Compare commits
No commits in common. 'c9-beta' and 'i9c' have entirely different histories.
@ -0,0 +1,88 @@
|
||||
From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
|
||||
From: Serhiy Storchaka <storchaka@gmail.com>
|
||||
Date: Sun, 11 Feb 2024 12:08:39 +0200
|
||||
Subject: [PATCH] 00422: gh-115133: Fix tests for XMLPullParser with Expat
|
||||
2.6.0
|
||||
|
||||
Feeding the parser by too small chunks defers parsing to prevent
|
||||
CVE-2023-52425. Future versions of Expat may be more reactive.
|
||||
|
||||
(cherry picked from commit 4a08e7b3431cd32a0daf22a33421cd3035343dc4)
|
||||
---
|
||||
Lib/test/test_xml_etree.py | 58 ++++++++++++-------
|
||||
...-02-08-14-21-28.gh-issue-115133.ycl4ko.rst | 2 +
|
||||
2 files changed, 38 insertions(+), 22 deletions(-)
|
||||
create mode 100644 Misc/NEWS.d/next/Library/2024-02-08-14-21-28.gh-issue-115133.ycl4ko.rst
|
||||
|
||||
diff --git a/Lib/test/test_xml_etree.py b/Lib/test/test_xml_etree.py
|
||||
index b50898f1d1..6fb888cb21 100644
|
||||
--- a/Lib/test/test_xml_etree.py
|
||||
+++ b/Lib/test/test_xml_etree.py
|
||||
@@ -1400,28 +1400,37 @@ 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()
|
||||
diff --git a/Misc/NEWS.d/next/Library/2024-02-08-14-21-28.gh-issue-115133.ycl4ko.rst b/Misc/NEWS.d/next/Library/2024-02-08-14-21-28.gh-issue-115133.ycl4ko.rst
|
||||
new file mode 100644
|
||||
index 0000000000..6f1015235c
|
||||
--- /dev/null
|
||||
+++ b/Misc/NEWS.d/next/Library/2024-02-08-14-21-28.gh-issue-115133.ycl4ko.rst
|
||||
@@ -0,0 +1,2 @@
|
||||
+Fix tests for :class:`~xml.etree.ElementTree.XMLPullParser` with Expat
|
||||
+2.6.0.
|
||||
@ -0,0 +1,345 @@
|
||||
From 7a25b2f511054dd2011308275bb24e914e1977af Mon Sep 17 00:00:00 2001
|
||||
From: Petr Viktorin <encukou@gmail.com>
|
||||
Date: Tue, 6 Aug 2024 19:07:19 +0200
|
||||
Subject: [PATCH] gh-121650: Encode newlines in headers, and verify headers are
|
||||
sound (GH-122233) (#122599)
|
||||
|
||||
* gh-121650: Encode newlines in headers, and verify headers are sound (GH-122233)
|
||||
|
||||
- Encode header parts that contain newlines
|
||||
|
||||
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.
|
||||
|
||||
- Verify that email headers are well-formed
|
||||
|
||||
This should fail for custom fold() implementations that aren't careful
|
||||
about newlines.
|
||||
|
||||
Co-authored-by: Bas Bloemsaat <bas@bloemsaat.org>
|
||||
Co-authored-by: Serhiy Storchaka <storchaka@gmail.com>
|
||||
(cherry picked from commit 097633981879b3c9de9a1dd120d3aa585ecc2384)
|
||||
|
||||
* Document changes as made in 3.12.5
|
||||
---
|
||||
Doc/library/email.errors.rst | 7 +++
|
||||
Doc/library/email.policy.rst | 18 ++++++
|
||||
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 ++
|
||||
9 files changed, 151 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 56aea65..27b0481 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 fd47dd0..6ec6e4d 100644
|
||||
--- a/Doc/library/email.policy.rst
|
||||
+++ b/Doc/library/email.policy.rst
|
||||
@@ -230,6 +230,24 @@ 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:: 3.12.5
|
||||
+
|
||||
+
|
||||
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/Lib/email/_header_value_parser.py b/Lib/email/_header_value_parser.py
|
||||
index 0d6bd81..362edc5 100644
|
||||
--- a/Lib/email/_header_value_parser.py
|
||||
+++ b/Lib/email/_header_value_parser.py
|
||||
@@ -92,6 +92,8 @@ TOKEN_ENDS = TSPECIALS | WSP
|
||||
ASPECIALS = TSPECIALS | set("*'%")
|
||||
ATTRIBUTE_ENDS = ASPECIALS | WSP
|
||||
EXTENDED_ATTRIBUTE_ENDS = ATTRIBUTE_ENDS - set('%')
|
||||
+NLSET = {'\n', '\r'}
|
||||
+SPECIALSNL = SPECIALS | NLSET
|
||||
|
||||
def quote_string(value):
|
||||
return '"'+str(value).replace('\\', '\\\\').replace('"', r'\"')+'"'
|
||||
@@ -2776,9 +2778,13 @@ 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 c9cbadd..d1f4821 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 3ad0056..02aa5ec 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 7ccbe10..ea87ad2 100644
|
||||
--- a/Lib/email/generator.py
|
||||
+++ b/Lib/email/generator.py
|
||||
@@ -14,12 +14,14 @@ import random
|
||||
from copy import deepcopy
|
||||
from io import StringIO, BytesIO
|
||||
from email.utils import _has_surrogates
|
||||
+from email.errors import HeaderWriteError
|
||||
|
||||
UNDERSCORE = '_'
|
||||
NL = '\n' # XXX: no longer used by the code below.
|
||||
|
||||
NLCRE = re.compile(r'\r\n|\r|\n')
|
||||
fcre = re.compile(r'^From ', re.MULTILINE)
|
||||
+NEWLINE_WITHOUT_FWSP = re.compile(r'\r\n[^ \t]|\r[^ \n\t]|\n[^ \t]')
|
||||
|
||||
|
||||
class Generator:
|
||||
@@ -222,7 +224,16 @@ class Generator:
|
||||
|
||||
def _write_headers(self, msg):
|
||||
for h, v in msg.raw_items():
|
||||
- self.write(self.policy.fold(h, v))
|
||||
+ folded = self.policy.fold(h, v)
|
||||
+ if self.policy.verify_generated_headers:
|
||||
+ linesep = self.policy.linesep
|
||||
+ if not folded.endswith(self.policy.linesep):
|
||||
+ raise HeaderWriteError(
|
||||
+ f'folded header does not end with {linesep!r}: {folded!r}')
|
||||
+ if NEWLINE_WITHOUT_FWSP.search(folded.removesuffix(linesep)):
|
||||
+ raise HeaderWriteError(
|
||||
+ f'folded header contains newline: {folded!r}')
|
||||
+ self.write(folded)
|
||||
# A blank line always separates headers from body
|
||||
self.write(self._NL)
|
||||
|
||||
diff --git a/Lib/test/test_email/test_generator.py b/Lib/test/test_email/test_generator.py
|
||||
index 89e7ede..d29400f 100644
|
||||
--- a/Lib/test/test_email/test_generator.py
|
||||
+++ b/Lib/test/test_email/test_generator.py
|
||||
@@ -6,6 +6,7 @@ from email.message import EmailMessage
|
||||
from email.generator import Generator, BytesGenerator
|
||||
from email.headerregistry import Address
|
||||
from email import policy
|
||||
+import email.errors
|
||||
from test.test_email import TestEmailBase, parameterize
|
||||
|
||||
|
||||
@@ -216,6 +217,44 @@ class TestGeneratorBase:
|
||||
g.flatten(msg)
|
||||
self.assertEqual(s.getvalue(), self.typ(expected))
|
||||
|
||||
+ def test_keep_encoded_newlines(self):
|
||||
+ msg = self.msgmaker(self.typ(textwrap.dedent("""\
|
||||
+ To: nobody
|
||||
+ Subject: Bad subject=?UTF-8?Q?=0A?=Bcc: injection@example.com
|
||||
+
|
||||
+ None
|
||||
+ """)))
|
||||
+ expected = textwrap.dedent("""\
|
||||
+ To: nobody
|
||||
+ Subject: Bad subject=?UTF-8?Q?=0A?=Bcc: injection@example.com
|
||||
+
|
||||
+ None
|
||||
+ """)
|
||||
+ s = self.ioclass()
|
||||
+ g = self.genclass(s, policy=self.policy.clone(max_line_length=80))
|
||||
+ g.flatten(msg)
|
||||
+ self.assertEqual(s.getvalue(), self.typ(expected))
|
||||
+
|
||||
+ def test_keep_long_encoded_newlines(self):
|
||||
+ msg = self.msgmaker(self.typ(textwrap.dedent("""\
|
||||
+ To: nobody
|
||||
+ Subject: Bad subject=?UTF-8?Q?=0A?=Bcc: injection@example.com
|
||||
+
|
||||
+ None
|
||||
+ """)))
|
||||
+ expected = textwrap.dedent("""\
|
||||
+ To: nobody
|
||||
+ Subject: Bad subject
|
||||
+ =?utf-8?q?=0A?=Bcc:
|
||||
+ injection@example.com
|
||||
+
|
||||
+ None
|
||||
+ """)
|
||||
+ s = self.ioclass()
|
||||
+ g = self.genclass(s, policy=self.policy.clone(max_line_length=30))
|
||||
+ g.flatten(msg)
|
||||
+ self.assertEqual(s.getvalue(), self.typ(expected))
|
||||
+
|
||||
|
||||
class TestGenerator(TestGeneratorBase, TestEmailBase):
|
||||
|
||||
@@ -224,6 +263,29 @@ class TestGenerator(TestGeneratorBase, TestEmailBase):
|
||||
ioclass = io.StringIO
|
||||
typ = str
|
||||
|
||||
+ def test_verify_generated_headers(self):
|
||||
+ """gh-121650: by default the generator prevents header injection"""
|
||||
+ class LiteralHeader(str):
|
||||
+ name = 'Header'
|
||||
+ def fold(self, **kwargs):
|
||||
+ return self
|
||||
+
|
||||
+ for text in (
|
||||
+ 'Value\r\nBad Injection\r\n',
|
||||
+ 'NoNewLine'
|
||||
+ ):
|
||||
+ with self.subTest(text=text):
|
||||
+ message = message_from_string(
|
||||
+ "Header: Value\r\n\r\nBody",
|
||||
+ policy=self.policy,
|
||||
+ )
|
||||
+
|
||||
+ del message['Header']
|
||||
+ message['Header'] = LiteralHeader(text)
|
||||
+
|
||||
+ with self.assertRaises(email.errors.HeaderWriteError):
|
||||
+ message.as_string()
|
||||
+
|
||||
|
||||
class TestBytesGenerator(TestGeneratorBase, TestEmailBase):
|
||||
|
||||
diff --git a/Lib/test/test_email/test_policy.py b/Lib/test/test_email/test_policy.py
|
||||
index e87c275..ff1ddf7 100644
|
||||
--- a/Lib/test/test_email/test_policy.py
|
||||
+++ b/Lib/test/test_email/test_policy.py
|
||||
@@ -26,6 +26,7 @@ class PolicyAPITests(unittest.TestCase):
|
||||
'raise_on_defect': False,
|
||||
'mangle_from_': True,
|
||||
'message_factory': None,
|
||||
+ 'verify_generated_headers': True,
|
||||
}
|
||||
# These default values are the ones set on email.policy.default.
|
||||
# If any of these defaults change, the docs must be updated.
|
||||
@@ -277,6 +278,31 @@ class PolicyAPITests(unittest.TestCase):
|
||||
with self.assertRaises(email.errors.HeaderParseError):
|
||||
policy.fold("Subject", subject)
|
||||
|
||||
+ def test_verify_generated_headers(self):
|
||||
+ """Turning protection off allows header injection"""
|
||||
+ policy = email.policy.default.clone(verify_generated_headers=False)
|
||||
+ for text in (
|
||||
+ 'Header: Value\r\nBad: Injection\r\n',
|
||||
+ 'Header: NoNewLine'
|
||||
+ ):
|
||||
+ with self.subTest(text=text):
|
||||
+ message = email.message_from_string(
|
||||
+ "Header: Value\r\n\r\nBody",
|
||||
+ policy=policy,
|
||||
+ )
|
||||
+ class LiteralHeader(str):
|
||||
+ name = 'Header'
|
||||
+ def fold(self, **kwargs):
|
||||
+ return self
|
||||
+
|
||||
+ del message['Header']
|
||||
+ message['Header'] = LiteralHeader(text)
|
||||
+
|
||||
+ self.assertEqual(
|
||||
+ message.as_string(),
|
||||
+ f"{text}\nBody",
|
||||
+ )
|
||||
+
|
||||
# XXX: Need subclassing tests.
|
||||
# For adding subclassed objects, make sure the usual rules apply (subclass
|
||||
# wins), but that the order still works (right overrides left).
|
||||
diff --git a/Misc/NEWS.d/next/Library/2024-07-27-16-10-41.gh-issue-121650.nf6oc9.rst b/Misc/NEWS.d/next/Library/2024-07-27-16-10-41.gh-issue-121650.nf6oc9.rst
|
||||
new file mode 100644
|
||||
index 0000000..83dd28d
|
||||
--- /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`.)
|
||||
--
|
||||
2.45.2
|
||||
|
||||
@ -0,0 +1,121 @@
|
||||
From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
|
||||
From: "Miss Islington (bot)"
|
||||
<31488909+miss-islington@users.noreply.github.com>
|
||||
Date: Mon, 12 Aug 2024 02:35:17 +0200
|
||||
Subject: [PATCH] 00436: [CVE-2024-8088] gh-122905: Sanitize names in
|
||||
zipfile.Path.
|
||||
|
||||
---
|
||||
Lib/test/test_zipfile/_path/test_path.py | 17 +++++
|
||||
Lib/zipfile/_path/__init__.py | 64 ++++++++++++++++++-
|
||||
...-08-11-14-08-04.gh-issue-122905.7tDsxA.rst | 1 +
|
||||
3 files changed, 81 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/_path/test_path.py b/Lib/test/test_zipfile/_path/test_path.py
|
||||
index 06d5aab69b..90885dbbe3 100644
|
||||
--- a/Lib/test/test_zipfile/_path/test_path.py
|
||||
+++ b/Lib/test/test_zipfile/_path/test_path.py
|
||||
@@ -577,3 +577,20 @@ def test_getinfo_missing(self, alpharep):
|
||||
zipfile.Path(alpharep)
|
||||
with self.assertRaises(KeyError):
|
||||
alpharep.getinfo('does-not-exist')
|
||||
+
|
||||
+ 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',
|
||||
+ ]
|
||||
diff --git a/Lib/zipfile/_path/__init__.py b/Lib/zipfile/_path/__init__.py
|
||||
index 78c413563b..42f9fded21 100644
|
||||
--- a/Lib/zipfile/_path/__init__.py
|
||||
+++ b/Lib/zipfile/_path/__init__.py
|
||||
@@ -83,7 +83,69 @@ def __setstate__(self, state):
|
||||
super().__init__(*args, **kwargs)
|
||||
|
||||
|
||||
-class CompleteDirs(InitializedState, zipfile.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(InitializedState, SanitizedNames, zipfile.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.
|
||||
Loading…
Reference in new issue