// Copyright 2012 The Rust Project Developers. See the COPYRIGHT // file at the top-level directory of this distribution and at // http://rust-lang.org/COPYRIGHT. // // Licensed under the Apache License, Version 2.0 or the MIT license // , at your // option. This file may not be copied, modified, or distributed // except according to those terms. use alloc::{ borrow::{Borrow, Cow, ToOwned}, boxed::Box, rc::Rc, string::String, sync::Arc, vec::Vec, }; use core::{ ascii, cmp::Ordering, fmt::{self, Write}, mem, ops, ptr, slice, str::{self, Utf8Error}, }; use crate::{header::string::strlen, platform::types::*}; pub fn memchr(needle: u8, haystack: &[u8]) -> Option { use crate::header::string; let p = unsafe { string::memchr( haystack.as_ptr() as *const c_void, needle as c_int, haystack.len(), ) }; if p.is_null() { None } else { Some(p as usize - (haystack.as_ptr() as usize)) } } /// A type representing an owned, C-compatible, nul-terminated string with no nul bytes in the /// middle. /// /// This type serves the purpose of being able to safely generate a /// C-compatible string from a Rust byte slice or vector. An instance of this /// type is a static guarantee that the underlying bytes contain no interior 0 /// bytes ("nul characters") and that the final byte is 0 ("nul terminator"). /// /// `CString` is to [`CStr`] as [`String`] is to [`&str`]: the former /// in each pair are owned strings; the latter are borrowed /// references. /// /// # Creating a `CString` /// /// A `CString` is created from either a byte slice or a byte vector, /// or anything that implements [`Into`]`<`[`Vec`]`<`[`u8`]`>>` (for /// example, you can build a `CString` straight out of a [`String`] or /// a [`&str`], since both implement that trait). /// /// The [`new`] method will actually check that the provided `&[u8]` /// does not have 0 bytes in the middle, and return an error if it /// finds one. /// /// # Extracting a raw pointer to the whole C string /// /// `CString` implements a [`as_ptr`] method through the [`Deref`] /// trait. This method will give you a `*const c_char` which you can /// feed directly to extern functions that expect a nul-terminated /// string, like C's `strdup()`. /// /// # Extracting a slice of the whole C string /// /// Alternatively, you can obtain a `&[`[`u8`]`]` slice from a /// `CString` with the [`as_bytes`] method. Slices produced in this /// way do *not* contain the trailing nul terminator. This is useful /// when you will be calling an extern function that takes a `*const /// u8` argument which is not necessarily nul-terminated, plus another /// argument with the length of the string — like C's `strndup()`. /// You can of course get the slice's length with its /// [`len`][slice.len] method. /// /// If you need a `&[`[`u8`]`]` slice *with* the nul terminator, you /// can use [`as_bytes_with_nul`] instead. /// /// Once you have the kind of slice you need (with or without a nul /// terminator), you can call the slice's own /// [`as_ptr`][slice.as_ptr] method to get a raw pointer to pass to /// extern functions. See the documentation for that function for a /// discussion on ensuring the lifetime of the raw pointer. /// /// [`Into`]: ../convert/trait.Into.html /// [`Vec`]: ../vec/struct.Vec.html /// [`String`]: ../string/struct.String.html /// [`&str`]: ../primitive.str.html /// [`u8`]: ../primitive.u8.html /// [`new`]: #method.new /// [`as_bytes`]: #method.as_bytes /// [`as_bytes_with_nul`]: #method.as_bytes_with_nul /// [`as_ptr`]: #method.as_ptr /// [slice.as_ptr]: ../primitive.slice.html#method.as_ptr /// [slice.len]: ../primitive.slice.html#method.len /// [`Deref`]: ../ops/trait.Deref.html /// [`CStr`]: struct.CStr.html /// /// # Examples /// /// ```ignore (extern-declaration) /// # fn main() { /// use std::ffi::CString; /// use std::os::raw::c_char; /// /// extern { /// fn my_printer(s: *const c_char); /// } /// /// // We are certain that our string doesn't have 0 bytes in the middle, /// // so we can .unwrap() /// let c_to_print = CString::new("Hello, world!").unwrap(); /// unsafe { /// my_printer(c_to_print.as_ptr()); /// } /// # } /// ``` /// /// # Safety /// /// `CString` is intended for working with traditional C-style strings /// (a sequence of non-nul bytes terminated by a single nul byte); the /// primary use case for these kinds of strings is interoperating with C-like /// code. Often you will need to transfer ownership to/from that external /// code. It is strongly recommended that you thoroughly read through the /// documentation of `CString` before use, as improper ownership management /// of `CString` instances can lead to invalid memory accesses, memory leaks, /// and other memory errors. #[derive(PartialEq, PartialOrd, Eq, Ord, Hash, Clone)] pub struct CString { // Invariant 1: the slice ends with a zero byte and has a length of at least one. // Invariant 2: the slice contains only one zero byte. // Improper usage of unsafe function can break Invariant 2, but not Invariant 1. inner: Box<[u8]>, } /// Representation of a borrowed C string. /// /// This type represents a borrowed reference to a nul-terminated /// array of bytes. It can be constructed safely from a `&[`[`u8`]`]` /// slice, or unsafely from a raw `*const c_char`. It can then be /// converted to a Rust [`&str`] by performing UTF-8 validation, or /// into an owned [`CString`]. /// /// `CStr` is to [`CString`] as [`&str`] is to [`String`]: the former /// in each pair are borrowed references; the latter are owned /// strings. /// /// Note that this structure is **not** `repr(C)` and is not recommended to be /// placed in the signatures of FFI functions. Instead, safe wrappers of FFI /// functions may leverage the unsafe [`from_ptr`] constructor to provide a safe /// interface to other consumers. /// /// # Examples /// /// Inspecting a foreign C string: /// /// ```ignore (extern-declaration) /// use std::ffi::CStr; /// use std::os::raw::c_char; /// /// extern { fn my_string() -> *const c_char; } /// /// unsafe { /// let slice = CStr::from_ptr(my_string()); /// println!("string buffer size without nul terminator: {}", slice.to_bytes().len()); /// } /// ``` /// /// Passing a Rust-originating C string: /// /// ```ignore (extern-declaration) /// use std::ffi::{CString, CStr}; /// use std::os::raw::c_char; /// /// fn work(data: &CStr) { /// extern { fn work_with(data: *const c_char); } /// /// unsafe { work_with(data.as_ptr()) } /// } /// /// let s = CString::new("data data data data").unwrap(); /// work(&s); /// ``` /// /// Converting a foreign C string into a Rust [`String`]: /// /// ```ignore (extern-declaration) /// use std::ffi::CStr; /// use std::os::raw::c_char; /// /// extern { fn my_string() -> *const c_char; } /// /// fn my_string_safe() -> String { /// unsafe { /// CStr::from_ptr(my_string()).to_string_lossy().into_owned() /// } /// } /// /// println!("string: {}", my_string_safe()); /// ``` /// /// [`u8`]: ../primitive.u8.html /// [`&str`]: ../primitive.str.html /// [`String`]: ../string/struct.String.html /// [`CString`]: struct.CString.html /// [`from_ptr`]: #method.from_ptr #[derive(Hash)] pub struct CStr { // FIXME: this should not be represented with a DST slice but rather with // just a raw `c_char` along with some form of marker to make // this an unsized type. Essentially `sizeof(&CStr)` should be the // same as `sizeof(&c_char)` but `CStr` should be an unsized type. inner: [c_char], } /// An error indicating that an interior nul byte was found. /// /// While Rust strings may contain nul bytes in the middle, C strings /// can't, as that byte would effectively truncate the string. /// /// This error is created by the [`new`][`CString::new`] method on /// [`CString`]. See its documentation for more. /// /// [`CString`]: struct.CString.html /// [`CString::new`]: struct.CString.html#method.new /// /// # Examples /// /// ``` /// use std::ffi::{CString, NulError}; /// /// let _: NulError = CString::new(b"f\0oo".to_vec()).unwrap_err(); /// ``` #[derive(Clone, PartialEq, Eq, Debug)] pub struct NulError(usize, Vec); /// An error indicating that a nul byte was not in the expected position. /// /// The slice used to create a [`CStr`] must have one and only one nul /// byte at the end of the slice. /// /// This error is created by the /// [`from_bytes_with_nul`][`CStr::from_bytes_with_nul`] method on /// [`CStr`]. See its documentation for more. /// /// [`CStr`]: struct.CStr.html /// [`CStr::from_bytes_with_nul`]: struct.CStr.html#method.from_bytes_with_nul /// /// # Examples /// /// ``` /// use std::ffi::{CStr, FromBytesWithNulError}; /// /// let _: FromBytesWithNulError = CStr::from_bytes_with_nul(b"f\0oo").unwrap_err(); /// ``` #[derive(Clone, PartialEq, Eq, Debug)] pub struct FromBytesWithNulError { kind: FromBytesWithNulErrorKind, } #[derive(Clone, PartialEq, Eq, Debug)] enum FromBytesWithNulErrorKind { InteriorNul(usize), NotNulTerminated, } impl FromBytesWithNulError { fn interior_nul(pos: usize) -> FromBytesWithNulError { FromBytesWithNulError { kind: FromBytesWithNulErrorKind::InteriorNul(pos), } } fn not_nul_terminated() -> FromBytesWithNulError { FromBytesWithNulError { kind: FromBytesWithNulErrorKind::NotNulTerminated, } } fn description(&self) -> &str { match self.kind { FromBytesWithNulErrorKind::InteriorNul(..) => { "data provided contains an interior nul byte" } FromBytesWithNulErrorKind::NotNulTerminated => "data provided is not nul terminated", } } } /// An error indicating invalid UTF-8 when converting a [`CString`] into a [`String`]. /// /// `CString` is just a wrapper over a buffer of bytes with a nul /// terminator; [`into_string`][`CString::into_string`] performs UTF-8 /// validation on those bytes and may return this error. /// /// This `struct` is created by the /// [`into_string`][`CString::into_string`] method on [`CString`]. See /// its documentation for more. /// /// [`String`]: ../string/struct.String.html /// [`CString`]: struct.CString.html /// [`CString::into_string`]: struct.CString.html#method.into_string #[derive(Clone, PartialEq, Eq, Debug)] pub struct IntoStringError { inner: CString, error: Utf8Error, } impl CString { /// Creates a new C-compatible string from a container of bytes. /// /// This function will consume the provided data and use the /// underlying bytes to construct a new string, ensuring that /// there is a trailing 0 byte. This trailing 0 byte will be /// appended by this function; the provided data should *not* /// contain any 0 bytes in it. /// /// # Examples /// /// ```ignore (extern-declaration) /// use std::ffi::CString; /// use std::os::raw::c_char; /// /// extern { fn puts(s: *const c_char); } /// /// let to_print = CString::new("Hello!").unwrap(); /// unsafe { /// puts(to_print.as_ptr()); /// } /// ``` /// /// # Errors /// /// This function will return an error if the supplied bytes contain an /// internal 0 byte. The [`NulError`] returned will contain the bytes as well as /// the position of the nul byte. /// /// [`NulError`]: struct.NulError.html pub fn new>>(t: T) -> Result { Self::_new(t.into()) } fn _new(bytes: Vec) -> Result { match memchr(0, &bytes) { Some(i) => Err(NulError(i, bytes)), None => Ok(unsafe { CString::from_vec_unchecked(bytes) }), } } /// Creates a C-compatible string by consuming a byte vector, /// without checking for interior 0 bytes. /// /// This method is equivalent to [`new`] except that no runtime assertion /// is made that `v` contains no 0 bytes, and it requires an actual /// byte vector, not anything that can be converted to one with Into. /// /// [`new`]: #method.new /// /// # Examples /// /// ``` /// use std::ffi::CString; /// /// let raw = b"foo".to_vec(); /// unsafe { /// let c_string = CString::from_vec_unchecked(raw); /// } /// ``` pub unsafe fn from_vec_unchecked(mut v: Vec) -> CString { v.reserve_exact(1); v.push(0); CString { inner: v.into_boxed_slice(), } } /// Retakes ownership of a `CString` that was transferred to C via [`into_raw`]. /// /// Additionally, the length of the string will be recalculated from the pointer. /// /// # Safety /// /// This should only ever be called with a pointer that was earlier /// obtained by calling [`into_raw`] on a `CString`. Other usage (e.g. trying to take /// ownership of a string that was allocated by foreign code) is likely to lead /// to undefined behavior or allocator corruption. /// /// > **Note:** If you need to borrow a string that was allocated by /// > foreign code, use [`CStr`]. If you need to take ownership of /// > a string that was allocated by foreign code, you will need to /// > make your own provisions for freeing it appropriately, likely /// > with the foreign code's API to do that. /// /// [`into_raw`]: #method.into_raw /// [`CStr`]: struct.CStr.html /// /// # Examples /// /// Create a `CString`, pass ownership to an `extern` function (via raw pointer), then retake /// ownership with `from_raw`: /// /// ```ignore (extern-declaration) /// use std::ffi::CString; /// use std::os::raw::c_char; /// /// extern { /// fn some_extern_function(s: *mut c_char); /// } /// /// let c_string = CString::new("Hello!").unwrap(); /// let raw = c_string.into_raw(); /// unsafe { /// some_extern_function(raw); /// let c_string = CString::from_raw(raw); /// } /// ``` pub unsafe fn from_raw(ptr: *mut c_char) -> CString { let len = strlen(ptr) + 1; // Including the NUL byte let slice = slice::from_raw_parts_mut(ptr, len as usize); CString { inner: Box::from_raw(slice as *mut [c_char] as *mut [u8]), } } /// Consumes the `CString` and transfers ownership of the string to a C caller. /// /// The pointer which this function returns must be returned to Rust and reconstituted using /// [`from_raw`] to be properly deallocated. Specifically, one /// should *not* use the standard C `free()` function to deallocate /// this string. /// /// Failure to call [`from_raw`] will lead to a memory leak. /// /// [`from_raw`]: #method.from_raw /// /// # Examples /// /// ``` /// use std::ffi::CString; /// /// let c_string = CString::new("foo").unwrap(); /// /// let ptr = c_string.into_raw(); /// /// unsafe { /// assert_eq!(b'f', *ptr as u8); /// assert_eq!(b'o', *ptr.offset(1) as u8); /// assert_eq!(b'o', *ptr.offset(2) as u8); /// assert_eq!(b'\0', *ptr.offset(3) as u8); /// /// // retake pointer to free memory /// let _ = CString::from_raw(ptr); /// } /// ``` #[inline] pub fn into_raw(self) -> *mut c_char { Box::into_raw(self.into_inner()) as *mut c_char } /// Converts the `CString` into a [`String`] if it contains valid UTF-8 data. /// /// On failure, ownership of the original `CString` is returned. /// /// [`String`]: ../string/struct.String.html /// /// # Examples /// /// ``` /// use std::ffi::CString; /// /// let valid_utf8 = vec![b'f', b'o', b'o']; /// let cstring = CString::new(valid_utf8).unwrap(); /// assert_eq!(cstring.into_string().unwrap(), "foo"); /// /// let invalid_utf8 = vec![b'f', 0xff, b'o', b'o']; /// let cstring = CString::new(invalid_utf8).unwrap(); /// let err = cstring.into_string().err().unwrap(); /// assert_eq!(err.utf8_error().valid_up_to(), 1); /// ``` pub fn into_string(self) -> Result { String::from_utf8(self.into_bytes()).map_err(|e| IntoStringError { error: e.utf8_error(), inner: unsafe { CString::from_vec_unchecked(e.into_bytes()) }, }) } /// Consumes the `CString` and returns the underlying byte buffer. /// /// The returned buffer does **not** contain the trailing nul /// terminator, and it is guaranteed to not have any interior nul /// bytes. /// /// # Examples /// /// ``` /// use std::ffi::CString; /// /// let c_string = CString::new("foo").unwrap(); /// let bytes = c_string.into_bytes(); /// assert_eq!(bytes, vec![b'f', b'o', b'o']); /// ``` pub fn into_bytes(self) -> Vec { let mut vec = self.into_inner().into_vec(); let _nul = vec.pop(); debug_assert_eq!(_nul, Some(0u8)); vec } /// Equivalent to the [`into_bytes`] function except that the returned vector /// includes the trailing nul terminator. /// /// [`into_bytes`]: #method.into_bytes /// /// # Examples /// /// ``` /// use std::ffi::CString; /// /// let c_string = CString::new("foo").unwrap(); /// let bytes = c_string.into_bytes_with_nul(); /// assert_eq!(bytes, vec![b'f', b'o', b'o', b'\0']); /// ``` pub fn into_bytes_with_nul(self) -> Vec { self.into_inner().into_vec() } /// Returns the contents of this `CString` as a slice of bytes. /// /// The returned slice does **not** contain the trailing nul /// terminator, and it is guaranteed to not have any interior nul /// bytes. If you need the nul terminator, use /// [`as_bytes_with_nul`] instead. /// /// [`as_bytes_with_nul`]: #method.as_bytes_with_nul /// /// # Examples /// /// ``` /// use std::ffi::CString; /// /// let c_string = CString::new("foo").unwrap(); /// let bytes = c_string.as_bytes(); /// assert_eq!(bytes, &[b'f', b'o', b'o']); /// ``` #[inline] pub fn as_bytes(&self) -> &[u8] { &self.inner[..self.inner.len() - 1] } /// Equivalent to the [`as_bytes`] function except that the returned slice /// includes the trailing nul terminator. /// /// [`as_bytes`]: #method.as_bytes /// /// # Examples /// /// ``` /// use std::ffi::CString; /// /// let c_string = CString::new("foo").unwrap(); /// let bytes = c_string.as_bytes_with_nul(); /// assert_eq!(bytes, &[b'f', b'o', b'o', b'\0']); /// ``` #[inline] pub fn as_bytes_with_nul(&self) -> &[u8] { &self.inner } /// Extracts a [`CStr`] slice containing the entire string. /// /// [`CStr`]: struct.CStr.html /// /// # Examples /// /// ``` /// use std::ffi::{CString, CStr}; /// /// let c_string = CString::new(b"foo".to_vec()).unwrap(); /// let c_str = c_string.as_c_str(); /// assert_eq!(c_str, CStr::from_bytes_with_nul(b"foo\0").unwrap()); /// ``` #[inline] pub fn as_c_str(&self) -> &CStr { &*self } /// Converts this `CString` into a boxed [`CStr`]. /// /// [`CStr`]: struct.CStr.html /// /// # Examples /// /// ``` /// use std::ffi::{CString, CStr}; /// /// let c_string = CString::new(b"foo".to_vec()).unwrap(); /// let boxed = c_string.into_boxed_c_str(); /// assert_eq!(&*boxed, CStr::from_bytes_with_nul(b"foo\0").unwrap()); /// ``` pub fn into_boxed_c_str(self) -> Box { unsafe { Box::from_raw(Box::into_raw(self.into_inner()) as *mut CStr) } } // Bypass "move out of struct which implements [`Drop`] trait" restriction. /// /// [`Drop`]: ../ops/trait.Drop.html fn into_inner(self) -> Box<[u8]> { unsafe { let result = ptr::read(&self.inner); mem::forget(self); result } } } // Turns this `CString` into an empty string to prevent // memory unsafe code from working by accident. Inline // to prevent LLVM from optimizing it away in debug builds. impl Drop for CString { #[inline] fn drop(&mut self) { unsafe { *self.inner.get_unchecked_mut(0) = 0; } } } impl ops::Deref for CString { type Target = CStr; #[inline] fn deref(&self) -> &CStr { unsafe { CStr::from_bytes_with_nul_unchecked(self.as_bytes_with_nul()) } } } impl fmt::Debug for CString { fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result { fmt::Debug::fmt(&**self, f) } } impl From for Vec { /// Converts a [`CString`] into a [`Vec`]``. /// /// The conversion consumes the [`CString`], and removes the terminating NUL byte. /// /// [`Vec`]: ../vec/struct.Vec.html /// [`CString`]: ../ffi/struct.CString.html #[inline] fn from(s: CString) -> Vec { s.into_bytes() } } impl fmt::Debug for CStr { fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result { write!(f, "\"")?; for byte in self .to_bytes() .iter() .flat_map(|&b| ascii::escape_default(b)) { f.write_char(byte as char)?; } write!(f, "\"") } } impl<'a> Default for &'a CStr { fn default() -> &'a CStr { const SLICE: &[c_char] = &[0]; unsafe { CStr::from_ptr(SLICE.as_ptr()) } } } impl Default for CString { /// Creates an empty `CString`. fn default() -> CString { let a: &CStr = Default::default(); a.to_owned() } } impl Borrow for CString { #[inline] fn borrow(&self) -> &CStr { self } } impl<'a> From> for CString { #[inline] fn from(s: Cow<'a, CStr>) -> Self { s.into_owned() } } impl<'a> From<&'a CStr> for Box { fn from(s: &'a CStr) -> Box { let boxed: Box<[u8]> = Box::from(s.to_bytes_with_nul()); unsafe { Box::from_raw(Box::into_raw(boxed) as *mut CStr) } } } impl From> for CString { /// Converts a [`Box`]`` into a [`CString`] without copying or allocating. /// /// [`Box`]: ../boxed/struct.Box.html /// [`CString`]: ../ffi/struct.CString.html #[inline] fn from(s: Box) -> CString { s.into_c_string() } } impl Clone for Box { #[inline] fn clone(&self) -> Self { (**self).into() } } impl From for Box { /// Converts a [`CString`] into a [`Box`]`` without copying or allocating. /// /// [`CString`]: ../ffi/struct.CString.html /// [`Box`]: ../boxed/struct.Box.html #[inline] fn from(s: CString) -> Box { s.into_boxed_c_str() } } impl<'a> From for Cow<'a, CStr> { #[inline] fn from(s: CString) -> Cow<'a, CStr> { Cow::Owned(s) } } impl<'a> From<&'a CStr> for Cow<'a, CStr> { #[inline] fn from(s: &'a CStr) -> Cow<'a, CStr> { Cow::Borrowed(s) } } impl<'a> From<&'a CString> for Cow<'a, CStr> { #[inline] fn from(s: &'a CString) -> Cow<'a, CStr> { Cow::Borrowed(s.as_c_str()) } } impl From for Arc { /// Converts a [`CString`] into a [`Arc`]`` without copying or allocating. /// /// [`CString`]: ../ffi/struct.CString.html /// [`Arc`]: ../sync/struct.Arc.html #[inline] fn from(s: CString) -> Arc { let arc: Arc<[u8]> = Arc::from(s.into_inner()); unsafe { Arc::from_raw(Arc::into_raw(arc) as *const CStr) } } } impl<'a> From<&'a CStr> for Arc { #[inline] fn from(s: &CStr) -> Arc { let arc: Arc<[u8]> = Arc::from(s.to_bytes_with_nul()); unsafe { Arc::from_raw(Arc::into_raw(arc) as *const CStr) } } } impl From for Rc { /// Converts a [`CString`] into a [`Rc`]`` without copying or allocating. /// /// [`CString`]: ../ffi/struct.CString.html /// [`Rc`]: ../rc/struct.Rc.html #[inline] fn from(s: CString) -> Rc { let rc: Rc<[u8]> = Rc::from(s.into_inner()); unsafe { Rc::from_raw(Rc::into_raw(rc) as *const CStr) } } } impl<'a> From<&'a CStr> for Rc { #[inline] fn from(s: &CStr) -> Rc { let rc: Rc<[u8]> = Rc::from(s.to_bytes_with_nul()); unsafe { Rc::from_raw(Rc::into_raw(rc) as *const CStr) } } } impl Default for Box { fn default() -> Box { let boxed: Box<[u8]> = Box::from([0]); unsafe { Box::from_raw(Box::into_raw(boxed) as *mut CStr) } } } impl NulError { /// Returns the position of the nul byte in the slice that caused /// [`CString::new`] to fail. /// /// [`CString::new`]: struct.CString.html#method.new /// /// # Examples /// /// ``` /// use std::ffi::CString; /// /// let nul_error = CString::new("foo\0bar").unwrap_err(); /// assert_eq!(nul_error.nul_position(), 3); /// /// let nul_error = CString::new("foo bar\0").unwrap_err(); /// assert_eq!(nul_error.nul_position(), 7); /// ``` pub fn nul_position(&self) -> usize { self.0 } /// Consumes this error, returning the underlying vector of bytes which /// generated the error in the first place. /// /// # Examples /// /// ``` /// use std::ffi::CString; /// /// let nul_error = CString::new("foo\0bar").unwrap_err(); /// assert_eq!(nul_error.into_vec(), b"foo\0bar"); /// ``` pub fn into_vec(self) -> Vec { self.1 } } impl fmt::Display for NulError { fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result { write!(f, "nul byte found in provided data at position: {}", self.0) } } impl fmt::Display for FromBytesWithNulError { fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result { f.write_str(self.description())?; if let FromBytesWithNulErrorKind::InteriorNul(pos) = self.kind { write!(f, " at byte pos {}", pos)?; } Ok(()) } } impl IntoStringError { /// Consumes this error, returning original [`CString`] which generated the /// error. /// /// [`CString`]: struct.CString.html pub fn into_cstring(self) -> CString { self.inner } /// Access the underlying UTF-8 error that was the cause of this error. pub fn utf8_error(&self) -> Utf8Error { self.error } fn description(&self) -> &str { "C string contained non-utf8 bytes" } } impl fmt::Display for IntoStringError { fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result { self.description().fmt(f) } } impl CStr { /// Wraps a raw C string with a safe C string wrapper. /// /// This function will wrap the provided `ptr` with a `CStr` wrapper, which /// allows inspection and interoperation of non-owned C strings. This method /// is unsafe for a number of reasons: /// /// * There is no guarantee to the validity of `ptr`. /// * The returned lifetime is not guaranteed to be the actual lifetime of /// `ptr`. /// * There is no guarantee that the memory pointed to by `ptr` contains a /// valid nul terminator byte at the end of the string. /// * It is not guaranteed that the memory pointed by `ptr` won't change /// before the `CStr` has been destroyed. /// /// > **Note**: This operation is intended to be a 0-cost cast but it is /// > currently implemented with an up-front calculation of the length of /// > the string. This is not guaranteed to always be the case. /// /// # Examples /// /// ```ignore (extern-declaration) /// # fn main() { /// use std::ffi::CStr; /// use std::os::raw::c_char; /// /// extern { /// fn my_string() -> *const c_char; /// } /// /// unsafe { /// let slice = CStr::from_ptr(my_string()); /// println!("string returned: {}", slice.to_str().unwrap()); /// } /// # } /// ``` pub unsafe fn from_ptr<'a>(ptr: *const c_char) -> &'a CStr { let len = strlen(ptr); let ptr = ptr as *const u8; CStr::from_bytes_with_nul_unchecked(slice::from_raw_parts(ptr, len as usize + 1)) } /// Creates a C string wrapper from a byte slice. /// /// This function will cast the provided `bytes` to a `CStr` /// wrapper after ensuring that the byte slice is nul-terminated /// and does not contain any interior nul bytes. /// /// # Examples /// /// ``` /// use std::ffi::CStr; /// /// let cstr = CStr::from_bytes_with_nul(b"hello\0"); /// assert!(cstr.is_ok()); /// ``` /// /// Creating a `CStr` without a trailing nul terminator is an error: /// /// ``` /// use std::ffi::CStr; /// /// let c_str = CStr::from_bytes_with_nul(b"hello"); /// assert!(c_str.is_err()); /// ``` /// /// Creating a `CStr` with an interior nul byte is an error: /// /// ``` /// use std::ffi::CStr; /// /// let c_str = CStr::from_bytes_with_nul(b"he\0llo\0"); /// assert!(c_str.is_err()); /// ``` pub fn from_bytes_with_nul(bytes: &[u8]) -> Result<&CStr, FromBytesWithNulError> { let nul_pos = memchr(0, bytes); if let Some(nul_pos) = nul_pos { if nul_pos + 1 != bytes.len() { return Err(FromBytesWithNulError::interior_nul(nul_pos)); } Ok(unsafe { CStr::from_bytes_with_nul_unchecked(bytes) }) } else { Err(FromBytesWithNulError::not_nul_terminated()) } } /// Unsafely creates a C string wrapper from a byte slice. /// /// This function will cast the provided `bytes` to a `CStr` wrapper without /// performing any sanity checks. The provided slice **must** be nul-terminated /// and not contain any interior nul bytes. /// /// # Examples /// /// ``` /// use std::ffi::{CStr, CString}; /// /// unsafe { /// let cstring = CString::new("hello").unwrap(); /// let cstr = CStr::from_bytes_with_nul_unchecked(cstring.to_bytes_with_nul()); /// assert_eq!(cstr, &*cstring); /// } /// ``` #[inline] pub const unsafe fn from_bytes_with_nul_unchecked(bytes: &[u8]) -> &CStr { &*(bytes as *const [u8] as *const CStr) } /// Returns the inner pointer to this C string. /// /// The returned pointer will be valid for as long as `self` is, and points /// to a contiguous region of memory terminated with a 0 byte to represent /// the end of the string. /// /// **WARNING** /// /// It is your responsibility to make sure that the underlying memory is not /// freed too early. For example, the following code will cause undefined /// behavior when `ptr` is used inside the `unsafe` block: /// /// ```no_run /// # #![allow(unused_must_use)] /// use std::ffi::{CString}; /// /// let ptr = CString::new("Hello").unwrap().as_ptr(); /// unsafe { /// // `ptr` is dangling /// *ptr; /// } /// ``` /// /// This happens because the pointer returned by `as_ptr` does not carry any /// lifetime information and the [`CString`] is deallocated immediately after /// the `CString::new("Hello").unwrap().as_ptr()` expression is evaluated. /// To fix the problem, bind the `CString` to a local variable: /// /// ```no_run /// # #![allow(unused_must_use)] /// use std::ffi::{CString}; /// /// let hello = CString::new("Hello").unwrap(); /// let ptr = hello.as_ptr(); /// unsafe { /// // `ptr` is valid because `hello` is in scope /// *ptr; /// } /// ``` /// /// This way, the lifetime of the `CString` in `hello` encompasses /// the lifetime of `ptr` and the `unsafe` block. /// /// [`CString`]: struct.CString.html #[inline] pub fn as_ptr(&self) -> *const c_char { self.inner.as_ptr() } /// Converts this C string to a byte slice. /// /// The returned slice will **not** contain the trailing nul terminator that this C /// string has. /// /// > **Note**: This method is currently implemented as a constant-time /// > cast, but it is planned to alter its definition in the future to /// > perform the length calculation whenever this method is called. /// /// # Examples /// /// ``` /// use std::ffi::CStr; /// /// let c_str = CStr::from_bytes_with_nul(b"foo\0").unwrap(); /// assert_eq!(c_str.to_bytes(), b"foo"); /// ``` #[inline] pub fn to_bytes(&self) -> &[u8] { let bytes = self.to_bytes_with_nul(); &bytes[..bytes.len() - 1] } /// Converts this C string to a byte slice containing the trailing 0 byte. /// /// This function is the equivalent of [`to_bytes`] except that it will retain /// the trailing nul terminator instead of chopping it off. /// /// > **Note**: This method is currently implemented as a 0-cost cast, but /// > it is planned to alter its definition in the future to perform the /// > length calculation whenever this method is called. /// /// [`to_bytes`]: #method.to_bytes /// /// # Examples /// /// ``` /// use std::ffi::CStr; /// /// let c_str = CStr::from_bytes_with_nul(b"foo\0").unwrap(); /// assert_eq!(c_str.to_bytes_with_nul(), b"foo\0"); /// ``` #[inline] pub fn to_bytes_with_nul(&self) -> &[u8] { unsafe { &*(&self.inner as *const [c_char] as *const [u8]) } } /// 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. /// /// > **Note**: This method is currently implemented to check for validity /// > after a constant-time cast, but it is planned to alter its definition /// > in the future to perform the length calculation in addition to the /// > UTF-8 check whenever this method is called. /// /// [`&str`]: ../primitive.str.html /// /// # Examples /// /// ``` /// use std::ffi::CStr; /// /// let c_str = CStr::from_bytes_with_nul(b"foo\0").unwrap(); /// assert_eq!(c_str.to_str(), Ok("foo")); /// ``` pub fn to_str(&self) -> Result<&str, str::Utf8Error> { // NB: When CStr is changed to perform the length check in .to_bytes() // instead of in from_ptr(), it may be worth considering if this should // be rewritten to do the UTF-8 check inline with the length calculation // instead of doing it afterwards. str::from_utf8(self.to_bytes()) } /// Converts a `CStr` into a [`Cow`]`<`[`str`]`>`. /// /// If the contents of the `CStr` are valid UTF-8 data, this /// function will return a [`Cow`]`::`[`Borrowed`]`(`[`&str`]`)` /// with the the corresponding [`&str`] slice. Otherwise, it will /// replace any invalid UTF-8 sequences with /// [`U+FFFD REPLACEMENT CHARACTER`][U+FFFD] and return a /// [`Cow`]`::`[`Owned`]`(`[`String`]`)` with the result. /// /// > **Note**: This method is currently implemented to check for validity /// > after a constant-time cast, but it is planned to alter its definition /// > in the future to perform the length calculation in addition to the /// > UTF-8 check whenever this method is called. /// /// [`Cow`]: ../borrow/enum.Cow.html /// [`Borrowed`]: ../borrow/enum.Cow.html#variant.Borrowed /// [`Owned`]: ../borrow/enum.Cow.html#variant.Owned /// [`str`]: ../primitive.str.html /// [`String`]: ../string/struct.String.html /// [U+FFFD]: ../char/constant.REPLACEMENT_CHARACTER.html /// /// # Examples /// /// Calling `to_string_lossy` on a `CStr` containing valid UTF-8: /// /// ``` /// use std::borrow::Cow; /// use std::ffi::CStr; /// /// let c_str = CStr::from_bytes_with_nul(b"Hello World\0").unwrap(); /// assert_eq!(c_str.to_string_lossy(), Cow::Borrowed("Hello World")); /// ``` /// /// Calling `to_string_lossy` on a `CStr` containing invalid UTF-8: /// /// ``` /// use std::borrow::Cow; /// use std::ffi::CStr; /// /// let c_str = CStr::from_bytes_with_nul(b"Hello \xF0\x90\x80World\0").unwrap(); /// assert_eq!( /// c_str.to_string_lossy(), /// Cow::Owned(String::from("Hello �World")) as Cow /// ); /// ``` pub fn to_string_lossy(&self) -> Cow { String::from_utf8_lossy(self.to_bytes()) } /// Converts a [`Box`]`` into a [`CString`] without copying or allocating. /// /// [`Box`]: ../boxed/struct.Box.html /// [`CString`]: struct.CString.html /// /// # Examples /// /// ``` /// use std::ffi::CString; /// /// let c_string = CString::new(b"foo".to_vec()).unwrap(); /// let boxed = c_string.into_boxed_c_str(); /// assert_eq!(boxed.into_c_string(), CString::new("foo").unwrap()); /// ``` pub fn into_c_string(self: Box) -> CString { let raw = Box::into_raw(self) as *mut [u8]; CString { inner: unsafe { Box::from_raw(raw) }, } } } impl PartialEq for CStr { fn eq(&self, other: &CStr) -> bool { self.to_bytes().eq(other.to_bytes()) } } impl Eq for CStr {} impl PartialOrd for CStr { fn partial_cmp(&self, other: &CStr) -> Option { self.to_bytes().partial_cmp(&other.to_bytes()) } } impl Ord for CStr { fn cmp(&self, other: &CStr) -> Ordering { self.to_bytes().cmp(&other.to_bytes()) } } impl ToOwned for CStr { type Owned = CString; fn to_owned(&self) -> CString { CString { inner: self.to_bytes_with_nul().into(), } } } impl<'a> From<&'a CStr> for CString { fn from(s: &'a CStr) -> CString { s.to_owned() } } impl ops::Index for CString { type Output = CStr; #[inline] fn index(&self, _index: ops::RangeFull) -> &CStr { self } } impl AsRef for CStr { #[inline] fn as_ref(&self) -> &CStr { self } } impl AsRef for CString { #[inline] fn as_ref(&self) -> &CStr { self } }