Skip to content

Preserve str subclasses in ascii() for ASCII-only __repr__ results #7455

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 4 commits into from
Mar 19, 2026
Merged

Preserve str subclasses in ascii() for ASCII-only __repr__ results #7455

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
043bf3e
Initial plan
Copilot Mar 17, 2026
18fb23e
Preserve str subclasses in ascii
Copilot Mar 17, 2026
6803cee
Fix ruff formatting in builtin_ascii.py snippet
Copilot Mar 17, 2026
77767fc
Delegate builtin_ascii() to PyObject::ascii() to eliminate duplication
Copilot Mar 18, 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_str.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -112,7 +112,6 @@ def test_literals(self):
# raw strings should not have unicode escapes
self.assertNotEqual(r"\u0020", " ")

@unittest.expectedFailure # TODO: RUSTPYTHON; AssertionError: <class 'str'> is not <class 'test.test_str.StrSubclass'>
def test_ascii(self):
self.assertEqual(ascii('abc'), "'abc'")
self.assertEqual(ascii('ab\\c'), "'ab\\\\c'")
Expand Down
4 changes: 2 additions & 2 deletions crates/vm/src/cformat.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -28,7 +28,7 @@ fn spec_format_bytes(
// Unlike strings, %r and %a are identical for bytes: the behaviour corresponds to
// %a for strings (not %r)
CFormatConversion::Repr | CFormatConversion::Ascii => {
let b = builtins::ascii(obj, vm)?.into();
let b = builtins::ascii(obj, vm)?.as_bytes().to_vec();
Ok(b)
}
CFormatConversion::Str | CFormatConversion::Bytes => {
Expand Down Expand Up @@ -132,7 +132,7 @@ fn spec_format_string(
match &spec.format_type {
CFormatType::String(conversion) => {
let result = match conversion {
CFormatConversion::Ascii => builtins::ascii(obj, vm)?.into(),
CFormatConversion::Ascii => builtins::ascii(obj, vm)?.as_wtf8().to_owned(),
CFormatConversion::Str => obj.str(vm)?.as_wtf8().to_owned(),
CFormatConversion::Repr => obj.repr(vm)?.as_wtf8().to_owned(),
CFormatConversion::Bytes => {
Expand Down
4 changes: 1 addition & 3 deletions crates/vm/src/format.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -159,9 +159,7 @@ fn format_internal(
let argument = match conversion_spec.and_then(FormatConversion::from_char) {
Some(FormatConversion::Str) => argument.str(vm)?.into(),
Some(FormatConversion::Repr) => argument.repr(vm)?.into(),
Some(FormatConversion::Ascii) => {
vm.ctx.new_str(builtins::ascii(argument, vm)?).into()
}
Some(FormatConversion::Ascii) => builtins::ascii(argument, vm)?.into(),
Some(FormatConversion::Bytes) => {
vm.call_method(&argument, identifier!(vm, decode).as_str(), ())?
}
Expand Down
2 changes: 1 addition & 1 deletion crates/vm/src/frame.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7104,7 +7104,7 @@ impl ExecutingFrame<'_> {
let value = match conversion {
ConvertValueOparg::Str => value.str(vm)?.into(),
ConvertValueOparg::Repr => value.repr(vm)?.into(),
ConvertValueOparg::Ascii => vm.ctx.new_str(builtins::ascii(value, vm)?).into(),
ConvertValueOparg::Ascii => builtins::ascii(value, vm)?.into(),
ConvertValueOparg::None => value,
};

Expand Down
9 changes: 6 additions & 3 deletions crates/vm/src/protocol/object.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -370,10 +370,13 @@ impl PyObject {
})
}

pub fn ascii(&self, vm: &VirtualMachine) -> PyResult<ascii::AsciiString> {
pub fn ascii(&self, vm: &VirtualMachine) -> PyResult<PyRef<PyStr>> {
let repr = self.repr(vm)?;
let ascii = to_ascii(repr.as_wtf8());
Ok(ascii)
if repr.as_wtf8().is_ascii() {
Ok(repr)
} else {
Ok(vm.ctx.new_str(to_ascii(repr.as_wtf8())))
}
}

pub fn str_utf8(&self, vm: &VirtualMachine) -> PyResult<PyRef<PyUtf8Str>> {
Expand Down
8 changes: 3 additions & 5 deletions crates/vm/src/stdlib/builtins.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,7 +18,7 @@ mod builtins {
iter::PyCallableIterator,
list::{PyList, SortOptions},
},
common::{hash::PyHash, str::to_ascii},
common::hash::PyHash,
function::{
ArgBytesLike, ArgCallable, ArgIndex, ArgIntoBool, ArgIterable, ArgMapping,
ArgStrOrBytesLike, Either, FsPath, FuncArgs, KwArgs, OptionalArg, OptionalOption,
Expand Down Expand Up @@ -64,10 +64,8 @@ mod builtins {
}

#[pyfunction]
pub fn ascii(obj: PyObjectRef, vm: &VirtualMachine) -> PyResult<ascii::AsciiString> {
let repr = obj.repr(vm)?;
let ascii = to_ascii(repr.as_wtf8());
Ok(ascii)
pub fn ascii(obj: PyObjectRef, vm: &VirtualMachine) -> PyResult<PyStrRef> {
obj.ascii(vm)
}

#[pyfunction]
Expand Down
20 changes: 20 additions & 0 deletions extra_tests/snippets/builtin_ascii.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,3 +5,23 @@
assert ascii(chr(0x10001)) == "'\\U00010001'"
assert ascii(chr(0x9999)) == "'\\u9999'"
assert ascii(chr(0x0A)) == "'\\n'"


class MyStr(str):
Copy link
Contributor

@github-actions github-actions bot Mar 17, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

[auto-format] reported by reviewdog 🐶

Suggested change
class MyStr(str):
class MyStr(str):

pass


class Foo:
Copy link
Contributor

@github-actions github-actions bot Mar 17, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

[auto-format] reported by reviewdog 🐶

Suggested change
class Foo:
class Foo:

def __repr__(self):
return MyStr("hello")


class Bar:
Copy link
Contributor

@github-actions github-actions bot Mar 17, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

[auto-format] reported by reviewdog 🐶

Suggested change
class Bar:
class Bar:

def __repr__(self):
return MyStr("héllo")


assert type(ascii(Foo())) is MyStr
Copy link
Contributor

@github-actions github-actions bot Mar 17, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

[auto-format] reported by reviewdog 🐶

Suggested change
assert type(ascii(Foo())) is MyStr
assert type(ascii(Foo())) is MyStr

assert ascii(Foo()) == MyStr("hello")
assert type(ascii(Bar())) is str
assert ascii(Bar()) == "h\\xe9llo"
Loading