Skip to content

Report bytes out-of-range elements as CPython does #8679

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 2 commits into from
Sep 11, 2026
Merged

Report bytes out-of-range elements as CPython does #8679

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
e07c6b5
Report `bytes` out-of-range elements as CPython does
rawsun007 Sep 8, 2026
abd0e65
Keep the bytearray wording in PyByteArray_FromObject
rawsun007 Sep 9, 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
4 changes: 2 additions & 2 deletions crates/capi/src/bytearrayobject.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,7 +3,7 @@ use crate::object::define_py_check;
use crate::pystate::with_vm;
use core::ffi::c_char;
use rustpython_vm::builtins::PyByteArray;
use rustpython_vm::byte::bytes_from_object;
use rustpython_vm::byte::bytearray_from_object;

define_py_check!(fn PyByteArray_Check, types.bytearray_type);

Expand Down Expand Up @@ -41,7 +41,7 @@ pub unsafe extern "C" fn PyByteArray_FromStringAndSize(
pub unsafe extern "C" fn PyByteArray_FromObject(obj: *mut PyObject) -> *mut PyObject {
with_vm(|vm| {
let obj = unsafe { &*obj };
let data = bytes_from_object(vm, obj)?;
let data = bytearray_from_object(vm, obj)?;
Ok(vm.ctx.new_bytearray(data))
})
}
Expand Down
30 changes: 23 additions & 7 deletions crates/vm/src/byte.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,9 +7,15 @@ use crate::{
protocol::{BufferFlags, PyBuffer},
};

/// The element error `bytes` reports, which is the one entry point here that does
/// not name a single byte: `bytes([256])` says "bytes must be in range(0, 256)"
/// where every `bytearray` path says "byte".
const BYTES_ELEMENT_ERROR: &str = "bytes must be in range(0, 256)";
const BYTE_ELEMENT_ERROR: &str = "byte must be in range(0, 256)";

// PyBytes_FromObject
pub fn bytes_from_object(vm: &VirtualMachine, obj: &PyObject) -> PyResult<Vec<u8>> {
collect_bytes(vm, obj, true, |name| {
collect_bytes(vm, obj, true, BYTES_ELEMENT_ERROR, |name| {

@chatgpt-codex-connector chatgpt-codex-connector Bot Sep 9, 2026

Copy link
Copy Markdown

Choose a reason for hiding this comment

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

P2 Badge Preserve the bytearray C-API error wording

Use a caller-specific element error instead of unconditionally selecting the bytes wording here. When an extension passes [256] to PyByteArray_FromObject, crates/capi/src/bytearrayobject.rs calls bytes_from_object, so this change makes that bytearray API raise ValueError: bytes must be in range(0, 256); CPython's PyByteArray_FromObject raises the singular byte must be in range(0, 256) for this input.

Useful? React with 👍 / 👎.

format!("cannot convert '{name}' object to bytes")
})
}
Expand All @@ -18,25 +24,27 @@ pub fn bytes_from_object(vm: &VirtualMachine, obj: &PyObject) -> PyResult<Vec<u8
/// slice of one, which run the iterator without asking the object they were
/// handed how long it is.
pub fn bytearray_from_object(vm: &VirtualMachine, obj: &PyObject) -> PyResult<Vec<u8>> {
collect_bytes(vm, obj, false, |name| {
collect_bytes(vm, obj, false, BYTE_ELEMENT_ERROR, |name| {
format!("cannot convert '{name}' object to bytearray")
})
}

/// [`bytes_from_object`] for `bytearray_extend()`, which names what it was
/// doing rather than what it was converting to.
pub fn bytearray_extend_from_object(vm: &VirtualMachine, obj: &PyObject) -> PyResult<Vec<u8>> {
collect_bytes(vm, obj, true, |name| {
collect_bytes(vm, obj, true, BYTE_ELEMENT_ERROR, |name| {
format!("can't extend bytearray with {name}")
})
}

/// `measured` is whether the object is asked how long it is; `unusable` names,
/// from the class name, what could not be done with one that is not iterable.
/// `measured` is whether the object is asked how long it is; `element` is the error
/// for a value outside `range(0, 256)`; `unusable` names, from the class name, what
/// could not be done with one that is not iterable.
fn collect_bytes(
vm: &VirtualMachine,
obj: &PyObject,
measured: bool,
element: &'static str,
unusable: impl FnOnce(&str) -> String,
) -> PyResult<Vec<u8>> {
if obj.check_buffer() {
Expand All @@ -52,7 +60,7 @@ fn collect_bytes(
if cls.slots.iter.load().is_none() && !cls.has_attr(identifier!(vm, __getitem__)) {
return Err(vm.new_type_error(unusable(&cls.name())));
}
let value = |x: PyObjectRef| value_from_object(vm, &x);
let value = |x: PyObjectRef| value_from_object_with(vm, &x, element);
let elements = if measured {
vm.map_iterable_object_sized(obj, value)
} else {
Expand All @@ -67,8 +75,16 @@ fn collect_bytes(
}

pub fn value_from_object(vm: &VirtualMachine, obj: &PyObject) -> PyResult<u8> {
value_from_object_with(vm, obj, BYTE_ELEMENT_ERROR)
}

fn value_from_object_with(
vm: &VirtualMachine,
obj: &PyObject,
element: &'static str,
) -> PyResult<u8> {
obj.try_index(vm)?
.as_bigint()
.to_u8()
.ok_or_else(|| vm.new_value_error("byte must be in range(0, 256)"))
.ok_or_else(|| vm.new_value_error(element))
}
19 changes: 19 additions & 0 deletions extra_tests/snippets/builtin_bytes.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -813,3 +813,22 @@ def cannot(fn, message):
lambda: bytearray(b"ab").__setitem__(slice(0, 2), "ab"),
"can assign only bytes, buffers, or iterables of ints in range(0, 256)",
)


def out_of_range(fn, message):

@chatgpt-codex-connector chatgpt-codex-connector Bot Sep 9, 2026

Copy link
Copy Markdown

Choose a reason for hiding this comment

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

P1 Badge Remove the prohibited snippet test additions

Remove this new helper and its associated assertions from extra_tests/snippets/builtin_bytes.py: the repository explicitly restricts test-file changes to adding or removing expected-failure markers, so adding new test logic and test data here violates the contribution rules.

AGENTS.md reference: AGENTS.md:L273-L279

Useful? React with 👍 / 👎.

try:
fn()
except ValueError as e:
assert str(e) == message, e
else:
raise AssertionError(f"expected ValueError: {message}")


# `bytes` is the one entry point that does not name a single byte, and both the
# sized and unsized iterator paths report it that way.
out_of_range(lambda: bytes([256]), "bytes must be in range(0, 256)")
out_of_range(lambda: bytes(iter([256])), "bytes must be in range(0, 256)")
out_of_range(lambda: bytes([-1]), "bytes must be in range(0, 256)")
out_of_range(lambda: bytearray([256]), "byte must be in range(0, 256)")
out_of_range(lambda: bytearray(iter([256])), "byte must be in range(0, 256)")
out_of_range(lambda: bytearray().extend([256]), "byte must be in range(0, 256)")
Loading