Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
12 changes: 12 additions & 0 deletions debian/changelog
Original file line number Diff line number Diff line change
@@ -1,3 +1,15 @@
python3.12 (3.12.11-0deepin4) unstable; urgency=medium

* Fix: Documentation doesn't generate with docutils >= 0.22

-- lichenggang <lichenggang@deepin.org> Thu, 29 Jan 2026 15:04:07 +0800

python3.12 (3.12.11-0deepin3) unstable; urgency=medium

* Fix: CVE-2025-13836 CVE-2025-6069 CVE-2025-6075 CVE-2025-8194 CVE-2025-8291

-- lichenggang <lichenggang@deepin.org> Wed, 28 Jan 2026 15:37:16 +0800

python3.12 (3.12.11-0deepin2) unstable; urgency=medium

* feat: add sw64 support.
Expand Down
140 changes: 140 additions & 0 deletions debian/patches/CVE-2025-13836.patch
Original file line number Diff line number Diff line change
@@ -0,0 +1,140 @@
From 03336d7373be3eb6dcdd94a075089c417dda5df1 Mon Sep 17 00:00:00 2001
From: Serhiy Storchaka <storchaka@gmail.com>
Date: Mon, 1 Dec 2025 17:26:07 +0200
Subject: [PATCH] gh-119451: Fix a potential denial of service in http.client
(GH-119454)

Reading the whole body of the HTTP response could cause OOM if
the Content-Length value is too large even if the server does not send
a large amount of data. Now the HTTP client reads large data by chunks,
therefore the amount of consumed memory is proportional to the amount
of sent data.
(cherry picked from commit 5a4c4a033a4a54481be6870aa1896fad732555b5)

Co-authored-by: Serhiy Storchaka <storchaka@gmail.com>
---
Lib/http/client.py | 28 ++++++--
Lib/test/test_httplib.py | 66 +++++++++++++++++++
...-05-23-11-47-48.gh-issue-119451.qkJe9-.rst | 5 ++
3 files changed, 95 insertions(+), 4 deletions(-)
create mode 100644 Misc/NEWS.d/next/Security/2024-05-23-11-47-48.gh-issue-119451.qkJe9-.rst

--- python3.12-3.12.3.orig/Lib/http/client.py
+++ python3.12-3.12.3/Lib/http/client.py
@@ -111,6 +111,11 @@ responses = {v: v.phrase for v in http.H
_MAXLINE = 65536
_MAXHEADERS = 100

+# Data larger than this will be read in chunks, to prevent extreme
+# overallocation.
+_MIN_READ_BUF_SIZE = 1 << 20
+
+
# Header name/value ABNF (http://tools.ietf.org/html/rfc7230#section-3.2)
#
# VCHAR = %x21-7E
@@ -637,10 +642,25 @@ class HTTPResponse(io.BufferedIOBase):
reading. If the bytes are truly not available (due to EOF), then the
IncompleteRead exception can be used to detect the problem.
"""
- data = self.fp.read(amt)
- if len(data) < amt:
- raise IncompleteRead(data, amt-len(data))
- return data
+ cursize = min(amt, _MIN_READ_BUF_SIZE)
+ data = self.fp.read(cursize)
+ if len(data) >= amt:
+ return data
+ if len(data) < cursize:
+ raise IncompleteRead(data, amt - len(data))
+
+ data = io.BytesIO(data)
+ data.seek(0, 2)
+ while True:
+ # This is a geometric increase in read size (never more than
+ # doubling out the current length of data per loop iteration).
+ delta = min(cursize, amt - cursize)
+ data.write(self.fp.read(delta))
+ if data.tell() >= amt:
+ return data.getvalue()
+ cursize += delta
+ if data.tell() < cursize:
+ raise IncompleteRead(data.getvalue(), amt - data.tell())

def _safe_readinto(self, b):
"""Same as _safe_read, but for reading into a buffer."""
--- python3.12-3.12.3.orig/Lib/test/test_httplib.py
+++ python3.12-3.12.3/Lib/test/test_httplib.py
@@ -1433,6 +1433,72 @@ class BasicTest(TestCase):
thread.join()
self.assertEqual(result, b"proxied data\n")

+ def test_large_content_length(self):
+ serv = socket.create_server((HOST, 0))
+ self.addCleanup(serv.close)
+
+ def run_server():
+ [conn, address] = serv.accept()
+ with conn:
+ while conn.recv(1024):
+ conn.sendall(
+ b"HTTP/1.1 200 Ok\r\n"
+ b"Content-Length: %d\r\n"
+ b"\r\n" % size)
+ conn.sendall(b'A' * (size//3))
+ conn.sendall(b'B' * (size - size//3))
+
+ thread = threading.Thread(target=run_server)
+ thread.start()
+ self.addCleanup(thread.join, 1.0)
+
+ conn = client.HTTPConnection(*serv.getsockname())
+ try:
+ for w in range(15, 27):
+ size = 1 << w
+ conn.request("GET", "/")
+ with conn.getresponse() as response:
+ self.assertEqual(len(response.read()), size)
+ finally:
+ conn.close()
+ thread.join(1.0)
+
+ def test_large_content_length_truncated(self):
+ serv = socket.create_server((HOST, 0))
+ self.addCleanup(serv.close)
+
+ def run_server():
+ while True:
+ [conn, address] = serv.accept()
+ with conn:
+ conn.recv(1024)
+ if not size:
+ break
+ conn.sendall(
+ b"HTTP/1.1 200 Ok\r\n"
+ b"Content-Length: %d\r\n"
+ b"\r\n"
+ b"Text" % size)
+
+ thread = threading.Thread(target=run_server)
+ thread.start()
+ self.addCleanup(thread.join, 1.0)
+
+ conn = client.HTTPConnection(*serv.getsockname())
+ try:
+ for w in range(18, 65):
+ size = 1 << w
+ conn.request("GET", "/")
+ with conn.getresponse() as response:
+ self.assertRaises(client.IncompleteRead, response.read)
+ conn.close()
+ finally:
+ conn.close()
+ size = 0
+ conn.request("GET", "/")
+ conn.close()
+ thread.join(1.0)
+
def test_putrequest_override_domain_validation(self):
"""
It should be possible to override the default validation
235 changes: 235 additions & 0 deletions debian/patches/CVE-2025-6069.patch
Original file line number Diff line number Diff line change
@@ -0,0 +1,235 @@
From ab0893fd5c579d9cea30841680e6d35fc478afb5 Mon Sep 17 00:00:00 2001
From: Serhiy Storchaka <storchaka@gmail.com>
Date: Fri, 4 Jul 2025 01:12:10 +0300
Subject: [PATCH] [3.12] gh-135462: Fix quadratic complexity in processing
special input in HTMLParser (GH-135464) (GH-135483)

End-of-file errors are now handled according to the HTML5 specs --
comments and declarations are automatically closed, tags are ignored.
(cherry picked from commit 6eb6c5dbfb528bd07d77b60fd71fd05d81d45c41)
---
Lib/html/parser.py | 41 +++++---
Lib/test/test_htmlparser.py | 94 ++++++++++++++++---
...-06-13-15-55-22.gh-issue-135462.KBeJpc.rst | 4 +
3 files changed, 116 insertions(+), 23 deletions(-)
create mode 100644 Misc/NEWS.d/next/Security/2025-06-13-15-55-22.gh-issue-135462.KBeJpc.rst

Index: python3.12-3.12.3/Lib/html/parser.py
===================================================================
--- python3.12-3.12.3.orig/Lib/html/parser.py
+++ python3.12-3.12.3/Lib/html/parser.py
@@ -25,6 +25,7 @@ entityref = re.compile('&([a-zA-Z][-.a-z
charref = re.compile('&#(?:[0-9]+|[xX][0-9a-fA-F]+)[^0-9a-fA-F]')

starttagopen = re.compile('<[a-zA-Z]')
+endtagopen = re.compile('</[a-zA-Z]')
piclose = re.compile('>')
commentclose = re.compile(r'--\s*>')
# Note:
@@ -177,7 +178,7 @@ class HTMLParser(_markupbase.ParserBase)
k = self.parse_pi(i)
elif startswith("<!", i):
k = self.parse_html_declaration(i)
- elif (i + 1) < n:
+ elif (i + 1) < n or end:
self.handle_data("<")
k = i + 1
else:
@@ -185,17 +186,35 @@ class HTMLParser(_markupbase.ParserBase)
if k < 0:
if not end:
break
- k = rawdata.find('>', i + 1)
- if k < 0:
- k = rawdata.find('<', i + 1)
- if k < 0:
- k = i + 1
+ if starttagopen.match(rawdata, i): # < + letter
+ pass
+ elif startswith("</", i):
+ if i + 2 == n:
+ self.handle_data("</")
+ elif endtagopen.match(rawdata, i): # </ + letter
+ pass
+ else:
+ # bogus comment
+ self.handle_comment(rawdata[i+2:])
+ elif startswith("<!--", i):
+ j = n
+ for suffix in ("--!", "--", "-"):
+ if rawdata.endswith(suffix, i+4):
+ j -= len(suffix)
+ break
+ self.handle_comment(rawdata[i+4:j])
+ elif startswith("<![CDATA[", i):
+ self.unknown_decl(rawdata[i+3:])
+ elif rawdata[i:i+9].lower() == '<!doctype':
+ self.handle_decl(rawdata[i+2:])
+ elif startswith("<!", i):
+ # bogus comment
+ self.handle_comment(rawdata[i+2:])
+ elif startswith("<?", i):
+ self.handle_pi(rawdata[i+2:])
else:
- k += 1
- if self.convert_charrefs and not self.cdata_elem:
- self.handle_data(unescape(rawdata[i:k]))
- else:
- self.handle_data(rawdata[i:k])
+ raise AssertionError("we should not get here!")
+ k = n
i = self.updatepos(i, k)
elif startswith("&#", i):
match = charref.match(rawdata, i)
Index: python3.12-3.12.3/Lib/test/test_htmlparser.py
===================================================================
--- python3.12-3.12.3.orig/Lib/test/test_htmlparser.py
+++ python3.12-3.12.3/Lib/test/test_htmlparser.py
@@ -5,6 +5,7 @@ import pprint
import unittest

from unittest.mock import patch
+from test import support


class EventCollector(html.parser.HTMLParser):
@@ -393,28 +394,34 @@ text
('data', '<'),
('starttag', 'bc<', [('a', None)]),
('endtag', 'html'),
- ('data', '\n<img src="URL>'),
- ('comment', '/img'),
- ('endtag', 'html<')])
+ ('data', '\n')])

def test_starttag_junk_chars(self):
+ self._run_check("<", [('data', '<')])
+ self._run_check("<>", [('data', '<>')])
+ self._run_check("< >", [('data', '< >')])
+ self._run_check("< ", [('data', '< ')])
self._run_check("</>", [])
+ self._run_check("<$>", [('data', '<$>')])
self._run_check("</$>", [('comment', '$')])
self._run_check("</", [('data', '</')])
- self._run_check("</a", [('data', '</a')])
+ self._run_check("</a", [])
+ self._run_check("</ a>", [('endtag', 'a')])
+ self._run_check("</ a", [('comment', ' a')])
self._run_check("<a<a>", [('starttag', 'a<a', [])])
self._run_check("</a<a>", [('endtag', 'a<a')])
- self._run_check("<!", [('data', '<!')])
- self._run_check("<a", [('data', '<a')])
- self._run_check("<a foo='bar'", [('data', "<a foo='bar'")])
- self._run_check("<a foo='bar", [('data', "<a foo='bar")])
- self._run_check("<a foo='>'", [('data', "<a foo='>'")])
- self._run_check("<a foo='>", [('data', "<a foo='>")])
+ self._run_check("<!", [('comment', '')])
+ self._run_check("<a", [])
+ self._run_check("<a foo='bar'", [])
+ self._run_check("<a foo='bar", [])
+ self._run_check("<a foo='>'", [])
+ self._run_check("<a foo='>", [])
self._run_check("<a$>", [('starttag', 'a$', [])])
self._run_check("<a$b>", [('starttag', 'a$b', [])])
self._run_check("<a$b/>", [('startendtag', 'a$b', [])])
self._run_check("<a$b >", [('starttag', 'a$b', [])])
self._run_check("<a$b />", [('startendtag', 'a$b', [])])
+ self._run_check("</a$b>", [('endtag', 'a$b')])

def test_slashes_in_starttag(self):
self._run_check('<a foo="var"/>', [('startendtag', 'a', [('foo', 'var')])])
@@ -539,13 +546,56 @@ text
for html, expected in data:
self._run_check(html, expected)

- def test_broken_comments(self):
- html = ('<! not really a comment >'
+ def test_eof_in_comments(self):
+ data = [
+ ('<!--', [('comment', '')]),
+ ('<!---', [('comment', '')]),
+ ('<!----', [('comment', '')]),
+ ('<!-----', [('comment', '-')]),
+ ('<!------', [('comment', '--')]),
+ ('<!----!', [('comment', '')]),
+ ('<!---!', [('comment', '-!')]),
+ ('<!---!>', [('comment', '-!>')]),
+ ('<!--foo', [('comment', 'foo')]),
+ ('<!--foo-', [('comment', 'foo')]),
+ ('<!--foo--', [('comment', 'foo')]),
+ ('<!--foo--!', [('comment', 'foo')]),
+ ('<!--<!--', [('comment', '<!')]),
+ ('<!--<!--!', [('comment', '<!')]),
+ ]
+ for html, expected in data:
+ self._run_check(html, expected)
+
+ def test_eof_in_declarations(self):
+ data = [
+ ('<!', [('comment', '')]),
+ ('<!-', [('comment', '-')]),
+ ('<![', [('comment', '[')]),
+ ('<![CDATA[', [('unknown decl', 'CDATA[')]),
+ ('<![CDATA[x', [('unknown decl', 'CDATA[x')]),
+ ('<![CDATA[x]', [('unknown decl', 'CDATA[x]')]),
+ ('<![CDATA[x]]', [('unknown decl', 'CDATA[x]]')]),
+ ('<!DOCTYPE', [('decl', 'DOCTYPE')]),
+ ('<!DOCTYPE ', [('decl', 'DOCTYPE ')]),
+ ('<!DOCTYPE html', [('decl', 'DOCTYPE html')]),
+ ('<!DOCTYPE html ', [('decl', 'DOCTYPE html ')]),
+ ('<!DOCTYPE html PUBLIC', [('decl', 'DOCTYPE html PUBLIC')]),
+ ('<!DOCTYPE html PUBLIC "foo', [('decl', 'DOCTYPE html PUBLIC "foo')]),
+ ('<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01//EN" "foo',
+ [('decl', 'DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01//EN" "foo')]),
+ ]
+ for html, expected in data:
+ self._run_check(html, expected)
+
+ def test_bogus_comments(self):
+ html = ('<!ELEMENT br EMPTY>'
+ '<! not really a comment >'
'<! not a comment either -->'
'<! -- close enough -->'
'<!><!<-- this was an empty comment>'
'<!!! another bogus comment !!!>')
expected = [
+ ('comment', 'ELEMENT br EMPTY'),
('comment', ' not really a comment '),
('comment', ' not a comment either --'),
('comment', ' -- close enough --'),
@@ -600,6 +650,26 @@ text
('endtag', 'a'), ('data', ' bar & baz')]
)

+ @support.requires_resource('cpu')
+ def test_eof_no_quadratic_complexity(self):
+ # Each of these examples used to take about an hour.
+ # Now they take a fraction of a second.
+ def check(source):
+ parser = html.parser.HTMLParser()
+ parser.feed(source)
+ parser.close()
+ n = 120_000
+ check("<a " * n)
+ check("<a a=" * n)
+ check("</a " * 14 * n)
+ check("</a a=" * 11 * n)
+ check("<!--" * 4 * n)
+ check("<!" * 60 * n)
+ check("<?" * 19 * n)
+ check("</$" * 15 * n)
+ check("<![CDATA[" * 9 * n)
+ check("<!doctype" * 35 * n)
+

class AttributesTestCase(TestCaseBase):

Index: python3.12-3.12.3/Misc/NEWS.d/next/Security/2025-06-13-15-55-22.gh-issue-135462.KBeJpc.rst
===================================================================
--- /dev/null
+++ python3.12-3.12.3/Misc/NEWS.d/next/Security/2025-06-13-15-55-22.gh-issue-135462.KBeJpc.rst
@@ -0,0 +1,4 @@
+Fix quadratic complexity in processing specially crafted input in
+:class:`html.parser.HTMLParser`. End-of-file errors are now handled according
+to the HTML5 specs -- comments and declarations are automatically closed,
+tags are ignored.
Loading
Loading