Skip to content

Match CPython error type for non-ASCII struct format arguments #7681

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 3 commits into from
Apr 26, 2026
+46 −8
Merged

Match CPython error type for non-ASCII struct format arguments #7681

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
3209a59
Match CPython error type for non-ASCII struct format arguments
changjoon-park Apr 25, 2026
d0ed04a
Add regression test for non-ASCII format string error types
changjoon-park Apr 25, 2026
b0faf80
Use raise AssertionError instead of assert False (B011)
changjoon-park Apr 25, 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
38 changes: 30 additions & 8 deletions crates/stdlib/src/pystruct.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -26,20 +26,42 @@ pub(crate) mod _struct {

impl TryFromObject for IntoStructFormatBytes {
fn try_from_object(vm: &VirtualMachine, obj: PyObjectRef) -> PyResult<Self> {
// CPython turns str to bytes but we do reversed way here
// The only performance difference is this transition cost
// CPython turns str to bytes (via str.encode('ascii')) but we keep str.
// The error reporting for non-ASCII input still matches CPython:
// - str input with non-ASCII char: UnicodeEncodeError, the same exception
// str.encode('ascii') would produce.
// - bytes input with non-ASCII byte: struct.error("bad char in struct format"),
// matching CPython where bytes are passed through to the format parser.
let fmt = match_class!(match obj {
s @ PyStr => s.isascii().then_some(s),
b @ PyBytes => ascii::AsciiStr::from_ascii(&b)
.ok()
.map(|s| vm.ctx.new_str(s)),
s @ PyStr => {
if !s.isascii() {
let start = s
.as_wtf8()
.code_points()
.position(|cp| !cp.to_char().is_some_and(|c| c.is_ascii()))
.unwrap_or(0);
return Err(vm.new_unicode_encode_error_real(
vm.ctx.new_str("ascii"),
s,
start,
start + 1,
vm.ctx.new_str("ordinal not in range(128)"),
));
}
s
}
b @ PyBytes => {
let ascii_str = ascii::AsciiStr::from_ascii(&b).map_err(|_| {
new_struct_error(vm, "bad char in struct format".to_owned())
})?;
vm.ctx.new_str(ascii_str)
}
other =>
return Err(vm.new_type_error(format!(
"Struct() argument 1 must be a str or bytes object, not {}",
other.class().name()
))),
})
.ok_or_else(|| vm.new_unicode_decode_error("Struct format must be a ascii string"))?;
});
Ok(Self(fmt))
}
}
Expand Down
16 changes: 16 additions & 0 deletions extra_tests/snippets/stdlib_struct.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -76,3 +76,19 @@ def __index__(self):

assert struct.error.__module__ == "struct"
assert struct.error.__name__ == "error"

# Non-ASCII format string: error type matches CPython.
# str → UnicodeEncodeError (encoding='ascii')
# bytes → struct.error
try:
struct.Struct("\udc00")
except UnicodeEncodeError as e:
assert e.encoding == "ascii"
else:
raise AssertionError("expected UnicodeEncodeError")

with assert_raises(UnicodeEncodeError):
struct.Struct("한")

with assert_raises(struct.error):
struct.Struct(b"\xff")
Loading