Skip to content

Introduce PyUtf8Str and fix(sqlite): validate surrogates in SQL statements #5969

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 5 commits into from
Jul 14, 2025
Merged

Introduce PyUtf8Str and fix(sqlite): validate surrogates in SQL statements #5969

Changes from 1 commit
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
b78f4db
fix(sqlite): validate surrogates in SQL statements
ever0de Jul 14, 2025
716efc4
Add `PyUtf8Str` wrapper for safe conversion
ever0de Jul 14, 2025
62b8a56
discord review,
ever0de Jul 14, 2025
a50a7bc
cargo check
ever0de Jul 14, 2025
3899fbe
fix review
ever0de Jul 14, 2025
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
Prev Previous commit
Next Next commit
discord review, 
<https://discord.com/channels/1043121930691149845/1044243281153888416/1394329627480035470>
  • Loading branch information
@ever0de
ever0de committed Jul 14, 2025
commit 62b8a568d5030cca0ebb04352d782e750f333069
26 changes: 19 additions & 7 deletions vm/src/builtins/str.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -95,7 +95,11 @@ impl PyUtf8Str {
/// Returns the underlying string slice. This is safe because the
/// type invariant guarantees UTF-8 validity.
pub fn as_str(&self) -> &str {
self.0.to_str().expect("PyUtf8Str invariant was violated")
debug_assert!(
self.0.is_utf8(),
"PyUtf8Str invariant violated: inner string is not valid UTF-8"
);
unsafe { self.0.to_str().unwrap_unchecked() }
}
}

Expand Down Expand Up @@ -452,21 +456,29 @@ impl PyStr {
self.data.as_str()
}

pub fn try_to_str(&self, vm: &VirtualMachine) -> PyResult<&str> {
self.to_str().ok_or_else(|| {
fn ensure_valid_utf8(&self, vm: &VirtualMachine) -> PyResult<()> {
if self.is_utf8() {
Ok(())
} else {
let start = self
.as_wtf8()
.code_points()
.position(|c| c.to_char().is_none())
.unwrap();
vm.new_unicode_encode_error_real(
Err(vm.new_unicode_encode_error_real(
identifier!(vm, utf_8).to_owned(),
vm.ctx.new_str(self.data.clone()),
start,
start + 1,
vm.ctx.new_str("surrogates not allowed"),
)
})
))
}
}

pub fn try_to_str(&self, vm: &VirtualMachine) -> PyResult<&str> {
self.ensure_valid_utf8(vm)?;
// SAFETY: ensure_valid_utf8 passed, so unwrap is safe.
Ok(unsafe { self.to_str().unwrap_unchecked() })
}

pub fn to_string_lossy(&self) -> Cow<'_, str> {
Expand Down Expand Up @@ -1507,7 +1519,7 @@ impl PyStrRef {
}

pub fn try_into_utf8(self, vm: &VirtualMachine) -> PyResult<PyRef<PyUtf8Str>> {
let _ = self.try_to_str(vm)?;
self.ensure_valid_utf8(vm)?;
Ok(unsafe { mem::transmute::<PyRef<PyStr>, PyRef<PyUtf8Str>>(self) })
}
}
Expand Down
Loading