792 lines Β· 25.9 KB Β· Rust
RawDownload
// SPDX-License-Identifier: GPL-2.0 //! String representations. use alloc::alloc::AllocError;use alloc::vec::Vec;use core::fmt::{self, Write};use core::ops::{self, Deref, Index}; use crate::{    bindings,    error::{code::*, Error},}; /// 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 { &*(bytes as *const [u8] as *const BStr) }    }} impl fmt::Display for BStr {    /// Formats printable ASCII characters, escaping the rest.    ///    /// ```    /// # use kernel::{fmt, b_str, str::{BStr, CString}};    /// let ascii = b_str!("Hello, BStr!");    /// let s = CString::try_from_fmt(fmt!("{}", ascii)).unwrap();    /// assert_eq!(s.as_bytes(), "Hello, BStr!".as_bytes());    ///    /// let non_ascii = b_str!("πŸ¦€");    /// let s = CString::try_from_fmt(fmt!("{}", non_ascii)).unwrap();    /// assert_eq!(s.as_bytes(), "\\xf0\\x9f\\xa6\\x80".as_bytes());    /// ```    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{:02x}", b)?,            }        }        Ok(())    }} impl fmt::Debug for BStr {    /// Formats printable ASCII characters with a double quote on either end,    /// escaping the rest.    ///    /// ```    /// # use kernel::{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)).unwrap();    /// assert_eq!(s.as_bytes(), "\"Hello, \\\"BStr\\\"!\"".as_bytes());    ///    /// let non_ascii = b_str!("😺");    /// let s = CString::try_from_fmt(fmt!("{:?}", non_ascii)).unwrap();    /// assert_eq!(s.as_bytes(), "\"\\xf0\\x9f\\x98\\xba\"".as_bytes());    /// ```    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{:02x}", b)?,            }        }        f.write_char('"')    }} impl Deref for BStr {    type Target = [u8];     #[inline]    fn deref(&self) -> &Self::Target {        &self.0    }} /// 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    }};} /// Possible errors when using conversion functions in [`CStr`].#[derive(Debug, Clone, Copy)]pub enum CStrConvertError {    /// Supplied bytes contain an interior `NUL`.    InteriorNul,     /// Supplied bytes are not terminated by `NUL`.    NotNulTerminated,} impl From<CStrConvertError> for Error {    #[inline]    fn from(_: CStrConvertError) -> Error {        EINVAL    }} /// A string that is guaranteed to have exactly one `NUL` byte, which is at the/// end.////// Used for interoperability with kernel APIs that take C strings.#[repr(transparent)]pub struct CStr([u8]); impl CStr {    /// Returns the length of this string excluding `NUL`.    #[inline]    pub const fn len(&self) -> usize {        self.len_with_nul() - 1    }     /// Returns the length of this string with `NUL`.    #[inline]    pub const fn len_with_nul(&self) -> usize {        // SAFETY: This is one of the invariant of `CStr`.        // We add a `unreachable_unchecked` here to hint the optimizer that        // the value returned from this function is non-zero.        if self.0.is_empty() {            unsafe { core::hint::unreachable_unchecked() };        }        self.0.len()    }     /// Returns `true` if the string only includes `NUL`.    #[inline]    pub const fn is_empty(&self) -> bool {        self.len() == 0    }     /// 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.    #[inline]    pub unsafe fn from_char_ptr<'a>(ptr: *const core::ffi::c_char) -> &'a Self {        // SAFETY: The safety precondition guarantees `ptr` is a valid pointer        // to a `NUL`-terminated C string.        let len = unsafe { bindings::strlen(ptr) } + 1;        // SAFETY: Lifetime guaranteed by the safety precondition.        let bytes = unsafe { core::slice::from_raw_parts(ptr as _, len as _) };        // SAFETY: As `len` is returned by `strlen`, `bytes` does not contain interior `NUL`.        // As we have added 1 to `len`, the last byte is known to be `NUL`.        unsafe { Self::from_bytes_with_nul_unchecked(bytes) }    }     /// Creates a [`CStr`] from a `[u8]`.    ///    /// The provided slice must be `NUL`-terminated, does not contain any    /// interior `NUL` bytes.    pub const fn from_bytes_with_nul(bytes: &[u8]) -> Result<&Self, CStrConvertError> {        if bytes.is_empty() {            return Err(CStrConvertError::NotNulTerminated);        }        if bytes[bytes.len() - 1] != 0 {            return Err(CStrConvertError::NotNulTerminated);        }        let mut i = 0;        // `i + 1 < bytes.len()` allows LLVM to optimize away bounds checking,        // while it couldn't optimize away bounds checks for `i < bytes.len() - 1`.        while i + 1 < bytes.len() {            if bytes[i] == 0 {                return Err(CStrConvertError::InteriorNul);            }            i += 1;        }        // SAFETY: We just checked that all properties hold.        Ok(unsafe { Self::from_bytes_with_nul_unchecked(bytes) })    }     /// Creates a [`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 const unsafe fn from_bytes_with_nul_unchecked(bytes: &[u8]) -> &CStr {        // SAFETY: Properties of `bytes` guaranteed by the safety precondition.        unsafe { core::mem::transmute(bytes) }    }     /// Returns a C pointer to the string.    #[inline]    pub const fn as_char_ptr(&self) -> *const core::ffi::c_char {        self.0.as_ptr() as _    }     /// Convert the string to a byte slice without the trailing `NUL` byte.    #[inline]    pub fn as_bytes(&self) -> &[u8] {        &self.0[..self.len()]    }     /// Convert the string to a byte slice containing the trailing `NUL` byte.    #[inline]    pub const fn as_bytes_with_nul(&self) -> &[u8] {        &self.0    }     /// Yields a [`&str`] slice if the [`CStr`] contains valid UTF-8.    ///    /// If the contents of the [`CStr`] are valid UTF-8 data, this    /// function will return the corresponding [`&str`] slice. Otherwise,    /// it will return an error with details of where UTF-8 validation failed.    ///    /// # Examples    ///    /// ```    /// # use kernel::str::CStr;    /// let cstr = CStr::from_bytes_with_nul(b"foo\0").unwrap();    /// assert_eq!(cstr.to_str(), Ok("foo"));    /// ```    #[inline]    pub fn to_str(&self) -> Result<&str, core::str::Utf8Error> {        core::str::from_utf8(self.as_bytes())    }     /// Unsafely convert this [`CStr`] into a [`&str`], without checking for    /// valid UTF-8.    ///    /// # Safety    ///    /// The contents must be valid UTF-8.    ///    /// # Examples    ///    /// ```    /// # use kernel::c_str;    /// # use kernel::str::CStr;    /// let bar = c_str!("ツ");    /// // SAFETY: String literals are guaranteed to be valid UTF-8    /// // by the Rust compiler.    /// assert_eq!(unsafe { bar.as_str_unchecked() }, "ツ");    /// ```    #[inline]    pub unsafe fn as_str_unchecked(&self) -> &str {        unsafe { core::str::from_utf8_unchecked(self.as_bytes()) }    }     /// Convert this [`CStr`] into a [`CString`] by allocating memory and    /// copying over the string data.    pub fn to_cstring(&self) -> Result<CString, AllocError> {        CString::try_from(self)    }} impl fmt::Display for CStr {    /// Formats printable ASCII characters, escaping the rest.    ///    /// ```    /// # use kernel::c_str;    /// # use kernel::fmt;    /// # use kernel::str::CStr;    /// # use kernel::str::CString;    /// let penguin = c_str!("🐧");    /// let s = CString::try_from_fmt(fmt!("{}", penguin)).unwrap();    /// assert_eq!(s.as_bytes_with_nul(), "\\xf0\\x9f\\x90\\xa7\0".as_bytes());    ///    /// let ascii = c_str!("so \"cool\"");    /// let s = CString::try_from_fmt(fmt!("{}", ascii)).unwrap();    /// assert_eq!(s.as_bytes_with_nul(), "so \"cool\"\0".as_bytes());    /// ```    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {        for &c in self.as_bytes() {            if (0x20..0x7f).contains(&c) {                // Printable character.                f.write_char(c as char)?;            } else {                write!(f, "\\x{:02x}", c)?;            }        }        Ok(())    }} impl fmt::Debug for CStr {    /// Formats printable ASCII characters with a double quote on either end, escaping the rest.    ///    /// ```    /// # use kernel::c_str;    /// # use kernel::fmt;    /// # use kernel::str::CStr;    /// # use kernel::str::CString;    /// let penguin = c_str!("🐧");    /// let s = CString::try_from_fmt(fmt!("{:?}", penguin)).unwrap();    /// assert_eq!(s.as_bytes_with_nul(), "\"\\xf0\\x9f\\x90\\xa7\"\0".as_bytes());    ///    /// // Embedded double quotes are escaped.    /// let ascii = c_str!("so \"cool\"");    /// let s = CString::try_from_fmt(fmt!("{:?}", ascii)).unwrap();    /// assert_eq!(s.as_bytes_with_nul(), "\"so \\\"cool\\\"\"\0".as_bytes());    /// ```    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {        f.write_str("\"")?;        for &c in self.as_bytes() {            match c {                // Printable characters.                b'\"' => f.write_str("\\\"")?,                0x20..=0x7e => f.write_char(c as char)?,                _ => write!(f, "\\x{:02x}", c)?,            }        }        f.write_str("\"")    }} impl AsRef<BStr> for CStr {    #[inline]    fn as_ref(&self) -> &BStr {        BStr::from_bytes(self.as_bytes())    }} impl Deref for CStr {    type Target = BStr;     #[inline]    fn deref(&self) -> &Self::Target {        self.as_ref()    }} impl Index<ops::RangeFrom<usize>> for CStr {    type Output = CStr;     #[inline]    fn index(&self, index: ops::RangeFrom<usize>) -> &Self::Output {        // Delegate bounds checking to slice.        // Assign to _ to mute clippy's unnecessary operation warning.        let _ = &self.as_bytes()[index.start..];        // SAFETY: We just checked the bounds.        unsafe { Self::from_bytes_with_nul_unchecked(&self.0[index.start..]) }    }} impl Index<ops::RangeFull> for CStr {    type Output = CStr;     #[inline]    fn index(&self, _index: ops::RangeFull) -> &Self::Output {        self    }} mod private {    use core::ops;     // Marker trait for index types that can be forward to `BStr`.    pub trait CStrIndex {}     impl CStrIndex for usize {}    impl CStrIndex for ops::Range<usize> {}    impl CStrIndex for ops::RangeInclusive<usize> {}    impl CStrIndex for ops::RangeToInclusive<usize> {}} impl<Idx> Index<Idx> for CStrwhere    Idx: private::CStrIndex,    BStr: Index<Idx>,{    type Output = <BStr as Index<Idx>>::Output;     #[inline]    fn index(&self, index: Idx) -> &Self::Output {        &self.as_ref()[index]    }} /// Creates a new [`CStr`] from a string literal.////// The string literal should not contain any `NUL` bytes.////// # Examples////// ```/// # use kernel::c_str;/// # use kernel::str::CStr;/// const MY_CSTR: &CStr = c_str!("My awesome CStr!");/// ```#[macro_export]macro_rules! c_str {    ($str:expr) => {{        const S: &str = concat!($str, "\0");        const C: &$crate::str::CStr = match $crate::str::CStr::from_bytes_with_nul(S.as_bytes()) {            Ok(v) => v,            Err(_) => panic!("string contains interior NUL"),        };        C    }};} #[cfg(test)]mod tests {    use super::*;    use alloc::format;     const ALL_ASCII_CHARS: &'static str =        "\\x01\\x02\\x03\\x04\\x05\\x06\\x07\\x08\\x09\\x0a\\x0b\\x0c\\x0d\\x0e\\x0f\        \\x10\\x11\\x12\\x13\\x14\\x15\\x16\\x17\\x18\\x19\\x1a\\x1b\\x1c\\x1d\\x1e\\x1f \        !\"#$%&'()*+,-./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() {        let good_bytes = b"\xf0\x9f\xa6\x80\0";        let checked_cstr = CStr::from_bytes_with_nul(good_bytes).unwrap();        let checked_str = checked_cstr.to_str().unwrap();        assert_eq!(checked_str, "πŸ¦€");    }     #[test]    #[should_panic]    fn test_cstr_to_str_panic() {        let bad_bytes = b"\xc3\x28\0";        let checked_cstr = CStr::from_bytes_with_nul(bad_bytes).unwrap();        checked_cstr.to_str().unwrap();    }     #[test]    fn test_cstr_as_str_unchecked() {        let good_bytes = b"\xf0\x9f\x90\xA7\0";        let checked_cstr = CStr::from_bytes_with_nul(good_bytes).unwrap();        let unchecked_str = unsafe { checked_cstr.as_str_unchecked() };        assert_eq!(unchecked_str, "🐧");    }     #[test]    fn test_cstr_display() {        let hello_world = CStr::from_bytes_with_nul(b"hello, world!\0").unwrap();        assert_eq!(format!("{}", hello_world), "hello, world!");        let non_printables = CStr::from_bytes_with_nul(b"\x01\x09\x0a\0").unwrap();        assert_eq!(format!("{}", non_printables), "\\x01\\x09\\x0a");        let non_ascii = CStr::from_bytes_with_nul(b"d\xe9j\xe0 vu\0").unwrap();        assert_eq!(format!("{}", non_ascii), "d\\xe9j\\xe0 vu");

Lines 1–500 of 792.