Merging upstream version 1.72.1+dfsg1.

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

2 files changed, 96 insertions, 14 deletions

diff --git a/library/std/src/ffi/mod.rs b/library/std/src/ffi/mod.rs
index d987bf69b..3ddb87487 100644
--- a/library/std/src/ffi/mod.rs
+++ b/library/std/src/ffi/mod.rs
@@ -127,6 +127,14 @@
 //! trait, which provides a [`from_wide`] method to convert a native Windows
 //! string (without the terminating nul character) to an [`OsString`].
 //!
+//! ## On all platforms
+//!
+//! On all platforms, [`OsStr`] consists of a sequence of bytes that is encoded as a superset of
+//! UTF-8; see [`OsString`] for more details on its encoding on different platforms.
+//!
+//! For limited, inexpensive conversions from and to bytes, see [`OsStr::as_os_str_bytes`] and
+//! [`OsStr::from_os_str_bytes_unchecked`].
+//!
 //! [Unicode scalar value]: https://www.unicode.org/glossary/#unicode_scalar_value
 //! [Unicode code point]: https://www.unicode.org/glossary/#code_point
 //! [`env::set_var()`]: crate::env::set_var "env::set_var"
diff --git a/library/std/src/ffi/os_str.rs b/library/std/src/ffi/os_str.rs
index 5c0541d3c..e7bad9d54 100644
--- a/library/std/src/ffi/os_str.rs
+++ b/library/std/src/ffi/os_str.rs
@@ -667,6 +667,51 @@ impl OsStr {
         s.as_ref()
     }
 
+    /// Converts a slice of bytes to an OS string slice without checking that the string contains
+    /// valid `OsStr`-encoded data.
+    ///
+    /// The byte encoding is an unspecified, platform-specific, self-synchronizing superset of UTF-8.
+    /// By being a self-synchronizing superset of UTF-8, this encoding is also a superset of 7-bit
+    /// ASCII.
+    ///
+    /// See the [module's toplevel documentation about conversions][conversions] for safe,
+    /// cross-platform [conversions] from/to native representations.
+    ///
+    /// # Safety
+    ///
+    /// As the encoding is unspecified, callers must pass in bytes that originated as a mixture of
+    /// validated UTF-8 and bytes from [`OsStr::as_os_str_bytes`] from within the same rust version
+    /// built for the same target platform.  For example, reconstructing an `OsStr` from bytes sent
+    /// over the network or stored in a file will likely violate these safety rules.
+    ///
+    /// Due to the encoding being self-synchronizing, the bytes from [`OsStr::as_os_str_bytes`] can be
+    /// split either immediately before or immediately after any valid non-empty UTF-8 substring.
+    ///
+    /// # Example
+    ///
+    /// ```
+    /// #![feature(os_str_bytes)]
+    ///
+    /// use std::ffi::OsStr;
+    ///
+    /// let os_str = OsStr::new("Mary had a little lamb");
+    /// let bytes = os_str.as_os_str_bytes();
+    /// let words = bytes.split(|b| *b == b' ');
+    /// let words: Vec<&OsStr> = words.map(|word| {
+    ///     // SAFETY:
+    ///     // - Each `word` only contains content that originated from `OsStr::as_os_str_bytes`
+    ///     // - Only split with ASCII whitespace which is a non-empty UTF-8 substring
+    ///     unsafe { OsStr::from_os_str_bytes_unchecked(word) }
+    /// }).collect();
+    /// ```
+    ///
+    /// [conversions]: super#conversions
+    #[inline]
+    #[unstable(feature = "os_str_bytes", issue = "111544")]
+    pub unsafe fn from_os_str_bytes_unchecked(bytes: &[u8]) -> &Self {
+        Self::from_inner(Slice::from_os_str_bytes_unchecked(bytes))
+    }
+
     #[inline]
     fn from_inner(inner: &Slice) -> &OsStr {
         // SAFETY: OsStr is just a wrapper of Slice,
@@ -700,7 +745,7 @@ impl OsStr {
                   without modifying the original"]
     #[inline]
     pub fn to_str(&self) -> Option<&str> {
-        self.inner.to_str()
+        self.inner.to_str().ok()
     }
 
     /// Converts an `OsStr` to a <code>[Cow]<[str]></code>.
@@ -837,13 +882,24 @@ impl OsStr {
         OsString { inner: Buf::from_box(boxed) }
     }
 
-    /// Gets the underlying byte representation.
+    /// Converts an OS string slice to a byte slice.  To convert the byte slice back into an OS
+    /// string slice, use the [`OsStr::from_os_str_bytes_unchecked`] function.
+    ///
+    /// The byte encoding is an unspecified, platform-specific, self-synchronizing superset of UTF-8.
+    /// By being a self-synchronizing superset of UTF-8, this encoding is also a superset of 7-bit
+    /// ASCII.
+    ///
+    /// Note: As the encoding is unspecified, any sub-slice of bytes that is not valid UTF-8 should
+    /// be treated as opaque and only comparable within the same rust version built for the same
+    /// target platform.  For example, sending the slice over the network or storing it in a file
+    /// will likely result in incompatible byte slices.  See [`OsString`] for more encoding details
+    /// and [`std::ffi`] for platform-specific, specified conversions.
     ///
-    /// Note: it is *crucial* that this API is not externally public, to avoid
-    /// revealing the internal, platform-specific encodings.
+    /// [`std::ffi`]: crate::ffi
     #[inline]
-    pub(crate) fn bytes(&self) -> &[u8] {
-        unsafe { &*(&self.inner as *const _ as *const [u8]) }
+    #[unstable(feature = "os_str_bytes", issue = "111544")]
+    pub fn as_os_str_bytes(&self) -> &[u8] {
+        self.inner.as_os_str_bytes()
     }
 
     /// Converts this string to its ASCII lower case equivalent in-place.
@@ -1109,6 +1165,24 @@ impl<'a> From<Cow<'a, OsStr>> for OsString {
     }
 }
 
+#[stable(feature = "str_tryfrom_osstr_impl", since = "1.72.0")]
+impl<'a> TryFrom<&'a OsStr> for &'a str {
+    type Error = crate::str::Utf8Error;
+
+    /// Tries to convert an `&OsStr` to a `&str`.
+    ///
+    /// ```
+    /// use std::ffi::OsStr;
+    ///
+    /// let os_str = OsStr::new("foo");
+    /// let as_str = <&str>::try_from(os_str).unwrap();
+    /// assert_eq!(as_str, "foo");
+    /// ```
+    fn try_from(value: &'a OsStr) -> Result<Self, Self::Error> {
+        value.inner.to_str()
+    }
+}
+
 #[stable(feature = "box_default_extra", since = "1.17.0")]
 impl Default for Box<OsStr> {
     #[inline]
@@ -1131,7 +1205,7 @@ impl Default for &OsStr {
 impl PartialEq for OsStr {
     #[inline]
     fn eq(&self, other: &OsStr) -> bool {
-        self.bytes().eq(other.bytes())
+        self.as_os_str_bytes().eq(other.as_os_str_bytes())
     }
 }
 
@@ -1158,23 +1232,23 @@ impl Eq for OsStr {}
 impl PartialOrd for OsStr {
     #[inline]
     fn partial_cmp(&self, other: &OsStr) -> Option<cmp::Ordering> {
-        self.bytes().partial_cmp(other.bytes())
+        self.as_os_str_bytes().partial_cmp(other.as_os_str_bytes())
     }
     #[inline]
     fn lt(&self, other: &OsStr) -> bool {
-        self.bytes().lt(other.bytes())
+        self.as_os_str_bytes().lt(other.as_os_str_bytes())
     }
     #[inline]
     fn le(&self, other: &OsStr) -> bool {
-        self.bytes().le(other.bytes())
+        self.as_os_str_bytes().le(other.as_os_str_bytes())
     }
     #[inline]
     fn gt(&self, other: &OsStr) -> bool {
-        self.bytes().gt(other.bytes())
+        self.as_os_str_bytes().gt(other.as_os_str_bytes())
     }
     #[inline]
     fn ge(&self, other: &OsStr) -> bool {
-        self.bytes().ge(other.bytes())
+        self.as_os_str_bytes().ge(other.as_os_str_bytes())
     }
 }
 
@@ -1193,7 +1267,7 @@ impl PartialOrd<str> for OsStr {
 impl Ord for OsStr {
     #[inline]
     fn cmp(&self, other: &OsStr) -> cmp::Ordering {
-        self.bytes().cmp(other.bytes())
+        self.as_os_str_bytes().cmp(other.as_os_str_bytes())
     }
 }
 
@@ -1243,7 +1317,7 @@ impl_cmp!(Cow<'a, OsStr>, OsString);
 impl Hash for OsStr {
     #[inline]
     fn hash<H: Hasher>(&self, state: &mut H) {
-        self.bytes().hash(state)
+        self.as_os_str_bytes().hash(state)
     }
 }