963 lines Β· 31.4 KB Β· Rust
RawDownload
// SPDX-License-Identifier: GPL-2.0 //! String representations. use crate::alloc::{flags::*, AllocError, KVec};use crate::fmt::{self, Write};use core::ops::{self, Deref, DerefMut, Index}; use crate::prelude::*; /// 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!("πŸ¦€");    /// 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]pub const fn as_char_ptr_in_const_context(c_str: &CStr) -> *const c_char {    c_str.0.as_ptr()} /// 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 {        if self.0.is_empty() {            // 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.            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 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.cast(), len) };        // 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) }    }     /// 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 *(core::ptr::from_mut(bytes) as *mut CStr) }    }     /// Returns a C pointer to the string.    ///    /// Using this function in a const context is deprecated in favor of    /// [`as_char_ptr_in_const_context`] in preparation for replacing `CStr` with `core::ffi::CStr`    /// which does not have this method.    #[inline]    pub const fn as_char_ptr(&self) -> *const c_char {        as_char_ptr_in_const_context(self)    }     /// Convert the string to a byte slice without the trailing `NUL` byte.    #[inline]    pub fn to_bytes(&self) -> &[u8] {        &self.0[..self.len()]    }     /// Convert the string to a byte slice without the trailing `NUL` byte.    ///    /// This function is deprecated in favor of [`Self::to_bytes`] in preparation for replacing    /// `CStr` with `core::ffi::CStr` which does not have this method.    #[inline]    pub fn as_bytes(&self) -> &[u8] {        self.to_bytes()    }     /// Convert the string to a byte slice containing the trailing `NUL` byte.    #[inline]    pub const fn to_bytes_with_nul(&self) -> &[u8] {        &self.0    }     /// Convert the string to a byte slice containing the trailing `NUL` byte.    ///    /// This function is deprecated in favor of [`Self::to_bytes_with_nul`] in preparation for    /// replacing `CStr` with `core::ffi::CStr` which does not have this method.    #[inline]    pub const fn as_bytes_with_nul(&self) -> &[u8] {        self.to_bytes_with_nul()    }     /// 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")?;    /// assert_eq!(cstr.to_str(), Ok("foo"));    /// # Ok::<(), kernel::error::Error>(())    /// ```    #[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 {        // SAFETY: TODO.        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)    }     /// 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 {    /// Formats printable ASCII characters, escaping the rest.    ///    /// ```    /// # use kernel::c_str;    /// # use kernel::prelude::fmt;    /// # use kernel::str::CStr;    /// # use kernel::str::CString;    /// let penguin = c_str!("🐧");    /// 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_str!("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(())    }} 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::prelude::fmt;    /// # use kernel::str::CStr;    /// # use kernel::str::CString;    /// let penguin = c_str!("🐧");    /// let s = CString::try_from_fmt(fmt!("{penguin:?}"))?;    /// assert_eq!(s.as_bytes_with_nul(), "\"\\xf0\\x9f\\x90\\xa7\"\0".as_bytes());    ///    /// // Embedded double quotes are escaped.

Lines 1–500 of 963.