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).

1 files changed, 7 insertions, 1 deletions

diff --git a/library/std/src/sys_common/wtf8.rs b/library/std/src/sys_common/wtf8.rs
index ff96c35fb0b..31bb0ad25a6 100644
--- a/library/std/src/sys_common/wtf8.rs
+++ b/library/std/src/sys_common/wtf8.rs
@@ -570,7 +570,7 @@ impl Wtf8 {
     /// Since the byte slice is not checked for valid WTF-8, this functions is
     /// marked unsafe.
     #[inline]
-    unsafe fn from_bytes_unchecked(value: &[u8]) -> &Wtf8 {
+    pub unsafe fn from_bytes_unchecked(value: &[u8]) -> &Wtf8 {
         mem::transmute(value)
     }
 
@@ -614,6 +614,12 @@ impl Wtf8 {
         Wtf8CodePoints { bytes: self.bytes.iter() }
     }
 
+    /// Access raw bytes of WTF-8 data
+    #[inline]
+    pub fn as_bytes(&self) -> &[u8] {
+        &self.bytes
+    }
+
     /// Tries to convert the string to UTF-8 and return a `&str` slice.
     ///
     /// Returns `None` if the string contains surrogates.