918 lines · 30.5 KB · Rust
RawDownload
// SPDX-License-Identifier: GPL-2.0 //! String representations. use crate::{    alloc::{        AllocError,        KVec, //    },    error::{        to_result,        Result, //    },    fmt::{        self,        Write, //    },    prelude::*, //};use core::{    marker::PhantomData,    ops::{        Deref,        DerefMut,        Index, //    }, //}; pub use crate::prelude::CStr; pub mod parse_int; /// Byte string without UTF-8 validity guarantee.#[repr(transparent)]pub struct BStr([u8]); impl BStr {    /// Returns the length of this string.    #[inline]    pub const fn len(&self) -> usize {        self.0.len()    }     /// Returns `true` if the string is empty.    #[inline]    pub const fn is_empty(&self) -> bool {        self.len() == 0    }     /// Creates a [`BStr`] from a `[u8]`.    #[inline]    pub const fn from_bytes(bytes: &[u8]) -> &Self {        // SAFETY: `BStr` is transparent to `[u8]`.        unsafe { &*(core::ptr::from_ref(bytes) as *const BStr) }    }     /// Strip a prefix from `self`. Delegates to [`slice::strip_prefix`].    ///    /// # Examples    ///    /// ```    /// # use kernel::b_str;    /// assert_eq!(Some(b_str!("bar")), b_str!("foobar").strip_prefix(b_str!("foo")));    /// assert_eq!(None, b_str!("foobar").strip_prefix(b_str!("bar")));    /// assert_eq!(Some(b_str!("foobar")), b_str!("foobar").strip_prefix(b_str!("")));    /// assert_eq!(Some(b_str!("")), b_str!("foobar").strip_prefix(b_str!("foobar")));    /// ```    pub fn strip_prefix(&self, pattern: impl AsRef<Self>) -> Option<&BStr> {        self.deref()            .strip_prefix(pattern.as_ref().deref())            .map(Self::from_bytes)    }} impl fmt::Display for BStr {    /// Formats printable ASCII characters, escaping the rest.    ///    /// ```    /// # use kernel::{prelude::fmt, b_str, str::{BStr, CString}};    /// let ascii = b_str!("Hello, BStr!");    /// let s = CString::try_from_fmt(fmt!("{ascii}"))?;    /// assert_eq!(s.to_bytes(), "Hello, BStr!".as_bytes());    ///    /// let non_ascii = b_str!("🦀");    /// let s = CString::try_from_fmt(fmt!("{non_ascii}"))?;    /// assert_eq!(s.to_bytes(), "\\xf0\\x9f\\xa6\\x80".as_bytes());    /// # Ok::<(), kernel::error::Error>(())    /// ```    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {        for &b in &self.0 {            match b {                // Common escape codes.                b'\t' => f.write_str("\\t")?,                b'\n' => f.write_str("\\n")?,                b'\r' => f.write_str("\\r")?,                // Printable characters.                0x20..=0x7e => f.write_char(b as char)?,                _ => write!(f, "\\x{b:02x}")?,            }        }        Ok(())    }} impl fmt::Debug for BStr {    /// Formats printable ASCII characters with a double quote on either end,    /// escaping the rest.    ///    /// ```    /// # use kernel::{prelude::fmt, b_str, str::{BStr, CString}};    /// // Embedded double quotes are escaped.    /// let ascii = b_str!("Hello, \"BStr\"!");    /// let s = CString::try_from_fmt(fmt!("{ascii:?}"))?;    /// assert_eq!(s.to_bytes(), "\"Hello, \\\"BStr\\\"!\"".as_bytes());    ///    /// let non_ascii = b_str!("😺");    /// let s = CString::try_from_fmt(fmt!("{non_ascii:?}"))?;    /// assert_eq!(s.to_bytes(), "\"\\xf0\\x9f\\x98\\xba\"".as_bytes());    /// # Ok::<(), kernel::error::Error>(())    /// ```    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {        f.write_char('"')?;        for &b in &self.0 {            match b {                // Common escape codes.                b'\t' => f.write_str("\\t")?,                b'\n' => f.write_str("\\n")?,                b'\r' => f.write_str("\\r")?,                // String escape characters.                b'\"' => f.write_str("\\\"")?,                b'\\' => f.write_str("\\\\")?,                // Printable characters.                0x20..=0x7e => f.write_char(b as char)?,                _ => write!(f, "\\x{b:02x}")?,            }        }        f.write_char('"')    }} impl Deref for BStr {    type Target = [u8];     #[inline]    fn deref(&self) -> &Self::Target {        &self.0    }} impl PartialEq for BStr {    fn eq(&self, other: &Self) -> bool {        self.deref().eq(other.deref())    }} impl<Idx> Index<Idx> for BStrwhere    [u8]: Index<Idx, Output = [u8]>,{    type Output = Self;     fn index(&self, index: Idx) -> &Self::Output {        BStr::from_bytes(&self.0[index])    }} impl AsRef<BStr> for [u8] {    fn as_ref(&self) -> &BStr {        BStr::from_bytes(self)    }} impl AsRef<BStr> for BStr {    fn as_ref(&self) -> &BStr {        self    }} /// Creates a new [`BStr`] from a string literal.////// `b_str!` converts the supplied string literal to byte string, so non-ASCII/// characters can be included.////// # Examples////// ```/// # use kernel::b_str;/// # use kernel::str::BStr;/// const MY_BSTR: &BStr = b_str!("My awesome BStr!");/// ```#[macro_export]macro_rules! b_str {    ($str:literal) => {{        const S: &'static str = $str;        const C: &'static $crate::str::BStr = $crate::str::BStr::from_bytes(S.as_bytes());        C    }};} /// Returns a C pointer to the string.// It is a free function rather than a method on an extension trait because://// - error[E0379]: functions in trait impls cannot be declared const#[inline]#[expect(clippy::disallowed_methods, reason = "internal implementation")]pub const fn as_char_ptr_in_const_context(c_str: &CStr) -> *const c_char {    c_str.as_ptr().cast()} mod private {    pub trait Sealed {}     impl Sealed for super::CStr {}} /// Extensions to [`CStr`].pub trait CStrExt: private::Sealed {    /// Wraps a raw C string pointer.    ///    /// # Safety    ///    /// `ptr` must be a valid pointer to a `NUL`-terminated C string, and it must    /// last at least `'a`. When `CStr` is alive, the memory pointed by `ptr`    /// must not be mutated.    // This function exists to paper over the fact that `CStr::from_ptr` takes a `*const    // core::ffi::c_char` rather than a `*const crate::ffi::c_char`.    unsafe fn from_char_ptr<'a>(ptr: *const c_char) -> &'a Self;     /// 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).    unsafe fn from_bytes_with_nul_unchecked_mut(bytes: &mut [u8]) -> &mut Self;     /// Returns a C pointer to the string.    // This function exists to paper over the fact that `CStr::as_ptr` returns a `*const    // core::ffi::c_char` rather than a `*const crate::ffi::c_char`.    fn as_char_ptr(&self) -> *const c_char;     /// Convert this [`CStr`] into a [`CString`] by allocating memory and    /// copying over the string data.    fn to_cstring(&self) -> Result<CString, AllocError>;     /// 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    fn make_ascii_lowercase(&mut self);     /// 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    fn make_ascii_uppercase(&mut self);     /// 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    fn to_ascii_lowercase(&self) -> Result<CString, AllocError>;     /// 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    fn to_ascii_uppercase(&self) -> Result<CString, AllocError>;} impl fmt::Display for CStr {    /// Formats printable ASCII characters, escaping the rest.    ///    /// ```    /// # use kernel::prelude::fmt;    /// # use kernel::str::CStr;    /// # use kernel::str::CString;    /// let penguin = c"🐧";    /// let s = CString::try_from_fmt(fmt!("{penguin}"))?;    /// assert_eq!(s.to_bytes_with_nul(), "\\xf0\\x9f\\x90\\xa7\0".as_bytes());    ///    /// let ascii = c"so \"cool\"";    /// let s = CString::try_from_fmt(fmt!("{ascii}"))?;    /// assert_eq!(s.to_bytes_with_nul(), "so \"cool\"\0".as_bytes());    /// # Ok::<(), kernel::error::Error>(())    /// ```    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {        for &c in self.to_bytes() {            if (0x20..0x7f).contains(&c) {                // Printable character.                f.write_char(c as char)?;            } else {                write!(f, "\\x{c:02x}")?;            }        }        Ok(())    }} /// Converts a mutable C string to a mutable byte slice.////// # Safety////// The caller must ensure that the slice ends in a NUL byte and contains no other NUL bytes before/// the borrow ends and the underlying [`CStr`] is used.unsafe fn to_bytes_mut(s: &mut CStr) -> &mut [u8] {    // SAFETY: the cast from `&CStr` to `&[u8]` is safe since `CStr` has the same layout as `&[u8]`    // (this is technically not guaranteed, but we rely on it here). The pointer dereference is    // safe since it comes from a mutable reference which is guaranteed to be valid for writes.    unsafe { &mut *(core::ptr::from_mut(s) as *mut [u8]) }} impl CStrExt for CStr {    #[inline]    #[expect(clippy::disallowed_methods, reason = "internal implementation")]    unsafe fn from_char_ptr<'a>(ptr: *const c_char) -> &'a Self {        // SAFETY: The safety preconditions are the same as for `CStr::from_ptr`.        unsafe { CStr::from_ptr(ptr.cast()) }    }     #[inline]    unsafe fn from_bytes_with_nul_unchecked_mut(bytes: &mut [u8]) -> &mut Self {        // SAFETY: the cast from `&[u8]` to `&CStr` is safe since the properties of `bytes` are        // guaranteed by the safety precondition and `CStr` has the same layout as `&[u8]` (this is        // technically not guaranteed, but we rely on it here). The pointer dereference is safe        // since it comes from a mutable reference which is guaranteed to be valid for writes.        unsafe { &mut *(core::ptr::from_mut(bytes) as *mut CStr) }    }     #[inline]    #[expect(clippy::disallowed_methods, reason = "internal implementation")]    fn as_char_ptr(&self) -> *const c_char {        self.as_ptr().cast()    }     fn to_cstring(&self) -> Result<CString, AllocError> {        CString::try_from(self)    }     fn make_ascii_lowercase(&mut self) {        // SAFETY: This doesn't introduce or remove NUL bytes in the C string.        unsafe { to_bytes_mut(self) }.make_ascii_lowercase();    }     fn make_ascii_uppercase(&mut self) {        // SAFETY: This doesn't introduce or remove NUL bytes in the C string.        unsafe { to_bytes_mut(self) }.make_ascii_uppercase();    }     fn to_ascii_lowercase(&self) -> Result<CString, AllocError> {        let mut s = self.to_cstring()?;         s.make_ascii_lowercase();         Ok(s)    }     fn to_ascii_uppercase(&self) -> Result<CString, AllocError> {        let mut s = self.to_cstring()?;         s.make_ascii_uppercase();         Ok(s)    }} impl AsRef<BStr> for CStr {    #[inline]    fn as_ref(&self) -> &BStr {        BStr::from_bytes(self.to_bytes())    }} /// Creates a new [`CStr`] at compile time.////// Rust supports C string literals since Rust 1.77, and they should be used instead of this macro/// where possible. This macro exists to allow static *non-literal* C strings to be created at/// compile time. This is most often used in other macros.////// # Panics////// This macro panics if the operand contains an interior `NUL` byte.////// # Examples////// ```/// # use kernel::c_str;/// # use kernel::str::CStr;/// // This is allowed, but `c"literal"` should be preferred for literals./// const BAD: &CStr = c_str!("literal");////// // `c_str!` is still needed for static non-literal C strings./// const GOOD: &CStr = c_str!(concat!(file!(), ":", line!(), ": My CStr!"));/// ```#[macro_export]macro_rules! c_str {    // NB: We could write `($str:lit) => compile_error!("use a C string literal instead");` here but    // that would trigger when the literal is at the top of several macro expansions. That would be    // too limiting to macro authors.    ($str:expr) => {{        const S: &str = concat!($str, "\0");        const C: &$crate::str::CStr = match $crate::str::CStr::from_bytes_with_nul(S.as_bytes()) {            Ok(v) => v,            Err(_) => panic!("string contains interior NUL"),        };        C    }};} #[cfg(CONFIG_RUST_STR_KUNIT_TEST)]#[kunit_tests(rust_kernel_str)]mod tests {    use super::*;     impl From<core::ffi::FromBytesWithNulError> for Error {        #[inline]        fn from(_: core::ffi::FromBytesWithNulError) -> Error {            EINVAL        }    }     macro_rules! format {        ($($f:tt)*) => ({            CString::try_from_fmt(fmt!($($f)*))?.to_str()?        })    }     const ALL_ASCII_CHARS: &str =        "\\x01\\x02\\x03\\x04\\x05\\x06\\x07\\x08\\x09\\x0a\\x0b\\x0c\\x0d\\x0e\\x0f\        \\x10\\x11\\x12\\x13\\x14\\x15\\x16\\x17\\x18\\x19\\x1a\\x1b\\x1c\\x1d\\x1e\\x1f \        !\"#$%&'()*+,-./0123456789:;<=>?@\        ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\\x7f\        \\x80\\x81\\x82\\x83\\x84\\x85\\x86\\x87\\x88\\x89\\x8a\\x8b\\x8c\\x8d\\x8e\\x8f\        \\x90\\x91\\x92\\x93\\x94\\x95\\x96\\x97\\x98\\x99\\x9a\\x9b\\x9c\\x9d\\x9e\\x9f\        \\xa0\\xa1\\xa2\\xa3\\xa4\\xa5\\xa6\\xa7\\xa8\\xa9\\xaa\\xab\\xac\\xad\\xae\\xaf\        \\xb0\\xb1\\xb2\\xb3\\xb4\\xb5\\xb6\\xb7\\xb8\\xb9\\xba\\xbb\\xbc\\xbd\\xbe\\xbf\        \\xc0\\xc1\\xc2\\xc3\\xc4\\xc5\\xc6\\xc7\\xc8\\xc9\\xca\\xcb\\xcc\\xcd\\xce\\xcf\        \\xd0\\xd1\\xd2\\xd3\\xd4\\xd5\\xd6\\xd7\\xd8\\xd9\\xda\\xdb\\xdc\\xdd\\xde\\xdf\        \\xe0\\xe1\\xe2\\xe3\\xe4\\xe5\\xe6\\xe7\\xe8\\xe9\\xea\\xeb\\xec\\xed\\xee\\xef\        \\xf0\\xf1\\xf2\\xf3\\xf4\\xf5\\xf6\\xf7\\xf8\\xf9\\xfa\\xfb\\xfc\\xfd\\xfe\\xff";     #[test]    fn test_cstr_to_str() -> Result {        let cstr = c"\xf0\x9f\xa6\x80";        let checked_str = cstr.to_str()?;        assert_eq!(checked_str, "🦀");        Ok(())    }     #[test]    fn test_cstr_to_str_invalid_utf8() -> Result {        let cstr = c"\xc3\x28";        assert!(cstr.to_str().is_err());        Ok(())    }     #[test]    fn test_cstr_display() -> Result {        let hello_world = c"hello, world!";        assert_eq!(format!("{hello_world}"), "hello, world!");        let non_printables = c"\x01\x09\x0a";        assert_eq!(format!("{non_printables}"), "\\x01\\x09\\x0a");        let non_ascii = c"d\xe9j\xe0 vu";        assert_eq!(format!("{non_ascii}"), "d\\xe9j\\xe0 vu");        let good_bytes = c"\xf0\x9f\xa6\x80";        assert_eq!(format!("{good_bytes}"), "\\xf0\\x9f\\xa6\\x80");        Ok(())    }     #[test]    fn test_cstr_display_all_bytes() -> Result {        let mut bytes: [u8; 256] = [0; 256];        // fill `bytes` with [1..=255] + [0]        for i in u8::MIN..=u8::MAX {            bytes[i as usize] = i.wrapping_add(1);        }        let cstr = CStr::from_bytes_with_nul(&bytes)?;        assert_eq!(format!("{cstr}"), ALL_ASCII_CHARS);        Ok(())

Lines 1–500 of 918.