Skip to content

Preserve requested encoding names in codec lookup errors #9036

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
Oct 10, 2026
Merged

Preserve requested encoding names in codec lookup errors #9036

Show file tree
Hide file tree
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
3 changes: 2 additions & 1 deletion crates/vm/src/codecs.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -261,6 +261,7 @@ impl CodecsRegistry {
}

pub fn lookup(&self, encoding: &str, vm: &VirtualMachine) -> PyResult<PyCodec> {
let original_encoding = encoding;
let encoding = normalize_encoding_name(encoding);
let search_path = {
let inner = self.inner.read();
Expand All @@ -286,7 +287,7 @@ impl CodecsRegistry {
}
}

Err(vm.new_lookup_error(format!("unknown encoding: {encoding}")))
Err(vm.new_lookup_error(format!("unknown encoding: {original_encoding}")))
}

fn _lookup_text_encoding(
Expand Down
36 changes: 36 additions & 0 deletions extra_tests/snippets/stdlib_codecs_wide.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -28,3 +28,39 @@
_codecs.utf_32_ex_decode(b"\xff\xfe\x00\x00h\x00\x00\x00", "strict", 0, True)[0]
== "h"
)


# Lookup errors preserve the requested spelling, while search hooks receive
# the Python 3.14 normalized registry key.
import codecs

seen_encoding_names = []


def record_unknown_encoding(name):
seen_encoding_names.append(name)
return None


codecs.register(record_unknown_encoding)
try:
for requested, normalized in (
("NO Such Codec!", "no_such_codec"),
("x_ weird--Ω .Ab", "x_weird_.ab"),
):
for lookup in (
codecs.lookup,
lambda name: codecs.encode("value", name),
lambda name: codecs.decode(b"value", name),
lambda name: "value".encode(name),
lambda name: b"value".decode(name),
):
try:
lookup(requested)
except LookupError as error:
assert str(error) == "unknown encoding: " + requested
else:
assert False, "unknown encoding was accepted"
assert seen_encoding_names[-1] == normalized
finally:
codecs.unregister(record_unknown_encoding)
Loading