Auto merge of rust-lang#83799 - crlf0710:stablize_non_ascii_idents, r=Manishearth

Stablize `non-ascii-idents`

This is the stablization PR for RFC 2457. Currently this is waiting on fcp in [tracking issue](rust-lang#55467).

r? `@Manishearth`

Author: bors

compiler/rustc_ast_passes/src/feature_gate.rs

@@ -8,7 +8,7 @@ use rustc_feature::{Features, GateIssue};
 use rustc_session::parse::{feature_err, feature_err_issue};
 use rustc_session::Session;
 use rustc_span::source_map::Spanned;
-use rustc_span::symbol::{sym, Symbol};
+use rustc_span::symbol::sym;
 use rustc_span::Span;
 
 use tracing::debug;
@@ -328,17 +328,6 @@ impl<'a> Visitor<'a> for PostExpansionVisitor<'a> {
         }
     }
 
-    fn visit_name(&mut self, sp: Span, name: Symbol) {
-        if !name.as_str().is_ascii() {
-            gate_feature_post!(
-                &self,
-                non_ascii_idents,
-                self.sess.parse_sess.source_map().guess_head_span(sp),
-                "non-ascii idents are not fully supported"
-            );
-        }
-    }
-
     fn visit_item(&mut self, i: &'a ast::Item) {
         match i.kind {
             ast::ItemKind::ForeignMod(ref foreign_module) => {

compiler/rustc_error_codes/src/error_codes/E0554.md

@@ -4,8 +4,8 @@ beta compilers will not comply.
 Erroneous code example:
 
 ```ignore (depends on release channel)
-#![feature(non_ascii_idents)] // error: `#![feature]` may not be used on the
-                              //        stable release channel
+#![feature(lang_items)] // error: `#![feature]` may not be used on the
+                        //        stable release channel
 ```
 
 If you need the feature, make sure to use a nightly release of the compiler

compiler/rustc_error_codes/src/error_codes/E0754.md

@@ -3,7 +3,6 @@ A non-ASCII identifier was used in an invalid context.
 Erroneous code examples:
 
 ```compile_fail,E0754
-# #![feature(non_ascii_idents)]
 
 mod řųśť; // error!
 
@@ -17,8 +16,6 @@ Non-ASCII can be used as module names if it is inlined or if a `#[path]`
 attribute is specified. For example:
 
 ```
-# #![feature(non_ascii_idents)]
-
 mod řųśť { // ok!
     const IS_GREAT: bool = true;
 }

compiler/rustc_feature/src/accepted.rs

@@ -279,6 +279,8 @@ declare_features! (
     (accepted, unsafe_block_in_unsafe_fn, "1.52.0", Some(71668), None),
     /// Allows the use of or-patterns (e.g., `0 | 1`).
     (accepted, or_patterns, "1.53.0", Some(54883), None),
+    /// Allows defining identifiers beyond ASCII.
+    (accepted, non_ascii_idents, "1.53.0", Some(55467), None),
 
     // -------------------------------------------------------------------------
     // feature-group-end: accepted features

compiler/rustc_feature/src/active.rs

@@ -255,9 +255,6 @@ declare_features! (
     // feature-group-start: actual feature gates
     // -------------------------------------------------------------------------
 
-    /// Allows defining identifiers beyond ASCII.
-    (active, non_ascii_idents, "1.0.0", Some(55467), None),
-
     /// Allows using `#[plugin_registrar]` on functions.
     (active, plugin_registrar, "1.0.0", Some(29597), None),
 

compiler/rustc_lint/src/non_ascii_idents.rs

@@ -10,7 +10,6 @@ declare_lint! {
     ///
     /// ```rust,compile_fail
     /// # #![allow(unused)]
-    /// #![feature(non_ascii_idents)]
     /// #![deny(non_ascii_idents)]
     /// fn main() {
     ///     let föö = 1;
@@ -21,14 +20,11 @@ declare_lint! {
     ///
     /// ### Explanation
     ///
-    /// Currently on stable Rust, identifiers must contain ASCII characters.
-    /// The [`non_ascii_idents`] nightly-only feature allows identifiers to
-    /// contain non-ASCII characters. This lint allows projects that wish to
-    /// retain the limit of only using ASCII characters to switch this lint to
-    /// "forbid" (for example to ease collaboration or for security reasons).
+    /// This lint allows projects that wish to retain the limit of only using
+    /// ASCII characters to switch this lint to "forbid" (for example to ease
+    /// collaboration or for security reasons).
     /// See [RFC 2457] for more details.
     ///
-    /// [`non_ascii_idents`]: https://doc.rust-lang.org/nightly/unstable-book/language-features/non-ascii-idents.html
     /// [RFC 2457]: https://github.com/rust-lang/rfcs/blob/master/text/2457-non-ascii-idents.md
     pub NON_ASCII_IDENTS,
     Allow,
@@ -44,18 +40,15 @@ declare_lint! {
     ///
     /// ```rust
     /// # #![allow(unused)]
-    /// #![feature(non_ascii_idents)]
     /// const µ: f64 = 0.000001;
     /// ```
     ///
     /// {{produces}}
     ///
     /// ### Explanation
     ///
-    /// With the [`non_ascii_idents`] nightly-only feature enabled,
-    /// identifiers are allowed to use non-ASCII characters. This lint warns
-    /// about using characters which are not commonly used, and may cause
-    /// visual confusion.
+    /// This lint warns about using characters which are not commonly used, and may
+    /// cause visual confusion.
     ///
     /// This lint is triggered by identifiers that contain a codepoint that is
     /// not part of the set of "Allowed" codepoints as described by [Unicode®
@@ -66,7 +59,6 @@ declare_lint! {
     /// that if you "forbid" this lint that existing code may fail in the
     /// future.
     ///
-    /// [`non_ascii_idents`]: https://doc.rust-lang.org/nightly/unstable-book/language-features/non-ascii-idents.html
     /// [TR39Allowed]: https://www.unicode.org/reports/tr39/#General_Security_Profile
     pub UNCOMMON_CODEPOINTS,
     Warn,
@@ -81,8 +73,6 @@ declare_lint! {
     /// ### Example
     ///
     /// ```rust
-    /// #![feature(non_ascii_idents)]
-    ///
     /// // Latin Capital Letter E With Caron
     /// pub const Ě: i32 = 1;
     /// // Latin Capital Letter E With Breve
@@ -93,10 +83,8 @@ declare_lint! {
     ///
     /// ### Explanation
     ///
-    /// With the [`non_ascii_idents`] nightly-only feature enabled,
-    /// identifiers are allowed to use non-ASCII characters. This lint warns
-    /// when different identifiers may appear visually similar, which can
-    /// cause confusion.
+    /// This lint warns when different identifiers may appear visually similar,
+    /// which can cause confusion.
     ///
     /// The confusable detection algorithm is based on [Unicode® Technical
     /// Standard #39 Unicode Security Mechanisms Section 4 Confusable
@@ -110,7 +98,6 @@ declare_lint! {
     /// Beware that if you "forbid" this lint that existing code may fail in
     /// the future.
     ///
-    /// [`non_ascii_idents`]: https://doc.rust-lang.org/nightly/unstable-book/language-features/non-ascii-idents.html
     /// [TR39Confusable]: https://www.unicode.org/reports/tr39/#Confusable_Detection
     pub CONFUSABLE_IDENTS,
     Warn,
@@ -127,8 +114,6 @@ declare_lint! {
     /// ### Example
     ///
     /// ```rust
-    /// #![feature(non_ascii_idents)]
-    ///
     /// // The Japanese katakana character エ can be confused with the Han character 工.
     /// const エ: &'static str = "アイウ";
     /// ```
@@ -137,10 +122,8 @@ declare_lint! {
     ///
     /// ### Explanation
     ///
-    /// With the [`non_ascii_idents`] nightly-only feature enabled,
-    /// identifiers are allowed to use non-ASCII characters. This lint warns
-    /// when characters between different scripts may appear visually similar,
-    /// which can cause confusion.
+    /// This lint warns when characters between different scripts may appear
+    /// visually similar, which can cause confusion.
     ///
     /// If the crate contains other identifiers in the same script that have
     /// non-confusable characters, then this lint will *not* be issued. For
@@ -152,8 +135,6 @@ declare_lint! {
     /// Note that the set of confusable characters may change over time.
     /// Beware that if you "forbid" this lint that existing code may fail in
     /// the future.
-    ///
-    /// [`non_ascii_idents`]: https://doc.rust-lang.org/nightly/unstable-book/language-features/non-ascii-idents.html
     pub MIXED_SCRIPT_CONFUSABLES,
     Warn,
     "detects Unicode scripts whose mixed script confusables codepoints are solely used",

src/doc/unstable-book/src/language-features/non-ascii-idents.md

@@ -2,8 +2,6 @@
 
 // compile-flags:-g
 
-#![feature(non_ascii_idents)]
-
 // This test checks whether debuginfo generation can handle multi-byte UTF-8
 // characters at the end of a block. There's no need to do anything in the
 // debugger -- just make sure that the compiler doesn't crash.

src/test/debuginfo/multi-byte-chars.rs

@@ -1,5 +1,3 @@
-#![feature(non_ascii_idents)]
-
 fn main() {
     let _ = ("a̐éö̲", 0u7); //~ ERROR invalid width
     let _ = ("아あ", 1i42); //~ ERROR invalid width

src/test/ui/codemap_tests/unicode_2.rs

@@ -1,21 +1,21 @@
 error: invalid width `7` for integer literal
-  --> $DIR/unicode_2.rs:4:25
+  --> $DIR/unicode_2.rs:2:25
    |
 LL |     let _ = ("a̐éö̲", 0u7);
    |                     ^^^
    |
    = help: valid widths are 8, 16, 32, 64 and 128
 
 error: invalid width `42` for integer literal
-  --> $DIR/unicode_2.rs:5:20
+  --> $DIR/unicode_2.rs:3:20
    |
 LL |     let _ = ("아あ", 1i42);
    |                      ^^^^
    |
    = help: valid widths are 8, 16, 32, 64 and 128
 
 error[E0425]: cannot find value `a̐é` in this scope
-  --> $DIR/unicode_2.rs:6:13
+  --> $DIR/unicode_2.rs:4:13
    |
 LL |     let _ = a̐é;
    |             ^^ not found in this scope