blob: 44f39e59c10721f00c473e0b11e7d308600813dc [file] [log] [blame]
// Copyright (C) 2017-2018 Baidu, Inc. All Rights Reserved.
//
// Redistribution and use in source and binary forms, with or without
// modification, are permitted provided that the following conditions
// are met:
//
// * Redistributions of source code must retain the above copyright
// notice, this list of conditions and the following disclaimer.
// * Redistributions in binary form must reproduce the above copyright
// notice, this list of conditions and the following disclaimer in
// the documentation and/or other materials provided with the
// distribution.
// * Neither the name of Baidu, Inc., nor the names of its
// contributors may be used to endorse or promote products derived
// from this software without specific prior written permission.
//
// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
// "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
// LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
// A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
// OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
// SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
// LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
// DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
// THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
// (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
/// 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").
///
use sgx_types::c_char;
use libc;
use memchr;
use ascii;
//use error::Error;
//use io;
use core::ops;
use core::cmp::Ordering;
use core::mem;
use core::ptr;
use core::fmt::{self, Write};
use alloc::boxed::Box;
use alloc::borrow::{Cow, Borrow, ToOwned};
use alloc::vec::Vec;
use alloc::string::String;
use alloc::slice;
use alloc::rc::Rc;
use alloc::sync::Arc;
use alloc::str::{self, Utf8Error};
/// A type representing an owned C-compatible string
///
#[derive(PartialEq, PartialOrd, Eq, Ord, Hash, Clone)]
pub struct CString {
inner: Box<[u8]>,
}
/// Representation of a borrowed C string.
///
#[derive(Hash, Eq, PartialEq)]
pub struct CStr {
inner: [c_char]
}
/// An error returned from `CString::new` to indicate that a nul byte was found
/// in the vector provided.
#[derive(Clone, PartialEq, Eq, Debug)]
pub struct NulError(usize, Vec<u8>);
/// An error returned from `CStr::from_bytes_with_nul` to indicate that a nul
/// byte was found too early in the slice provided or one wasn't found at all.
#[derive(Clone, PartialEq, Eq, Debug)]
pub struct FromBytesWithNulError {
kind: FromBytesWithNulErrorKind,
}
#[derive(Clone, PartialEq, Eq, Debug)]
enum FromBytesWithNulErrorKind {
InteriorNul(usize),
NotNulTerminated,
}
impl FromBytesWithNulError {
fn interior_nul(pos: usize) -> FromBytesWithNulError {
FromBytesWithNulError {
kind: FromBytesWithNulErrorKind::InteriorNul(pos),
}
}
fn not_nul_terminated() -> FromBytesWithNulError {
FromBytesWithNulError {
kind: FromBytesWithNulErrorKind::NotNulTerminated,
}
}
pub fn __description(&self) -> &str {
match self.kind {
FromBytesWithNulErrorKind::InteriorNul(..) =>
"data provided contains an interior nul byte",
FromBytesWithNulErrorKind::NotNulTerminated =>
"data provided is not nul terminated",
}
}
}
/// An error returned from `CString::into_string` to indicate that a UTF-8 error
/// was encountered during the conversion.
#[derive(Clone, PartialEq, Eq, Debug)]
pub struct IntoStringError {
inner: CString,
error: Utf8Error,
}
impl CString {
/// Creates a new C-compatible string from a container of bytes.
///
/// This method will consume the provided data and use the underlying bytes
/// to construct a new string, ensuring that there is a trailing 0 byte.
///
/// # Errors
///
/// This function will return an error if the bytes yielded contain an
/// internal 0 byte. The error returned will contain the bytes as well as
/// the position of the nul byte.
pub fn new<T: Into<Vec<u8>>>(t: T) -> Result<CString, NulError> {
Self::_new(t.into())
}
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 from a byte vector without checking for
/// interior 0 bytes.
///
/// This method is equivalent to `new` except that no runtime assertion
/// is made that `v` contains no 0 bytes, and it requires an actual
/// byte vector, not anything that can be converted to one with Into.
///
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.
///
/// 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.
pub unsafe fn from_raw(ptr: *mut c_char) -> CString {
let len = libc::strlen(ptr) + 1; // Including the NUL byte
let slice = slice::from_raw_parts_mut(ptr, len as usize);
CString { inner: Box::from_raw(slice as *mut [c_char] as *mut [u8]) }
}
/// Transfers ownership of the string to a C caller.
///
/// The pointer must be returned to Rust and reconstituted using
/// `from_raw` to be properly deallocated. Specifically, one
/// should *not* use the standard C `free` function to deallocate
/// this string.
///
/// Failure to call `from_raw` will lead to a memory leak.
pub fn into_raw(self) -> *mut c_char {
Box::into_raw(self.into_inner()) as *mut c_char
}
/// Converts the `CString` into a `String` if it contains valid Unicode data.
///
/// On failure, ownership of the original `CString` is returned.
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()) },
})
}
/// Returns the underlying byte buffer.
///
/// The returned buffer does **not** contain the trailing nul separator and
/// it is guaranteed to not have any interior nul bytes.
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 byte.
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 separator and
/// it is guaranteed to not have any interior nul bytes.
pub fn as_bytes(&self) -> &[u8] {
&self.inner[..self.inner.len() - 1]
}
/// Equivalent to the `as_bytes` function except that the returned slice
/// includes the trailing nul byte.
pub fn as_bytes_with_nul(&self) -> &[u8] {
&self.inner
}
/// Extracts a `CStr` slice containing the entire string.
pub fn as_c_str(&self) -> &CStr {
&*self
}
/// Converts this `CString` into a boxed `CStr`.
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.
fn into_inner(self) -> Box<[u8]> {
unsafe {
let result = ptr::read(&self.inner);
mem::forget(self);
result
}
}
}
// Turns this `CString` into an empty string to prevent
// memory unsafe code from working by accident. Inline
// to prevent LLVM from optimizing it away in debug builds.
impl Drop for CString {
#[inline]
fn drop(&mut self) {
unsafe { *self.inner.get_unchecked_mut(0) = 0; }
}
}
impl ops::Deref for CString {
type Target = CStr;
#[inline]
fn deref(&self) -> &CStr {
unsafe { CStr::from_bytes_with_nul_unchecked(self.as_bytes_with_nul()) }
}
}
impl fmt::Debug for CString {
fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
fmt::Debug::fmt(&**self, f)
}
}
impl From<CString> for Vec<u8> {
#[inline]
fn from(s: CString) -> Vec<u8> {
s.into_bytes()
}
}
impl fmt::Debug for CStr {
fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
write!(f, "\"")?;
for byte in self.to_bytes().iter().flat_map(|&b| ascii::escape_default(b)) {
f.write_char(byte as char)?;
}
write!(f, "\"")
}
}
impl<'a> Default for &'a CStr {
fn default() -> &'a CStr {
const SLICE: & [c_char] = &[0];
unsafe { CStr::from_ptr(SLICE.as_ptr()) }
}
}
impl Default for CString {
/// Creates an empty `CString`.
fn default() -> CString {
let a: &CStr = Default::default();
a.to_owned()
}
}
impl Borrow<CStr> for CString {
#[inline]
fn borrow(&self) -> &CStr { self }
}
impl<'a> From<&'a CStr> for Box<CStr> {
fn from(s: &'a 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) }
}
}
impl From<Box<CStr>> for CString {
#[inline]
fn from(s: Box<CStr>) -> CString {
s.into_c_string()
}
}
impl From<CString> for Box<CStr> {
#[inline]
fn from(s: CString) -> Box<CStr> {
s.into_boxed_c_str()
}
}
impl From<CString> for Arc<CStr> {
#[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) }
}
}
impl<'a> From<&'a 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) }
}
}
impl From<CString> for Rc<CStr> {
#[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) }
}
}
impl<'a> From<&'a 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) }
}
}
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 was provided to
/// `CString::new`.
///
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.
///
pub fn into_vec(self) -> Vec<u8> { self.1 }
}
impl fmt::Display for NulError {
fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
write!(f, "nul byte found in provided data at position: {}", self.0)
}
}
impl fmt::Display for FromBytesWithNulError {
fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
f.write_str(self.__description())?;
if let FromBytesWithNulErrorKind::InteriorNul(pos) = self.kind {
write!(f, " at byte pos {}", pos)?;
}
Ok(())
}
}
impl IntoStringError {
/// Consumes this error, returning original `CString` which generated the
/// error.
pub fn into_cstring(self) -> CString {
self.inner
}
/// Access the underlying UTF-8 error that was the cause of this error.
pub fn utf8_error(&self) -> Utf8Error {
self.error
}
pub fn __description(&self) -> &str {
"C string contained non-utf8 bytes"
}
pub fn __cause(&self) -> Option<&Utf8Error> {
Some(&self.error)
}
}
impl fmt::Display for IntoStringError {
fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
self.__description().fmt(f)
}
}
impl CStr {
/// Wraps a raw C string with a safe C string wrapper.
///
/// This function will wrap the provided `ptr` with a `CStr` wrapper, which
/// allows inspection and interoperation of non-owned C strings. This method
/// is unsafe for a number of reasons:
///
/// * There is no guarantee to the validity of `ptr`.
/// * The returned lifetime is not guaranteed to be the actual lifetime of
/// `ptr`.
/// * There is no guarantee that the memory pointed to by `ptr` contains a
/// valid nul terminator byte at the end of the string.
/// * It is not guaranteed that the memory pointed by `ptr` won't change
/// before the `CStr` has been destroyed.
///
/// > **Note**: This operation is intended to be a 0-cost cast but it is
/// > currently implemented with an up-front calculation of the length of
/// > the string. This is not guaranteed to always be the case.
///
pub unsafe fn from_ptr<'a>(ptr: *const c_char) -> &'a CStr {
let len = libc::strlen(ptr);
let ptr = ptr as *const u8;
CStr::from_bytes_with_nul_unchecked(slice::from_raw_parts(ptr, len as usize + 1))
}
/// Creates a C string wrapper from a byte slice.
///
/// This function will cast the provided `bytes` to a `CStr`
/// wrapper after ensuring that the byte slice is nul-terminated
/// and does not contain any interior nul bytes.
///
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.
///
pub 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.
///
pub fn as_ptr(&self) -> *const c_char {
self.inner.as_ptr()
}
/// Converts this C string to a byte slice.
///
/// The returned slice will **not** contain the trailing nul terminator that this C
/// string has.
///
/// > **Note**: This method is currently implemented as a constant-time
/// > cast, but it is planned to alter its definition in the future to
/// > perform the length calculation whenever this method is called.
///
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
///
pub fn to_bytes_with_nul(&self) -> &[u8] {
unsafe { &*(&self.inner as *const [c_char] as *const [u8]) }
}
/// Yields a [`&str`] slice if the `CStr` contains valid UTF-8.
///
/// If the contents of the `CStr` are valid UTF-8 data, this
/// function will return the corresponding [`&str`] slice. Otherwise,
/// it will return an error with details of where UTF-8 validation failed.
///
/// > **Note**: This method is currently implemented to check for validity
/// > after a constant-time cast, but it is planned to alter its definition
/// > in the future to perform the length calculation in addition to the
/// > UTF-8 check whenever this method is called.
///
/// [`&str`]: ../primitive.str.html
///
pub fn to_str(&self) -> Result<&str, str::Utf8Error> {
// NB: When CStr is changed to perform the length check in .to_bytes()
// instead of in from_ptr(), it may be worth considering if this should
// be rewritten to do the UTF-8 check inline with the length calculation
// instead of doing it afterwards.
str::from_utf8(self.to_bytes())
}
/// Converts a `CStr` into a [`Cow`]`<`[`str`]`>`.
///
/// If the contents of the `CStr` are valid UTF-8 data, this
/// function will return a [`Cow`]`::`[`Borrowed`]`(`[`&str`]`)`
/// with the the corresponding [`&str`] slice. Otherwise, it will
/// replace any invalid UTF-8 sequences with `U+FFFD REPLACEMENT
/// CHARACTER` and return a [`Cow`]`::`[`Owned`]`(`[`String`]`)`
/// with the result.
///
/// > **Note**: This method is currently implemented to check for validity
/// > after a constant-time cast, but it is planned to alter its definition
/// > in the future to perform the length calculation in addition to the
/// > UTF-8 check whenever this method is called.
///
/// [`Cow`]: ../borrow/enum.Cow.html
/// [`Borrowed`]: ../borrow/enum.Cow.html#variant.Borrowed
/// [`str`]: ../primitive.str.html
/// [`String`]: ../string/struct.String.html
///
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
///
#[allow(clippy::wrong_self_convention)]
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) } }
}
}
//impl PartialEq for CStr {
// fn eq(&self, other: &CStr) -> bool {
// self.to_bytes().eq(other.to_bytes())
// }
//}
//impl Eq for CStr {}
impl PartialOrd for CStr {
fn partial_cmp(&self, other: &CStr) -> Option<Ordering> {
self.to_bytes().partial_cmp(&other.to_bytes())
}
}
impl Ord for CStr {
fn cmp(&self, other: &CStr) -> Ordering {
self.to_bytes().cmp(&other.to_bytes())
}
}
impl ToOwned for CStr {
type Owned = CString;
fn to_owned(&self) -> CString {
CString { inner: self.to_bytes_with_nul().into() }
}
}
impl<'a> From<&'a CStr> for CString {
fn from(s: &'a CStr) -> CString {
s.to_owned()
}
}
impl ops::Index<ops::RangeFull> for CString {
type Output = CStr;
#[inline]
fn index(&self, _index: ops::RangeFull) -> &CStr {
self
}
}
impl AsRef<CStr> for CStr {
#[inline]
fn as_ref(&self) -> &CStr {
self
}
}
impl AsRef<CStr> for CString {
#[inline]
fn as_ref(&self) -> &CStr {
self
}
}