Re: [PATCH v4 3/4] rust: str: add radix prefixed integer parsing functions

[Gary Guo <gary@garyguo.net>]

On Thu, 09 Jan 2025 11:54:58 +0100
Andreas Hindborg <a.hindborg@kernel.org> wrote:

> Add the trait `ParseInt` for parsing string representations of integers
> where the string representations are optionally prefixed by a radix
> specifier. Implement the trait for the primitive integer types.
> 
> Signed-off-by: Andreas Hindborg <a.hindborg@kernel.org>
> ---
>  rust/kernel/str.rs | 118 +++++++++++++++++++++++++++++++++++++++++++++++++++++
>  1 file changed, 118 insertions(+)
> 
> diff --git a/rust/kernel/str.rs b/rust/kernel/str.rs
> index 9c446ff1ad7adba7ca09a5ae9df00fd369a32899..14da40213f9eafa07a104eba3129efe07c8343f3 100644
> --- a/rust/kernel/str.rs
> +++ b/rust/kernel/str.rs
> @@ -914,3 +914,121 @@ fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
>  macro_rules! fmt {
>      ($($f:tt)*) => ( core::format_args!($($f)*) )
>  }
> +
> +pub mod parse_int {
> +    //! Integer parsing functions for parsing signed and unsigned integers
> +    //! potentially prefixed with `0x`, `0o`, or `0b`.
> +
> +    use crate::alloc::flags;
> +    use crate::prelude::*;
> +    use crate::str::BStr;
> +
> +    /// Trait that allows parsing a [`&BStr`] to an integer with a radix.
> +    ///
> +    /// [`&BStr`]: kernel::str::BStr
> +    // This is required because the `from_str_radix` function on the primitive
> +    // integer types is not part of any trait.
> +    pub trait FromStrRadix: Sized {
> +        /// Parse `src` to `Self` using radix `radix`.
> +        fn from_str_radix(src: &BStr, radix: u32) -> Result<Self, crate::error::Error>;
> +    }
> +
> +    /// Extract the radix from an integer literal optionally prefixed with
> +    /// one of `0x`, `0X`, `0o`, `0O`, `0b`, `0B`, `0`.
> +    fn strip_radix(src: &BStr) -> (u32, &BStr) {
> +        if let Some(n) = src.strip_prefix(b_str!("0x")) {
> +            (16, n)
> +        } else if let Some(n) = src.strip_prefix(b_str!("0X")) {
> +            (16, n)
> +        } else if let Some(n) = src.strip_prefix(b_str!("0o")) {
> +            (8, n)
> +        } else if let Some(n) = src.strip_prefix(b_str!("0O")) {
> +            (8, n)
> +        } else if let Some(n) = src.strip_prefix(b_str!("0b")) {
> +            (2, n)
> +        } else if let Some(n) = src.strip_prefix(b_str!("0B")) {
> +            (2, n)
> +        } else if let Some(n) = src.strip_prefix(b_str!("0")) {
> +            (8, n)
> +        } else {
> +            (10, src)
> +        }

This can be done better with a match:

match src.deref() {
    [b'0', b'x' | b'X', ..] => (16, &src[2..]),
    [b'0', b'o' | b'O', ..] => (8, &src[2..]),
    [b'0', b'b' | b'B', ..] => (2, &src[2..]),
    [b'0', ..] => (8, &src[1..]),
    _ => (10, src),
}

> +    }
> +
> +    /// Trait for parsing string representations of integers.
> +    ///
> +    /// Strings beginning with `0x`, `0o`, or `0b` are parsed as hex, octal, or
> +    /// binary respectively. Strings beginning with `0` otherwise are parsed as
> +    /// octal. Anything else is parsed as decimal. A leading `+` or `-` is also
> +    /// permitted. Any string parsed by [`kstrtol()`] or [`kstrtoul()`] will be
> +    /// successfully parsed.
> +    ///
> +    /// [`kstrtol()`]: https://www.kernel.org/doc/html/latest/core-api/kernel-api.html#c.kstrtol
> +    /// [`kstrtoul()`]: https://www.kernel.org/doc/html/latest/core-api/kernel-api.html#c.kstrtoul
> +    ///
> +    /// # Example
> +    /// ```
> +    /// use kernel::str::parse_int::ParseInt;
> +    /// use kernel::b_str;
> +    ///
> +    /// assert_eq!(Ok(0xa2u8), u8::from_str(b_str!("0xa2")));
> +    /// assert_eq!(Ok(-0xa2i32), i32::from_str(b_str!("-0xa2")));
> +    ///
> +    /// assert_eq!(Ok(-0o57i8), i8::from_str(b_str!("-0o57")));
> +    /// assert_eq!(Ok(0o57i8), i8::from_str(b_str!("057")));
> +    ///
> +    /// assert_eq!(Ok(0b1001i16), i16::from_str(b_str!("0b1001")));
> +    /// assert_eq!(Ok(-0b1001i16), i16::from_str(b_str!("-0b1001")));
> +    ///
> +    /// assert_eq!(Ok(127), i8::from_str(b_str!("127")));
> +    /// assert!(i8::from_str(b_str!("128")).is_err());
> +    /// assert_eq!(Ok(-128), i8::from_str(b_str!("-128")));
> +    /// assert!(i8::from_str(b_str!("-129")).is_err());
> +    /// assert_eq!(Ok(255), u8::from_str(b_str!("255")));
> +    /// assert!(u8::from_str(b_str!("256")).is_err());
> +    /// ```
> +    pub trait ParseInt: FromStrRadix {
> +        /// Parse a string according to the description in [`Self`].
> +        fn from_str(src: &BStr) -> Result<Self> {
> +            match src.iter().next() {
> +                None => Err(EINVAL),
> +                Some(sign @ b'-') | Some(sign @ b'+') => {
> +                    let (radix, digits) = strip_radix(BStr::from_bytes(&src[1..]));
> +                    let mut n_digits: KVec<u8> =
> +                        KVec::with_capacity(digits.len() + 1, flags::GFP_KERNEL)?;

I don't think we should allocate for parsing. This can trivially be a
non-allocating. Just check that the next byte is an ASCII digit (reject
if so, in case people give multiple signs), and then from_str_radix and
return as is or use `checked_neg`.

> +                    n_digits.push(*sign, flags::GFP_KERNEL)?;
> +                    n_digits.extend_from_slice(digits, flags::GFP_KERNEL)?;
> +                    Self::from_str_radix(BStr::from_bytes(&n_digits), radix).map_err(|_| EINVAL)
> +                }
> +                Some(_) => {
> +                    let (radix, digits) = strip_radix(src);
> +                    Self::from_str_radix(digits, radix).map_err(|_| EINVAL)
> +                }
> +            }
> +        }
> +    }
> +
> +    macro_rules! impl_parse_int {
> +        ($ty:ty) => {
> +            impl FromStrRadix for $ty {
> +                fn from_str_radix(src: &BStr, radix: u32) -> Result<Self, crate::error::Error> {
> +                    <$ty>::from_str_radix(core::str::from_utf8(src).map_err(|_| EINVAL)?, radix)
> +                        .map_err(|_| EINVAL)
> +                }
> +            }
> +
> +            impl ParseInt for $ty {}
> +        };
> +    }
> +
> +    impl_parse_int!(i8);
> +    impl_parse_int!(u8);
> +    impl_parse_int!(i16);
> +    impl_parse_int!(u16);
> +    impl_parse_int!(i32);
> +    impl_parse_int!(u32);
> +    impl_parse_int!(i64);
> +    impl_parse_int!(u64);
> +    impl_parse_int!(isize);
> +    impl_parse_int!(usize);
> +}
>