about summary refs log tree commit diff
path: root/src/libstd
diff options
context:
space:
mode:
authorbors <bors@rust-lang.org>2015-06-10 22:37:38 +0000
committerbors <bors@rust-lang.org>2015-06-10 22:37:38 +0000
commit01ab4f761c09830bdd77726f5ae2351e9e3432c4 (patch)
tree4974ad2f22af5f67ed695d20f9848d28e4561cf5 /src/libstd
parentdb0c1cb13c9a1e68c09e2074b6d3a7b38122fb76 (diff)
parente20a6dbeed095427e5d5487844f65e7eb1599651 (diff)
downloadrust-01ab4f761c09830bdd77726f5ae2351e9e3432c4.tar.gz
rust-01ab4f761c09830bdd77726f5ae2351e9e3432c4.zip
Auto merge of #25777 - shepmaster:cstring-return-to-c, r=alexcrichton
As far as I was able to determine, it's currently *impossible* to allocate a C NUL-terminated string in Rust and then return it to C (transferring ownership), without leaking memory. There is support for passing the string to C (borrowing).

To complicate matters, it's not possible for the C code to just call `free` on the allocated string, due to the different allocators in use.

`CString` has no way to recreate itself from a pointer. This commit adds one. This is complicated a bit because Rust `Vec`s want the pointer, size, and capacity.

To deal with that, another method to shrink and "leak" the `CString` to a `char *` is also provided. 

We can then use `strlen` to determine the length of the string, which must match the capacity. 

**TODO**

- [x] Improve documentation
- [x] Add stability markers
- [x] Convert to `Box<[u8]>`

### Example code

With this example code:

```rust
#![feature(libc)]
#![feature(cstr_to_str)]
#![feature(c_str_memory)]

extern crate libc;

use std::ffi::{CStr,CString};

#[no_mangle]
pub extern fn reverse(s: *const libc::c_char) -> *const libc::c_char {
    let s = unsafe { CStr::from_ptr(s) };
    let s2 = s.to_str().unwrap();
    let s3: String = s2.chars().rev().collect();
    let s4 = CString::new(s3).unwrap();
    s4.into_ptr()
}

#[no_mangle]
pub extern fn cleanup(s: *const libc::c_char) {
    unsafe { CString::from_ptr(s) };
}
```

Compiled using `rustc --crate-type dylib str.rs`, I was able to link against it from C (`gcc -L. -l str str.c -o str`):
 
```c
#include <stdio.h>

extern char *reverse(char *);
extern void cleanup(char *);

int main() {
  char *s = reverse("Hello, world!");
  printf("%s\n", s);
  cleanup(s);
}
```

As well as dynamically link via Ruby:

```ruby
require 'fiddle'
require 'fiddle/import'

module LibSum
  extend Fiddle::Importer

  dlload './libstr.dylib'
  extern 'char* reverse(char *)'
  extern 'void cleanup(char *)'
end

s = LibSum.reverse("hello, world!")
puts s
LibSum.cleanup(s)
```
Diffstat (limited to 'src/libstd')
-rw-r--r--src/libstd/ffi/c_str.rs45
1 files changed, 41 insertions, 4 deletions
diff --git a/src/libstd/ffi/c_str.rs b/src/libstd/ffi/c_str.rs
index 8c066b3dc2e..433bb335a80 100644
--- a/src/libstd/ffi/c_str.rs
+++ b/src/libstd/ffi/c_str.rs
@@ -10,7 +10,9 @@
 
 #![unstable(feature = "std_misc")]
 
-use borrow::Cow;
+use borrow::{Cow, ToOwned};
+use boxed::{self, Box};
+use clone::Clone;
 use convert::{Into, From};
 use cmp::{PartialEq, Eq, PartialOrd, Ord, Ordering};
 use error::Error;
@@ -61,10 +63,10 @@ use vec::Vec;
 /// }
 /// # }
 /// ```
-#[derive(Clone, PartialEq, PartialOrd, Eq, Ord, Hash)]
+#[derive(PartialEq, PartialOrd, Eq, Ord, Hash)]
 #[stable(feature = "rust1", since = "1.0.0")]
 pub struct CString {
-    inner: Vec<u8>,
+    inner: Box<[u8]>,
 }
 
 /// Representation of a borrowed C string.
@@ -197,7 +199,35 @@ impl CString {
     #[stable(feature = "rust1", since = "1.0.0")]
     pub unsafe fn from_vec_unchecked(mut v: Vec<u8>) -> CString {
         v.push(0);
-        CString { inner: v }
+        CString { inner: v.into_boxed_slice() }
+    }
+
+    /// Retakes ownership of a CString that was transferred to C.
+    ///
+    /// The only appropriate argument is a pointer obtained by calling
+    /// `into_ptr`. The length of the string will be recalculated
+    /// using the pointer.
+    #[unstable(feature = "cstr_memory", reason = "recently added")]
+    pub unsafe fn from_ptr(ptr: *const libc::c_char) -> CString {
+        let len = libc::strlen(ptr) + 1; // Including the NUL byte
+        let slice = slice::from_raw_parts(ptr, len as usize);
+        CString { inner: mem::transmute(slice) }
+    }
+
+    /// Transfers ownership of the string to a C caller.
+    ///
+    /// The pointer must be returned to Rust and reconstituted using
+    /// `from_ptr` to be properly deallocated. Specifically, one
+    /// should *not* use the standard C `free` function to deallocate
+    /// this string.
+    ///
+    /// Failure to call `from_ptr` will lead to a memory leak.
+    #[unstable(feature = "cstr_memory", reason = "recently added")]
+    pub fn into_ptr(self) -> *const libc::c_char {
+        // It is important that the bytes be sized to fit - we need
+        // the capacity to be determinable from the string length, and
+        // shrinking to fit is the only way to be sure.
+        boxed::into_raw(self.inner) as *const libc::c_char
     }
 
     /// Returns the contents of this `CString` as a slice of bytes.
@@ -218,6 +248,13 @@ impl CString {
 }
 
 #[stable(feature = "rust1", since = "1.0.0")]
+impl Clone for CString {
+    fn clone(&self) -> Self {
+        CString { inner: self.inner.to_owned().into_boxed_slice() }
+    }
+}
+
+#[stable(feature = "rust1", since = "1.0.0")]
 impl Deref for CString {
     type Target = CStr;