Skip to content

Accept bytes in Unicode name lookup #9585

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 1 commit into from
Nov 3, 2026
Merged

Accept bytes in Unicode name lookup #9585

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
23 changes: 19 additions & 4 deletions crates/stdlib/src/unicodedata.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -34,7 +34,7 @@ mod unicodedata {
use super::{NormalizeFormArg, unicode_core};
use crate::vm::{
Py, PyObject, PyObjectRef, PyPayload, PyResult, VirtualMachine,
builtins::{PyModule, PyStr, PyStrRef},
builtins::{PyBytes, PyModule, PyStr, PyStrRef, PyUtf8Str},
common::lock::PyMutex,
function::OptionalArg,
protocol::PyIterReturn,
Expand Down Expand Up @@ -342,18 +342,33 @@ mod unicodedata {
}

#[pymethod]
fn lookup(zelf: &Py<Self>, name: PyStrRef, vm: &VirtualMachine) -> PyResult<String> {
if let Some(name_str) = name.to_str()
fn lookup(zelf: &Py<Self>, name: PyObjectRef, vm: &VirtualMachine) -> PyResult<String> {
let name_bytes = if let Some(bytes) = name.downcast_ref::<PyBytes>() {
bytes.as_bytes()
} else {
name.try_downcast_ref::<PyUtf8Str>(vm)?.as_bytes()
};
// CPython's generated Unicode name database limits names to 256 bytes.
if name_bytes.len() > 256 {
return Err(vm.new_key_error(vm.ctx.new_str("name too long").into()));
}
if let Ok(name_str) = core::str::from_utf8(name_bytes)
&& let Some(found) = zelf.inner.lookup(name_str)
{
return Ok(match found {
unicode_core::LookupResult::Character(ch) => ch.to_string(),
unicode_core::LookupResult::Sequence(seq) => seq.to_string(),
});
}
// CPython formats the failed name as a NUL-terminated UTF-8 string.
let prefix = name_bytes
.split(|&byte| byte == 0)
.next()
.unwrap_or_default();
let display = String::from_utf8_lossy(prefix);
Err(vm.new_key_error(
vm.ctx
.new_str(format!("undefined character name '{name}'"))
.new_str(format!("undefined character name '{display}'"))
.into(),
))
}
Expand Down
Loading