_email_header_tuples:
|
||||||
|
+ if '[' in v[1]:
|
||||||
|
+ v = ('', '')
|
||||||
|
+ accepted_values.append(v)
|
||||||
|
+
|
||||||
|
+ return accepted_values
|
||||||
|
|
||||||
|
|
||||||
|
def _format_timetuple_and_zone(timetuple, zone):
|
||||||
|
@@ -205,16 +321,33 @@ def parsedate_to_datetime(data):
|
||||||
|
tzinfo=datetime.timezone(datetime.timedelta(seconds=tz)))
|
||||||
|
|
||||||
|
|
||||||
|
-def parseaddr(addr):
|
||||||
|
+def parseaddr(addr, *, strict=True):
|
||||||
|
"""
|
||||||
|
Parse addr into its constituent realname and email address parts.
|
||||||
|
|
||||||
|
Return a tuple of realname and email address, unless the parse fails, in
|
||||||
|
which case return a 2-tuple of ('', '').
|
||||||
|
+
|
||||||
|
+ If strict is True, use a strict parser which rejects malformed inputs.
|
||||||
|
"""
|
||||||
|
- addrs = _AddressList(addr).addresslist
|
||||||
|
- if not addrs:
|
||||||
|
- return '', ''
|
||||||
|
+ if not strict:
|
||||||
|
+ addrs = _AddressList(addr).addresslist
|
||||||
|
+ if not addrs:
|
||||||
|
+ return ('', '')
|
||||||
|
+ return addrs[0]
|
||||||
|
+
|
||||||
|
+ if isinstance(addr, list):
|
||||||
|
+ addr = addr[0]
|
||||||
|
+
|
||||||
|
+ if not isinstance(addr, str):
|
||||||
|
+ return ('', '')
|
||||||
|
+
|
||||||
|
+ addr = _pre_parse_validation([addr])[0]
|
||||||
|
+ addrs = _post_parse_validation(_AddressList(addr).addresslist)
|
||||||
|
+
|
||||||
|
+ if not addrs or len(addrs) > 1:
|
||||||
|
+ return ('', '')
|
||||||
|
+
|
||||||
|
return addrs[0]
|
||||||
|
|
||||||
|
|
||||||
|
diff --git a/Lib/test/test_email/test_email.py b/Lib/test/test_email/test_email.py
|
||||||
|
index 677f209..20b6779 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
|
||||||
|
@@ -3321,15 +3322,154 @@ 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"""
|
||||||
|
@@ -3520,6 +3660,54 @@ 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.
|
||||||
|
--
|
||||||
|
2.43.0
|
||||||
|
|
||||||
|
|
||||||
|
From 6c34f5b95da90bd494e29776c0e807af44689fae Mon Sep 17 00:00:00 2001
|
||||||
|
From: Lumir Balhar <lbalhar@redhat.com>
|
||||||
|
Date: Wed, 10 Jan 2024 08:53:53 +0100
|
||||||
|
Subject: [PATCH 2/2] Make it possible to disable strict parsing in email
|
||||||
|
module
|
||||||
|
|
||||||
|
---
|
||||||
|
Doc/library/email.utils.rst | 26 +++++++++++
|
||||||
|
Lib/email/utils.py | 54 +++++++++++++++++++++-
|
||||||
|
Lib/test/test_email/test_email.py | 74 ++++++++++++++++++++++++++++++-
|
||||||
|
3 files changed, 150 insertions(+), 4 deletions(-)
|
||||||
|
|
||||||
|
diff --git a/Doc/library/email.utils.rst b/Doc/library/email.utils.rst
|
||||||
|
index 6723dc4..c89602d 100644
|
||||||
|
--- a/Doc/library/email.utils.rst
|
||||||
|
+++ b/Doc/library/email.utils.rst
|
||||||
|
@@ -69,6 +69,19 @@ of the new API.
|
||||||
|
|
||||||
|
If *strict* is true, use a strict parser which rejects malformed inputs.
|
||||||
|
|
||||||
|
+ The default setting for *strict* is set to ``True``, but you can override
|
||||||
|
+ it by setting the environment variable ``PYTHON_EMAIL_DISABLE_STRICT_ADDR_PARSING``
|
||||||
|
+ to non-empty string.
|
||||||
|
+
|
||||||
|
+ Additionally, you can permanently set the default value for *strict* to
|
||||||
|
+ ``False`` by creating the configuration file ``/etc/python/email.cfg``
|
||||||
|
+ with the following content:
|
||||||
|
+
|
||||||
|
+ .. code-block:: ini
|
||||||
|
+
|
||||||
|
+ [email_addr_parsing]
|
||||||
|
+ PYTHON_EMAIL_DISABLE_STRICT_ADDR_PARSING = true
|
||||||
|
+
|
||||||
|
.. versionchanged:: 3.13
|
||||||
|
Add *strict* optional parameter and reject malformed inputs by default.
|
||||||
|
|
||||||
|
@@ -97,6 +110,19 @@ of the new API.
|
||||||
|
|
||||||
|
If *strict* is true, use a strict parser which rejects malformed inputs.
|
||||||
|
|
||||||
|
+ The default setting for *strict* is set to ``True``, but you can override
|
||||||
|
+ it by setting the environment variable ``PYTHON_EMAIL_DISABLE_STRICT_ADDR_PARSING``
|
||||||
|
+ to non-empty string.
|
||||||
|
+
|
||||||
|
+ Additionally, you can permanently set the default value for *strict* to
|
||||||
|
+ ``False`` by creating the configuration file ``/etc/python/email.cfg``
|
||||||
|
+ with the following content:
|
||||||
|
+
|
||||||
|
+ .. code-block:: ini
|
||||||
|
+
|
||||||
|
+ [email_addr_parsing]
|
||||||
|
+ PYTHON_EMAIL_DISABLE_STRICT_ADDR_PARSING = true
|
||||||
|
+
|
||||||
|
Here's a simple example that gets all the recipients of a message::
|
||||||
|
|
||||||
|
from email.utils import getaddresses
|
||||||
|
diff --git a/Lib/email/utils.py b/Lib/email/utils.py
|
||||||
|
index 9522341..2e30e09 100644
|
||||||
|
--- a/Lib/email/utils.py
|
||||||
|
+++ b/Lib/email/utils.py
|
||||||
|
@@ -48,6 +48,46 @@ TICK = "'"
|
||||||
|
specialsre = re.compile(r'[][\\()<>@,:;".]')
|
||||||
|
escapesre = re.compile(r'[\\"]')
|
||||||
|
|
||||||
|
+_EMAIL_CONFIG_FILE = "/etc/python/email.cfg"
|
||||||
|
+_cached_strict_addr_parsing = None
|
||||||
|
+
|
||||||
|
+
|
||||||
|
+def _use_strict_email_parsing():
|
||||||
|
+ """"Cache implementation for _cached_strict_addr_parsing"""
|
||||||
|
+ global _cached_strict_addr_parsing
|
||||||
|
+ if _cached_strict_addr_parsing is None:
|
||||||
|
+ _cached_strict_addr_parsing = _use_strict_email_parsing_impl()
|
||||||
|
+ return _cached_strict_addr_parsing
|
||||||
|
+
|
||||||
|
+
|
||||||
|
+def _use_strict_email_parsing_impl():
|
||||||
|
+ """Returns True if strict email parsing is not disabled by
|
||||||
|
+ config file or env variable.
|
||||||
|
+ """
|
||||||
|
+ disabled = bool(os.environ.get("PYTHON_EMAIL_DISABLE_STRICT_ADDR_PARSING"))
|
||||||
|
+ if disabled:
|
||||||
|
+ return False
|
||||||
|
+
|
||||||
|
+ try:
|
||||||
|
+ file = open(_EMAIL_CONFIG_FILE)
|
||||||
|
+ except FileNotFoundError:
|
||||||
|
+ pass
|
||||||
|
+ else:
|
||||||
|
+ with file:
|
||||||
|
+ import configparser
|
||||||
|
+ config = configparser.ConfigParser(
|
||||||
|
+ interpolation=None,
|
||||||
|
+ comment_prefixes=('#', ),
|
||||||
|
+
|
||||||
|
+ )
|
||||||
|
+ config.read_file(file)
|
||||||
|
+ disabled = config.getboolean('email_addr_parsing', "PYTHON_EMAIL_DISABLE_STRICT_ADDR_PARSING", fallback=None)
|
||||||
|
+
|
||||||
|
+ if disabled:
|
||||||
|
+ return False
|
||||||
|
+
|
||||||
|
+ return True
|
||||||
|
+
|
||||||
|
|
||||||
|
def _has_surrogates(s):
|
||||||
|
"""Return True if s contains surrogate-escaped binary data."""
|
||||||
|
@@ -149,7 +189,7 @@ def _strip_quoted_realnames(addr):
|
||||||
|
|
||||||
|
supports_strict_parsing = True
|
||||||
|
|
||||||
|
-def getaddresses(fieldvalues, *, strict=True):
|
||||||
|
+def getaddresses(fieldvalues, *, strict=None):
|
||||||
|
"""Return a list of (REALNAME, EMAIL) or ('','') for each fieldvalue.
|
||||||
|
|
||||||
|
When parsing fails for a fieldvalue, a 2-tuple of ('', '') is returned in
|
||||||
|
@@ -158,6 +198,11 @@ def getaddresses(fieldvalues, *, strict=True):
|
||||||
|
If strict is true, use a strict parser which rejects malformed inputs.
|
||||||
|
"""
|
||||||
|
|
||||||
|
+ # If default is used, it's True unless disabled
|
||||||
|
+ # by env variable or config file.
|
||||||
|
+ if strict == None:
|
||||||
|
+ strict = _use_strict_email_parsing()
|
||||||
|
+
|
||||||
|
# If strict is true, if the resulting list of parsed addresses is greater
|
||||||
|
# than the number of fieldvalues in the input list, a parsing error has
|
||||||
|
# occurred and consequently a list containing a single empty 2-tuple [('',
|
||||||
|
@@ -321,7 +366,7 @@ def parsedate_to_datetime(data):
|
||||||
|
tzinfo=datetime.timezone(datetime.timedelta(seconds=tz)))
|
||||||
|
|
||||||
|
|
||||||
|
-def parseaddr(addr, *, strict=True):
|
||||||
|
+def parseaddr(addr, *, strict=None):
|
||||||
|
"""
|
||||||
|
Parse addr into its constituent realname and email address parts.
|
||||||
|
|
||||||
|
@@ -330,6 +375,11 @@ def parseaddr(addr, *, strict=True):
|
||||||
|
|
||||||
|
If strict is True, use a strict parser which rejects malformed inputs.
|
||||||
|
"""
|
||||||
|
+ # If default is used, it's True unless disabled
|
||||||
|
+ # by env variable or config file.
|
||||||
|
+ if strict == None:
|
||||||
|
+ strict = _use_strict_email_parsing()
|
||||||
|
+
|
||||||
|
if not strict:
|
||||||
|
addrs = _AddressList(addr).addresslist
|
||||||
|
if not addrs:
|
||||||
|
diff --git a/Lib/test/test_email/test_email.py b/Lib/test/test_email/test_email.py
|
||||||
|
index 20b6779..d7d99f0 100644
|
||||||
|
--- a/Lib/test/test_email/test_email.py
|
||||||
|
+++ b/Lib/test/test_email/test_email.py
|
||||||
|
@@ -8,6 +8,9 @@ import base64
|
||||||
|
import unittest
|
||||||
|
import textwrap
|
||||||
|
import warnings
|
||||||
|
+import contextlib
|
||||||
|
+import tempfile
|
||||||
|
+import os
|
||||||
|
|
||||||
|
from io import StringIO, BytesIO
|
||||||
|
from itertools import chain
|
||||||
|
@@ -41,8 +44,8 @@ from email import quoprimime
|
||||||
|
from email import utils
|
||||||
|
|
||||||
|
from test import support
|
||||||
|
-from test.support import threading_helper
|
||||||
|
-from test.support.os_helper import unlink
|
||||||
|
+from test.support import threading_helper, swap_attr
|
||||||
|
+from test.support.os_helper import unlink, EnvironmentVarGuard
|
||||||
|
from test.test_email import openfile, TestEmailBase
|
||||||
|
|
||||||
|
# These imports are documented to work, but we are testing them using a
|
||||||
|
@@ -3427,6 +3430,73 @@ Foo
|
||||||
|
# Test email.utils.supports_strict_parsing attribute
|
||||||
|
self.assertEqual(email.utils.supports_strict_parsing, True)
|
||||||
|
|
||||||
|
+ def test_parsing_errors_strict_set_via_env_var(self):
|
||||||
|
+ address = 'alice@example.org )Alice('
|
||||||
|
+ empty = ('', '')
|
||||||
|
+
|
||||||
|
+ # Reset cached default value to make the function
|
||||||
|
+ # reload the config file provided below.
|
||||||
|
+ utils._cached_strict_addr_parsing = None
|
||||||
|
+
|
||||||
|
+ # Strict disabled via env variable, old behavior expected
|
||||||
|
+ with EnvironmentVarGuard() as environ:
|
||||||
|
+ environ["PYTHON_EMAIL_DISABLE_STRICT_ADDR_PARSING"] = "1"
|
||||||
|
+
|
||||||
|
+ self.assertEqual(utils.getaddresses([address]),
|
||||||
|
+ [('', 'alice@example.org'), ('', ''), ('', 'Alice')])
|
||||||
|
+ self.assertEqual(utils.parseaddr([address]), ('', address))
|
||||||
|
+
|
||||||
|
+ # Clear cache again
|
||||||
|
+ utils._cached_strict_addr_parsing = None
|
||||||
|
+
|
||||||
|
+ # Default strict=True, empty result expected
|
||||||
|
+ self.assertEqual(utils.getaddresses([address]), [empty])
|
||||||
|
+ self.assertEqual(utils.parseaddr([address]), empty)
|
||||||
|
+
|
||||||
|
+ # Clear cache again
|
||||||
|
+ utils._cached_strict_addr_parsing = None
|
||||||
|
+
|
||||||
|
+ # Empty string in env variable = strict parsing enabled (default)
|
||||||
|
+ with EnvironmentVarGuard() as environ:
|
||||||
|
+ environ["PYTHON_EMAIL_DISABLE_STRICT_ADDR_PARSING"] = ""
|
||||||
|
+
|
||||||
|
+ # Default strict=True, empty result expected
|
||||||
|
+ self.assertEqual(utils.getaddresses([address]), [empty])
|
||||||
|
+ self.assertEqual(utils.parseaddr([address]), empty)
|
||||||
|
+
|
||||||
|
+ @contextlib.contextmanager
|
||||||
|
+ def _email_strict_parsing_conf(self):
|
||||||
|
+ """Context for the given email strict parsing configured in config file"""
|
||||||
|
+ with tempfile.TemporaryDirectory() as tmpdirname:
|
||||||
|
+ filename = os.path.join(tmpdirname, 'conf.cfg')
|
||||||
|
+ with swap_attr(utils, "_EMAIL_CONFIG_FILE", filename):
|
||||||
|
+ with open(filename, 'w') as file:
|
||||||
|
+ file.write('[email_addr_parsing]\n')
|
||||||
|
+ file.write('PYTHON_EMAIL_DISABLE_STRICT_ADDR_PARSING = true')
|
||||||
|
+ utils._EMAIL_CONFIG_FILE = filename
|
||||||
|
+ yield
|
||||||
|
+
|
||||||
|
+ def test_parsing_errors_strict_disabled_via_config_file(self):
|
||||||
|
+ address = 'alice@example.org )Alice('
|
||||||
|
+ empty = ('', '')
|
||||||
|
+
|
||||||
|
+ # Reset cached default value to make the function
|
||||||
|
+ # reload the config file provided below.
|
||||||
|
+ utils._cached_strict_addr_parsing = None
|
||||||
|
+
|
||||||
|
+ # Strict disabled via config file, old results expected
|
||||||
|
+ with self._email_strict_parsing_conf():
|
||||||
|
+ self.assertEqual(utils.getaddresses([address]),
|
||||||
|
+ [('', 'alice@example.org'), ('', ''), ('', 'Alice')])
|
||||||
|
+ self.assertEqual(utils.parseaddr([address]), ('', address))
|
||||||
|
+
|
||||||
|
+ # Clear cache again
|
||||||
|
+ utils._cached_strict_addr_parsing = None
|
||||||
|
+
|
||||||
|
+ # Default strict=True, empty result expected
|
||||||
|
+ self.assertEqual(utils.getaddresses([address]), [empty])
|
||||||
|
+ self.assertEqual(utils.parseaddr([address]), empty)
|
||||||
|
+
|
||||||
|
def test_getaddresses_nasty(self):
|
||||||
|
for addresses, expected in (
|
||||||
|
(['"Sürname, Firstname" <to@example.com>'],
|
||||||
|
--
|
||||||
|
2.43.0
|
||||||
|
|
@ -0,0 +1,77 @@
|
|||||||
|
From c9364e8727ea2426519a74593ab03ebcb0da72b8 Mon Sep 17 00:00:00 2001
|
||||||
|
From: Lumir Balhar <lbalhar@redhat.com>
|
||||||
|
Date: Fri, 3 May 2024 14:17:48 +0200
|
||||||
|
Subject: [PATCH] Expect failures in tests not working properly with expat with
|
||||||
|
a fixed CVE in RHEL
|
||||||
|
|
||||||
|
---
|
||||||
|
Lib/test/test_xml_etree.py | 53 ++++++++++++++++++++++----------------
|
||||||
|
1 file changed, 31 insertions(+), 22 deletions(-)
|
||||||
|
|
||||||
|
diff --git a/Lib/test/test_xml_etree.py b/Lib/test/test_xml_etree.py
|
||||||
|
index 7c346f2..24e0bb8 100644
|
||||||
|
--- a/Lib/test/test_xml_etree.py
|
||||||
|
+++ b/Lib/test/test_xml_etree.py
|
||||||
|
@@ -1391,28 +1391,37 @@ class XMLPullParserTest(unittest.TestCase):
|
||||||
|
self.assertEqual([(action, elem.tag) for action, elem in events],
|
||||||
|
expected)
|
||||||
|
|
||||||
|
- def test_simple_xml(self):
|
||||||
|
- for chunk_size in (None, 1, 5):
|
||||||
|
- with self.subTest(chunk_size=chunk_size):
|
||||||
|
- parser = ET.XMLPullParser()
|
||||||
|
- self.assert_event_tags(parser, [])
|
||||||
|
- self._feed(parser, "<!-- comment -->\n", chunk_size)
|
||||||
|
- self.assert_event_tags(parser, [])
|
||||||
|
- self._feed(parser,
|
||||||
|
- "<root>\n <element key='value'>text</element",
|
||||||
|
- chunk_size)
|
||||||
|
- self.assert_event_tags(parser, [])
|
||||||
|
- self._feed(parser, ">\n", chunk_size)
|
||||||
|
- self.assert_event_tags(parser, [('end', 'element')])
|
||||||
|
- self._feed(parser, "<element>text</element>tail\n", chunk_size)
|
||||||
|
- self._feed(parser, "<empty-element/>\n", chunk_size)
|
||||||
|
- self.assert_event_tags(parser, [
|
||||||
|
- ('end', 'element'),
|
||||||
|
- ('end', 'empty-element'),
|
||||||
|
- ])
|
||||||
|
- self._feed(parser, "</root>\n", chunk_size)
|
||||||
|
- self.assert_event_tags(parser, [('end', 'root')])
|
||||||
|
- self.assertIsNone(parser.close())
|
||||||
|
+ def test_simple_xml(self, chunk_size=None):
|
||||||
|
+ parser = ET.XMLPullParser()
|
||||||
|
+ self.assert_event_tags(parser, [])
|
||||||
|
+ self._feed(parser, "<!-- comment -->\n", chunk_size)
|
||||||
|
+ self.assert_event_tags(parser, [])
|
||||||
|
+ self._feed(parser,
|
||||||
|
+ "<root>\n <element key='value'>text</element",
|
||||||
|
+ chunk_size)
|
||||||
|
+ self.assert_event_tags(parser, [])
|
||||||
|
+ self._feed(parser, ">\n", chunk_size)
|
||||||
|
+ self.assert_event_tags(parser, [('end', 'element')])
|
||||||
|
+ self._feed(parser, "<element>text</element>tail\n", chunk_size)
|
||||||
|
+ self._feed(parser, "<empty-element/>\n", chunk_size)
|
||||||
|
+ self.assert_event_tags(parser, [
|
||||||
|
+ ('end', 'element'),
|
||||||
|
+ ('end', 'empty-element'),
|
||||||
|
+ ])
|
||||||
|
+ self._feed(parser, "</root>\n", chunk_size)
|
||||||
|
+ self.assert_event_tags(parser, [('end', 'root')])
|
||||||
|
+ self.assertIsNone(parser.close())
|
||||||
|
+
|
||||||
|
+ @unittest.expectedFailure
|
||||||
|
+ def test_simple_xml_chunk_1(self):
|
||||||
|
+ self.test_simple_xml(chunk_size=1)
|
||||||
|
+
|
||||||
|
+ @unittest.expectedFailure
|
||||||
|
+ def test_simple_xml_chunk_5(self):
|
||||||
|
+ self.test_simple_xml(chunk_size=5)
|
||||||
|
+
|
||||||
|
+ def test_simple_xml_chunk_22(self):
|
||||||
|
+ self.test_simple_xml(chunk_size=22)
|
||||||
|
|
||||||
|
def test_feed_while_iterating(self):
|
||||||
|
parser = ET.XMLPullParser()
|
||||||
|
--
|
||||||
|
2.45.0
|
||||||
|
|
@ -0,0 +1,215 @@
|
|||||||
|
From 5585334d772b253a01a6730e8202ffb1607c3d25 Mon Sep 17 00:00:00 2001
|
||||||
|
From: Serhiy Storchaka <storchaka@gmail.com>
|
||||||
|
Date: Thu, 7 Dec 2023 18:37:10 +0200
|
||||||
|
Subject: [PATCH] [3.11] gh-91133: tempfile.TemporaryDirectory: fix symlink bug
|
||||||
|
in cleanup (GH-99930) (GH-112839)
|
||||||
|
MIME-Version: 1.0
|
||||||
|
Content-Type: text/plain; charset=UTF-8
|
||||||
|
Content-Transfer-Encoding: 8bit
|
||||||
|
|
||||||
|
(cherry picked from commit 81c16cd94ec38d61aa478b9a452436dc3b1b524d)
|
||||||
|
|
||||||
|
Co-authored-by: Søren Løvborg <sorenl@unity3d.com>
|
||||||
|
---
|
||||||
|
Lib/tempfile.py | 27 +++--
|
||||||
|
Lib/test/test_tempfile.py | 111 +++++++++++++++++-
|
||||||
|
...2-12-01-16-57-44.gh-issue-91133.LKMVCV.rst | 2 +
|
||||||
|
3 files changed, 125 insertions(+), 15 deletions(-)
|
||||||
|
create mode 100644 Misc/NEWS.d/next/Library/2022-12-01-16-57-44.gh-issue-91133.LKMVCV.rst
|
||||||
|
|
||||||
|
diff --git a/Lib/tempfile.py b/Lib/tempfile.py
|
||||||
|
index aace11fa7b19b9..f59a63a7b45b36 100644
|
||||||
|
--- a/Lib/tempfile.py
|
||||||
|
+++ b/Lib/tempfile.py
|
||||||
|
@@ -270,6 +270,22 @@ def _mkstemp_inner(dir, pre, suf, flags, output_type):
|
||||||
|
raise FileExistsError(_errno.EEXIST,
|
||||||
|
"No usable temporary file name found")
|
||||||
|
|
||||||
|
+def _dont_follow_symlinks(func, path, *args):
|
||||||
|
+ # Pass follow_symlinks=False, unless not supported on this platform.
|
||||||
|
+ if func in _os.supports_follow_symlinks:
|
||||||
|
+ func(path, *args, follow_symlinks=False)
|
||||||
|
+ elif _os.name == 'nt' or not _os.path.islink(path):
|
||||||
|
+ func(path, *args)
|
||||||
|
+
|
||||||
|
+def _resetperms(path):
|
||||||
|
+ try:
|
||||||
|
+ chflags = _os.chflags
|
||||||
|
+ except AttributeError:
|
||||||
|
+ pass
|
||||||
|
+ else:
|
||||||
|
+ _dont_follow_symlinks(chflags, path, 0)
|
||||||
|
+ _dont_follow_symlinks(_os.chmod, path, 0o700)
|
||||||
|
+
|
||||||
|
|
||||||
|
# User visible interfaces.
|
||||||
|
|
||||||
|
@@ -863,17 +879,10 @@ def __init__(self, suffix=None, prefix=None, dir=None,
|
||||||
|
def _rmtree(cls, name, ignore_errors=False):
|
||||||
|
def onerror(func, path, exc_info):
|
||||||
|
if issubclass(exc_info[0], PermissionError):
|
||||||
|
- def resetperms(path):
|
||||||
|
- try:
|
||||||
|
- _os.chflags(path, 0)
|
||||||
|
- except AttributeError:
|
||||||
|
- pass
|
||||||
|
- _os.chmod(path, 0o700)
|
||||||
|
-
|
||||||
|
try:
|
||||||
|
if path != name:
|
||||||
|
- resetperms(_os.path.dirname(path))
|
||||||
|
- resetperms(path)
|
||||||
|
+ _resetperms(_os.path.dirname(path))
|
||||||
|
+ _resetperms(path)
|
||||||
|
|
||||||
|
try:
|
||||||
|
_os.unlink(path)
|
||||||
|
diff --git a/Lib/test/test_tempfile.py b/Lib/test/test_tempfile.py
|
||||||
|
index 1242ec7e3cc9a1..675edc8de9cca5 100644
|
||||||
|
--- a/Lib/test/test_tempfile.py
|
||||||
|
+++ b/Lib/test/test_tempfile.py
|
||||||
|
@@ -1565,6 +1565,103 @@ def test_cleanup_with_symlink_to_a_directory(self):
|
||||||
|
"were deleted")
|
||||||
|
d2.cleanup()
|
||||||
|
|
||||||
|
+ @os_helper.skip_unless_symlink
|
||||||
|
+ def test_cleanup_with_symlink_modes(self):
|
||||||
|
+ # cleanup() should not follow symlinks when fixing mode bits (#91133)
|
||||||
|
+ with self.do_create(recurse=0) as d2:
|
||||||
|
+ file1 = os.path.join(d2, 'file1')
|
||||||
|
+ open(file1, 'wb').close()
|
||||||
|
+ dir1 = os.path.join(d2, 'dir1')
|
||||||
|
+ os.mkdir(dir1)
|
||||||
|
+ for mode in range(8):
|
||||||
|
+ mode <<= 6
|
||||||
|
+ with self.subTest(mode=format(mode, '03o')):
|
||||||
|
+ def test(target, target_is_directory):
|
||||||
|
+ d1 = self.do_create(recurse=0)
|
||||||
|
+ symlink = os.path.join(d1.name, 'symlink')
|
||||||
|
+ os.symlink(target, symlink,
|
||||||
|
+ target_is_directory=target_is_directory)
|
||||||
|
+ try:
|
||||||
|
+ os.chmod(symlink, mode, follow_symlinks=False)
|
||||||
|
+ except NotImplementedError:
|
||||||
|
+ pass
|
||||||
|
+ try:
|
||||||
|
+ os.chmod(symlink, mode)
|
||||||
|
+ except FileNotFoundError:
|
||||||
|
+ pass
|
||||||
|
+ os.chmod(d1.name, mode)
|
||||||
|
+ d1.cleanup()
|
||||||
|
+ self.assertFalse(os.path.exists(d1.name))
|
||||||
|
+
|
||||||
|
+ with self.subTest('nonexisting file'):
|
||||||
|
+ test('nonexisting', target_is_directory=False)
|
||||||
|
+ with self.subTest('nonexisting dir'):
|
||||||
|
+ test('nonexisting', target_is_directory=True)
|
||||||
|
+
|
||||||
|
+ with self.subTest('existing file'):
|
||||||
|
+ os.chmod(file1, mode)
|
||||||
|
+ old_mode = os.stat(file1).st_mode
|
||||||
|
+ test(file1, target_is_directory=False)
|
||||||
|
+ new_mode = os.stat(file1).st_mode
|
||||||
|
+ self.assertEqual(new_mode, old_mode,
|
||||||
|
+ '%03o != %03o' % (new_mode, old_mode))
|
||||||
|
+
|
||||||
|
+ with self.subTest('existing dir'):
|
||||||
|
+ os.chmod(dir1, mode)
|
||||||
|
+ old_mode = os.stat(dir1).st_mode
|
||||||
|
+ test(dir1, target_is_directory=True)
|
||||||
|
+ new_mode = os.stat(dir1).st_mode
|
||||||
|
+ self.assertEqual(new_mode, old_mode,
|
||||||
|
+ '%03o != %03o' % (new_mode, old_mode))
|
||||||
|
+
|
||||||
|
+ @unittest.skipUnless(hasattr(os, 'chflags'), 'requires os.chflags')
|
||||||
|
+ @os_helper.skip_unless_symlink
|
||||||
|
+ def test_cleanup_with_symlink_flags(self):
|
||||||
|
+ # cleanup() should not follow symlinks when fixing flags (#91133)
|
||||||
|
+ flags = stat.UF_IMMUTABLE | stat.UF_NOUNLINK
|
||||||
|
+ self.check_flags(flags)
|
||||||
|
+
|
||||||
|
+ with self.do_create(recurse=0) as d2:
|
||||||
|
+ file1 = os.path.join(d2, 'file1')
|
||||||
|
+ open(file1, 'wb').close()
|
||||||
|
+ dir1 = os.path.join(d2, 'dir1')
|
||||||
|
+ os.mkdir(dir1)
|
||||||
|
+ def test(target, target_is_directory):
|
||||||
|
+ d1 = self.do_create(recurse=0)
|
||||||
|
+ symlink = os.path.join(d1.name, 'symlink')
|
||||||
|
+ os.symlink(target, symlink,
|
||||||
|
+ target_is_directory=target_is_directory)
|
||||||
|
+ try:
|
||||||
|
+ os.chflags(symlink, flags, follow_symlinks=False)
|
||||||
|
+ except NotImplementedError:
|
||||||
|
+ pass
|
||||||
|
+ try:
|
||||||
|
+ os.chflags(symlink, flags)
|
||||||
|
+ except FileNotFoundError:
|
||||||
|
+ pass
|
||||||
|
+ os.chflags(d1.name, flags)
|
||||||
|
+ d1.cleanup()
|
||||||
|
+ self.assertFalse(os.path.exists(d1.name))
|
||||||
|
+
|
||||||
|
+ with self.subTest('nonexisting file'):
|
||||||
|
+ test('nonexisting', target_is_directory=False)
|
||||||
|
+ with self.subTest('nonexisting dir'):
|
||||||
|
+ test('nonexisting', target_is_directory=True)
|
||||||
|
+
|
||||||
|
+ with self.subTest('existing file'):
|
||||||
|
+ os.chflags(file1, flags)
|
||||||
|
+ old_flags = os.stat(file1).st_flags
|
||||||
|
+ test(file1, target_is_directory=False)
|
||||||
|
+ new_flags = os.stat(file1).st_flags
|
||||||
|
+ self.assertEqual(new_flags, old_flags)
|
||||||
|
+
|
||||||
|
+ with self.subTest('existing dir'):
|
||||||
|
+ os.chflags(dir1, flags)
|
||||||
|
+ old_flags = os.stat(dir1).st_flags
|
||||||
|
+ test(dir1, target_is_directory=True)
|
||||||
|
+ new_flags = os.stat(dir1).st_flags
|
||||||
|
+ self.assertEqual(new_flags, old_flags)
|
||||||
|
+
|
||||||
|
@support.cpython_only
|
||||||
|
def test_del_on_collection(self):
|
||||||
|
# A TemporaryDirectory is deleted when garbage collected
|
||||||
|
@@ -1737,10 +1834,7 @@ def test_modes(self):
|
||||||
|
d.cleanup()
|
||||||
|
self.assertFalse(os.path.exists(d.name))
|
||||||
|
|
||||||
|
- @unittest.skipUnless(hasattr(os, 'chflags'), 'requires os.chflags')
|
||||||
|
- def test_flags(self):
|
||||||
|
- flags = stat.UF_IMMUTABLE | stat.UF_NOUNLINK
|
||||||
|
-
|
||||||
|
+ def check_flags(self, flags):
|
||||||
|
# skip the test if these flags are not supported (ex: FreeBSD 13)
|
||||||
|
filename = os_helper.TESTFN
|
||||||
|
try:
|
||||||
|
@@ -1749,13 +1843,18 @@ def test_flags(self):
|
||||||
|
os.chflags(filename, flags)
|
||||||
|
except OSError as exc:
|
||||||
|
# "OSError: [Errno 45] Operation not supported"
|
||||||
|
- self.skipTest(f"chflags() doesn't support "
|
||||||
|
- f"UF_IMMUTABLE|UF_NOUNLINK: {exc}")
|
||||||
|
+ self.skipTest(f"chflags() doesn't support flags "
|
||||||
|
+ f"{flags:#b}: {exc}")
|
||||||
|
else:
|
||||||
|
os.chflags(filename, 0)
|
||||||
|
finally:
|
||||||
|
os_helper.unlink(filename)
|
||||||
|
|
||||||
|
+ @unittest.skipUnless(hasattr(os, 'chflags'), 'requires os.chflags')
|
||||||
|
+ def test_flags(self):
|
||||||
|
+ flags = stat.UF_IMMUTABLE | stat.UF_NOUNLINK
|
||||||
|
+ self.check_flags(flags)
|
||||||
|
+
|
||||||
|
d = self.do_create(recurse=3, dirs=2, files=2)
|
||||||
|
with d:
|
||||||
|
# Change files and directories flags recursively.
|
||||||
|
diff --git a/Misc/NEWS.d/next/Library/2022-12-01-16-57-44.gh-issue-91133.LKMVCV.rst b/Misc/NEWS.d/next/Library/2022-12-01-16-57-44.gh-issue-91133.LKMVCV.rst
|
||||||
|
new file mode 100644
|
||||||
|
index 00000000000000..7991048fc48e03
|
||||||
|
--- /dev/null
|
||||||
|
+++ b/Misc/NEWS.d/next/Library/2022-12-01-16-57-44.gh-issue-91133.LKMVCV.rst
|
||||||
|
@@ -0,0 +1,2 @@
|
||||||
|
+Fix a bug in :class:`tempfile.TemporaryDirectory` cleanup, which now no longer
|
||||||
|
+dereferences symlinks when working around file system permission errors.
|
@ -1,16 +0,0 @@
|
|||||||
-----BEGIN PGP SIGNATURE-----
|
|
||||||
|
|
||||||
iQIzBAABCAAdFiEEz9yiRbEEPPKl+Xhl/+h0BBaL2EcFAmTnS9sACgkQ/+h0BBaL
|
|
||||||
2EeG8g//Q6EC79SSFl4BPb064d8X1q8agfLN+D07N6ULsaOL1baOClLbMxiCgquQ
|
|
||||||
R1CVzEXc0osL25Xw/7rTIBO0tCSS2yNcQ3GMuetBO4wfofDvs9V2ydaVQdrIHEQm
|
|
||||||
OTOveioF9TOaQ/zozi9Hecl4RY289kCD64sWNkwPYBJzO9KQD/UGRS/b5a4CGKyP
|
|
||||||
GSQEFdfevYsuLxLtwNh1z8af1LKRGhuWoZOBhDgpz4foH4EQdz80sssXzm2vG3tS
|
|
||||||
hAeniPphjZyRfl8kC1C86M/hH08S3h4bf/LF/OQ0OYUrwOquqOsLlz03XzJ+COGK
|
|
||||||
nBa/CGsFrxeby2oI/XF8YZrFzt9LKyWYc2p+AIU+u2EnYwOmAkrE4QaczqOV8ldD
|
|
||||||
UvfZLTeMVG/Q6JGkNS/OyM3SZoVKDdGJlg5yVAQtbQjdsB5QjVDcysLhhZ+qnuJv
|
|
||||||
pnQ6anbbX5r4X4ji/2Uar5cwO/jf7QenTKLtgGY67Q2oRE20w6F5rbYHEdO4a4MM
|
|
||||||
OkI/0pUaU5MGRJfowwtcD5AbWPKo1XXqw2UY8p+biEaVQOj+kWhoB8YA5Qz1utHJ
|
|
||||||
GiPP69oDIjfn3sPMxB/C1pBdB/m3i8za58b+G3aYtAWWP1q0abaHqPusACotvxPp
|
|
||||||
3IvB3ryLlTyUYqqTiDp9wgYh2Nr+a9b6i6yW0ptcdycnzDWC1/E=
|
|
||||||
=Lzjg
|
|
||||||
-----END PGP SIGNATURE-----
|
|
@ -0,0 +1,16 @@
|
|||||||
|
-----BEGIN PGP SIGNATURE-----
|
||||||
|
|
||||||
|
iQIzBAABCAAdFiEEz9yiRbEEPPKl+Xhl/+h0BBaL2EcFAmVuFigACgkQ/+h0BBaL
|
||||||
|
2EeHPg/+LU5xs2ZDrQogDcH+A1v8RyursiggypdM5hXTrsFsTCIk4iekcI9xkhG1
|
||||||
|
ltNX4UuCe5PUEbTgtaWP0ncXARrUnPCoQaQ1sHVDTYoHegancsk+sXZc1JM7qr0p
|
||||||
|
Y4Ig6mKjuHFMXCInQSI2GaH4t5r4Z1jGk/PGrecIHOPJgqfA/6Z3TBF5N+y3jEvS
|
||||||
|
2QazMB298q4RDhh9m3REe8LwFPHDlfw9eRohv0MB8xygg9KtxhLZrN7gLBQZvKGD
|
||||||
|
ihNw6EgJj5OZ0dvwKCCXnlZuwknuJW7vAOPHhYeenPdVdYCGoRSyN7JdD07L+5AG
|
||||||
|
O14l2rqZrz5Eu28by+kAUrcPYAfAXekw1PmtT3HSd9U/nqnUiTkkJcjyGG/e3cjJ
|
||||||
|
sUDKMNCSBq0G7j5DB3bB6VHkZjVuz+T+iR5QdfJ4kI2pYSuE/rUj1rhkUXApYsHl
|
||||||
|
7Wff0QbOW6QT1wCtQcMpJSzkTDVJVYxiqrko/ihlOhphDHYLdOIGOrxWAUwc06x/
|
||||||
|
BhJD6tM1kEVZvifoJp1OsNwDzZ/Ku6CUs05E1vWxdeNVeANyKAgCZ5hOVmhnv866
|
||||||
|
11zfgo/znRsMzMIyJuy0bhO0C6omVLzzfhipAbZM2jDorn37xxV0v/I0pceNtLrp
|
||||||
|
YR7Tjs7+Ihe6/oItjW53j9T7ANdgQ1RVDg98lKlPFNL+hxfctwY=
|
||||||
|
=0Pkd
|
||||||
|
-----END PGP SIGNATURE-----
|
Loading…
Reference in new issue