Rollup merge of #86509 - CDirkx:os_str, r=m-ou-se

Move `os_str_bytes` to `sys::unix`

Followup to #84967, with `OsStrExt` and `OsStringExt` moved out of `sys_common`, there is no reason anymore for `os_str_bytes` to live in `sys_common` and not in sys. This pr moves it to the location `sys::unix::os_str` and reuses the code on other platforms via `#[path]` (as is common in `sys`) instead of importing.

9 files changed, 276 insertions, 10 deletions

diff --git a/library/std/src/sys/hermit/mod.rs b/library/std/src/sys/hermit/mod.rs
index 10c19424953..185b68c0a78 100644
--- a/library/std/src/sys/hermit/mod.rs
+++ b/library/std/src/sys/hermit/mod.rs
@@ -32,6 +32,8 @@ pub mod memchr;
 pub mod mutex;
 pub mod net;
 pub mod os;
+#[path = "../unix/os_str.rs"]
+pub mod os_str;
 #[path = "../unix/path.rs"]
 pub mod path;
 #[path = "../unsupported/pipe.rs"]
@@ -47,7 +49,6 @@ pub mod thread_local_key;
 pub mod time;
 
 use crate::io::ErrorKind;
-pub use crate::sys_common::os_str_bytes as os_str;
 
 #[allow(unused_extern_crates)]
 pub extern crate hermit_abi as abi;
diff --git a/library/std/src/sys/sgx/mod.rs b/library/std/src/sys/sgx/mod.rs
index fce6b420732..a2a763c2b4e 100644
--- a/library/std/src/sys/sgx/mod.rs
+++ b/library/std/src/sys/sgx/mod.rs
@@ -26,6 +26,8 @@ pub mod memchr;
 pub mod mutex;
 pub mod net;
 pub mod os;
+#[path = "../unix/os_str.rs"]
+pub mod os_str;
 pub mod path;
 #[path = "../unsupported/pipe.rs"]
 pub mod pipe;
@@ -37,8 +39,6 @@ pub mod thread;
 pub mod thread_local_key;
 pub mod time;
 
-pub use crate::sys_common::os_str_bytes as os_str;
-
 // SAFETY: must be called only once during runtime initialization.
 // NOTE: this is not guaranteed to run, for example when Rust code is called externally.
 pub unsafe fn init(argc: isize, argv: *const *const u8) {
diff --git a/library/std/src/sys/unix/mod.rs b/library/std/src/sys/unix/mod.rs
index 9e553ec7682..f827a4bca53 100644
--- a/library/std/src/sys/unix/mod.rs
+++ b/library/std/src/sys/unix/mod.rs
@@ -30,6 +30,7 @@ pub mod net;
 #[cfg(target_os = "l4re")]
 pub use self::l4re::net;
 pub mod os;
+pub mod os_str;
 pub mod path;
 pub mod pipe;
 pub mod process;
@@ -42,8 +43,6 @@ pub mod thread_local_dtor;
 pub mod thread_local_key;
 pub mod time;
 
-pub use crate::sys_common::os_str_bytes as os_str;
-
 // SAFETY: must be called only once during runtime initialization.
 // NOTE: this is not guaranteed to run, for example when Rust code is called externally.
 pub unsafe fn init(argc: isize, argv: *const *const u8) {
diff --git a/library/std/src/sys/unix/os_str.rs b/library/std/src/sys/unix/os_str.rs
new file mode 100644
index 00000000000..ae96d6b4df4
--- /dev/null
+++ b/library/std/src/sys/unix/os_str.rs
@@ -0,0 +1,255 @@
+//! The underlying OsString/OsStr implementation on Unix and many other
+//! systems: just a `Vec<u8>`/`[u8]`.
+
+use crate::borrow::Cow;
+use crate::fmt;
+use crate::fmt::Write;
+use crate::mem;
+use crate::rc::Rc;
+use crate::str;
+use crate::sync::Arc;
+use crate::sys_common::{AsInner, IntoInner};
+
+use core::str::lossy::{Utf8Lossy, Utf8LossyChunk};
+
+#[cfg(test)]
+#[path = "../unix/os_str/tests.rs"]
+mod tests;
+
+#[derive(Hash)]
+#[repr(transparent)]
+pub struct Buf {
+    pub inner: Vec<u8>,
+}
+
+#[repr(transparent)]
+pub struct Slice {
+    pub inner: [u8],
+}
+
+impl fmt::Debug for Slice {
+    fn fmt(&self, formatter: &mut fmt::Formatter<'_>) -> fmt::Result {
+        // Writes out a valid unicode string with the correct escape sequences
+
+        formatter.write_str("\"")?;
+        for Utf8LossyChunk { valid, broken } in Utf8Lossy::from_bytes(&self.inner).chunks() {
+            for c in valid.chars().flat_map(|c| c.escape_debug()) {
+                formatter.write_char(c)?
+            }
+
+            for b in broken {
+                write!(formatter, "\\x{:02X}", b)?;
+            }
+        }
+        formatter.write_str("\"")
+    }
+}
+
+impl fmt::Display for Slice {
+    fn fmt(&self, formatter: &mut fmt::Formatter<'_>) -> fmt::Result {
+        fmt::Display::fmt(&Utf8Lossy::from_bytes(&self.inner), formatter)
+    }
+}
+
+impl fmt::Debug for Buf {
+    fn fmt(&self, formatter: &mut fmt::Formatter<'_>) -> fmt::Result {
+        fmt::Debug::fmt(self.as_slice(), formatter)
+    }
+}
+
+impl fmt::Display for Buf {
+    fn fmt(&self, formatter: &mut fmt::Formatter<'_>) -> fmt::Result {
+        fmt::Display::fmt(self.as_slice(), formatter)
+    }
+}
+
+impl Clone for Buf {
+    #[inline]
+    fn clone(&self) -> Self {
+        Buf { inner: self.inner.clone() }
+    }
+
+    #[inline]
+    fn clone_from(&mut self, source: &Self) {
+        self.inner.clone_from(&source.inner)
+    }
+}
+
+impl IntoInner<Vec<u8>> for Buf {
+    fn into_inner(self) -> Vec<u8> {
+        self.inner
+    }
+}
+
+impl AsInner<[u8]> for Buf {
+    fn as_inner(&self) -> &[u8] {
+        &self.inner
+    }
+}
+
+impl Buf {
+    pub fn from_string(s: String) -> Buf {
+        Buf { inner: s.into_bytes() }
+    }
+
+    #[inline]
+    pub fn with_capacity(capacity: usize) -> Buf {
+        Buf { inner: Vec::with_capacity(capacity) }
+    }
+
+    #[inline]
+    pub fn clear(&mut self) {
+        self.inner.clear()
+    }
+
+    #[inline]
+    pub fn capacity(&self) -> usize {
+        self.inner.capacity()
+    }
+
+    #[inline]
+    pub fn reserve(&mut self, additional: usize) {
+        self.inner.reserve(additional)
+    }
+
+    #[inline]
+    pub fn reserve_exact(&mut self, additional: usize) {
+        self.inner.reserve_exact(additional)
+    }
+
+    #[inline]
+    pub fn shrink_to_fit(&mut self) {
+        self.inner.shrink_to_fit()
+    }
+
+    #[inline]
+    pub fn shrink_to(&mut self, min_capacity: usize) {
+        self.inner.shrink_to(min_capacity)
+    }
+
+    #[inline]
+    pub fn as_slice(&self) -> &Slice {
+        // SAFETY: Slice just wraps [u8],
+        // and &*self.inner is &[u8], therefore
+        // transmuting &[u8] to &Slice is safe.
+        unsafe { mem::transmute(&*self.inner) }
+    }
+
+    #[inline]
+    pub fn as_mut_slice(&mut self) -> &mut Slice {
+        // SAFETY: Slice just wraps [u8],
+        // and &mut *self.inner is &mut [u8], therefore
+        // transmuting &mut [u8] to &mut Slice is safe.
+        unsafe { mem::transmute(&mut *self.inner) }
+    }
+
+    pub fn into_string(self) -> Result<String, Buf> {
+        String::from_utf8(self.inner).map_err(|p| Buf { inner: p.into_bytes() })
+    }
+
+    pub fn push_slice(&mut self, s: &Slice) {
+        self.inner.extend_from_slice(&s.inner)
+    }
+
+    #[inline]
+    pub fn into_box(self) -> Box<Slice> {
+        unsafe { mem::transmute(self.inner.into_boxed_slice()) }
+    }
+
+    #[inline]
+    pub fn from_box(boxed: Box<Slice>) -> Buf {
+        let inner: Box<[u8]> = unsafe { mem::transmute(boxed) };
+        Buf { inner: inner.into_vec() }
+    }
+
+    #[inline]
+    pub fn into_arc(&self) -> Arc<Slice> {
+        self.as_slice().into_arc()
+    }
+
+    #[inline]
+    pub fn into_rc(&self) -> Rc<Slice> {
+        self.as_slice().into_rc()
+    }
+}
+
+impl Slice {
+    #[inline]
+    fn from_u8_slice(s: &[u8]) -> &Slice {
+        unsafe { mem::transmute(s) }
+    }
+
+    #[inline]
+    pub fn from_str(s: &str) -> &Slice {
+        Slice::from_u8_slice(s.as_bytes())
+    }
+
+    pub fn to_str(&self) -> Option<&str> {
+        str::from_utf8(&self.inner).ok()
+    }
+
+    pub fn to_string_lossy(&self) -> Cow<'_, str> {
+        String::from_utf8_lossy(&self.inner)
+    }
+
+    pub fn to_owned(&self) -> Buf {
+        Buf { inner: self.inner.to_vec() }
+    }
+
+    pub fn clone_into(&self, buf: &mut Buf) {
+        self.inner.clone_into(&mut buf.inner)
+    }
+
+    #[inline]
+    pub fn into_box(&self) -> Box<Slice> {
+        let boxed: Box<[u8]> = self.inner.into();
+        unsafe { mem::transmute(boxed) }
+    }
+
+    pub fn empty_box() -> Box<Slice> {
+        let boxed: Box<[u8]> = Default::default();
+        unsafe { mem::transmute(boxed) }
+    }
+
+    #[inline]
+    pub fn into_arc(&self) -> Arc<Slice> {
+        let arc: Arc<[u8]> = Arc::from(&self.inner);
+        unsafe { Arc::from_raw(Arc::into_raw(arc) as *const Slice) }
+    }
+
+    #[inline]
+    pub fn into_rc(&self) -> Rc<Slice> {
+        let rc: Rc<[u8]> = Rc::from(&self.inner);
+        unsafe { Rc::from_raw(Rc::into_raw(rc) as *const Slice) }
+    }
+
+    #[inline]
+    pub fn make_ascii_lowercase(&mut self) {
+        self.inner.make_ascii_lowercase()
+    }
+
+    #[inline]
+    pub fn make_ascii_uppercase(&mut self) {
+        self.inner.make_ascii_uppercase()
+    }
+
+    #[inline]
+    pub fn to_ascii_lowercase(&self) -> Buf {
+        Buf { inner: self.inner.to_ascii_lowercase() }
+    }
+
+    #[inline]
+    pub fn to_ascii_uppercase(&self) -> Buf {
+        Buf { inner: self.inner.to_ascii_uppercase() }
+    }
+
+    #[inline]
+    pub fn is_ascii(&self) -> bool {
+        self.inner.is_ascii()
+    }
+
+    #[inline]
+    pub fn eq_ignore_ascii_case(&self, other: &Self) -> bool {
+        self.inner.eq_ignore_ascii_case(&other.inner)
+    }
+}
diff --git a/library/std/src/sys/unix/os_str/tests.rs b/library/std/src/sys/unix/os_str/tests.rs
new file mode 100644
index 00000000000..37967378155
--- /dev/null
+++ b/library/std/src/sys/unix/os_str/tests.rs
@@ -0,0 +1,10 @@
+use super::*;
+
+#[test]
+fn slice_debug_output() {
+    let input = Slice::from_u8_slice(b"\xF0hello,\tworld");
+    let expected = r#""\xF0hello,\tworld""#;
+    let output = format!("{:?}", input);
+
+    assert_eq!(output, expected);
+}
diff --git a/library/std/src/sys/unsupported/common.rs b/library/std/src/sys/unsupported/common.rs
index 4e6c301d29f..a06b44e96a9 100644
--- a/library/std/src/sys/unsupported/common.rs
+++ b/library/std/src/sys/unsupported/common.rs
@@ -4,8 +4,6 @@ pub mod memchr {
     pub use core::slice::memchr::{memchr, memrchr};
 }
 
-pub use crate::sys_common::os_str_bytes as os_str;
-
 // This is not necessarily correct. May want to consider making it part of the
 // spec definition?
 use crate::os::raw::c_char;
diff --git a/library/std/src/sys/unsupported/mod.rs b/library/std/src/sys/unsupported/mod.rs
index 3ef4c6b8a8f..a1276193bda 100644
--- a/library/std/src/sys/unsupported/mod.rs
+++ b/library/std/src/sys/unsupported/mod.rs
@@ -11,6 +11,8 @@ pub mod io;
 pub mod mutex;
 pub mod net;
 pub mod os;
+#[path = "../unix/os_str.rs"]
+pub mod os_str;
 #[path = "../unix/path.rs"]
 pub mod path;
 pub mod pipe;
diff --git a/library/std/src/sys/wasi/mod.rs b/library/std/src/sys/wasi/mod.rs
index 4af99bfa464..8d62335aae5 100644
--- a/library/std/src/sys/wasi/mod.rs
+++ b/library/std/src/sys/wasi/mod.rs
@@ -32,7 +32,8 @@ pub mod io;
 pub mod mutex;
 pub mod net;
 pub mod os;
-pub use crate::sys_common::os_str_bytes as os_str;
+#[path = "../unix/os_str.rs"]
+pub mod os_str;
 #[path = "../unix/path.rs"]
 pub mod path;
 #[path = "../unsupported/pipe.rs"]
diff --git a/library/std/src/sys/wasm/mod.rs b/library/std/src/sys/wasm/mod.rs
index cd701a333f8..c81d653a5e3 100644
--- a/library/std/src/sys/wasm/mod.rs
+++ b/library/std/src/sys/wasm/mod.rs
@@ -30,6 +30,8 @@ pub mod io;
 pub mod net;
 #[path = "../unsupported/os.rs"]
 pub mod os;
+#[path = "../unix/os_str.rs"]
+pub mod os_str;
 #[path = "../unix/path.rs"]
 pub mod path;
 #[path = "../unsupported/pipe.rs"]
@@ -45,8 +47,6 @@ pub mod thread_local_key;
 #[path = "../unsupported/time.rs"]
 pub mod time;
 
-pub use crate::sys_common::os_str_bytes as os_str;
-
 cfg_if::cfg_if! {
     if #[cfg(target_feature = "atomics")] {
         #[path = "atomics/condvar.rs"]