Re: [PATCH v5] rust: str: add {make,to}_{upper,lower}case() to CString

[Danilo Krummrich <dakr@redhat.com>]

On 2/23/24 17:37, Danilo Krummrich wrote:
> Add functions to convert a CString to upper- / lowercase, either
> in-place or by creating a copy of the original CString.
> 
> Naming followes the one from the Rust stdlib, where functions starting
> with 'to' create a copy and functions starting with 'make' perform an
> in-place conversion.
> 
> This is required by the Nova project (GSP only Rust successor of
> Nouveau) to convert stringified enum values (representing different GPU
> chipsets) to strings in order to generate the corresponding firmware
> paths. See also [1].

Gentle ping.

> 
> [1] https://rust-for-linux.zulipchat.com/#narrow/stream/288089-General/topic/String.20manipulation.20in.20kernel.20Rust
> 
> Reviewed-by: Alice Ryhl <aliceryhl@google.com>
> Signed-off-by: Danilo Krummrich <dakr@redhat.com>
> ---
> Changes in V5:
>    - remove unneeded return statements
>    - use Vec::as_mut_slice() instead of a dereference
> Changes in V4:
>    - move to_ascii_{lower,upper}case() to CStr
>    - add a few comments suggested by Alice
> Changes in V3:
>    - add an `impl DerefMut for CString`, such that these functions can be defined
>      for `CStr` as `&mut self` and still be called on a `CString`
> Changes in V2:
>    - expand commit message mentioning the use case
>    - expand function doc comments to match the ones from Rust's stdlib
>    - rename to_* to make_* and add the actual to_* implementations
> ---
>   rust/kernel/str.rs | 87 +++++++++++++++++++++++++++++++++++++++++++++-
>   1 file changed, 86 insertions(+), 1 deletion(-)
> 
> diff --git a/rust/kernel/str.rs b/rust/kernel/str.rs
> index 7d848b83add4..c1c8ccc80c52 100644
> --- a/rust/kernel/str.rs
> +++ b/rust/kernel/str.rs
> @@ -5,7 +5,7 @@
>   use alloc::alloc::AllocError;
>   use alloc::vec::Vec;
>   use core::fmt::{self, Write};
> -use core::ops::{self, Deref, Index};
> +use core::ops::{self, Deref, DerefMut, Index};
>   
>   use crate::{
>       bindings,
> @@ -143,6 +143,19 @@ pub const fn from_bytes_with_nul(bytes: &[u8]) -> Result<&Self, CStrConvertError
>           unsafe { core::mem::transmute(bytes) }
>       }
>   
> +    /// Creates a mutable [`CStr`] from a `[u8]` without performing any
> +    /// additional checks.
> +    ///
> +    /// # Safety
> +    ///
> +    /// `bytes` *must* end with a `NUL` byte, and should only have a single
> +    /// `NUL` byte (or the string will be truncated).
> +    #[inline]
> +    pub unsafe fn from_bytes_with_nul_unchecked_mut(bytes: &mut [u8]) -> &mut CStr {
> +        // SAFETY: Properties of `bytes` guaranteed by the safety precondition.
> +        unsafe { &mut *(bytes as *mut [u8] as *mut CStr) }
> +    }
> +
>       /// Returns a C pointer to the string.
>       #[inline]
>       pub const fn as_char_ptr(&self) -> *const core::ffi::c_char {
> @@ -206,6 +219,70 @@ pub unsafe fn as_str_unchecked(&self) -> &str {
>       pub fn to_cstring(&self) -> Result<CString, AllocError> {
>           CString::try_from(self)
>       }
> +
> +    /// Converts this [`CStr`] to its ASCII lower case equivalent in-place.
> +    ///
> +    /// ASCII letters 'A' to 'Z' are mapped to 'a' to 'z',
> +    /// but non-ASCII letters are unchanged.
> +    ///
> +    /// To return a new lowercased value without modifying the existing one, use
> +    /// [`to_ascii_lowercase()`].
> +    ///
> +    /// [`to_ascii_lowercase()`]: #method.to_ascii_lowercase
> +    pub fn make_ascii_lowercase(&mut self) {
> +        // INVARIANT: This doesn't introduce or remove NUL bytes in the C
> +        // string.
> +        self.0.make_ascii_lowercase();
> +    }
> +
> +    /// Converts this [`CStr`] to its ASCII upper case equivalent in-place.
> +    ///
> +    /// ASCII letters 'a' to 'z' are mapped to 'A' to 'Z',
> +    /// but non-ASCII letters are unchanged.
> +    ///
> +    /// To return a new uppercased value without modifying the existing one, use
> +    /// [`to_ascii_uppercase()`].
> +    ///
> +    /// [`to_ascii_uppercase()`]: #method.to_ascii_uppercase
> +    pub fn make_ascii_uppercase(&mut self) {
> +        // INVARIANT: This doesn't introduce or remove NUL bytes in the C
> +        // string.
> +        self.0.make_ascii_uppercase();
> +    }
> +
> +    /// Returns a copy of this [`CString`] where each character is mapped to its
> +    /// ASCII lower case equivalent.
> +    ///
> +    /// ASCII letters 'A' to 'Z' are mapped to 'a' to 'z',
> +    /// but non-ASCII letters are unchanged.
> +    ///
> +    /// To lowercase the value in-place, use [`make_ascii_lowercase`].
> +    ///
> +    /// [`make_ascii_lowercase`]: str::make_ascii_lowercase
> +    pub fn to_ascii_lowercase(&self) -> Result<CString, AllocError> {
> +        let mut s = self.to_cstring()?;
> +
> +        s.make_ascii_lowercase();
> +
> +        Ok(s)
> +    }
> +
> +    /// Returns a copy of this [`CString`] where each character is mapped to its
> +    /// ASCII upper case equivalent.
> +    ///
> +    /// ASCII letters 'a' to 'z' are mapped to 'A' to 'Z',
> +    /// but non-ASCII letters are unchanged.
> +    ///
> +    /// To uppercase the value in-place, use [`make_ascii_uppercase`].
> +    ///
> +    /// [`make_ascii_uppercase`]: str::make_ascii_uppercase
> +    pub fn to_ascii_uppercase(&self) -> Result<CString, AllocError> {
> +        let mut s = self.to_cstring()?;
> +
> +        s.make_ascii_uppercase();
> +
> +        Ok(s)
> +    }
>   }
>   
>   impl fmt::Display for CStr {
> @@ -593,6 +670,14 @@ fn deref(&self) -> &Self::Target {
>       }
>   }
>   
> +impl DerefMut for CString {
> +    fn deref_mut(&mut self) -> &mut Self::Target {
> +        // SAFETY: A `CString` is always NUL-terminated and contains no other
> +        // NUL bytes.
> +        unsafe { CStr::from_bytes_with_nul_unchecked_mut(self.buf.as_mut_slice()) }
> +    }
> +}
> +
>   impl<'a> TryFrom<&'a CStr> for CString {
>       type Error = AllocError;
>   
> 
> base-commit: 39133352cbed6626956d38ed72012f49b0421e7b