diff options
| author | mark <markm@cs.wisc.edu> | 2020-06-11 21:31:49 -0500 |
|---|---|---|
| committer | mark <markm@cs.wisc.edu> | 2020-07-27 19:51:13 -0500 |
| commit | 2c31b45ae878b821975c4ebd94cc1e49f6073fd0 (patch) | |
| tree | 14f64e683e3f64dcbcfb8c2c7cb45ac7592e6e09 /library/std/src/ffi | |
| parent | 9be8ffcb0206fc1558069a7b4766090df7877659 (diff) | |
| download | rust-2c31b45ae878b821975c4ebd94cc1e49f6073fd0.tar.gz rust-2c31b45ae878b821975c4ebd94cc1e49f6073fd0.zip | |
mv std libs to library/
Diffstat (limited to 'library/std/src/ffi')
| -rw-r--r-- | library/std/src/ffi/c_str.rs | 1788 | ||||
| -rw-r--r-- | library/std/src/ffi/mod.rs | 180 | ||||
| -rw-r--r-- | library/std/src/ffi/os_str.rs | 1365 |
3 files changed, 3333 insertions, 0 deletions
diff --git a/library/std/src/ffi/c_str.rs b/library/std/src/ffi/c_str.rs new file mode 100644 index 00000000000..da25a0ede72 --- /dev/null +++ b/library/std/src/ffi/c_str.rs @@ -0,0 +1,1788 @@ +use crate::ascii; +use crate::borrow::{Borrow, Cow}; +use crate::cmp::Ordering; +use crate::error::Error; +use crate::fmt::{self, Write}; +use crate::io; +use crate::mem; +use crate::memchr; +use crate::num::NonZeroU8; +use crate::ops; +use crate::os::raw::c_char; +use crate::ptr; +use crate::rc::Rc; +use crate::slice; +use crate::str::{self, Utf8Error}; +use crate::sync::Arc; +use crate::sys; + +/// 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()`. Notice that [`as_ptr`] returns a +/// read-only pointer; if the C code writes to it, that causes +/// undefined behavior. +/// +/// # 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 read-only 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 +/// [`&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 .expect() +/// let c_to_print = CString::new("Hello, world!").expect("CString::new failed"); +/// 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)] +#[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 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").expect("CString::new failed"); +/// 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)] +#[stable(feature = "rust1", since = "1.0.0")] +// FIXME: +// `fn from` in `impl From<&CStr> for Box<CStr>` current implementation relies +// on `CStr` being layout-compatible with `[u8]`. +// When attribute privacy is implemented, `CStr` should be annotated as `#[repr(transparent)]`. +// Anyway, `CStr` representation and layout are considered implementation detail, are +// not documented and must not be relied upon. +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)] +#[stable(feature = "rust1", since = "1.0.0")] +pub struct NulError(usize, Vec<u8>); + +/// 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, +/// positioned at the end. +/// +/// This error is created by the [`from_bytes_with_nul`] method on [`CStr`]. +/// See its documentation for more. +/// +/// [`CStr`]: struct.CStr.html +/// [`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)] +#[stable(feature = "cstr_from_bytes", since = "1.10.0")] +pub struct FromBytesWithNulError { + kind: FromBytesWithNulErrorKind, +} + +/// An error indicating that a nul byte was not in the expected position. +/// +/// The vector used to create a [`CString`] must have one and only one nul byte, +/// positioned at the end. +/// +/// This error is created by the [`from_vec_with_nul`] method on [`CString`]. +/// See its documentation for more. +/// +/// [`CString`]: struct.CString.html +/// [`from_vec_with_nul`]: struct.CString.html#method.from_vec_with_nul +/// +/// # Examples +/// +/// ``` +/// #![feature(cstring_from_vec_with_nul)] +/// use std::ffi::{CString, FromVecWithNulError}; +/// +/// let _: FromVecWithNulError = CString::from_vec_with_nul(b"f\0oo".to_vec()).unwrap_err(); +/// ``` +#[derive(Clone, PartialEq, Eq, Debug)] +#[unstable(feature = "cstring_from_vec_with_nul", issue = "73179")] +pub struct FromVecWithNulError { + error_kind: FromBytesWithNulErrorKind, + bytes: Vec<u8>, +} + +#[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 } + } +} + +#[unstable(feature = "cstring_from_vec_with_nul", issue = "73179")] +impl FromVecWithNulError { + /// Returns a slice of [`u8`]s bytes that were attempted to convert to a [`CString`]. + /// + /// # Examples + /// + /// Basic usage: + /// + /// ``` + /// #![feature(cstring_from_vec_with_nul)] + /// use std::ffi::CString; + /// + /// // Some invalid bytes in a vector + /// let bytes = b"f\0oo".to_vec(); + /// + /// let value = CString::from_vec_with_nul(bytes.clone()); + /// + /// assert_eq!(&bytes[..], value.unwrap_err().as_bytes()); + /// ``` + /// + /// [`CString`]: struct.CString.html + pub fn as_bytes(&self) -> &[u8] { + &self.bytes[..] + } + + /// Returns the bytes that were attempted to convert to a [`CString`]. + /// + /// This method is carefully constructed to avoid allocation. It will + /// consume the error, moving out the bytes, so that a copy of the bytes + /// does not need to be made. + /// + /// # Examples + /// + /// Basic usage: + /// + /// ``` + /// #![feature(cstring_from_vec_with_nul)] + /// use std::ffi::CString; + /// + /// // Some invalid bytes in a vector + /// let bytes = b"f\0oo".to_vec(); + /// + /// let value = CString::from_vec_with_nul(bytes.clone()); + /// + /// assert_eq!(bytes, value.unwrap_err().into_bytes()); + /// ``` + /// + /// [`CString`]: struct.CString.html + pub fn into_bytes(self) -> Vec<u8> { + self.bytes + } +} + +/// 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)] +#[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 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!").expect("CString::new failed"); + /// 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 + #[stable(feature = "rust1", since = "1.0.0")] + pub fn new<T: Into<Vec<u8>>>(t: T) -> Result<CString, NulError> { + trait SpecIntoVec { + fn into_vec(self) -> Vec<u8>; + } + impl<T: Into<Vec<u8>>> SpecIntoVec for T { + default fn into_vec(self) -> Vec<u8> { + self.into() + } + } + // Specialization for avoiding reallocation. + impl SpecIntoVec for &'_ [u8] { + fn into_vec(self) -> Vec<u8> { + let mut v = Vec::with_capacity(self.len() + 1); + v.extend(self); + v + } + } + impl SpecIntoVec for &'_ str { + fn into_vec(self) -> Vec<u8> { + let mut v = Vec::with_capacity(self.len() + 1); + v.extend(self.as_bytes()); + v + } + } + + Self::_new(SpecIntoVec::into_vec(t)) + } + + fn _new(bytes: Vec<u8>) -> Result<CString, NulError> { + match memchr::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); + /// } + /// ``` + #[stable(feature = "rust1", since = "1.0.0")] + pub unsafe fn from_vec_unchecked(mut v: Vec<u8>) -> 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. + /// + /// It should be noted that the length isn't just "recomputed," but that + /// the recomputed length must match the original length from the + /// [`into_raw`] call. This means the [`into_raw`]/`from_raw` methods + /// should not be used when passing the string to C functions that can + /// modify the string's length. + /// + /// > **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 + /// + /// Creates 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!").expect("CString::new failed"); + /// let raw = c_string.into_raw(); + /// unsafe { + /// some_extern_function(raw); + /// let c_string = CString::from_raw(raw); + /// } + /// ``` + #[stable(feature = "cstr_memory", since = "1.4.0")] + pub unsafe fn from_raw(ptr: *mut c_char) -> CString { + let len = sys::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. + /// + /// The C side must **not** modify the length of the string (by writing a + /// `NULL` somewhere inside the string or removing the final one) before + /// it makes it back into Rust using [`from_raw`]. See the safety section + /// in [`from_raw`]. + /// + /// [`from_raw`]: #method.from_raw + /// + /// # Examples + /// + /// ``` + /// use std::ffi::CString; + /// + /// let c_string = CString::new("foo").expect("CString::new failed"); + /// + /// 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 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).expect("CString::new failed"); + /// assert_eq!(cstring.into_string().expect("into_string() call failed"), "foo"); + /// + /// let invalid_utf8 = vec![b'f', 0xff, b'o', b'o']; + /// let cstring = CString::new(invalid_utf8).expect("CString::new failed"); + /// let err = cstring.into_string().err().expect("into_string().err() failed"); + /// assert_eq!(err.utf8_error().valid_up_to(), 1); + /// ``` + + #[stable(feature = "cstring_into", since = "1.7.0")] + pub fn into_string(self) -> Result<String, IntoStringError> { + 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").expect("CString::new failed"); + /// 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<u8> { + 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").expect("CString::new failed"); + /// 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<u8> { + 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").expect("CString::new failed"); + /// 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 terminator. + /// + /// [`as_bytes`]: #method.as_bytes + /// + /// # Examples + /// + /// ``` + /// use std::ffi::CString; + /// + /// let c_string = CString::new("foo").expect("CString::new failed"); + /// 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 + /// + /// # Examples + /// + /// ``` + /// use std::ffi::{CString, CStr}; + /// + /// let c_string = CString::new(b"foo".to_vec()).expect("CString::new failed"); + /// let cstr = c_string.as_c_str(); + /// assert_eq!(cstr, + /// CStr::from_bytes_with_nul(b"foo\0").expect("CStr::from_bytes_with_nul failed")); + /// ``` + #[inline] + #[stable(feature = "as_c_str", since = "1.20.0")] + 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()).expect("CString::new failed"); + /// let boxed = c_string.into_boxed_c_str(); + /// assert_eq!(&*boxed, + /// CStr::from_bytes_with_nul(b"foo\0").expect("CStr::from_bytes_with_nul failed")); + /// ``` + #[stable(feature = "into_boxed_c_str", since = "1.20.0")] + pub fn into_boxed_c_str(self) -> Box<CStr> { + 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]> { + // Rationale: `mem::forget(self)` invalidates the previous call to `ptr::read(&self.inner)` + // so we use `ManuallyDrop` to ensure `self` is not dropped. + // Then we can return the box directly without invalidating it. + // See https://github.com/rust-lang/rust/issues/62553. + let this = mem::ManuallyDrop::new(self); + unsafe { ptr::read(&this.inner) } + } + + /// Converts a `Vec` of `u8` to a `CString` without checking the invariants + /// on the given `Vec`. + /// + /// # Safety + /// + /// The given `Vec` **must** have one nul byte as its last element. + /// This means it cannot be empty nor have any other nul byte anywhere else. + /// + /// # Example + /// + /// ``` + /// #![feature(cstring_from_vec_with_nul)] + /// use std::ffi::CString; + /// assert_eq!( + /// unsafe { CString::from_vec_with_nul_unchecked(b"abc\0".to_vec()) }, + /// unsafe { CString::from_vec_unchecked(b"abc".to_vec()) } + /// ); + /// ``` + #[unstable(feature = "cstring_from_vec_with_nul", issue = "73179")] + pub unsafe fn from_vec_with_nul_unchecked(v: Vec<u8>) -> Self { + Self { inner: v.into_boxed_slice() } + } + + /// Attempts to converts a `Vec` of `u8` to a `CString`. + /// + /// Runtime checks are present to ensure there is only one nul byte in the + /// `Vec`, its last element. + /// + /// # Errors + /// + /// If a nul byte is present and not the last element or no nul bytes + /// is present, an error will be returned. + /// + /// # Examples + /// + /// A successful conversion will produce the same result as [`new`] when + /// called without the ending nul byte. + /// + /// ``` + /// #![feature(cstring_from_vec_with_nul)] + /// use std::ffi::CString; + /// assert_eq!( + /// CString::from_vec_with_nul(b"abc\0".to_vec()) + /// .expect("CString::from_vec_with_nul failed"), + /// CString::new(b"abc".to_vec()).expect("CString::new failed") + /// ); + /// ``` + /// + /// A incorrectly formatted vector will produce an error. + /// + /// ``` + /// #![feature(cstring_from_vec_with_nul)] + /// use std::ffi::{CString, FromVecWithNulError}; + /// // Interior nul byte + /// let _: FromVecWithNulError = CString::from_vec_with_nul(b"a\0bc".to_vec()).unwrap_err(); + /// // No nul byte + /// let _: FromVecWithNulError = CString::from_vec_with_nul(b"abc".to_vec()).unwrap_err(); + /// ``` + /// + /// [`new`]: #method.new + #[unstable(feature = "cstring_from_vec_with_nul", issue = "73179")] + pub fn from_vec_with_nul(v: Vec<u8>) -> Result<Self, FromVecWithNulError> { + let nul_pos = memchr::memchr(0, &v); + match nul_pos { + Some(nul_pos) if nul_pos + 1 == v.len() => { + // SAFETY: We know there is only one nul byte, at the end + // of the vec. + Ok(unsafe { Self::from_vec_with_nul_unchecked(v) }) + } + Some(nul_pos) => Err(FromVecWithNulError { + error_kind: FromBytesWithNulErrorKind::InteriorNul(nul_pos), + bytes: v, + }), + None => Err(FromVecWithNulError { + error_kind: FromBytesWithNulErrorKind::NotNulTerminated, + bytes: v, + }), + } + } +} + +// 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<CString> for Vec<u8> { + /// Converts a [`CString`] into a [`Vec`]`<u8>`. + /// + /// 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<u8> { + 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 Default for &CStr { + fn default() -> Self { + const SLICE: &[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<CStr> for CString { + #[inline] + fn borrow(&self) -> &CStr { + self + } +} + +#[stable(feature = "cstring_from_cow_cstr", since = "1.28.0")] +impl<'a> From<Cow<'a, CStr>> for CString { + #[inline] + fn from(s: Cow<'a, CStr>) -> Self { + s.into_owned() + } +} + +#[stable(feature = "box_from_c_str", since = "1.17.0")] +impl From<&CStr> for Box<CStr> { + fn from(s: &CStr) -> Box<CStr> { + let boxed: Box<[u8]> = Box::from(s.to_bytes_with_nul()); + unsafe { Box::from_raw(Box::into_raw(boxed) as *mut CStr) } + } +} + +#[stable(feature = "box_from_cow", since = "1.45.0")] +impl From<Cow<'_, CStr>> for Box<CStr> { + #[inline] + fn from(cow: Cow<'_, CStr>) -> Box<CStr> { + match cow { + Cow::Borrowed(s) => Box::from(s), + Cow::Owned(s) => Box::from(s), + } + } +} + +#[stable(feature = "c_string_from_box", since = "1.18.0")] +impl From<Box<CStr>> for CString { + /// Converts a [`Box`]`<CStr>` into a [`CString`] without copying or allocating. + /// + /// [`Box`]: ../boxed/struct.Box.html + /// [`CString`]: ../ffi/struct.CString.html + #[inline] + fn from(s: Box<CStr>) -> CString { + s.into_c_string() + } +} + +#[stable(feature = "cstring_from_vec_of_nonzerou8", since = "1.43.0")] +impl From<Vec<NonZeroU8>> for CString { + /// Converts a [`Vec`]`<`[`NonZeroU8`]`>` into a [`CString`] without + /// copying nor checking for inner null bytes. + /// + /// [`CString`]: ../ffi/struct.CString.html + /// [`NonZeroU8`]: ../num/struct.NonZeroU8.html + /// [`Vec`]: ../vec/struct.Vec.html + #[inline] + fn from(v: Vec<NonZeroU8>) -> CString { + unsafe { + // Transmute `Vec<NonZeroU8>` to `Vec<u8>`. + let v: Vec<u8> = { + // Safety: + // - transmuting between `NonZeroU8` and `u8` is sound; + // - `alloc::Layout<NonZeroU8> == alloc::Layout<u8>`. + let (ptr, len, cap): (*mut NonZeroU8, _, _) = Vec::into_raw_parts(v); + Vec::from_raw_parts(ptr.cast::<u8>(), len, cap) + }; + // Safety: `v` cannot contain null bytes, given the type-level + // invariant of `NonZeroU8`. + CString::from_vec_unchecked(v) + } + } +} + +#[stable(feature = "more_box_slice_clone", since = "1.29.0")] +impl Clone for Box<CStr> { + #[inline] + fn clone(&self) -> Self { + (**self).into() + } +} + +#[stable(feature = "box_from_c_string", since = "1.20.0")] +impl From<CString> for Box<CStr> { + /// Converts a [`CString`] into a [`Box`]`<CStr>` without copying or allocating. + /// + /// [`CString`]: ../ffi/struct.CString.html + /// [`Box`]: ../boxed/struct.Box.html + #[inline] + fn from(s: CString) -> Box<CStr> { + s.into_boxed_c_str() + } +} + +#[stable(feature = "cow_from_cstr", since = "1.28.0")] +impl<'a> From<CString> for Cow<'a, CStr> { + #[inline] + fn from(s: CString) -> Cow<'a, CStr> { + Cow::Owned(s) + } +} + +#[stable(feature = "cow_from_cstr", since = "1.28.0")] +impl<'a> From<&'a CStr> for Cow<'a, CStr> { + #[inline] + fn from(s: &'a CStr) -> Cow<'a, CStr> { + Cow::Borrowed(s) + } +} + +#[stable(feature = "cow_from_cstr", since = "1.28.0")] +impl<'a> From<&'a CString> for Cow<'a, CStr> { + #[inline] + fn from(s: &'a CString) -> Cow<'a, CStr> { + Cow::Borrowed(s.as_c_str()) + } +} + +#[stable(feature = "shared_from_slice2", since = "1.24.0")] +impl From<CString> for Arc<CStr> { + /// Converts a [`CString`] into a [`Arc`]`<CStr>` without copying or allocating. + /// + /// [`CString`]: ../ffi/struct.CString.html + /// [`Arc`]: ../sync/struct.Arc.html + #[inline] + fn from(s: CString) -> Arc<CStr> { + let arc: Arc<[u8]> = Arc::from(s.into_inner()); + unsafe { Arc::from_raw(Arc::into_raw(arc) as *const CStr) } + } +} + +#[stable(feature = "shared_from_slice2", since = "1.24.0")] +impl From<&CStr> for Arc<CStr> { + #[inline] + fn from(s: &CStr) -> Arc<CStr> { + let arc: Arc<[u8]> = Arc::from(s.to_bytes_with_nul()); + unsafe { Arc::from_raw(Arc::into_raw(arc) as *const CStr) } + } +} + +#[stable(feature = "shared_from_slice2", since = "1.24.0")] +impl From<CString> for Rc<CStr> { + /// Converts a [`CString`] into a [`Rc`]`<CStr>` without copying or allocating. + /// + /// [`CString`]: ../ffi/struct.CString.html + /// [`Rc`]: ../rc/struct.Rc.html + #[inline] + fn from(s: CString) -> Rc<CStr> { + let rc: Rc<[u8]> = Rc::from(s.into_inner()); + unsafe { Rc::from_raw(Rc::into_raw(rc) as *const CStr) } + } +} + +#[stable(feature = "shared_from_slice2", since = "1.24.0")] +impl From<&CStr> for Rc<CStr> { + #[inline] + fn from(s: &CStr) -> Rc<CStr> { + let rc: Rc<[u8]> = Rc::from(s.to_bytes_with_nul()); + unsafe { Rc::from_raw(Rc::into_raw(rc) as *const CStr) } + } +} + +#[stable(feature = "default_box_extra", since = "1.17.0")] +impl Default for Box<CStr> { + fn default() -> Box<CStr> { + 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); + /// ``` + #[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<u8> { + self.1 + } +} + +#[stable(feature = "rust1", since = "1.0.0")] +impl Error for NulError { + #[allow(deprecated)] + 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<NulError> for io::Error { + /// Converts a [`NulError`] into a [`io::Error`]. + /// + /// [`NulError`]: ../ffi/struct.NulError.html + /// [`io::Error`]: ../io/struct.Error.html + 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 { + #[allow(deprecated)] + 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 { + #[allow(deprecated, deprecated_in_future)] + 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(()) + } +} + +#[unstable(feature = "cstring_from_vec_with_nul", issue = "73179")] +impl Error for FromVecWithNulError {} + +#[unstable(feature = "cstring_from_vec_with_nul", issue = "73179")] +impl fmt::Display for FromVecWithNulError { + fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result { + match self.error_kind { + FromBytesWithNulErrorKind::InteriorNul(pos) => { + write!(f, "data provided contains an interior nul byte at pos {}", pos) + } + FromBytesWithNulErrorKind::NotNulTerminated => { + write!(f, "data provided is not nul terminated") + } + } + } +} + +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 { + #[allow(deprecated)] + fn description(&self) -> &str { + "C string contained non-utf8 bytes" + } + + fn source(&self) -> Option<&(dyn Error + 'static)> { + Some(&self.error) + } +} + +#[stable(feature = "cstring_into", since = "1.7.0")] +impl fmt::Display for IntoStringError { + #[allow(deprecated, deprecated_in_future)] + 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. The total + /// size of the raw C string must be smaller than `isize::MAX` **bytes** + /// in memory due to calling the `slice::from_raw_parts` function. + /// 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()); + /// } + /// # } + /// ``` + #[stable(feature = "rust1", since = "1.0.0")] + pub unsafe fn from_ptr<'a>(ptr: *const c_char) -> &'a CStr { + let len = sys::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 cstr = CStr::from_bytes_with_nul(b"hello"); + /// assert!(cstr.is_err()); + /// ``` + /// + /// Creating a `CStr` with an interior nul byte is an error: + /// + /// ``` + /// use std::ffi::CStr; + /// + /// let cstr = CStr::from_bytes_with_nul(b"he\0llo\0"); + /// assert!(cstr.is_err()); + /// ``` + #[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 nul-terminated + /// and not contain any interior nul bytes. + /// + /// # Examples + /// + /// ``` + /// use std::ffi::{CStr, CString}; + /// + /// unsafe { + /// let cstring = CString::new("hello").expect("CString::new failed"); + /// 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")] + #[rustc_const_unstable(feature = "const_cstr_unchecked", issue = "none")] + 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** + /// + /// The returned pointer is read-only; writing to it (including passing it + /// to C code that writes to it) causes undefined behavior. + /// + /// 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").expect("CString::new failed").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").expect("CString::new failed").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").expect("CString::new failed"); + /// 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] + #[stable(feature = "rust1", since = "1.0.0")] + #[rustc_const_stable(feature = "const_str_as_ptr", since = "1.32.0")] + pub const 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 cstr = CStr::from_bytes_with_nul(b"foo\0").expect("CStr::from_bytes_with_nul failed"); + /// assert_eq!(cstr.to_bytes(), b"foo"); + /// ``` + #[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 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 cstr = CStr::from_bytes_with_nul(b"foo\0").expect("CStr::from_bytes_with_nul failed"); + /// assert_eq!(cstr.to_bytes_with_nul(), b"foo\0"); + /// ``` + #[inline] + #[stable(feature = "rust1", since = "1.0.0")] + 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. + /// + /// [`&str`]: ../primitive.str.html + /// + /// # Examples + /// + /// ``` + /// use std::ffi::CStr; + /// + /// let cstr = CStr::from_bytes_with_nul(b"foo\0").expect("CStr::from_bytes_with_nul failed"); + /// assert_eq!(cstr.to_str(), Ok("foo")); + /// ``` + #[stable(feature = "cstr_to_str", since = "1.4.0")] + pub fn to_str(&self) -> Result<&str, str::Utf8Error> { + // N.B., 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 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. + /// + /// [`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 cstr = CStr::from_bytes_with_nul(b"Hello World\0") + /// .expect("CStr::from_bytes_with_nul failed"); + /// assert_eq!(cstr.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 cstr = CStr::from_bytes_with_nul(b"Hello \xF0\x90\x80World\0") + /// .expect("CStr::from_bytes_with_nul failed"); + /// assert_eq!( + /// cstr.to_string_lossy(), + /// Cow::Owned(String::from("Hello �World")) as Cow<'_, str> + /// ); + /// ``` + #[stable(feature = "cstr_to_str", since = "1.4.0")] + pub fn to_string_lossy(&self) -> Cow<'_, str> { + String::from_utf8_lossy(self.to_bytes()) + } + + /// Converts a [`Box`]`<CStr>` 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()).expect("CString::new failed"); + /// let boxed = c_string.into_boxed_c_str(); + /// assert_eq!(boxed.into_c_string(), CString::new("foo").expect("CString::new failed")); + /// ``` + #[stable(feature = "into_boxed_c_str", since = "1.20.0")] + pub fn into_c_string(self: Box<CStr>) -> CString { + let raw = Box::into_raw(self) as *mut [u8]; + CString { inner: unsafe { Box::from_raw(raw) } } + } +} + +#[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<Ordering> { + 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() } + } + + fn clone_into(&self, target: &mut CString) { + let mut b = Vec::from(mem::take(&mut target.inner)); + self.to_bytes_with_nul().clone_into(&mut b); + target.inner = b.into_boxed_slice(); + } +} + +#[stable(feature = "cstring_asref", since = "1.7.0")] +impl From<&CStr> for CString { + fn from(s: &CStr) -> CString { + s.to_owned() + } +} + +#[stable(feature = "cstring_asref", since = "1.7.0")] +impl ops::Index<ops::RangeFull> for CString { + type Output = CStr; + + #[inline] + fn index(&self, _index: ops::RangeFull) -> &CStr { + self + } +} + +#[stable(feature = "cstr_range_from", since = "1.47.0")] +impl ops::Index<ops::RangeFrom<usize>> for CStr { + type Output = CStr; + + fn index(&self, index: ops::RangeFrom<usize>) -> &CStr { + let bytes = self.to_bytes_with_nul(); + // we need to manually check the starting index to account for the null + // byte, since otherwise we could get an empty string that doesn't end + // in a null. + if index.start < bytes.len() { + unsafe { CStr::from_bytes_with_nul_unchecked(&bytes[index.start..]) } + } else { + panic!( + "index out of bounds: the len is {} but the index is {}", + bytes.len(), + index.start + ); + } + } +} + +#[stable(feature = "cstring_asref", since = "1.7.0")] +impl AsRef<CStr> for CStr { + #[inline] + fn as_ref(&self) -> &CStr { + self + } +} + +#[stable(feature = "cstring_asref", since = "1.7.0")] +impl AsRef<CStr> for CString { + #[inline] + fn as_ref(&self) -> &CStr { + self + } +} + +#[cfg(test)] +mod tests { + use super::*; + use crate::borrow::Cow::{Borrowed, Owned}; + use crate::collections::hash_map::DefaultHasher; + use crate::hash::{Hash, Hasher}; + use crate::os::raw::c_char; + use crate::rc::Rc; + use crate::sync::Arc; + + #[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::<str>(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<CStr> = 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 = <Box<CStr>>::default(); + assert_eq!(boxed.to_bytes_with_nul(), &[0]); + } + + #[test] + fn test_c_str_clone_into() { + let mut c_string = CString::new("lorem").unwrap(); + let c_ptr = c_string.as_ptr(); + let c_str = CStr::from_bytes_with_nul(b"ipsum\0").unwrap(); + c_str.clone_into(&mut c_string); + assert_eq!(c_str, c_string.as_c_str()); + // The exact same size shouldn't have needed to move its allocation + assert_eq!(c_ptr, c_string.as_ptr()); + } + + #[test] + fn into_rc() { + let orig: &[u8] = b"Hello, world!\0"; + let cstr = CStr::from_bytes_with_nul(orig).unwrap(); + let rc: Rc<CStr> = Rc::from(cstr); + let arc: Arc<CStr> = Arc::from(cstr); + + assert_eq!(&*rc, cstr); + assert_eq!(&*arc, cstr); + + let rc2: Rc<CStr> = Rc::from(cstr.to_owned()); + let arc2: Arc<CStr> = Arc::from(cstr.to_owned()); + + assert_eq!(&*rc2, cstr); + assert_eq!(&*arc2, cstr); + } + + #[test] + fn cstr_const_constructor() { + const CSTR: &CStr = unsafe { CStr::from_bytes_with_nul_unchecked(b"Hello, world!\0") }; + + assert_eq!(CSTR.to_str().unwrap(), "Hello, world!"); + } + + #[test] + fn cstr_index_from() { + let original = b"Hello, world!\0"; + let cstr = CStr::from_bytes_with_nul(original).unwrap(); + let result = CStr::from_bytes_with_nul(&original[7..]).unwrap(); + + assert_eq!(&cstr[7..], result); + } + + #[test] + #[should_panic] + fn cstr_index_from_empty() { + let original = b"Hello, world!\0"; + let cstr = CStr::from_bytes_with_nul(original).unwrap(); + let _ = &cstr[original.len()..]; + } +} diff --git a/library/std/src/ffi/mod.rs b/library/std/src/ffi/mod.rs new file mode 100644 index 00000000000..f442d7fde1a --- /dev/null +++ b/library/std/src/ffi/mod.rs @@ -0,0 +1,180 @@ +//! Utilities related to FFI bindings. +//! +//! This module provides utilities to handle data across non-Rust +//! interfaces, like other programming languages and the underlying +//! operating system. It is mainly of use for FFI (Foreign Function +//! Interface) bindings and code that needs to exchange C-like strings +//! with other languages. +//! +//! # Overview +//! +//! Rust represents owned strings with the [`String`] type, and +//! borrowed slices of strings with the [`str`] primitive. Both are +//! always in UTF-8 encoding, and may contain nul bytes in the middle, +//! i.e., if you look at the bytes that make up the string, there may +//! be a `\0` among them. Both `String` and `str` store their length +//! explicitly; there are no nul terminators at the end of strings +//! like in C. +//! +//! C strings are different from Rust strings: +//! +//! * **Encodings** - Rust strings are UTF-8, but C strings may use +//! other encodings. If you are using a string from C, you should +//! check its encoding explicitly, rather than just assuming that it +//! is UTF-8 like you can do in Rust. +//! +//! * **Character size** - C strings may use `char` or `wchar_t`-sized +//! characters; please **note** that C's `char` is different from Rust's. +//! The C standard leaves the actual sizes of those types open to +//! interpretation, but defines different APIs for strings made up of +//! each character type. Rust strings are always UTF-8, so different +//! Unicode characters will be encoded in a variable number of bytes +//! each. The Rust type [`char`] represents a '[Unicode scalar +//! value]', which is similar to, but not the same as, a '[Unicode +//! code point]'. +//! +//! * **Nul terminators and implicit string lengths** - Often, C +//! strings are nul-terminated, i.e., they have a `\0` character at the +//! end. The length of a string buffer is not stored, but has to be +//! calculated; to compute the length of a string, C code must +//! manually call a function like `strlen()` for `char`-based strings, +//! or `wcslen()` for `wchar_t`-based ones. Those functions return +//! the number of characters in the string excluding the nul +//! terminator, so the buffer length is really `len+1` characters. +//! Rust strings don't have a nul terminator; their length is always +//! stored and does not need to be calculated. While in Rust +//! accessing a string's length is a `O(1)` operation (because the +//! length is stored); in C it is an `O(length)` operation because the +//! length needs to be computed by scanning the string for the nul +//! terminator. +//! +//! * **Internal nul characters** - When C strings have a nul +//! terminator character, this usually means that they cannot have nul +//! characters in the middle — a nul character would essentially +//! truncate the string. Rust strings *can* have nul characters in +//! the middle, because nul does not have to mark the end of the +//! string in Rust. +//! +//! # Representations of non-Rust strings +//! +//! [`CString`] and [`CStr`] are useful when you need to transfer +//! UTF-8 strings to and from languages with a C ABI, like Python. +//! +//! * **From Rust to C:** [`CString`] represents an owned, C-friendly +//! string: it is nul-terminated, and has no internal nul characters. +//! Rust code can create a [`CString`] out of a normal string (provided +//! that the string doesn't have nul characters in the middle), and +//! then use a variety of methods to obtain a raw `*mut `[`u8`] that can +//! then be passed as an argument to functions which use the C +//! conventions for strings. +//! +//! * **From C to Rust:** [`CStr`] represents a borrowed C string; it +//! is what you would use to wrap a raw `*const `[`u8`] that you got from +//! a C function. A [`CStr`] is guaranteed to be a nul-terminated array +//! of bytes. Once you have a [`CStr`], you can convert it to a Rust +//! [`&str`][`str`] if it's valid UTF-8, or lossily convert it by adding +//! replacement characters. +//! +//! [`OsString`] and [`OsStr`] are useful when you need to transfer +//! strings to and from the operating system itself, or when capturing +//! the output of external commands. Conversions between [`OsString`], +//! [`OsStr`] and Rust strings work similarly to those for [`CString`] +//! and [`CStr`]. +//! +//! * [`OsString`] represents an owned string in whatever +//! representation the operating system prefers. In the Rust standard +//! library, various APIs that transfer strings to/from the operating +//! system use [`OsString`] instead of plain strings. For example, +//! [`env::var_os()`] is used to query environment variables; it +//! returns an [`Option`]`<`[`OsString`]`>`. If the environment variable +//! exists you will get a [`Some`]`(os_string)`, which you can *then* try to +//! convert to a Rust string. This yields a [`Result<>`], so that +//! your code can detect errors in case the environment variable did +//! not in fact contain valid Unicode data. +//! +//! * [`OsStr`] represents a borrowed reference to a string in a +//! format that can be passed to the operating system. It can be +//! converted into an UTF-8 Rust string slice in a similar way to +//! [`OsString`]. +//! +//! # Conversions +//! +//! ## On Unix +//! +//! On Unix, [`OsStr`] implements the +//! `std::os::unix::ffi::`[`OsStrExt`][unix.OsStrExt] trait, which +//! augments it with two methods, [`from_bytes`] and [`as_bytes`]. +//! These do inexpensive conversions from and to UTF-8 byte slices. +//! +//! Additionally, on Unix [`OsString`] implements the +//! `std::os::unix::ffi::`[`OsStringExt`][unix.OsStringExt] trait, +//! which provides [`from_vec`] and [`into_vec`] methods that consume +//! their arguments, and take or produce vectors of [`u8`]. +//! +//! ## On Windows +//! +//! On Windows, [`OsStr`] implements the +//! `std::os::windows::ffi::`[`OsStrExt`][windows.OsStrExt] trait, +//! which provides an [`encode_wide`] method. This provides an +//! iterator that can be [`collect`]ed into a vector of [`u16`]. +//! +//! Additionally, on Windows [`OsString`] implements the +//! `std::os::windows:ffi::`[`OsStringExt`][windows.OsStringExt] +//! trait, which provides a [`from_wide`] method. The result of this +//! method is an [`OsString`] which can be round-tripped to a Windows +//! string losslessly. +//! +//! [`String`]: ../string/struct.String.html +//! [`str`]: ../primitive.str.html +//! [`char`]: ../primitive.char.html +//! [`u8`]: ../primitive.u8.html +//! [`u16`]: ../primitive.u16.html +//! [Unicode scalar value]: http://www.unicode.org/glossary/#unicode_scalar_value +//! [Unicode code point]: http://www.unicode.org/glossary/#code_point +//! [`CString`]: struct.CString.html +//! [`CStr`]: struct.CStr.html +//! [`OsString`]: struct.OsString.html +//! [`OsStr`]: struct.OsStr.html +//! [`env::set_var()`]: ../env/fn.set_var.html +//! [`env::var_os()`]: ../env/fn.var_os.html +//! [`Result<>`]: ../result/enum.Result.html +//! [unix.OsStringExt]: ../os/unix/ffi/trait.OsStringExt.html +//! [`from_vec`]: ../os/unix/ffi/trait.OsStringExt.html#tymethod.from_vec +//! [`into_vec`]: ../os/unix/ffi/trait.OsStringExt.html#tymethod.into_vec +//! [unix.OsStrExt]: ../os/unix/ffi/trait.OsStrExt.html +//! [`from_bytes`]: ../os/unix/ffi/trait.OsStrExt.html#tymethod.from_bytes +//! [`as_bytes`]: ../os/unix/ffi/trait.OsStrExt.html#tymethod.as_bytes +//! [`OsStrExt`]: ../os/unix/ffi/trait.OsStrExt.html +//! [windows.OsStrExt]: ../os/windows/ffi/trait.OsStrExt.html +//! [`encode_wide`]: ../os/windows/ffi/trait.OsStrExt.html#tymethod.encode_wide +//! [`collect`]: ../iter/trait.Iterator.html#method.collect +//! [windows.OsStringExt]: ../os/windows/ffi/trait.OsStringExt.html +//! [`from_wide`]: ../os/windows/ffi/trait.OsStringExt.html#tymethod.from_wide +//! [`Option`]: ../option/enum.Option.html +//! [`Some`]: ../option/enum.Option.html#variant.Some + +#![stable(feature = "rust1", since = "1.0.0")] + +#[stable(feature = "cstr_from_bytes", since = "1.10.0")] +pub use self::c_str::FromBytesWithNulError; +#[unstable(feature = "cstring_from_vec_with_nul", issue = "73179")] +pub use self::c_str::FromVecWithNulError; +#[stable(feature = "rust1", since = "1.0.0")] +pub use self::c_str::{CStr, CString, IntoStringError, NulError}; + +#[stable(feature = "rust1", since = "1.0.0")] +pub use self::os_str::{OsStr, OsString}; + +#[stable(feature = "core_c_void", since = "1.30.0")] +pub use core::ffi::c_void; + +#[unstable( + feature = "c_variadic", + reason = "the `c_variadic` feature has not been properly tested on \ + all supported platforms", + issue = "44930" +)] +pub use core::ffi::{VaList, VaListImpl}; + +mod c_str; +mod os_str; diff --git a/library/std/src/ffi/os_str.rs b/library/std/src/ffi/os_str.rs new file mode 100644 index 00000000000..d1eaf3c583f --- /dev/null +++ b/library/std/src/ffi/os_str.rs @@ -0,0 +1,1365 @@ +use crate::borrow::{Borrow, Cow}; +use crate::cmp; +use crate::fmt; +use crate::hash::{Hash, Hasher}; +use crate::ops; +use crate::rc::Rc; +use crate::str::FromStr; +use crate::sync::Arc; + +use crate::sys::os_str::{Buf, Slice}; +use crate::sys_common::{AsInner, FromInner, IntoInner}; + +/// A type that can represent owned, mutable platform-native strings, but is +/// cheaply inter-convertible with Rust strings. +/// +/// The need for this type arises from the fact that: +/// +/// * On Unix systems, strings are often arbitrary sequences of non-zero +/// bytes, in many cases interpreted as UTF-8. +/// +/// * On Windows, strings are often arbitrary sequences of non-zero 16-bit +/// values, interpreted as UTF-16 when it is valid to do so. +/// +/// * In Rust, strings are always valid UTF-8, which may contain zeros. +/// +/// `OsString` and [`OsStr`] bridge this gap by simultaneously representing Rust +/// and platform-native string values, and in particular allowing a Rust string +/// to be converted into an "OS" string with no cost if possible. A consequence +/// of this is that `OsString` instances are *not* `NUL` terminated; in order +/// to pass to e.g., Unix system call, you should create a [`CStr`]. +/// +/// `OsString` is to [`&OsStr`] as [`String`] is to [`&str`]: the former +/// in each pair are owned strings; the latter are borrowed +/// references. +/// +/// Note, `OsString` and [`OsStr`] internally do not necessarily hold strings in +/// the form native to the platform; While on Unix, strings are stored as a +/// sequence of 8-bit values, on Windows, where strings are 16-bit value based +/// as just discussed, strings are also actually stored as a sequence of 8-bit +/// values, encoded in a less-strict variant of UTF-8. This is useful to +/// understand when handling capacity and length values. +/// +/// # Creating an `OsString` +/// +/// **From a Rust string**: `OsString` implements +/// [`From`]`<`[`String`]`>`, so you can use `my_string.from` to +/// create an `OsString` from a normal Rust string. +/// +/// **From slices:** Just like you can start with an empty Rust +/// [`String`] and then [`push_str`][String.push_str] `&str` +/// sub-string slices into it, you can create an empty `OsString` with +/// the [`new`] method and then push string slices into it with the +/// [`push`] method. +/// +/// # Extracting a borrowed reference to the whole OS string +/// +/// You can use the [`as_os_str`] method to get an `&`[`OsStr`] from +/// an `OsString`; this is effectively a borrowed reference to the +/// whole string. +/// +/// # Conversions +/// +/// See the [module's toplevel documentation about conversions][conversions] for a discussion on +/// the traits which `OsString` implements for [conversions] from/to native representations. +/// +/// [`OsStr`]: struct.OsStr.html +/// [`&OsStr`]: struct.OsStr.html +/// [`CStr`]: struct.CStr.html +/// [`From`]: ../convert/trait.From.html +/// [`String`]: ../string/struct.String.html +/// [`&str`]: ../primitive.str.html +/// [`u8`]: ../primitive.u8.html +/// [`u16`]: ../primitive.u16.html +/// [String.push_str]: ../string/struct.String.html#method.push_str +/// [`new`]: #method.new +/// [`push`]: #method.push +/// [`as_os_str`]: #method.as_os_str +/// [conversions]: index.html#conversions +#[derive(Clone)] +#[stable(feature = "rust1", since = "1.0.0")] +pub struct OsString { + inner: Buf, +} + +/// Borrowed reference to an OS string (see [`OsString`]). +/// +/// This type represents a borrowed reference to a string in the operating system's preferred +/// representation. +/// +/// `&OsStr` is to [`OsString`] as [`&str`] is to [`String`]: the former in each pair are borrowed +/// references; the latter are owned strings. +/// +/// See the [module's toplevel documentation about conversions][conversions] for a discussion on +/// the traits which `OsStr` implements for [conversions] from/to native representations. +/// +/// [`OsString`]: struct.OsString.html +/// [`&str`]: ../primitive.str.html +/// [`String`]: ../string/struct.String.html +/// [conversions]: index.html#conversions +#[stable(feature = "rust1", since = "1.0.0")] +// FIXME: +// `OsStr::from_inner` current implementation relies +// on `OsStr` being layout-compatible with `Slice`. +// When attribute privacy is implemented, `OsStr` should be annotated as `#[repr(transparent)]`. +// Anyway, `OsStr` representation and layout are considered implementation detail, are +// not documented and must not be relied upon. +pub struct OsStr { + inner: Slice, +} + +impl OsString { + /// Constructs a new empty `OsString`. + /// + /// # Examples + /// + /// ``` + /// use std::ffi::OsString; + /// + /// let os_string = OsString::new(); + /// ``` + #[stable(feature = "rust1", since = "1.0.0")] + pub fn new() -> OsString { + OsString { inner: Buf::from_string(String::new()) } + } + + /// Converts to an [`OsStr`] slice. + /// + /// [`OsStr`]: struct.OsStr.html + /// + /// # Examples + /// + /// ``` + /// use std::ffi::{OsString, OsStr}; + /// + /// let os_string = OsString::from("foo"); + /// let os_str = OsStr::new("foo"); + /// assert_eq!(os_string.as_os_str(), os_str); + /// ``` + #[stable(feature = "rust1", since = "1.0.0")] + pub fn as_os_str(&self) -> &OsStr { + self + } + + /// Converts the `OsString` into a [`String`] if it contains valid Unicode data. + /// + /// On failure, ownership of the original `OsString` is returned. + /// + /// [`String`]: ../../std/string/struct.String.html + /// + /// # Examples + /// + /// ``` + /// use std::ffi::OsString; + /// + /// let os_string = OsString::from("foo"); + /// let string = os_string.into_string(); + /// assert_eq!(string, Ok(String::from("foo"))); + /// ``` + #[stable(feature = "rust1", since = "1.0.0")] + pub fn into_string(self) -> Result<String, OsString> { + self.inner.into_string().map_err(|buf| OsString { inner: buf }) + } + + /// Extends the string with the given [`&OsStr`] slice. + /// + /// [`&OsStr`]: struct.OsStr.html + /// + /// # Examples + /// + /// ``` + /// use std::ffi::OsString; + /// + /// let mut os_string = OsString::from("foo"); + /// os_string.push("bar"); + /// assert_eq!(&os_string, "foobar"); + /// ``` + #[stable(feature = "rust1", since = "1.0.0")] + pub fn push<T: AsRef<OsStr>>(&mut self, s: T) { + self.inner.push_slice(&s.as_ref().inner) + } + + /// Creates a new `OsString` with the given capacity. + /// + /// The string will be able to hold exactly `capacity` length units of other + /// OS strings without reallocating. If `capacity` is 0, the string will not + /// allocate. + /// + /// See main `OsString` documentation information about encoding. + /// + /// # Examples + /// + /// ``` + /// use std::ffi::OsString; + /// + /// let mut os_string = OsString::with_capacity(10); + /// let capacity = os_string.capacity(); + /// + /// // This push is done without reallocating + /// os_string.push("foo"); + /// + /// assert_eq!(capacity, os_string.capacity()); + /// ``` + #[stable(feature = "osstring_simple_functions", since = "1.9.0")] + pub fn with_capacity(capacity: usize) -> OsString { + OsString { inner: Buf::with_capacity(capacity) } + } + + /// Truncates the `OsString` to zero length. + /// + /// # Examples + /// + /// ``` + /// use std::ffi::OsString; + /// + /// let mut os_string = OsString::from("foo"); + /// assert_eq!(&os_string, "foo"); + /// + /// os_string.clear(); + /// assert_eq!(&os_string, ""); + /// ``` + #[stable(feature = "osstring_simple_functions", since = "1.9.0")] + pub fn clear(&mut self) { + self.inner.clear() + } + + /// Returns the capacity this `OsString` can hold without reallocating. + /// + /// See `OsString` introduction for information about encoding. + /// + /// # Examples + /// + /// ``` + /// use std::ffi::OsString; + /// + /// let os_string = OsString::with_capacity(10); + /// assert!(os_string.capacity() >= 10); + /// ``` + #[stable(feature = "osstring_simple_functions", since = "1.9.0")] + pub fn capacity(&self) -> usize { + self.inner.capacity() + } + + /// Reserves capacity for at least `additional` more capacity to be inserted + /// in the given `OsString`. + /// + /// The collection may reserve more space to avoid frequent reallocations. + /// + /// # Examples + /// + /// ``` + /// use std::ffi::OsString; + /// + /// let mut s = OsString::new(); + /// s.reserve(10); + /// assert!(s.capacity() >= 10); + /// ``` + #[stable(feature = "osstring_simple_functions", since = "1.9.0")] + pub fn reserve(&mut self, additional: usize) { + self.inner.reserve(additional) + } + + /// Reserves the minimum capacity for exactly `additional` more capacity to + /// be inserted in the given `OsString`. Does nothing if the capacity is + /// already sufficient. + /// + /// Note that the allocator may give the collection more space than it + /// requests. Therefore, capacity can not be relied upon to be precisely + /// minimal. Prefer reserve if future insertions are expected. + /// + /// # Examples + /// + /// ``` + /// use std::ffi::OsString; + /// + /// let mut s = OsString::new(); + /// s.reserve_exact(10); + /// assert!(s.capacity() >= 10); + /// ``` + #[stable(feature = "osstring_simple_functions", since = "1.9.0")] + pub fn reserve_exact(&mut self, additional: usize) { + self.inner.reserve_exact(additional) + } + + /// Shrinks the capacity of the `OsString` to match its length. + /// + /// # Examples + /// + /// ``` + /// use std::ffi::OsString; + /// + /// let mut s = OsString::from("foo"); + /// + /// s.reserve(100); + /// assert!(s.capacity() >= 100); + /// + /// s.shrink_to_fit(); + /// assert_eq!(3, s.capacity()); + /// ``` + #[stable(feature = "osstring_shrink_to_fit", since = "1.19.0")] + pub fn shrink_to_fit(&mut self) { + self.inner.shrink_to_fit() + } + + /// Shrinks the capacity of the `OsString` with a lower bound. + /// + /// The capacity will remain at least as large as both the length + /// and the supplied value. + /// + /// Panics if the current capacity is smaller than the supplied + /// minimum capacity. + /// + /// # Examples + /// + /// ``` + /// #![feature(shrink_to)] + /// use std::ffi::OsString; + /// + /// let mut s = OsString::from("foo"); + /// + /// s.reserve(100); + /// assert!(s.capacity() >= 100); + /// + /// s.shrink_to(10); + /// assert!(s.capacity() >= 10); + /// s.shrink_to(0); + /// assert!(s.capacity() >= 3); + /// ``` + #[inline] + #[unstable(feature = "shrink_to", reason = "new API", issue = "56431")] + pub fn shrink_to(&mut self, min_capacity: usize) { + self.inner.shrink_to(min_capacity) + } + + /// Converts this `OsString` into a boxed [`OsStr`]. + /// + /// [`OsStr`]: struct.OsStr.html + /// + /// # Examples + /// + /// ``` + /// use std::ffi::{OsString, OsStr}; + /// + /// let s = OsString::from("hello"); + /// + /// let b: Box<OsStr> = s.into_boxed_os_str(); + /// ``` + #[stable(feature = "into_boxed_os_str", since = "1.20.0")] + pub fn into_boxed_os_str(self) -> Box<OsStr> { + let rw = Box::into_raw(self.inner.into_box()) as *mut OsStr; + unsafe { Box::from_raw(rw) } + } +} + +#[stable(feature = "rust1", since = "1.0.0")] +impl From<String> for OsString { + /// Converts a [`String`] into a [`OsString`]. + /// + /// The conversion copies the data, and includes an allocation on the heap. + /// + /// [`OsString`]: ../../std/ffi/struct.OsString.html + fn from(s: String) -> OsString { + OsString { inner: Buf::from_string(s) } + } +} + +#[stable(feature = "rust1", since = "1.0.0")] +impl<T: ?Sized + AsRef<OsStr>> From<&T> for OsString { + fn from(s: &T) -> OsString { + s.as_ref().to_os_string() + } +} + +#[stable(feature = "rust1", since = "1.0.0")] +impl ops::Index<ops::RangeFull> for OsString { + type Output = OsStr; + + #[inline] + fn index(&self, _index: ops::RangeFull) -> &OsStr { + OsStr::from_inner(self.inner.as_slice()) + } +} + +#[stable(feature = "mut_osstr", since = "1.44.0")] +impl ops::IndexMut<ops::RangeFull> for OsString { + #[inline] + fn index_mut(&mut self, _index: ops::RangeFull) -> &mut OsStr { + OsStr::from_inner_mut(self.inner.as_mut_slice()) + } +} + +#[stable(feature = "rust1", since = "1.0.0")] +impl ops::Deref for OsString { + type Target = OsStr; + + #[inline] + fn deref(&self) -> &OsStr { + &self[..] + } +} + +#[stable(feature = "mut_osstr", since = "1.44.0")] +impl ops::DerefMut for OsString { + #[inline] + fn deref_mut(&mut self) -> &mut OsStr { + &mut self[..] + } +} + +#[stable(feature = "osstring_default", since = "1.9.0")] +impl Default for OsString { + /// Constructs an empty `OsString`. + #[inline] + fn default() -> OsString { + OsString::new() + } +} + +#[stable(feature = "rust1", since = "1.0.0")] +impl fmt::Debug for OsString { + fn fmt(&self, formatter: &mut fmt::Formatter<'_>) -> fmt::Result { + fmt::Debug::fmt(&**self, formatter) + } +} + +#[stable(feature = "rust1", since = "1.0.0")] +impl PartialEq for OsString { + fn eq(&self, other: &OsString) -> bool { + &**self == &**other + } +} + +#[stable(feature = "rust1", since = "1.0.0")] +impl PartialEq<str> for OsString { + fn eq(&self, other: &str) -> bool { + &**self == other + } +} + +#[stable(feature = "rust1", since = "1.0.0")] +impl PartialEq<OsString> for str { + fn eq(&self, other: &OsString) -> bool { + &**other == self + } +} + +#[stable(feature = "os_str_str_ref_eq", since = "1.29.0")] +impl PartialEq<&str> for OsString { + fn eq(&self, other: &&str) -> bool { + **self == **other + } +} + +#[stable(feature = "os_str_str_ref_eq", since = "1.29.0")] +impl<'a> PartialEq<OsString> for &'a str { + fn eq(&self, other: &OsString) -> bool { + **other == **self + } +} + +#[stable(feature = "rust1", since = "1.0.0")] +impl Eq for OsString {} + +#[stable(feature = "rust1", since = "1.0.0")] +impl PartialOrd for OsString { + #[inline] + fn partial_cmp(&self, other: &OsString) -> Option<cmp::Ordering> { + (&**self).partial_cmp(&**other) + } + #[inline] + fn lt(&self, other: &OsString) -> bool { + &**self < &**other + } + #[inline] + fn le(&self, other: &OsString) -> bool { + &**self <= &**other + } + #[inline] + fn gt(&self, other: &OsString) -> bool { + &**self > &**other + } + #[inline] + fn ge(&self, other: &OsString) -> bool { + &**self >= &**other + } +} + +#[stable(feature = "rust1", since = "1.0.0")] +impl PartialOrd<str> for OsString { + #[inline] + fn partial_cmp(&self, other: &str) -> Option<cmp::Ordering> { + (&**self).partial_cmp(other) + } +} + +#[stable(feature = "rust1", since = "1.0.0")] +impl Ord for OsString { + #[inline] + fn cmp(&self, other: &OsString) -> cmp::Ordering { + (&**self).cmp(&**other) + } +} + +#[stable(feature = "rust1", since = "1.0.0")] +impl Hash for OsString { + #[inline] + fn hash<H: Hasher>(&self, state: &mut H) { + (&**self).hash(state) + } +} + +impl OsStr { + /// Coerces into an `OsStr` slice. + /// + /// # Examples + /// + /// ``` + /// use std::ffi::OsStr; + /// + /// let os_str = OsStr::new("foo"); + /// ``` + #[inline] + #[stable(feature = "rust1", since = "1.0.0")] + pub fn new<S: AsRef<OsStr> + ?Sized>(s: &S) -> &OsStr { + s.as_ref() + } + + #[inline] + fn from_inner(inner: &Slice) -> &OsStr { + // Safety: OsStr is just a wrapper of Slice, + // therefore converting &Slice to &OsStr is safe. + unsafe { &*(inner as *const Slice as *const OsStr) } + } + + #[inline] + fn from_inner_mut(inner: &mut Slice) -> &mut OsStr { + // Safety: OsStr is just a wrapper of Slice, + // therefore converting &mut Slice to &mut OsStr is safe. + // Any method that mutates OsStr must be careful not to + // break platform-specific encoding, in particular Wtf8 on Windows. + unsafe { &mut *(inner as *mut Slice as *mut OsStr) } + } + + /// Yields a [`&str`] slice if the `OsStr` is valid Unicode. + /// + /// This conversion may entail doing a check for UTF-8 validity. + /// + /// [`&str`]: ../../std/primitive.str.html + /// + /// # Examples + /// + /// ``` + /// use std::ffi::OsStr; + /// + /// let os_str = OsStr::new("foo"); + /// assert_eq!(os_str.to_str(), Some("foo")); + /// ``` + #[stable(feature = "rust1", since = "1.0.0")] + pub fn to_str(&self) -> Option<&str> { + self.inner.to_str() + } + + /// Converts an `OsStr` to a [`Cow`]`<`[`str`]`>`. + /// + /// Any non-Unicode sequences are replaced with + /// [`U+FFFD REPLACEMENT CHARACTER`][U+FFFD]. + /// + /// [`Cow`]: ../../std/borrow/enum.Cow.html + /// [`str`]: ../../std/primitive.str.html + /// [U+FFFD]: ../../std/char/constant.REPLACEMENT_CHARACTER.html + /// + /// # Examples + /// + /// Calling `to_string_lossy` on an `OsStr` with invalid unicode: + /// + /// ``` + /// // Note, due to differences in how Unix and Windows represent strings, + /// // we are forced to complicate this example, setting up example `OsStr`s + /// // with different source data and via different platform extensions. + /// // Understand that in reality you could end up with such example invalid + /// // sequences simply through collecting user command line arguments, for + /// // example. + /// + /// #[cfg(any(unix, target_os = "redox"))] { + /// use std::ffi::OsStr; + /// use std::os::unix::ffi::OsStrExt; + /// + /// // Here, the values 0x66 and 0x6f correspond to 'f' and 'o' + /// // respectively. The value 0x80 is a lone continuation byte, invalid + /// // in a UTF-8 sequence. + /// let source = [0x66, 0x6f, 0x80, 0x6f]; + /// let os_str = OsStr::from_bytes(&source[..]); + /// + /// assert_eq!(os_str.to_string_lossy(), "fo�o"); + /// } + /// #[cfg(windows)] { + /// use std::ffi::OsString; + /// use std::os::windows::prelude::*; + /// + /// // Here the values 0x0066 and 0x006f correspond to 'f' and 'o' + /// // respectively. The value 0xD800 is a lone surrogate half, invalid + /// // in a UTF-16 sequence. + /// let source = [0x0066, 0x006f, 0xD800, 0x006f]; + /// let os_string = OsString::from_wide(&source[..]); + /// let os_str = os_string.as_os_str(); + /// + /// assert_eq!(os_str.to_string_lossy(), "fo�o"); + /// } + /// ``` + #[stable(feature = "rust1", since = "1.0.0")] + pub fn to_string_lossy(&self) -> Cow<'_, str> { + self.inner.to_string_lossy() + } + + /// Copies the slice into an owned [`OsString`]. + /// + /// [`OsString`]: struct.OsString.html + /// + /// # Examples + /// + /// ``` + /// use std::ffi::{OsStr, OsString}; + /// + /// let os_str = OsStr::new("foo"); + /// let os_string = os_str.to_os_string(); + /// assert_eq!(os_string, OsString::from("foo")); + /// ``` + #[stable(feature = "rust1", since = "1.0.0")] + pub fn to_os_string(&self) -> OsString { + OsString { inner: self.inner.to_owned() } + } + + /// Checks whether the `OsStr` is empty. + /// + /// # Examples + /// + /// ``` + /// use std::ffi::OsStr; + /// + /// let os_str = OsStr::new(""); + /// assert!(os_str.is_empty()); + /// + /// let os_str = OsStr::new("foo"); + /// assert!(!os_str.is_empty()); + /// ``` + #[stable(feature = "osstring_simple_functions", since = "1.9.0")] + #[inline] + pub fn is_empty(&self) -> bool { + self.inner.inner.is_empty() + } + + /// Returns the length of this `OsStr`. + /// + /// Note that this does **not** return the number of bytes in the string in + /// OS string form. + /// + /// The length returned is that of the underlying storage used by `OsStr`. + /// As discussed in the [`OsString`] introduction, [`OsString`] and `OsStr` + /// store strings in a form best suited for cheap inter-conversion between + /// native-platform and Rust string forms, which may differ significantly + /// from both of them, including in storage size and encoding. + /// + /// This number is simply useful for passing to other methods, like + /// [`OsString::with_capacity`] to avoid reallocations. + /// + /// [`OsString`]: struct.OsString.html + /// [`OsString::with_capacity`]: struct.OsString.html#method.with_capacity + /// + /// # Examples + /// + /// ``` + /// use std::ffi::OsStr; + /// + /// let os_str = OsStr::new(""); + /// assert_eq!(os_str.len(), 0); + /// + /// let os_str = OsStr::new("foo"); + /// assert_eq!(os_str.len(), 3); + /// ``` + #[stable(feature = "osstring_simple_functions", since = "1.9.0")] + pub fn len(&self) -> usize { + self.inner.inner.len() + } + + /// Converts a [`Box`]`<OsStr>` into an [`OsString`] without copying or allocating. + /// + /// [`Box`]: ../boxed/struct.Box.html + /// [`OsString`]: struct.OsString.html + #[stable(feature = "into_boxed_os_str", since = "1.20.0")] + pub fn into_os_string(self: Box<OsStr>) -> OsString { + let boxed = unsafe { Box::from_raw(Box::into_raw(self) as *mut Slice) }; + OsString { inner: Buf::from_box(boxed) } + } + + /// Gets the underlying byte representation. + /// + /// Note: it is *crucial* that this API is private, to avoid + /// revealing the internal, platform-specific encodings. + #[inline] + fn bytes(&self) -> &[u8] { + unsafe { &*(&self.inner as *const _ as *const [u8]) } + } + + /// Converts this string 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 + /// + /// # Examples + /// + /// ``` + /// #![feature(osstring_ascii)] + /// use std::ffi::OsString; + /// + /// let mut s = OsString::from("GRÜßE, JÜRGEN ❤"); + /// + /// s.make_ascii_lowercase(); + /// + /// assert_eq!("grÜße, jÜrgen ❤", s); + /// ``` + #[unstable(feature = "osstring_ascii", issue = "70516")] + pub fn make_ascii_lowercase(&mut self) { + self.inner.make_ascii_lowercase() + } + + /// Converts this string 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 + /// + /// # Examples + /// + /// ``` + /// #![feature(osstring_ascii)] + /// use std::ffi::OsString; + /// + /// let mut s = OsString::from("Grüße, Jürgen ❤"); + /// + /// s.make_ascii_uppercase(); + /// + /// assert_eq!("GRüßE, JüRGEN ❤", s); + /// ``` + #[unstable(feature = "osstring_ascii", issue = "70516")] + pub fn make_ascii_uppercase(&mut self) { + self.inner.make_ascii_uppercase() + } + + /// Returns a copy of this string 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`]: #method.make_ascii_lowercase + /// + /// # Examples + /// + /// ``` + /// #![feature(osstring_ascii)] + /// use std::ffi::OsString; + /// let s = OsString::from("Grüße, Jürgen ❤"); + /// + /// assert_eq!("grüße, jürgen ❤", s.to_ascii_lowercase()); + /// ``` + #[unstable(feature = "osstring_ascii", issue = "70516")] + pub fn to_ascii_lowercase(&self) -> OsString { + OsString::from_inner(self.inner.to_ascii_lowercase()) + } + + /// Returns a copy of this string 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`]: #method.make_ascii_uppercase + /// + /// # Examples + /// + /// ``` + /// #![feature(osstring_ascii)] + /// use std::ffi::OsString; + /// let s = OsString::from("Grüße, Jürgen ❤"); + /// + /// assert_eq!("GRüßE, JüRGEN ❤", s.to_ascii_uppercase()); + /// ``` + #[unstable(feature = "osstring_ascii", issue = "70516")] + pub fn to_ascii_uppercase(&self) -> OsString { + OsString::from_inner(self.inner.to_ascii_uppercase()) + } + + /// Checks if all characters in this string are within the ASCII range. + /// + /// # Examples + /// + /// ``` + /// #![feature(osstring_ascii)] + /// use std::ffi::OsString; + /// + /// let ascii = OsString::from("hello!\n"); + /// let non_ascii = OsString::from("Grüße, Jürgen ❤"); + /// + /// assert!(ascii.is_ascii()); + /// assert!(!non_ascii.is_ascii()); + /// ``` + #[unstable(feature = "osstring_ascii", issue = "70516")] + pub fn is_ascii(&self) -> bool { + self.inner.is_ascii() + } + + /// Checks that two strings are an ASCII case-insensitive match. + /// + /// Same as `to_ascii_lowercase(a) == to_ascii_lowercase(b)`, + /// but without allocating and copying temporaries. + /// + /// # Examples + /// + /// ``` + /// #![feature(osstring_ascii)] + /// use std::ffi::OsString; + /// + /// assert!(OsString::from("Ferris").eq_ignore_ascii_case("FERRIS")); + /// assert!(OsString::from("Ferrös").eq_ignore_ascii_case("FERRöS")); + /// assert!(!OsString::from("Ferrös").eq_ignore_ascii_case("FERRÖS")); + /// ``` + #[unstable(feature = "osstring_ascii", issue = "70516")] + pub fn eq_ignore_ascii_case<S: ?Sized + AsRef<OsStr>>(&self, other: &S) -> bool { + self.inner.eq_ignore_ascii_case(&other.as_ref().inner) + } +} + +#[stable(feature = "box_from_os_str", since = "1.17.0")] +impl From<&OsStr> for Box<OsStr> { + fn from(s: &OsStr) -> Box<OsStr> { + let rw = Box::into_raw(s.inner.into_box()) as *mut OsStr; + unsafe { Box::from_raw(rw) } + } +} + +#[stable(feature = "box_from_cow", since = "1.45.0")] +impl From<Cow<'_, OsStr>> for Box<OsStr> { + #[inline] + fn from(cow: Cow<'_, OsStr>) -> Box<OsStr> { + match cow { + Cow::Borrowed(s) => Box::from(s), + Cow::Owned(s) => Box::from(s), + } + } +} + +#[stable(feature = "os_string_from_box", since = "1.18.0")] +impl From<Box<OsStr>> for OsString { + /// Converts a [`Box`]`<`[`OsStr`]`>` into a `OsString` without copying or + /// allocating. + /// + /// [`Box`]: ../boxed/struct.Box.html + /// [`OsStr`]: ../ffi/struct.OsStr.html + fn from(boxed: Box<OsStr>) -> OsString { + boxed.into_os_string() + } +} + +#[stable(feature = "box_from_os_string", since = "1.20.0")] +impl From<OsString> for Box<OsStr> { + /// Converts a [`OsString`] into a [`Box`]`<OsStr>` without copying or allocating. + /// + /// [`Box`]: ../boxed/struct.Box.html + /// [`OsString`]: ../ffi/struct.OsString.html + fn from(s: OsString) -> Box<OsStr> { + s.into_boxed_os_str() + } +} + +#[stable(feature = "more_box_slice_clone", since = "1.29.0")] +impl Clone for Box<OsStr> { + #[inline] + fn clone(&self) -> Self { + self.to_os_string().into_boxed_os_str() + } +} + +#[stable(feature = "shared_from_slice2", since = "1.24.0")] +impl From<OsString> for Arc<OsStr> { + /// Converts a [`OsString`] into a [`Arc`]`<OsStr>` without copying or allocating. + /// + /// [`Arc`]: ../sync/struct.Arc.html + /// [`OsString`]: ../ffi/struct.OsString.html + #[inline] + fn from(s: OsString) -> Arc<OsStr> { + let arc = s.inner.into_arc(); + unsafe { Arc::from_raw(Arc::into_raw(arc) as *const OsStr) } + } +} + +#[stable(feature = "shared_from_slice2", since = "1.24.0")] +impl From<&OsStr> for Arc<OsStr> { + #[inline] + fn from(s: &OsStr) -> Arc<OsStr> { + let arc = s.inner.into_arc(); + unsafe { Arc::from_raw(Arc::into_raw(arc) as *const OsStr) } + } +} + +#[stable(feature = "shared_from_slice2", since = "1.24.0")] +impl From<OsString> for Rc<OsStr> { + /// Converts a [`OsString`] into a [`Rc`]`<OsStr>` without copying or allocating. + /// + /// [`Rc`]: ../rc/struct.Rc.html + /// [`OsString`]: ../ffi/struct.OsString.html + #[inline] + fn from(s: OsString) -> Rc<OsStr> { + let rc = s.inner.into_rc(); + unsafe { Rc::from_raw(Rc::into_raw(rc) as *const OsStr) } + } +} + +#[stable(feature = "shared_from_slice2", since = "1.24.0")] +impl From<&OsStr> for Rc<OsStr> { + #[inline] + fn from(s: &OsStr) -> Rc<OsStr> { + let rc = s.inner.into_rc(); + unsafe { Rc::from_raw(Rc::into_raw(rc) as *const OsStr) } + } +} + +#[stable(feature = "cow_from_osstr", since = "1.28.0")] +impl<'a> From<OsString> for Cow<'a, OsStr> { + #[inline] + fn from(s: OsString) -> Cow<'a, OsStr> { + Cow::Owned(s) + } +} + +#[stable(feature = "cow_from_osstr", since = "1.28.0")] +impl<'a> From<&'a OsStr> for Cow<'a, OsStr> { + #[inline] + fn from(s: &'a OsStr) -> Cow<'a, OsStr> { + Cow::Borrowed(s) + } +} + +#[stable(feature = "cow_from_osstr", since = "1.28.0")] +impl<'a> From<&'a OsString> for Cow<'a, OsStr> { + #[inline] + fn from(s: &'a OsString) -> Cow<'a, OsStr> { + Cow::Borrowed(s.as_os_str()) + } +} + +#[stable(feature = "osstring_from_cow_osstr", since = "1.28.0")] +impl<'a> From<Cow<'a, OsStr>> for OsString { + #[inline] + fn from(s: Cow<'a, OsStr>) -> Self { + s.into_owned() + } +} + +#[stable(feature = "box_default_extra", since = "1.17.0")] +impl Default for Box<OsStr> { + fn default() -> Box<OsStr> { + let rw = Box::into_raw(Slice::empty_box()) as *mut OsStr; + unsafe { Box::from_raw(rw) } + } +} + +#[stable(feature = "osstring_default", since = "1.9.0")] +impl Default for &OsStr { + /// Creates an empty `OsStr`. + #[inline] + fn default() -> Self { + OsStr::new("") + } +} + +#[stable(feature = "rust1", since = "1.0.0")] +impl PartialEq for OsStr { + #[inline] + fn eq(&self, other: &OsStr) -> bool { + self.bytes().eq(other.bytes()) + } +} + +#[stable(feature = "rust1", since = "1.0.0")] +impl PartialEq<str> for OsStr { + #[inline] + fn eq(&self, other: &str) -> bool { + *self == *OsStr::new(other) + } +} + +#[stable(feature = "rust1", since = "1.0.0")] +impl PartialEq<OsStr> for str { + #[inline] + fn eq(&self, other: &OsStr) -> bool { + *other == *OsStr::new(self) + } +} + +#[stable(feature = "rust1", since = "1.0.0")] +impl Eq for OsStr {} + +#[stable(feature = "rust1", since = "1.0.0")] +impl PartialOrd for OsStr { + #[inline] + fn partial_cmp(&self, other: &OsStr) -> Option<cmp::Ordering> { + self.bytes().partial_cmp(other.bytes()) + } + #[inline] + fn lt(&self, other: &OsStr) -> bool { + self.bytes().lt(other.bytes()) + } + #[inline] + fn le(&self, other: &OsStr) -> bool { + self.bytes().le(other.bytes()) + } + #[inline] + fn gt(&self, other: &OsStr) -> bool { + self.bytes().gt(other.bytes()) + } + #[inline] + fn ge(&self, other: &OsStr) -> bool { + self.bytes().ge(other.bytes()) + } +} + +#[stable(feature = "rust1", since = "1.0.0")] +impl PartialOrd<str> for OsStr { + #[inline] + fn partial_cmp(&self, other: &str) -> Option<cmp::Ordering> { + self.partial_cmp(OsStr::new(other)) + } +} + +// FIXME (#19470): cannot provide PartialOrd<OsStr> for str until we +// have more flexible coherence rules. + +#[stable(feature = "rust1", since = "1.0.0")] +impl Ord for OsStr { + #[inline] + fn cmp(&self, other: &OsStr) -> cmp::Ordering { + self.bytes().cmp(other.bytes()) + } +} + +macro_rules! impl_cmp { + ($lhs:ty, $rhs: ty) => { + #[stable(feature = "cmp_os_str", since = "1.8.0")] + impl<'a, 'b> PartialEq<$rhs> for $lhs { + #[inline] + fn eq(&self, other: &$rhs) -> bool { + <OsStr as PartialEq>::eq(self, other) + } + } + + #[stable(feature = "cmp_os_str", since = "1.8.0")] + impl<'a, 'b> PartialEq<$lhs> for $rhs { + #[inline] + fn eq(&self, other: &$lhs) -> bool { + <OsStr as PartialEq>::eq(self, other) + } + } + + #[stable(feature = "cmp_os_str", since = "1.8.0")] + impl<'a, 'b> PartialOrd<$rhs> for $lhs { + #[inline] + fn partial_cmp(&self, other: &$rhs) -> Option<cmp::Ordering> { + <OsStr as PartialOrd>::partial_cmp(self, other) + } + } + + #[stable(feature = "cmp_os_str", since = "1.8.0")] + impl<'a, 'b> PartialOrd<$lhs> for $rhs { + #[inline] + fn partial_cmp(&self, other: &$lhs) -> Option<cmp::Ordering> { + <OsStr as PartialOrd>::partial_cmp(self, other) + } + } + }; +} + +impl_cmp!(OsString, OsStr); +impl_cmp!(OsString, &'a OsStr); +impl_cmp!(Cow<'a, OsStr>, OsStr); +impl_cmp!(Cow<'a, OsStr>, &'b OsStr); +impl_cmp!(Cow<'a, OsStr>, OsString); + +#[stable(feature = "rust1", since = "1.0.0")] +impl Hash for OsStr { + #[inline] + fn hash<H: Hasher>(&self, state: &mut H) { + self.bytes().hash(state) + } +} + +#[stable(feature = "rust1", since = "1.0.0")] +impl fmt::Debug for OsStr { + fn fmt(&self, formatter: &mut fmt::Formatter<'_>) -> fmt::Result { + fmt::Debug::fmt(&self.inner, formatter) + } +} + +impl OsStr { + pub(crate) fn display(&self, formatter: &mut fmt::Formatter<'_>) -> fmt::Result { + fmt::Display::fmt(&self.inner, formatter) + } +} + +#[stable(feature = "rust1", since = "1.0.0")] +impl Borrow<OsStr> for OsString { + fn borrow(&self) -> &OsStr { + &self[..] + } +} + +#[stable(feature = "rust1", since = "1.0.0")] +impl ToOwned for OsStr { + type Owned = OsString; + fn to_owned(&self) -> OsString { + self.to_os_string() + } + fn clone_into(&self, target: &mut OsString) { + self.inner.clone_into(&mut target.inner) + } +} + +#[stable(feature = "rust1", since = "1.0.0")] +impl AsRef<OsStr> for OsStr { + fn as_ref(&self) -> &OsStr { + self + } +} + +#[stable(feature = "rust1", since = "1.0.0")] +impl AsRef<OsStr> for OsString { + #[inline] + fn as_ref(&self) -> &OsStr { + self + } +} + +#[stable(feature = "rust1", since = "1.0.0")] +impl AsRef<OsStr> for str { + #[inline] + fn as_ref(&self) -> &OsStr { + OsStr::from_inner(Slice::from_str(self)) + } +} + +#[stable(feature = "rust1", since = "1.0.0")] +impl AsRef<OsStr> for String { + #[inline] + fn as_ref(&self) -> &OsStr { + (&**self).as_ref() + } +} + +impl FromInner<Buf> for OsString { + fn from_inner(buf: Buf) -> OsString { + OsString { inner: buf } + } +} + +impl IntoInner<Buf> for OsString { + fn into_inner(self) -> Buf { + self.inner + } +} + +impl AsInner<Slice> for OsStr { + #[inline] + fn as_inner(&self) -> &Slice { + &self.inner + } +} + +#[stable(feature = "osstring_from_str", since = "1.45.0")] +impl FromStr for OsString { + type Err = core::convert::Infallible; + + fn from_str(s: &str) -> Result<Self, Self::Err> { + Ok(OsString::from(s)) + } +} + +#[cfg(test)] +mod tests { + use super::*; + use crate::sys_common::{AsInner, IntoInner}; + + use crate::rc::Rc; + use crate::sync::Arc; + + #[test] + fn test_os_string_with_capacity() { + let os_string = OsString::with_capacity(0); + assert_eq!(0, os_string.inner.into_inner().capacity()); + + let os_string = OsString::with_capacity(10); + assert_eq!(10, os_string.inner.into_inner().capacity()); + + let mut os_string = OsString::with_capacity(0); + os_string.push("abc"); + assert!(os_string.inner.into_inner().capacity() >= 3); + } + + #[test] + fn test_os_string_clear() { + let mut os_string = OsString::from("abc"); + assert_eq!(3, os_string.inner.as_inner().len()); + + os_string.clear(); + assert_eq!(&os_string, ""); + assert_eq!(0, os_string.inner.as_inner().len()); + } + + #[test] + fn test_os_string_capacity() { + let os_string = OsString::with_capacity(0); + assert_eq!(0, os_string.capacity()); + + let os_string = OsString::with_capacity(10); + assert_eq!(10, os_string.capacity()); + + let mut os_string = OsString::with_capacity(0); + os_string.push("abc"); + assert!(os_string.capacity() >= 3); + } + + #[test] + fn test_os_string_reserve() { + let mut os_string = OsString::new(); + assert_eq!(os_string.capacity(), 0); + + os_string.reserve(2); + assert!(os_string.capacity() >= 2); + + for _ in 0..16 { + os_string.push("a"); + } + + assert!(os_string.capacity() >= 16); + os_string.reserve(16); + assert!(os_string.capacity() >= 32); + + os_string.push("a"); + + os_string.reserve(16); + assert!(os_string.capacity() >= 33) + } + + #[test] + fn test_os_string_reserve_exact() { + let mut os_string = OsString::new(); + assert_eq!(os_string.capacity(), 0); + + os_string.reserve_exact(2); + assert!(os_string.capacity() >= 2); + + for _ in 0..16 { + os_string.push("a"); + } + + assert!(os_string.capacity() >= 16); + os_string.reserve_exact(16); + assert!(os_string.capacity() >= 32); + + os_string.push("a"); + + os_string.reserve_exact(16); + assert!(os_string.capacity() >= 33) + } + + #[test] + fn test_os_string_default() { + let os_string: OsString = Default::default(); + assert_eq!("", &os_string); + } + + #[test] + fn test_os_str_is_empty() { + let mut os_string = OsString::new(); + assert!(os_string.is_empty()); + + os_string.push("abc"); + assert!(!os_string.is_empty()); + + os_string.clear(); + assert!(os_string.is_empty()); + } + + #[test] + fn test_os_str_len() { + let mut os_string = OsString::new(); + assert_eq!(0, os_string.len()); + + os_string.push("abc"); + assert_eq!(3, os_string.len()); + + os_string.clear(); + assert_eq!(0, os_string.len()); + } + + #[test] + fn test_os_str_default() { + let os_str: &OsStr = Default::default(); + assert_eq!("", os_str); + } + + #[test] + fn into_boxed() { + let orig = "Hello, world!"; + let os_str = OsStr::new(orig); + let boxed: Box<OsStr> = Box::from(os_str); + let os_string = os_str.to_owned().into_boxed_os_str().into_os_string(); + assert_eq!(os_str, &*boxed); + assert_eq!(&*boxed, &*os_string); + assert_eq!(&*os_string, os_str); + } + + #[test] + fn boxed_default() { + let boxed = <Box<OsStr>>::default(); + assert!(boxed.is_empty()); + } + + #[test] + fn test_os_str_clone_into() { + let mut os_string = OsString::with_capacity(123); + os_string.push("hello"); + let os_str = OsStr::new("bonjour"); + os_str.clone_into(&mut os_string); + assert_eq!(os_str, os_string); + assert!(os_string.capacity() >= 123); + } + + #[test] + fn into_rc() { + let orig = "Hello, world!"; + let os_str = OsStr::new(orig); + let rc: Rc<OsStr> = Rc::from(os_str); + let arc: Arc<OsStr> = Arc::from(os_str); + + assert_eq!(&*rc, os_str); + assert_eq!(&*arc, os_str); + + let rc2: Rc<OsStr> = Rc::from(os_str.to_owned()); + let arc2: Arc<OsStr> = Arc::from(os_str.to_owned()); + + assert_eq!(&*rc2, os_str); + assert_eq!(&*arc2, os_str); + } +} |
