Auto merge of #117472 - jmillikin:stable-c-str-literals, r=Nilstrieb

Stabilize C string literals

RFC: https://rust-lang.github.io/rfcs/3348-c-str-literal.html

Tracking issue: https://github.com/rust-lang/rust/issues/105723

Documentation PR (reference manual): https://github.com/rust-lang/reference/pull/1423

# Stabilization report

Stabilizes C string and raw C string literals (`c"..."` and `cr#"..."#`), which are expressions of type [`&CStr`](https://doc.rust-lang.org/stable/core/ffi/struct.CStr.html). Both new literals require Rust edition 2021 or later.

```rust
const HELLO: &core::ffi::CStr = c"Hello, world!";
```

C strings may contain any byte other than `NUL` (`b'\x00'`), and their in-memory representation is guaranteed to end with `NUL`.

## Implementation

Originally implemented by PR https://github.com/rust-lang/rust/pull/108801, which was reverted due to unintentional changes to lexer behavior in Rust editions < 2021.

The current implementation landed in PR https://github.com/rust-lang/rust/pull/113476, which restricts C string literals to Rust edition >= 2021.

## Resolutions to open questions from the RFC

* Adding C character literals (`c'.'`) of type `c_char` is not part of this feature.
  * Support for `c"..."` literals does not prevent `c'.'` literals from being added in the future.
* C string literals should not be blocked on making `&CStr` a thin pointer.
  * It's possible to declare constant expressions of type `&'static CStr` in stable Rust (as of v1.59), so C string literals are not adding additional coupling on the internal representation of `CStr`.
* The unstable `concat_bytes!` macro should not accept `c"..."` literals.
  * C strings have two equally valid `&[u8]` representations (with or without terminal `NUL`), so allowing them to be used in `concat_bytes!` would be ambiguous.
* Adding a type to represent C strings containing valid UTF-8 is not part of this feature.
  * Support for a hypothetical `&Utf8CStr` may be explored in the future, should such a type be added to Rust.

compiler/rustc_ast_passes/src/feature_gate.rs

@@ -515,7 +515,6 @@ pub fn check_crate(krate: &ast::Crate, sess: &Session, features: &Features) {
             }
         };
     }
-    gate_all!(c_str_literals, "`c\"..\"` literals are experimental");
     gate_all!(
         if_let_guard,
         "`if let` guards are experimental",

compiler/rustc_builtin_macros/src/concat_bytes.rs

@@ -19,8 +19,8 @@ fn invalid_type_err(
     let snippet = cx.sess.source_map().span_to_snippet(span).ok();
     match ast::LitKind::from_token_lit(token_lit) {
         Ok(ast::LitKind::CStr(_, _)) => {
-            // FIXME(c_str_literals): should concatenation of C string literals
+            // Avoid ambiguity in handling of terminal `NUL` by refusing to
-            // include the null bytes in the end?
+            // concatenate C string literals as bytes.
             cx.emit_err(errors::ConcatCStrLit { span: span });
         }
         Ok(ast::LitKind::Char(_)) => {

compiler/rustc_feature/src/accepted.rs

@@ -77,6 +77,8 @@ declare_features! (
     (accepted, bindings_after_at, "1.56.0", Some(65490), None),
     /// Allows empty structs and enum variants with braces.
     (accepted, braced_empty_structs, "1.8.0", Some(29720), None),
+    /// Allows `c"foo"` literals.
+    (accepted, c_str_literals, "CURRENT_RUSTC_VERSION", Some(105723), None),
     /// Allows `#[cfg_attr(predicate, multiple, attributes, here)]`.
     (accepted, cfg_attr_multi, "1.33.0", Some(54881), None),
     /// Allows the use of `#[cfg(doctest)]`, set when rustdoc is collecting doctests.

compiler/rustc_feature/src/unstable.rs

@@ -354,8 +354,6 @@ declare_features! (
     (unstable, async_fn_track_caller, "1.73.0", Some(110011), None),
     /// Allows builtin # foo() syntax
     (unstable, builtin_syntax, "1.71.0", Some(110680), None),
-    /// Allows `c"foo"` literals.
-    (unstable, c_str_literals, "1.71.0", Some(105723), None),
     /// Treat `extern "C"` function as nounwind.
     (unstable, c_unwind, "1.52.0", Some(74990), None),
     /// Allows using C-variadics.

compiler/rustc_parse/src/lexer/mod.rs

@@ -223,9 +223,6 @@ impl<'a> StringReader<'a> {
                 rustc_lexer::TokenKind::Literal { kind, suffix_start } => {
                     let suffix_start = start + BytePos(suffix_start);
                     let (kind, symbol) = self.cook_lexer_literal(start, suffix_start, kind);
-                    if let token::LitKind::CStr | token::LitKind::CStrRaw(_) = kind {
-                        self.sess.gated_spans.gate(sym::c_str_literals, self.mk_sp(start, self.pos));
-                    }
                     let suffix = if suffix_start < self.pos {
                         let string = self.str_from(suffix_start);
                         if string == "_" {

src/tools/clippy/tests/ui/needless_raw_string.fixed

@@ -1,6 +1,5 @@
 #![allow(clippy::needless_raw_string_hashes, clippy::no_effect, unused)]
 #![warn(clippy::needless_raw_strings)]
-#![feature(c_str_literals)]
 
 fn main() {
     "aaa";

src/tools/clippy/tests/ui/needless_raw_string.rs

@@ -1,6 +1,5 @@
 #![allow(clippy::needless_raw_string_hashes, clippy::no_effect, unused)]
 #![warn(clippy::needless_raw_strings)]
-#![feature(c_str_literals)]
 
 fn main() {
     r#"aaa"#;

src/tools/clippy/tests/ui/needless_raw_string.stderr

@@ -1,5 +1,5 @@
 error: unnecessary raw string literal
-  --> $DIR/needless_raw_string.rs:6:5
+  --> $DIR/needless_raw_string.rs:5:5
    |
 LL |     r#"aaa"#;
    |     ^^^^^^^^
@@ -13,7 +13,7 @@ LL +     "aaa";
    |
 
 error: unnecessary raw string literal
-  --> $DIR/needless_raw_string.rs:9:5
+  --> $DIR/needless_raw_string.rs:8:5
    |
 LL |     br#"aaa"#;
    |     ^^^^^^^^^
@@ -25,7 +25,7 @@ LL +     b"aaa";
    |
 
 error: unnecessary raw string literal
-  --> $DIR/needless_raw_string.rs:12:5
+  --> $DIR/needless_raw_string.rs:11:5
    |
 LL |     cr#"aaa"#;
    |     ^^^^^^^^^
@@ -37,7 +37,7 @@ LL +     c"aaa";
    |
 
 error: unnecessary raw string literal
-  --> $DIR/needless_raw_string.rs:16:5
+  --> $DIR/needless_raw_string.rs:15:5
    |
 LL | /     r#"
 LL | |         a
@@ -56,7 +56,7 @@ LL ~     ";
    |
 
 error: unnecessary raw string literal
-  --> $DIR/needless_raw_string.rs:22:5
+  --> $DIR/needless_raw_string.rs:21:5
    |
 LL |     r"no hashes";
    |     ^^^^^^^^^^^^
@@ -68,7 +68,7 @@ LL +     "no hashes";
    |
 
 error: unnecessary raw string literal
-  --> $DIR/needless_raw_string.rs:23:5
+  --> $DIR/needless_raw_string.rs:22:5
    |
 LL |     br"no hashes";
    |     ^^^^^^^^^^^^^
@@ -80,7 +80,7 @@ LL +     b"no hashes";
    |
 
 error: unnecessary raw string literal
-  --> $DIR/needless_raw_string.rs:24:5
+  --> $DIR/needless_raw_string.rs:23:5
    |
 LL |     cr"no hashes";
    |     ^^^^^^^^^^^^^

src/tools/clippy/tests/ui/needless_raw_string_hashes.fixed

@@ -1,6 +1,5 @@
 #![allow(clippy::no_effect, unused)]
 #![warn(clippy::needless_raw_string_hashes)]
-#![feature(c_str_literals)]
 
 fn main() {
     r"\aaa";

src/tools/clippy/tests/ui/needless_raw_string_hashes.rs

@@ -1,6 +1,5 @@
 #![allow(clippy::no_effect, unused)]
 #![warn(clippy::needless_raw_string_hashes)]
-#![feature(c_str_literals)]
 
 fn main() {
     r#"\aaa"#;

src/tools/clippy/tests/ui/needless_raw_string_hashes.stderr

@@ -1,5 +1,5 @@
 error: unnecessary hashes around raw string literal
-  --> $DIR/needless_raw_string_hashes.rs:6:5
+  --> $DIR/needless_raw_string_hashes.rs:5:5
    |
 LL |     r#"\aaa"#;
    |     ^^^^^^^^^
@@ -13,7 +13,7 @@ LL +     r"\aaa";
    |
 
 error: unnecessary hashes around raw string literal
-  --> $DIR/needless_raw_string_hashes.rs:7:5
+  --> $DIR/needless_raw_string_hashes.rs:6:5
    |
 LL |     r##"Hello "world"!"##;
    |     ^^^^^^^^^^^^^^^^^^^^^
@@ -25,7 +25,7 @@ LL +     r#"Hello "world"!"#;
    |
 
 error: unnecessary hashes around raw string literal
-  --> $DIR/needless_raw_string_hashes.rs:8:5
+  --> $DIR/needless_raw_string_hashes.rs:7:5
    |
 LL |     r######" "### "## "# "######;
    |     ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
@@ -37,7 +37,7 @@ LL +     r####" "### "## "# "####;
    |
 
 error: unnecessary hashes around raw string literal
-  --> $DIR/needless_raw_string_hashes.rs:9:5
+  --> $DIR/needless_raw_string_hashes.rs:8:5
    |
 LL |     r######" "aa" "# "## "######;
    |     ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
@@ -49,7 +49,7 @@ LL +     r###" "aa" "# "## "###;
    |
 
 error: unnecessary hashes around raw string literal
-  --> $DIR/needless_raw_string_hashes.rs:10:5
+  --> $DIR/needless_raw_string_hashes.rs:9:5
    |
 LL |     br#"\aaa"#;
    |     ^^^^^^^^^^
@@ -61,7 +61,7 @@ LL +     br"\aaa";
    |
 
 error: unnecessary hashes around raw string literal
-  --> $DIR/needless_raw_string_hashes.rs:11:5
+  --> $DIR/needless_raw_string_hashes.rs:10:5
    |
 LL |     br##"Hello "world"!"##;
    |     ^^^^^^^^^^^^^^^^^^^^^^
@@ -73,7 +73,7 @@ LL +     br#"Hello "world"!"#;
    |
 
 error: unnecessary hashes around raw string literal
-  --> $DIR/needless_raw_string_hashes.rs:12:5
+  --> $DIR/needless_raw_string_hashes.rs:11:5
    |
 LL |     br######" "### "## "# "######;
    |     ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
@@ -85,7 +85,7 @@ LL +     br####" "### "## "# "####;
    |
 
 error: unnecessary hashes around raw string literal
-  --> $DIR/needless_raw_string_hashes.rs:13:5
+  --> $DIR/needless_raw_string_hashes.rs:12:5
    |
 LL |     br######" "aa" "# "## "######;
    |     ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
@@ -97,7 +97,7 @@ LL +     br###" "aa" "# "## "###;
    |
 
 error: unnecessary hashes around raw string literal
-  --> $DIR/needless_raw_string_hashes.rs:14:5
+  --> $DIR/needless_raw_string_hashes.rs:13:5
    |
 LL |     cr#"\aaa"#;
    |     ^^^^^^^^^^
@@ -109,7 +109,7 @@ LL +     cr"\aaa";
    |
 
 error: unnecessary hashes around raw string literal
-  --> $DIR/needless_raw_string_hashes.rs:15:5
+  --> $DIR/needless_raw_string_hashes.rs:14:5
    |
 LL |     cr##"Hello "world"!"##;
    |     ^^^^^^^^^^^^^^^^^^^^^^
@@ -121,7 +121,7 @@ LL +     cr#"Hello "world"!"#;
    |
 
 error: unnecessary hashes around raw string literal
-  --> $DIR/needless_raw_string_hashes.rs:16:5
+  --> $DIR/needless_raw_string_hashes.rs:15:5
    |
 LL |     cr######" "### "## "# "######;
    |     ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
@@ -133,7 +133,7 @@ LL +     cr####" "### "## "# "####;
    |
 
 error: unnecessary hashes around raw string literal
-  --> $DIR/needless_raw_string_hashes.rs:17:5
+  --> $DIR/needless_raw_string_hashes.rs:16:5
    |
 LL |     cr######" "aa" "# "## "######;
    |     ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
@@ -145,7 +145,7 @@ LL +     cr###" "aa" "# "## "###;
    |
 
 error: unnecessary hashes around raw string literal
-  --> $DIR/needless_raw_string_hashes.rs:19:5
+  --> $DIR/needless_raw_string_hashes.rs:18:5
    |
 LL | /     r#"
 LL | |         \a
@@ -164,7 +164,7 @@ LL ~     ";
    |
 
 error: unnecessary hashes around raw string literal
-  --> $DIR/needless_raw_string_hashes.rs:25:5
+  --> $DIR/needless_raw_string_hashes.rs:24:5
    |
 LL |     r###"rust"###;
    |     ^^^^^^^^^^^^^
@@ -176,7 +176,7 @@ LL +     r"rust";
    |
 
 error: unnecessary hashes around raw string literal
-  --> $DIR/needless_raw_string_hashes.rs:26:5
+  --> $DIR/needless_raw_string_hashes.rs:25:5
    |
 LL |     r#"hello world"#;
    |     ^^^^^^^^^^^^^^^^

tests/ui/proc-macro/literal-to-string.rs

@@ -1,6 +1,5 @@
 // check-pass
 // edition: 2021
-#![feature(c_str_literals)]
 
 // aux-build: print-tokens.rs
 extern crate print_tokens;

tests/ui/proc-macro/literal-to-string.stdout

@@ -3,91 +3,91 @@ TokenStream [
         kind: Integer,
         symbol: "1",
         suffix: None,
-        span: #0 bytes(172..173),
+        span: #0 bytes(144..145),
     },
     Literal {
         kind: Integer,
         symbol: "17",
         suffix: Some("u8"),
-        span: #0 bytes(182..186),
+        span: #0 bytes(154..158),
     },
     Literal {
         kind: Float,
         symbol: "42.",
         suffix: None,
-        span: #0 bytes(195..198),
+        span: #0 bytes(167..170),
     },
     Literal {
         kind: Float,
         symbol: "3.14",
         suffix: Some("f32"),
-        span: #0 bytes(207..214),
+        span: #0 bytes(179..186),
     },
     Literal {
         kind: Byte,
         symbol: "a",
         suffix: None,
-        span: #0 bytes(223..227),
+        span: #0 bytes(195..199),
     },
     Literal {
         kind: Byte,
         symbol: "\xFF",
         suffix: None,
-        span: #0 bytes(236..243),
+        span: #0 bytes(208..215),
     },
     Literal {
         kind: Char,
         symbol: "c",
         suffix: None,
-        span: #0 bytes(252..255),
+        span: #0 bytes(224..227),
     },
     Literal {
         kind: Char,
         symbol: "\x32",
         suffix: None,
-        span: #0 bytes(264..270),
+        span: #0 bytes(236..242),
     },
     Literal {
         kind: Str,
         symbol: "\\"str\\"",
         suffix: None,
-        span: #0 bytes(279..288),
+        span: #0 bytes(251..260),
     },
     Literal {
         kind: StrRaw(1),
         symbol: "\"raw\" str",
         suffix: None,
-        span: #0 bytes(297..311),
+        span: #0 bytes(269..283),
     },
     Literal {
         kind: StrRaw(3),
         symbol: "very ##\"raw\"## str",
         suffix: None,
-        span: #0 bytes(320..347),
+        span: #0 bytes(292..319),
     },
     Literal {
         kind: ByteStr,
         symbol: "\\"byte\\" str",
         suffix: None,
-        span: #0 bytes(356..371),
+        span: #0 bytes(328..343),
     },
     Literal {
         kind: ByteStrRaw(1),
         symbol: "\"raw\" \"byte\" str",
         suffix: None,
-        span: #0 bytes(380..402),
+        span: #0 bytes(352..374),
     },
     Literal {
         kind: CStr,
         symbol: "\\"c\\" str",
         suffix: None,
-        span: #0 bytes(411..423),
+        span: #0 bytes(383..395),
     },
     Literal {
         kind: CStrRaw(1),
         symbol: "\"raw\" \"c\" str",
         suffix: None,
-        span: #0 bytes(432..451),
+        span: #0 bytes(404..423),
     },
 ]
 1

tests/ui/rfcs/rfc-3348-c-string-literals/basic.rs

@@ -1,8 +1,6 @@
 // run-pass
 // edition: 2021
 
-#![feature(c_str_literals)]
-
 fn main() {
     assert_eq!(b"test\0", c"test".to_bytes_with_nul());
 }

tests/ui/rfcs/rfc-3348-c-string-literals/gate.rs

@@ -1,15 +0,0 @@
-// gate-test-c_str_literals
-// known-bug: #113333
-// edition: 2021
-
-macro_rules! m {
-    ($t:tt) => {}
-}
-
-fn main() {
-    c"foo";
-    // FIXME(c_str_literals): This should be ``c".."` literals are experimental`
-
-    m!(c"test");
-    // FIXME(c_str_literals): This should be ``c".."` literals are experimental`
-}

tests/ui/rfcs/rfc-3348-c-string-literals/gate.stderr

@@ -1,21 +0,0 @@
-error[E0658]: `c".."` literals are experimental
-  --> $DIR/gate.rs:10:5
-   |
-LL |     c"foo";
-   |     ^^^^^^
-   |
-   = note: see issue #105723 <https://github.com/rust-lang/rust/issues/105723> for more information
-   = help: add `#![feature(c_str_literals)]` to the crate attributes to enable
-
-error[E0658]: `c".."` literals are experimental
-  --> $DIR/gate.rs:13:8
-   |
-LL |     m!(c"test");
-   |        ^^^^^^^
-   |
-   = note: see issue #105723 <https://github.com/rust-lang/rust/issues/105723> for more information
-   = help: add `#![feature(c_str_literals)]` to the crate attributes to enable
-
-error: aborting due to 2 previous errors
-
-For more information about this error, try `rustc --explain E0658`.

tests/ui/rfcs/rfc-3348-c-string-literals/non-ascii.rs

@@ -1,8 +1,6 @@
 // run-pass
 // edition: 2021
 
-#![feature(c_str_literals)]
-
 fn main() {
     assert_eq!(
         c"\xEF\x80🦀\u{1F980}".to_bytes_with_nul(),