https://github.com/python/cpython/commit/bc1be4f6174086b4a46e3fe656552f5bb4e6e7b2 commit: bc1be4f6174086b4a46e3fe656552f5bb4e6e7b2 branch: main author: ByteFlow <[email protected]> committer: picnixz <[email protected]> date: 2026-05-10T15:42:04+02:00 summary:
gh-148441: Avoid integer overflow in Expat's CharacterDataHandler (#148904) Co-authored-by: Bénédikt Tran <[email protected]> files: A Misc/NEWS.d/next/Library/2026-04-23-12-50-15.gh-issue-148441.zvpCkR.rst M Lib/test/test_pyexpat.py M Modules/pyexpat.c diff --git a/Lib/test/test_pyexpat.py b/Lib/test/test_pyexpat.py index aaa91aca36e3c4..9a1620029c6da9 100644 --- a/Lib/test/test_pyexpat.py +++ b/Lib/test/test_pyexpat.py @@ -712,6 +712,20 @@ def test_change_size_2(self): parser.Parse(xml2, True) self.assertEqual(self.n, 4) + @support.requires_resource('cpu') + @support.requires_resource('walltime') + @support.bigmemtest(size=2**31, memuse=4, dry_run=False) + def test_large_character_data_does_not_crash(self): + # See https://github.com/python/cpython/issues/148441 + parser = expat.ParserCreate() + parser.buffer_text = True + parser.buffer_size = 2**31 - 1 # INT_MAX + N = 2049 * (1 << 20) - 3 # Character data greater than INT_MAX + self.assertGreater(N, parser.buffer_size) + parser.CharacterDataHandler = lambda text: None + xml_data = b"<r>" + b"A" * N + b"</r>" + self.assertEqual(parser.Parse(xml_data, True), 1) + class ElementDeclHandlerTest(unittest.TestCase): def test_trigger_leak(self): # Unfixed, this test would leak the memory of the so-called diff --git a/Misc/NEWS.d/next/Library/2026-04-23-12-50-15.gh-issue-148441.zvpCkR.rst b/Misc/NEWS.d/next/Library/2026-04-23-12-50-15.gh-issue-148441.zvpCkR.rst new file mode 100644 index 00000000000000..762815270e4d40 --- /dev/null +++ b/Misc/NEWS.d/next/Library/2026-04-23-12-50-15.gh-issue-148441.zvpCkR.rst @@ -0,0 +1,4 @@ +:mod:`xml.parsers.expat`: prevent a crash in +:meth:`~xml.parsers.expat.xmlparser.CharacterDataHandler` +when the character data size exceeds the parser's +:attr:`buffer size <xml.parsers.expat.xmlparser.buffer_size>`. diff --git a/Modules/pyexpat.c b/Modules/pyexpat.c index 0f0afe17513ef1..c01f7babe74527 100644 --- a/Modules/pyexpat.c +++ b/Modules/pyexpat.c @@ -393,7 +393,7 @@ my_CharacterDataHandler(void *userData, const XML_Char *data, int len) if (self->buffer == NULL) call_character_handler(self, data, len); else { - if ((self->buffer_used + len) > self->buffer_size) { + if (len > (self->buffer_size - self->buffer_used)) { if (flush_character_buffer(self) < 0) return; /* handler might have changed; drop the rest on the floor _______________________________________________ Python-checkins mailing list -- [email protected] To unsubscribe send an email to [email protected] https://mail.python.org/mailman3//lists/python-checkins.python.org Member address: [email protected]
