// 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 ascii; use borrow::{Cow, Borrow}; use cmp::Ordering; use error::Error; use fmt::{self, Write}; use io; use libc; use mem; use memchr; use ops; use os::raw::c_char; use ptr; use slice; use str::{self, Utf8Error}; /// A type representing an owned C-compatible string. /// /// This type serves the primary 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 and the final byte is 0. /// /// A `CString` is created from either a byte slice or a byte vector. A [`u8`] /// slice can be obtained with the `as_bytes` method. Slices produced from a /// `CString` do *not* contain the trailing nul terminator unless otherwise /// specified. /// /// [`u8`]: ../primitive.u8.html /// /// # Examples /// /// ```no_run /// # fn main() { /// use std::ffi::CString; /// use std::os::raw::c_char; /// /// extern { /// fn my_printer(s: *const c_char); /// } /// /// 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-null bytes terminated by a single null 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)] #[stable(feature = "rust1", since = "1.0.0")] 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 dynamically sized type is only safely constructed via a borrowed /// version of an instance of `CString`. This type can be constructed from a raw /// C string as well and represents a C string borrowed from another location. /// /// 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. /// /// [`from_ptr`]: #method.from_ptr /// /// # Examples /// /// Inspecting a foreign C string: /// /// ```no_run /// 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 length: {}", slice.to_bytes().len()); /// } /// ``` /// /// Passing a Rust-originating C string: /// /// ```no_run /// 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`]: /// /// [`String`]: ../string/struct.String.html /// /// ```no_run /// 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()); /// ``` #[derive(Hash)] #[stable(feature = "rust1", since = "1.0.0")] 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 returned from [`CString::new`] to indicate that a nul byte was found /// in the vector provided. /// /// [`CString::new`]: struct.CString.html#method.new #[derive(Clone, PartialEq, Eq, Debug)] #[stable(feature = "rust1", since = "1.0.0")] pub struct NulError(usize, Vec); /// An error returned from [`CStr::from_bytes_with_nul`] to indicate that a nul /// byte was found too early in the slice provided or one wasn't found at all. /// /// [`CStr::from_bytes_with_nul`]: struct.CStr.html#method.from_bytes_with_nul #[derive(Clone, PartialEq, Eq, Debug)] #[stable(feature = "cstr_from_bytes", since = "1.10.0")] 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, } } } /// An error returned from [`CString::into_string`] to indicate that a UTF-8 error /// was encountered during the conversion. /// /// [`CString::into_string`]: struct.CString.html#method.into_string #[derive(Clone, PartialEq, Eq, Debug)] #[stable(feature = "cstring_into", since = "1.7.0")] pub struct IntoStringError { inner: CString, error: Utf8Error, } impl CString { /// Creates a new C-compatible string from a container of bytes. /// /// This method will consume the provided data and use the underlying bytes /// to construct a new string, ensuring that there is a trailing 0 byte. /// /// # Examples /// /// ```no_run /// 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 bytes yielded contain an /// internal 0 byte. The error returned will contain the bytes as well as /// the position of the nul byte. #[stable(feature = "rust1", since = "1.0.0")] pub fn new>>(t: T) -> Result { Self::_new(t.into()) } fn _new(bytes: Vec) -> Result { match memchr::memchr(0, &bytes) { Some(i) => Err(NulError(i, bytes)), None => Ok(unsafe { CString::from_vec_unchecked(bytes) }), } } /// Creates a C-compatible string from 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); /// } /// ``` #[stable(feature = "rust1", since = "1.0.0")] 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. /// /// 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. /// /// [`into_raw`]: #method.into_raw #[stable(feature = "cstr_memory", since = "1.4.0")] pub unsafe fn from_raw(ptr: *mut c_char) -> CString { let len = libc::strlen(ptr) + 1; // Including the NUL byte let slice = slice::from_raw_parts(ptr, len as usize); CString { inner: mem::transmute(slice) } } /// Transfers ownership of the string to a C caller. /// /// The pointer 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] #[stable(feature = "cstr_memory", since = "1.4.0")] 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 Unicode data. /// /// On failure, ownership of the original `CString` is returned. /// /// [`String`]: ../string/struct.String.html #[stable(feature = "cstring_into", since = "1.7.0")] 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()) }, }) } /// Returns the underlying byte buffer. /// /// The returned buffer does **not** contain the trailing nul separator 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']); /// ``` #[stable(feature = "cstring_into", since = "1.7.0")] 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 byte. /// /// [`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']); /// ``` #[stable(feature = "cstring_into", since = "1.7.0")] 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 separator 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.as_bytes(); /// assert_eq!(bytes, &[b'f', b'o', b'o']); /// ``` #[inline] #[stable(feature = "rust1", since = "1.0.0")] 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 byte. /// /// [`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] #[stable(feature = "rust1", since = "1.0.0")] pub fn as_bytes_with_nul(&self) -> &[u8] { &self.inner } /// Extracts a [`CStr`] slice containing the entire string. /// /// [`CStr`]: struct.CStr.html #[inline] #[unstable(feature = "as_c_str", issue = "40380")] pub fn as_c_str(&self) -> &CStr { &*self } /// Converts this `CString` into a boxed [`CStr`]. /// /// [`CStr`]: struct.CStr.html #[unstable(feature = "into_boxed_c_str", issue = "40380")] pub fn into_boxed_c_str(self) -> Box { unsafe { mem::transmute(self.into_inner()) } } // 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. #[stable(feature = "cstring_drop", since = "1.13.0")] impl Drop for CString { #[inline] fn drop(&mut self) { unsafe { *self.inner.get_unchecked_mut(0) = 0; } } } #[stable(feature = "rust1", since = "1.0.0")] 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()) } } } #[stable(feature = "rust1", since = "1.0.0")] impl fmt::Debug for CString { fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result { fmt::Debug::fmt(&**self, f) } } #[stable(feature = "cstring_into", since = "1.7.0")] impl From for Vec { #[inline] fn from(s: CString) -> Vec { s.into_bytes() } } #[stable(feature = "cstr_debug", since = "1.3.0")] 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, "\"") } } #[stable(feature = "cstr_default", since = "1.10.0")] impl<'a> Default for &'a CStr { fn default() -> &'a CStr { static SLICE: &'static [c_char] = &[0]; unsafe { CStr::from_ptr(SLICE.as_ptr()) } } } #[stable(feature = "cstr_default", since = "1.10.0")] impl Default for CString { /// Creates an empty `CString`. fn default() -> CString { let a: &CStr = Default::default(); a.to_owned() } } #[stable(feature = "cstr_borrow", since = "1.3.0")] impl Borrow for CString { #[inline] fn borrow(&self) -> &CStr { self } } #[stable(feature = "box_from_c_str", since = "1.17.0")] 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 { mem::transmute(boxed) } } } #[stable(feature = "c_string_from_box", since = "1.18.0")] impl From> for CString { #[inline] fn from(s: Box) -> CString { s.into_c_string() } } #[stable(feature = "box_from_c_string", since = "1.18.0")] impl Into> for CString { #[inline] fn into(self) -> Box { self.into_boxed_c_str() } } #[stable(feature = "default_box_extra", since = "1.17.0")] impl Default for Box { fn default() -> Box { let boxed: Box<[u8]> = Box::from([0]); unsafe { mem::transmute(boxed) } } } impl NulError { /// Returns the position of the nul byte in the slice that was provided to /// [`CString::new`]. /// /// [`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); /// ``` #[stable(feature = "rust1", since = "1.0.0")] 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"); /// ``` #[stable(feature = "rust1", since = "1.0.0")] pub fn into_vec(self) -> Vec { self.1 } } #[stable(feature = "rust1", since = "1.0.0")] impl Error for NulError { fn description(&self) -> &str { "nul byte found in data" } } #[stable(feature = "rust1", since = "1.0.0")] 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) } } #[stable(feature = "rust1", since = "1.0.0")] impl From for io::Error { fn from(_: NulError) -> io::Error { io::Error::new(io::ErrorKind::InvalidInput, "data provided contains a nul byte") } } #[stable(feature = "frombyteswithnulerror_impls", since = "1.17.0")] impl Error for FromBytesWithNulError { fn description(&self) -> &str { match self.kind { FromBytesWithNulErrorKind::InteriorNul(..) => "data provided contains an interior nul byte", FromBytesWithNulErrorKind::NotNulTerminated => "data provided is not nul terminated", } } } #[stable(feature = "frombyteswithnulerror_impls", since = "1.17.0")] 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 #[stable(feature = "cstring_into", since = "1.7.0")] pub fn into_cstring(self) -> CString { self.inner } /// Access the underlying UTF-8 error that was the cause of this error. #[stable(feature = "cstring_into", since = "1.7.0")] pub fn utf8_error(&self) -> Utf8Error { self.error } } #[stable(feature = "cstring_into", since = "1.7.0")] impl Error for IntoStringError { fn description(&self) -> &str { "C string contained non-utf8 bytes" } fn cause(&self) -> Option<&Error> { Some(&self.error) } } #[stable(feature = "cstring_into", since = "1.7.0")] impl fmt::Display for IntoStringError { fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result { self.description().fmt(f) } } impl CStr { /// Casts a raw C string to a safe C string wrapper. /// /// This function will cast the provided `ptr` to the `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. /// /// > **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 /// /// ```no_run /// # 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()); /// } /// # } /// ``` #[stable(feature = "rust1", since = "1.0.0")] pub unsafe fn from_ptr<'a>(ptr: *const c_char) -> &'a CStr { let len = libc::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 it is null 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()); /// ``` #[stable(feature = "cstr_from_bytes", since = "1.10.0")] pub fn from_bytes_with_nul(bytes: &[u8]) -> Result<&CStr, FromBytesWithNulError> { let nul_pos = memchr::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 null 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] #[stable(feature = "cstr_from_bytes", since = "1.10.0")] pub unsafe fn from_bytes_with_nul_unchecked(bytes: &[u8]) -> &CStr { mem::transmute(bytes) } /// 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 /// behaviour when `ptr` is used inside the `unsafe` block: /// /// ```no_run /// 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 string is deallocated immediately after /// the `CString::new("Hello").unwrap().as_ptr()` expression is evaluated. /// To fix the problem, bind the string to a local variable: /// /// ```no_run /// 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; /// } /// ``` #[inline] #[stable(feature = "rust1", since = "1.0.0")] pub fn as_ptr(&self) -> *const c_char { self.inner.as_ptr() } /// Converts this C string to a byte slice. /// /// This function will calculate the length of this string (which normally /// requires a linear amount of work to be done) and then return the /// resulting slice of `u8` elements. /// /// The returned slice will **not** contain the trailing nul that this C /// string has. /// /// > **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. #[inline] #[stable(feature = "rust1", since = "1.0.0")] 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 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 #[inline] #[stable(feature = "rust1", since = "1.0.0")] pub fn to_bytes_with_nul(&self) -> &[u8] { unsafe { mem::transmute(&self.inner) } } /// Yields a [`&str`] slice if the `CStr` contains valid UTF-8. /// /// This function will calculate the length of this string and check for /// UTF-8 validity, and then return the [`&str`] if it's valid. /// /// > **Note**: This method is currently implemented to check for validity /// > after a 0-cost 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 #[stable(feature = "cstr_to_str", since = "1.4.0")] 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`]`>`. /// /// This function will calculate the length of this string (which normally /// requires a linear amount of work to be done) and then return the /// resulting slice as a [`Cow`]`<`[`str`]`>`, replacing any invalid UTF-8 sequences /// with `U+FFFD REPLACEMENT CHARACTER`. /// /// > **Note**: This method is currently implemented to check for validity /// > after a 0-cost 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 /// [`str`]: ../primitive.str.html #[stable(feature = "cstr_to_str", since = "1.4.0")] 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 #[unstable(feature = "into_boxed_c_str", issue = "40380")] pub fn into_c_string(self: Box) -> CString { unsafe { mem::transmute(self) } } } #[stable(feature = "rust1", since = "1.0.0")] impl PartialEq for CStr { fn eq(&self, other: &CStr) -> bool { self.to_bytes().eq(other.to_bytes()) } } #[stable(feature = "rust1", since = "1.0.0")] impl Eq for CStr {} #[stable(feature = "rust1", since = "1.0.0")] impl PartialOrd for CStr { fn partial_cmp(&self, other: &CStr) -> Option { self.to_bytes().partial_cmp(&other.to_bytes()) } } #[stable(feature = "rust1", since = "1.0.0")] impl Ord for CStr { fn cmp(&self, other: &CStr) -> Ordering { self.to_bytes().cmp(&other.to_bytes()) } } #[stable(feature = "cstr_borrow", since = "1.3.0")] impl ToOwned for CStr { type Owned = CString; fn to_owned(&self) -> CString { CString { inner: self.to_bytes_with_nul().into() } } } #[stable(feature = "cstring_asref", since = "1.7.0")] impl<'a> From<&'a CStr> for CString { fn from(s: &'a CStr) -> CString { s.to_owned() } } #[stable(feature = "cstring_asref", since = "1.7.0")] impl ops::Index for CString { type Output = CStr; #[inline] fn index(&self, _index: ops::RangeFull) -> &CStr { self } } #[stable(feature = "cstring_asref", since = "1.7.0")] impl AsRef for CStr { #[inline] fn as_ref(&self) -> &CStr { self } } #[stable(feature = "cstring_asref", since = "1.7.0")] impl AsRef for CString { #[inline] fn as_ref(&self) -> &CStr { self } } #[cfg(test)] mod tests { use super::*; use os::raw::c_char; use borrow::Cow::{Borrowed, Owned}; use hash::{Hash, Hasher}; use collections::hash_map::DefaultHasher; #[test] fn c_to_rust() { let data = b"123\0"; let ptr = data.as_ptr() as *const c_char; unsafe { assert_eq!(CStr::from_ptr(ptr).to_bytes(), b"123"); assert_eq!(CStr::from_ptr(ptr).to_bytes_with_nul(), b"123\0"); } } #[test] fn simple() { let s = CString::new("1234").unwrap(); assert_eq!(s.as_bytes(), b"1234"); assert_eq!(s.as_bytes_with_nul(), b"1234\0"); } #[test] fn build_with_zero1() { assert!(CString::new(&b"\0"[..]).is_err()); } #[test] fn build_with_zero2() { assert!(CString::new(vec![0]).is_err()); } #[test] fn build_with_zero3() { unsafe { let s = CString::from_vec_unchecked(vec![0]); assert_eq!(s.as_bytes(), b"\0"); } } #[test] fn formatted() { let s = CString::new(&b"abc\x01\x02\n\xE2\x80\xA6\xFF"[..]).unwrap(); assert_eq!(format!("{:?}", s), r#""abc\x01\x02\n\xe2\x80\xa6\xff""#); } #[test] fn borrowed() { unsafe { let s = CStr::from_ptr(b"12\0".as_ptr() as *const _); assert_eq!(s.to_bytes(), b"12"); assert_eq!(s.to_bytes_with_nul(), b"12\0"); } } #[test] fn to_str() { let data = b"123\xE2\x80\xA6\0"; let ptr = data.as_ptr() as *const c_char; unsafe { assert_eq!(CStr::from_ptr(ptr).to_str(), Ok("123…")); assert_eq!(CStr::from_ptr(ptr).to_string_lossy(), Borrowed("123…")); } let data = b"123\xE2\0"; let ptr = data.as_ptr() as *const c_char; unsafe { assert!(CStr::from_ptr(ptr).to_str().is_err()); assert_eq!(CStr::from_ptr(ptr).to_string_lossy(), Owned::(format!("123\u{FFFD}"))); } } #[test] fn to_owned() { let data = b"123\0"; let ptr = data.as_ptr() as *const c_char; let owned = unsafe { CStr::from_ptr(ptr).to_owned() }; assert_eq!(owned.as_bytes_with_nul(), data); } #[test] fn equal_hash() { let data = b"123\xE2\xFA\xA6\0"; let ptr = data.as_ptr() as *const c_char; let cstr: &'static CStr = unsafe { CStr::from_ptr(ptr) }; let mut s = DefaultHasher::new(); cstr.hash(&mut s); let cstr_hash = s.finish(); let mut s = DefaultHasher::new(); CString::new(&data[..data.len() - 1]).unwrap().hash(&mut s); let cstring_hash = s.finish(); assert_eq!(cstr_hash, cstring_hash); } #[test] fn from_bytes_with_nul() { let data = b"123\0"; let cstr = CStr::from_bytes_with_nul(data); assert_eq!(cstr.map(CStr::to_bytes), Ok(&b"123"[..])); let cstr = CStr::from_bytes_with_nul(data); assert_eq!(cstr.map(CStr::to_bytes_with_nul), Ok(&b"123\0"[..])); unsafe { let cstr = CStr::from_bytes_with_nul(data); let cstr_unchecked = CStr::from_bytes_with_nul_unchecked(data); assert_eq!(cstr, Ok(cstr_unchecked)); } } #[test] fn from_bytes_with_nul_unterminated() { let data = b"123"; let cstr = CStr::from_bytes_with_nul(data); assert!(cstr.is_err()); } #[test] fn from_bytes_with_nul_interior() { let data = b"1\023\0"; let cstr = CStr::from_bytes_with_nul(data); assert!(cstr.is_err()); } #[test] fn into_boxed() { let orig: &[u8] = b"Hello, world!\0"; let cstr = CStr::from_bytes_with_nul(orig).unwrap(); let boxed: Box = Box::from(cstr); let cstring = cstr.to_owned().into_boxed_c_str().into_c_string(); assert_eq!(cstr, &*boxed); assert_eq!(&*boxed, &*cstring); assert_eq!(&*cstring, cstr); } #[test] fn boxed_default() { let boxed = >::default(); assert_eq!(boxed.to_bytes_with_nul(), &[0]); } }