Allow access to `OsStr` bytes

`OsStr` has historically kept its implementation details private out of
concern for locking us into a specific encoding on Windows.

This is an alternative to #95290 which proposed specifying the encoding on Windows.  Instead, this
only specifies that for cross-platform code, `OsStr`'s encoding is a superset of UTF-8 and defines
rules for safely interacting with it

At minimum, this can greatly simplify the `os_str_bytes` crate and every
arg parser that interacts with `OsStr` directly (which is most of those
that support invalid UTF-8).

3 files changed, 21 insertions, 7 deletions

diff --git a/library/std/src/sys/unix/os_str.rs b/library/std/src/sys/unix/os_str.rs
index 488217f3941..142fcb9ed0b 100644
--- a/library/std/src/sys/unix/os_str.rs
+++ b/library/std/src/sys/unix/os_str.rs
@@ -193,13 +193,18 @@ impl Buf {
 
 impl Slice {
     #[inline]
-    fn from_u8_slice(s: &[u8]) -> &Slice {
+    pub fn as_os_str_bytes(&self) -> &[u8] {
+        &self.inner
+    }
+
+    #[inline]
+    pub unsafe fn from_os_str_bytes_unchecked(s: &[u8]) -> &Slice {
         unsafe { mem::transmute(s) }
     }
 
     #[inline]
     pub fn from_str(s: &str) -> &Slice {
-        Slice::from_u8_slice(s.as_bytes())
+        unsafe { Slice::from_os_str_bytes_unchecked(s.as_bytes()) }
     }
 
     pub fn to_str(&self) -> Option<&str> {
diff --git a/library/std/src/sys/unix/os_str/tests.rs b/library/std/src/sys/unix/os_str/tests.rs
index 22ba0c92350..91bc0e61a4a 100644
--- a/library/std/src/sys/unix/os_str/tests.rs
+++ b/library/std/src/sys/unix/os_str/tests.rs
@@ -2,7 +2,7 @@ use super::*;
 
 #[test]
 fn slice_debug_output() {
-    let input = Slice::from_u8_slice(b"\xF0hello,\tworld");
+    let input = unsafe { Slice::from_os_str_bytes_unchecked(b"\xF0hello,\tworld") };
     let expected = r#""\xF0hello,\tworld""#;
     let output = format!("{input:?}");
 
@@ -11,8 +11,7 @@ fn slice_debug_output() {
 
 #[test]
 fn display() {
-    assert_eq!(
-        "Hello\u{FFFD}\u{FFFD} There\u{FFFD} Goodbye",
-        Slice::from_u8_slice(b"Hello\xC0\x80 There\xE6\x83 Goodbye").to_string(),
-    );
+    assert_eq!("Hello\u{FFFD}\u{FFFD} There\u{FFFD} Goodbye", unsafe {
+        Slice::from_os_str_bytes_unchecked(b"Hello\xC0\x80 There\xE6\x83 Goodbye").to_string()
+    },);
 }
diff --git a/library/std/src/sys/windows/os_str.rs b/library/std/src/sys/windows/os_str.rs
index 2f2b0e56e08..611f0d040f0 100644
--- a/library/std/src/sys/windows/os_str.rs
+++ b/library/std/src/sys/windows/os_str.rs
@@ -152,6 +152,16 @@ impl Buf {
 
 impl Slice {
     #[inline]
+    pub fn as_os_str_bytes(&self) -> &[u8] {
+        self.inner.as_bytes()
+    }
+
+    #[inline]
+    pub unsafe fn from_os_str_bytes_unchecked(s: &[u8]) -> &Slice {
+        mem::transmute(Wtf8::from_bytes_unchecked(s))
+    }
+
+    #[inline]
     pub fn from_str(s: &str) -> &Slice {
         unsafe { mem::transmute(Wtf8::from_str(s)) }
     }