Rollup merge of #135073 - joshtriplett:bstr, r=BurntSushi

Implement `ByteStr` and `ByteString` types

Approved ACP: rust-lang/libs-team#502
Tracking issue: #134915

These types represent human-readable strings that are conventionally,
but not always, UTF-8. The `Debug` impl prints non-UTF-8 bytes using
escape sequences, and the `Display` impl uses the Unicode replacement
character.

This is a minimal implementation of these types and associated trait
impls. It does not add any helper methods to other types such as `[u8]`
or `Vec<u8>`.

I've omitted a few implementations of `AsRef`, `AsMut`, and `Borrow`,
when those would be the second implementation for a type (counting the
`T` impl), to avoid potential inference failures. We can attempt to add
more impls later in standalone commits, and run them through crater.

In addition to the `bstr` feature, I've added a `bstr_internals` feature
for APIs provided by `core` for use by `alloc` but not currently
intended for stabilization.

This API and its implementation are based *heavily* on the `bstr` crate
by Andrew Gallant (`@BurntSushi).`

r? `@BurntSushi`

Author: matthiaskrgr

library/alloc/src/bstr.rs

@@ -102,6 +102,8 @@
 #![feature(async_fn_traits)]
 #![feature(async_iterator)]
 #![feature(box_uninit_write)]
+#![feature(bstr)]
+#![feature(bstr_internals)]
 #![feature(clone_to_uninit)]
 #![feature(coerce_unsized)]
 #![feature(const_eval_select)]
@@ -228,6 +230,8 @@ mod boxed {
     pub use std::boxed::Box;
 }
 pub mod borrow;
+#[unstable(feature = "bstr", issue = "134915")]
+pub mod bstr;
 pub mod collections;
 #[cfg(all(not(no_rc), not(no_sync), not(no_global_oom_handling)))]
 pub mod ffi;

library/alloc/src/lib.rs

@@ -311,6 +311,16 @@ unsafe impl CloneToUninit for crate::ffi::CStr {
     }
 }
 
+#[unstable(feature = "bstr", issue = "134915")]
+unsafe impl CloneToUninit for crate::bstr::ByteStr {
+    #[inline]
+    #[cfg_attr(debug_assertions, track_caller)]
+    unsafe fn clone_to_uninit(&self, dst: *mut u8) {
+        // SAFETY: ByteStr is a `#[repr(transparent)]` wrapper around `[u8]`
+        unsafe { self.as_bytes().clone_to_uninit(dst) }
+    }
+}
+
 /// Implementations of `Clone` for primitive types.
 ///
 /// Implementations that cannot be described in Rust

library/core/src/bstr.rs

@@ -111,6 +111,8 @@
 #![feature(array_ptr_get)]
 #![feature(asm_experimental_arch)]
 #![feature(bigint_helper_methods)]
+#![feature(bstr)]
+#![feature(bstr_internals)]
 #![feature(const_carrying_mul_add)]
 #![feature(const_eval_select)]
 #![feature(core_intrinsics)]
@@ -336,6 +338,8 @@ pub mod ascii;
 pub mod asserting;
 #[unstable(feature = "async_iterator", issue = "79024")]
 pub mod async_iter;
+#[unstable(feature = "bstr", issue = "134915")]
+pub mod bstr;
 pub mod cell;
 pub mod char;
 pub mod ffi;

library/core/src/clone.rs

@@ -0,0 +1,54 @@
+#![feature(bstr)]
+
+use core::ByteStr;
+
+#[test]
+fn test_debug() {
+    assert_eq!(
+        r#""\0\x01\x02\x03\x04\x05\x06\x07\x08\t\n\x11\x12\r\x14\x15\x16\x17\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f \x7f\x80\x81\xfe\xff""#,
+        format!("{:?}", ByteStr::new(b"\0\x01\x02\x03\x04\x05\x06\x07\x08\t\n\x11\x12\r\x14\x15\x16\x17\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f \x7f\x80\x81\xfe\xff")),
+    );
+}
+
+#[test]
+fn test_display() {
+    let b1 = ByteStr::new("abc");
+    let b2 = ByteStr::new(b"\xf0\x28\x8c\xbc");
+
+    assert_eq!(&format!("{b1}"), "abc");
+    assert_eq!(&format!("{b2}"), "�(��");
+
+    assert_eq!(&format!("{b1:<7}!"), "abc    !");
+    assert_eq!(&format!("{b1:>7}!"), "    abc!");
+    assert_eq!(&format!("{b1:^7}!"), "  abc  !");
+    assert_eq!(&format!("{b1:^6}!"), " abc  !");
+    assert_eq!(&format!("{b1:-<7}!"), "abc----!");
+    assert_eq!(&format!("{b1:->7}!"), "----abc!");
+    assert_eq!(&format!("{b1:-^7}!"), "--abc--!");
+    assert_eq!(&format!("{b1:-^6}!"), "-abc--!");
+
+    assert_eq!(&format!("{b2:<7}!"), "�(��   !");
+    assert_eq!(&format!("{b2:>7}!"), "   �(��!");
+    assert_eq!(&format!("{b2:^7}!"), " �(��  !");
+    assert_eq!(&format!("{b2:^6}!"), " �(�� !");
+    assert_eq!(&format!("{b2:-<7}!"), "�(��---!");
+    assert_eq!(&format!("{b2:->7}!"), "---�(��!");
+    assert_eq!(&format!("{b2:-^7}!"), "-�(��--!");
+    assert_eq!(&format!("{b2:-^6}!"), "-�(��-!");
+
+    assert_eq!(&format!("{b1:<2}!"), "abc!");
+    assert_eq!(&format!("{b1:>2}!"), "abc!");
+    assert_eq!(&format!("{b1:^2}!"), "abc!");
+    assert_eq!(&format!("{b1:-<2}!"), "abc!");
+    assert_eq!(&format!("{b1:->2}!"), "abc!");
+    assert_eq!(&format!("{b1:-^2}!"), "abc!");
+
+    assert_eq!(&format!("{b2:<3}!"), "�(��!");
+    assert_eq!(&format!("{b2:>3}!"), "�(��!");
+    assert_eq!(&format!("{b2:^3}!"), "�(��!");
+    assert_eq!(&format!("{b2:^2}!"), "�(��!");
+    assert_eq!(&format!("{b2:-<3}!"), "�(��!");
+    assert_eq!(&format!("{b2:->3}!"), "�(��!");
+    assert_eq!(&format!("{b2:-^3}!"), "�(��!");
+    assert_eq!(&format!("{b2:-^2}!"), "�(��!");
+}

library/core/src/lib.rs

@@ -0,0 +1,4 @@
+//! The `ByteStr` and `ByteString` types and trait implementations.
+
+#[unstable(feature = "bstr", issue = "134915")]
+pub use alloc::bstr::{ByteStr, ByteString};

library/core/tests/bstr.rs

@@ -320,6 +320,8 @@
 // Library features (core):
 // tidy-alphabetical-start
 #![feature(array_chunks)]
+#![feature(bstr)]
+#![feature(bstr_internals)]
 #![feature(c_str_module)]
 #![feature(char_internals)]
 #![feature(clone_to_uninit)]
@@ -581,6 +583,8 @@ pub mod f64;
 pub mod thread;
 pub mod ascii;
 pub mod backtrace;
+#[unstable(feature = "bstr", issue = "134915")]
+pub mod bstr;
 pub mod collections;
 pub mod env;
 pub mod error;

library/std/src/bstr.rs

@@ -50,6 +50,29 @@ const LINKCHECK_EXCEPTIONS: &[(&str, &[&str])] = &[
     ("alloc/slice/trait.Concat.html", &["#method.concat"]),
     ("alloc/slice/index.html", &["#method.concat", "#method.join"]),
     ("alloc/vec/struct.Vec.html", &["#method.sort_by_key", "#method.sort_by_cached_key"]),
+    ("alloc/bstr/struct.ByteStr.html", &[
+        "#method.to_ascii_uppercase",
+        "#method.to_ascii_lowercase",
+        "core/slice::sort_by_key",
+        "core\\slice::sort_by_key",
+        "#method.sort_by_cached_key",
+        "#method.sort_by_key"
+    ]),
+    ("alloc/bstr/struct.ByteString.html", &[
+        "#method.to_ascii_uppercase",
+        "#method.to_ascii_lowercase",
+        "core/slice::sort_by_key",
+        "core\\slice::sort_by_key",
+        "#method.sort_by_cached_key",
+        "#method.sort_by_key"
+    ]),
+    ("core/bstr/struct.ByteStr.html", &[
+        "#method.to_ascii_uppercase",
+        "#method.to_ascii_lowercase",
+        "core/bstr/slice::sort_by_key",
+        "core\\bstr\\slice::sort_by_key",
+        "#method.sort_by_cached_key"
+    ]),
     ("core/primitive.str.html", &["#method.to_ascii_uppercase", "#method.to_ascii_lowercase"]),
     ("core/primitive.slice.html", &["#method.to_ascii_uppercase", "#method.to_ascii_lowercase",
                                     "core/slice::sort_by_key", "core\\slice::sort_by_key",

library/std/src/lib.rs

@@ -40,14 +40,14 @@ LL | type X = std::ops::Deref::Target;
    |
 help: use fully-qualified syntax
    |
+LL | type X = <ByteStr as Deref>::Target;
+   |          ~~~~~~~~~~~~~~~~~~~~~~~~~~
+LL | type X = <ByteString as Deref>::Target;
+   |          ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 LL | type X = <CString as Deref>::Target;
    |          ~~~~~~~~~~~~~~~~~~~~~~~~~~
 LL | type X = <IoSlice<'_> as Deref>::Target;
    |          ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
-LL | type X = <IoSliceMut<'_> as Deref>::Target;
-   |          ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
-LL | type X = <OsString as Deref>::Target;
-   |          ~~~~~~~~~~~~~~~~~~~~~~~~~~~
      and N other candidates
 
 error: aborting due to 5 previous errors

src/tools/linkchecker/main.rs

@@ -32,13 +32,13 @@ LL |         [5; Self::HOST_SIZE] == [6; 0]
    = help: the following other types implement trait `PartialEq<Rhs>`:
              `&[T]` implements `PartialEq<Vec<U, A>>`
              `&[T]` implements `PartialEq<[U; N]>`
+             `&[u8; N]` implements `PartialEq<ByteStr>`
+             `&[u8; N]` implements `PartialEq<ByteString>`
+             `&[u8]` implements `PartialEq<ByteStr>`
+             `&[u8]` implements `PartialEq<ByteString>`
              `&mut [T]` implements `PartialEq<Vec<U, A>>`
              `&mut [T]` implements `PartialEq<[U; N]>`
-             `[T; N]` implements `PartialEq<&[U]>`
-             `[T; N]` implements `PartialEq<&mut [U]>`
-             `[T; N]` implements `PartialEq<[U; N]>`
-             `[T; N]` implements `PartialEq<[U]>`
-           and 3 others
+           and 11 others
 
 error: aborting due to 4 previous errors
 

tests/ui/associated-types/associated-types-in-ambiguous-context.stderr

@@ -6,11 +6,14 @@ LL |         if String::from("a") == "a".try_into().unwrap() {}
    |                              |
    |                              type must be known at this point
    |
-   = note: multiple `impl`s satisfying `String: PartialEq<_>` found in the `alloc` crate:
-           - impl PartialEq for String;
-           - impl<'a, 'b> PartialEq<&'a str> for String;
-           - impl<'a, 'b> PartialEq<Cow<'a, str>> for String;
-           - impl<'a, 'b> PartialEq<str> for String;
+   = note: cannot satisfy `String: PartialEq<_>`
+   = help: the following types implement trait `PartialEq<Rhs>`:
+             `String` implements `PartialEq<&str>`
+             `String` implements `PartialEq<ByteStr>`
+             `String` implements `PartialEq<ByteString>`
+             `String` implements `PartialEq<Cow<'_, str>>`
+             `String` implements `PartialEq<str>`
+             `String` implements `PartialEq`
 help: try using a fully qualified path to specify the expected types
    |
 LL |         if String::from("a") == <&str as TryInto<T>>::try_into("a").unwrap() {}

tests/ui/consts/too_generic_eval_ice.stderr

@@ -15,6 +15,7 @@ LL |     String::from("x".as_ref());
    |                      ^^^^^^
    |
    = note: multiple `impl`s satisfying `str: AsRef<_>` found in the following crates: `core`, `std`:
+           - impl AsRef<ByteStr> for str;
            - impl AsRef<OsStr> for str;
            - impl AsRef<Path> for str;
            - impl AsRef<[u8]> for str;
@@ -41,6 +42,7 @@ LL |     |x| String::from("x".as_ref());
    |                          ^^^^^^
    |
    = note: multiple `impl`s satisfying `str: AsRef<_>` found in the following crates: `core`, `std`:
+           - impl AsRef<ByteStr> for str;
            - impl AsRef<OsStr> for str;
            - impl AsRef<Path> for str;
            - impl AsRef<[u8]> for str;
@@ -57,6 +59,7 @@ LL |     let _ = "x".as_ref();
    |         ^       ------ type must be known at this point
    |
    = note: multiple `impl`s satisfying `str: AsRef<_>` found in the following crates: `core`, `std`:
+           - impl AsRef<ByteStr> for str;
            - impl AsRef<OsStr> for str;
            - impl AsRef<Path> for str;
            - impl AsRef<[u8]> for str;
@@ -83,6 +86,7 @@ LL |     String::from("x".as_ref());
    |                      ^^^^^^
    |
    = note: multiple `impl`s satisfying `str: AsRef<_>` found in the following crates: `core`, `std`:
+           - impl AsRef<ByteStr> for str;
            - impl AsRef<OsStr> for str;
            - impl AsRef<Path> for str;
            - impl AsRef<[u8]> for str;
@@ -109,6 +113,7 @@ LL |     String::from("x".as_ref());
    |                      ^^^^^^
    |
    = note: multiple `impl`s satisfying `str: AsRef<_>` found in the following crates: `core`, `std`:
+           - impl AsRef<ByteStr> for str;
            - impl AsRef<OsStr> for str;
            - impl AsRef<Path> for str;
            - impl AsRef<[u8]> for str;
@@ -135,6 +140,7 @@ LL |     String::from("x".as_ref());
    |                      ^^^^^^
    |
    = note: multiple `impl`s satisfying `str: AsRef<_>` found in the following crates: `core`, `std`:
+           - impl AsRef<ByteStr> for str;
            - impl AsRef<OsStr> for str;
            - impl AsRef<Path> for str;
            - impl AsRef<[u8]> for str;
@@ -161,6 +167,7 @@ LL |     String::from("x".as_ref());
    |                      ^^^^^^
    |
    = note: multiple `impl`s satisfying `str: AsRef<_>` found in the following crates: `core`, `std`:
+           - impl AsRef<ByteStr> for str;
            - impl AsRef<OsStr> for str;
            - impl AsRef<Path> for str;
            - impl AsRef<[u8]> for str;
@@ -187,6 +194,7 @@ LL |     String::from("x".as_ref());
    |                      ^^^^^^
    |
    = note: multiple `impl`s satisfying `str: AsRef<_>` found in the following crates: `core`, `std`:
+           - impl AsRef<ByteStr> for str;
            - impl AsRef<OsStr> for str;
            - impl AsRef<Path> for str;
            - impl AsRef<[u8]> for str;
@@ -213,6 +221,7 @@ LL |     String::from("x".as_ref());
    |                      ^^^^^^
    |
    = note: multiple `impl`s satisfying `str: AsRef<_>` found in the following crates: `core`, `std`:
+           - impl AsRef<ByteStr> for str;
            - impl AsRef<OsStr> for str;
            - impl AsRef<Path> for str;
            - impl AsRef<[u8]> for str;