Skip to content

Fix bytes constructor #5810

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
merged 1 commit into from
Jun 22, 2025
Merged

Fix bytes constructor #5810

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
2 changes: 0 additions & 2 deletions Lib/test/test_bytes.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -209,8 +209,6 @@ def test_constructor_overflow(self):
except (OverflowError, MemoryError):
pass

# TODO: RUSTPYTHON
@unittest.expectedFailure
def test_constructor_exceptions(self):
# Issue #34974: bytes and bytearray constructors replace unexpected
# exceptions.
Expand Down
57 changes: 40 additions & 17 deletions vm/src/bytes_inner.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -21,6 +21,9 @@ use itertools::Itertools;
use malachite_bigint::BigInt;
use num_traits::ToPrimitive;

const STRING_WITHOUT_ENCODING: &str = "string argument without an encoding";
const ENCODING_WITHOUT_STRING: &str = "encoding without a string argument";

#[derive(Debug, Default, Clone)]
pub struct PyBytesInner {
pub(super) elements: Vec<u8>,
Expand Down Expand Up @@ -75,6 +78,18 @@ impl ByteInnerNewOptions {
Ok(vec![0; size].into())
}

fn handle_object_fallback(obj: PyObjectRef, vm: &VirtualMachine) -> PyResult<PyBytesInner> {
match_class!(match obj {
i @ PyInt => {
Self::get_value_from_size(i, vm)
}
_s @ PyStr => Err(vm.new_type_error(STRING_WITHOUT_ENCODING.to_owned())),
obj => {
Self::get_value_from_source(obj, vm)
}
})
}

pub fn get_bytes(self, cls: PyTypeRef, vm: &VirtualMachine) -> PyResult<PyBytesRef> {
let inner = match (&self.source, &self.encoding, &self.errors) {
(OptionalArg::Present(obj), OptionalArg::Missing, OptionalArg::Missing) => {
Expand Down Expand Up @@ -113,40 +128,48 @@ impl ByteInnerNewOptions {
}

pub fn get_bytearray_inner(self, vm: &VirtualMachine) -> PyResult<PyBytesInner> {
const STRING_WITHOUT_ENCODING: &str = "string argument without an encoding";
const ENCODING_WITHOUT_STRING: &str = "encoding without a string argument";

match (self.source, self.encoding, self.errors) {
(OptionalArg::Present(obj), OptionalArg::Missing, OptionalArg::Missing) => {
match_class!(match obj {
i @ PyInt => {
Ok(Self::get_value_from_size(i, vm)?)
}
_s @ PyStr => Err(STRING_WITHOUT_ENCODING),
obj => {
Ok(Self::get_value_from_source(obj, vm)?)
// Try __index__ first to handle int-like objects that might raise custom exceptions
if let Some(index_result) = obj.try_index_opt(vm) {
match index_result {
Ok(index) => Self::get_value_from_size(index, vm),
Err(e) => {
// Only propagate non-TypeError exceptions
// TypeError means the object doesn't support __index__, so fall back
if e.fast_isinstance(vm.ctx.exceptions.type_error) {
// Fall back to treating as buffer-like object
Self::handle_object_fallback(obj, vm)
} else {
// Propagate other exceptions (e.g., ZeroDivisionError)
Err(e)
}
}
}
})
} else {
Self::handle_object_fallback(obj, vm)
}
}
(OptionalArg::Present(obj), OptionalArg::Present(encoding), errors) => {
if let Ok(s) = obj.downcast::<PyStr>() {
Ok(Self::get_value_from_string(s, encoding, errors, vm)?)
Self::get_value_from_string(s, encoding, errors, vm)
} else {
Err(ENCODING_WITHOUT_STRING)
Err(vm.new_type_error(ENCODING_WITHOUT_STRING.to_owned()))
}
}
(OptionalArg::Missing, OptionalArg::Missing, OptionalArg::Missing) => {
Ok(PyBytesInner::default())
}
(OptionalArg::Missing, OptionalArg::Present(_), _) => Err(ENCODING_WITHOUT_STRING),
(OptionalArg::Missing, OptionalArg::Present(_), _) => {
Err(vm.new_type_error(ENCODING_WITHOUT_STRING.to_owned()))
}
(OptionalArg::Missing, _, OptionalArg::Present(_)) => {
Err("errors without a string argument")
Err(vm.new_type_error("errors without a string argument".to_owned()))
}
(OptionalArg::Present(_), OptionalArg::Missing, OptionalArg::Present(_)) => {
Err(STRING_WITHOUT_ENCODING)
Err(vm.new_type_error(STRING_WITHOUT_ENCODING.to_owned()))
}
}
.map_err(|e| vm.new_type_error(e.to_owned()))
}
}

Expand Down
Loading