Skip to content

Validate pyexpat parser creation arguments #9575

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
youknowone merged 2 commits into from
Nov 4, 2026
Merged

Validate pyexpat parser creation arguments #9575

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
1e3862e
Validate pyexpat parser creation arguments
youknowdot Nov 3, 2026
045bb42
Retire passing namespace separator marker
youknowdot Nov 3, 2026
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
1 change: 0 additions & 1 deletion Lib/test/test_pyexpat.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -407,7 +407,6 @@ def test_legal(self):
expat.ParserCreate(namespace_separator=None)
expat.ParserCreate(namespace_separator=' ')

@unittest.expectedFailure # TODO: RUSTPYTHON
def test_illegal(self):
with self.assertRaisesRegex(TypeError,
r"ParserCreate\(\) argument (2|'namespace_separator') "
Expand Down
66 changes: 49 additions & 17 deletions crates/stdlib/src/pyexpat.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1883,36 +1883,68 @@ mod _pyexpat {
#[derive(FromArgs)]
struct ParserCreateArgs {
#[pyarg(any, optional)]
encoding: Option<PyStrRef>,
encoding: Option<PyObjectRef>,
#[pyarg(any, optional)]
namespace_separator: Option<PyUtf8StrRef>,
namespace_separator: Option<PyObjectRef>,
#[pyarg(any, optional)]
intern: OptionalOption<PyObjectRef>,
}

fn parser_create_string_arg(
value: Option<PyObjectRef>,
name: &str,
vm: &VirtualMachine,
) -> PyResult<Option<PyUtf8StrRef>> {
let Some(value) = value else {
return Ok(None);
};
let text = value.downcast::<PyStr>().map_err(|value| {
let actual = {
let actual = value.class().slot_name();
let mut end = actual.len().min(50);
while !actual.is_char_boundary(end) {
end -= 1;
}
actual[..end].to_owned()
};
vm.new_type_error(format!(
"ParserCreate() argument '{name}' must be str or None, not {actual}"
))
})?;
let text = text.try_into_utf8(vm)?;
if text.as_str().contains('\0') {
return Err(vm.new_value_error("embedded null character"));
}
Ok(Some(text))
}

#[pyfunction(name = "ParserCreate")]
fn parser_create(
args: ParserCreateArgs,
vm: &VirtualMachine,
) -> PyResult<PyExpatLikeXmlParserRef> {
// Validate namespace_separator: must be at most one character
let ns_sep = match args.namespace_separator {
Some(ref s) => {
if s.as_str().chars().count() > 1 {
return Err(vm.new_value_error(
"namespace_separator must be at most one character, omitted, or None",
));
}
Some(s.as_str().to_owned())
}
None => None,
};
// Clinic converts both strings before the implementation validates
// the separator and the intern dictionary.
let encoding = parser_create_string_arg(args.encoding, "encoding", vm)?;
let ns_sep = parser_create_string_arg(args.namespace_separator, "namespace_separator", vm)?;
if ns_sep.as_ref().is_some_and(|sep| sep.as_str().len() > 1) {
return Err(vm.new_value_error(
"namespace_separator must be at most one character, omitted, or None",
));
}
if let OptionalArg::Present(Some(ref intern)) = args.intern
&& intern
.downcast_ref::<crate::vm::builtins::PyDict>()
.is_none()
{
return Err(vm.new_type_error("intern must be a dictionary"));
}

// encoding parameter is currently not used (xml-rs handles encoding from XML declaration)
let _ = args.encoding;
// Encoding selection is still handled by the xml-rs backend.
let _ = encoding;

Ok(PyExpatLikeXmlParser::new(
ns_sep,
ns_sep.map(|sep| sep.as_str().to_owned()),
args.intern,
None,
None,
Expand Down
Loading