Skip to content

Implement CPython 3.15 Expat public error metadata #9493

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
Oct 31, 2026
Merged

Implement CPython 3.15 Expat public error metadata #9493

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
65fadc5
Implement Expat public error metadata
codex Oct 30, 2026
e09c4e8
Restore passing Expat error tests
codex Oct 30, 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
2 changes: 0 additions & 2 deletions Lib/test/test_pyexpat.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -921,13 +921,11 @@ def test2(self):
parser.Parse(xml, True)

class ErrorMessageTest(unittest.TestCase):
@unittest.expectedFailure # TODO: RUSTPYTHON
def test_codes(self):
# verify mapping of errors.codes and errors.messages
self.assertEqual(errors.XML_ERROR_SYNTAX,
errors.messages[errors.codes[errors.XML_ERROR_SYNTAX]])

@unittest.expectedFailure # TODO: RUSTPYTHON
def test_expaterror(self):
xml = b'<'
parser = expat.ParserCreate()
Expand Down
1 change: 0 additions & 1 deletion Lib/test/test_xml_etree.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4615,7 +4615,6 @@ def test_error_position(self):
self.assertEqual(self._get_error('<tag>&foo;</tag>').position, (1, 5))
self.assertEqual(self._get_error('foobar<').position, (1, 6))

@unittest.expectedFailure # TODO: RUSTPYTHON
def test_error_code(self):
import xml.parsers.expat.errors as ERRORS
self.assertEqual(self._get_error('foo').code,
Expand Down
154 changes: 150 additions & 4 deletions crates/stdlib/src/pyexpat.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -170,7 +170,9 @@ mod _pyexpat {
VirtualMachine,
builtins::{PyException, PyModule, PyStr, PyStrRef, PyType, PyUtf8StrRef},
extend_module,
function::{ArgBytesLike, ArgStrOrBytesLike, IntoFuncArgs, OptionalArg, OptionalOption},
function::{
ArgBytesLike, ArgIndex, ArgStrOrBytesLike, IntoFuncArgs, OptionalArg, OptionalOption,
},
types::Constructor,
};
use alloc::collections::VecDeque;
Expand All @@ -187,7 +189,14 @@ mod _pyexpat {

// Add submodules
let model = super::_model::module_def(&vm.ctx).create_module(vm)?;
let errors = super::_errors::module_def(&vm.ctx).create_module(vm)?;
let errors_def = super::_errors::module_def(&vm.ctx);
let errors = errors_def.create_module(vm)?;
errors_def.exec_module(vm, &errors)?;
vm.sys_module.get_attr("modules", vm)?.set_item(
"pyexpat.errors",
errors.clone().into(),
vm,
)?;

extend_module!(vm, module, {
"model" => model,
Expand All @@ -197,6 +206,18 @@ mod _pyexpat {
Ok(())
}

#[pyfunction(name = "ErrorString")]
fn error_string(code: ArgIndex, vm: &VirtualMachine) -> PyResult<Option<&'static str>> {
let code = code
.into_int_ref()
.try_to_primitive::<core::ffi::c_long>(vm)?;
// CPython converts a C long to int before calling XML_ErrorString.
let index = (code as core::ffi::c_int).wrapping_sub(1) as usize;
Ok(super::_errors::ERRORS
.get(index)
.map(|(_, message)| *message))
}

type MutableObject = PyRwLock<PyObjectRef>;

#[pyattr(name = "version_info")]
Expand Down Expand Up @@ -1914,5 +1935,130 @@ mod _pyexpat {
#[pymodule(name = "model")]
mod _model {}

#[pymodule(name = "errors")]
mod _errors {}
#[pymodule(name = "pyexpat.errors")]
mod _errors {
use crate::vm::{Py, PyResult, VirtualMachine, builtins::PyModule, extend_module};

// CPython 3.15 Modules/pyexpat.c error_info_of; code zero has no message.
pub(super) const ERRORS: &[(&str, &str)] = &[
("XML_ERROR_NO_MEMORY", "out of memory"),
("XML_ERROR_SYNTAX", "syntax error"),
("XML_ERROR_NO_ELEMENTS", "no element found"),
("XML_ERROR_INVALID_TOKEN", "not well-formed (invalid token)"),
("XML_ERROR_UNCLOSED_TOKEN", "unclosed token"),
("XML_ERROR_PARTIAL_CHAR", "partial character"),
("XML_ERROR_TAG_MISMATCH", "mismatched tag"),
("XML_ERROR_DUPLICATE_ATTRIBUTE", "duplicate attribute"),
(
"XML_ERROR_JUNK_AFTER_DOC_ELEMENT",
"junk after document element",
),
(
"XML_ERROR_PARAM_ENTITY_REF",
"illegal parameter entity reference",
),
("XML_ERROR_UNDEFINED_ENTITY", "undefined entity"),
(
"XML_ERROR_RECURSIVE_ENTITY_REF",
"recursive entity reference",
),
("XML_ERROR_ASYNC_ENTITY", "asynchronous entity"),
(
"XML_ERROR_BAD_CHAR_REF",
"reference to invalid character number",
),
("XML_ERROR_BINARY_ENTITY_REF", "reference to binary entity"),
(
"XML_ERROR_ATTRIBUTE_EXTERNAL_ENTITY_REF",
"reference to external entity in attribute",
),
(
"XML_ERROR_MISPLACED_XML_PI",
"XML or text declaration not at start of entity",
),
("XML_ERROR_UNKNOWN_ENCODING", "unknown encoding"),
(
"XML_ERROR_INCORRECT_ENCODING",
"encoding specified in XML declaration is incorrect",
),
("XML_ERROR_UNCLOSED_CDATA_SECTION", "unclosed CDATA section"),
(
"XML_ERROR_EXTERNAL_ENTITY_HANDLING",
"error in processing external entity reference",
),
("XML_ERROR_NOT_STANDALONE", "document is not standalone"),
(
"XML_ERROR_UNEXPECTED_STATE",
"unexpected parser state - please send a bug report",
),
(
"XML_ERROR_ENTITY_DECLARED_IN_PE",
"entity declared in parameter entity",
),
(
"XML_ERROR_FEATURE_REQUIRES_XML_DTD",
"requested feature requires XML_DTD support in Expat",
),
(
"XML_ERROR_CANT_CHANGE_FEATURE_ONCE_PARSING",
"cannot change setting once parsing has begun",
),
("XML_ERROR_UNBOUND_PREFIX", "unbound prefix"),
("XML_ERROR_UNDECLARING_PREFIX", "must not undeclare prefix"),
(
"XML_ERROR_INCOMPLETE_PE",
"incomplete markup in parameter entity",
),
("XML_ERROR_XML_DECL", "XML declaration not well-formed"),
("XML_ERROR_TEXT_DECL", "text declaration not well-formed"),
("XML_ERROR_PUBLICID", "illegal character(s) in public id"),
("XML_ERROR_SUSPENDED", "parser suspended"),
("XML_ERROR_NOT_SUSPENDED", "parser not suspended"),
("XML_ERROR_ABORTED", "parsing aborted"),
("XML_ERROR_FINISHED", "parsing finished"),
(
"XML_ERROR_SUSPEND_PE",
"cannot suspend in external parameter entity",
),
(
"XML_ERROR_RESERVED_PREFIX_XML",
"reserved prefix (xml) must not be undeclared or bound to another namespace name",
),
(
"XML_ERROR_RESERVED_PREFIX_XMLNS",
"reserved prefix (xmlns) must not be declared or undeclared",
),
(
"XML_ERROR_RESERVED_NAMESPACE_URI",
"prefix must not be bound to one of the reserved namespace names",
),
("XML_ERROR_INVALID_ARGUMENT", "invalid argument"),
(
"XML_ERROR_NO_BUFFER",
"a successful prior call to function XML_GetBuffer is required",
),
(
"XML_ERROR_AMPLIFICATION_LIMIT_BREACH",
"limit on input amplification factor (from DTD and entities) breached",
),
("XML_ERROR_NOT_STARTED", "parser not started"),
];

pub(crate) fn module_exec(vm: &VirtualMachine, module: &Py<PyModule>) -> PyResult<()> {
__module_exec(vm, module);
let codes = vm.ctx.new_dict();
let messages = vm.ctx.new_dict();
for (index, &(name, message)) in ERRORS.iter().enumerate() {
let code = vm.ctx.new_int(index + 1);
module.set_attr(name, vm.ctx.new_str(message), vm)?;
codes.set_item(message, code.clone().into(), vm)?;
messages.set_item(&(index + 1), vm.ctx.new_str(message).into(), vm)?;
}
extend_module!(vm, module, {
"__doc__" => vm.ctx.new_str("Constants used to describe error conditions."),
"codes" => codes,
"messages" => messages,
});
Ok(())
}
}
Loading