Lex lifetimes using emoji and emit appropriate error

Lex and parse emoji in lifetimes, and disallow them in the parser with a hard error. Allow emoji to start a lifetime name even if they are not XID_Start.

```
error: lifetimes cannot contain emoji
  --> $DIR/emoji-in-lifetime.rs:1:22
   |
LL | fn bad_lifetime_name<'🐛🐛🐛family👨👩👧👦>(
   |                      ^^^^^^^^^^^^^^^^^^^^^
```

Author: estebank

compiler/rustc_lexer/src/lib.rs

@@ -141,6 +141,7 @@ pub enum TokenKind {
     /// A lifetime, e.g. `'a`.
     Lifetime {
         starts_with_number: bool,
+        has_emoji: bool,
     },
 
     /// `;`
@@ -975,14 +976,20 @@ impl<'a> Cursor<'a> {
     fn lifetime_or_char(&mut self) -> TokenKind {
         debug_assert!(self.prev() == '\'');
 
+        let mut has_emoji = false;
         let can_be_a_lifetime = if self.second() == '\'' {
             // It's surely not a lifetime.
             false
         } else {
             // If the first symbol is valid for identifier, it can be a lifetime.
             // Also check if it's a number for a better error reporting (so '0 will
             // be reported as invalid lifetime and not as unterminated char literal).
-            is_id_start(self.first()) || self.first().is_ascii_digit()
+            let c = self.first();
+            let is_emoji = !c.is_ascii() && c.is_emoji_char();
+            if is_emoji {
+                has_emoji = true;
+            }
+            is_id_start(c) || c.is_ascii_digit() || is_emoji
         };
 
         if !can_be_a_lifetime {
@@ -1012,7 +1019,13 @@ impl<'a> Cursor<'a> {
         // First symbol can be a number (which isn't a valid identifier start),
         // so skip it without any checks.
         self.bump();
-        self.eat_while(is_id_continue);
+        self.eat_while(|c| {
+            let is_emoji = !c.is_ascii() && c.is_emoji_char();
+            if is_emoji {
+                has_emoji = true;
+            }
+            is_id_continue(c) || is_emoji
+        });
 
         match self.first() {
             // Check if after skipping literal contents we've met a closing
@@ -1024,7 +1037,7 @@ impl<'a> Cursor<'a> {
                 Literal { kind, suffix_start: self.pos_within_token() }
             }
             '#' if !starts_with_number => UnknownPrefixLifetime,
-            _ => Lifetime { starts_with_number },
+            _ => Lifetime { starts_with_number, has_emoji },
         }
     }
 

compiler/rustc_parse/src/lexer/mod.rs

@@ -316,19 +316,22 @@ impl<'psess, 'src> Lexer<'psess, 'src> {
                     self.lint_literal_unicode_text_flow(symbol, kind, self.mk_sp(start, self.pos), "literal");
                     token::Literal(token::Lit { kind, symbol, suffix })
                 }
-                rustc_lexer::TokenKind::Lifetime { starts_with_number } => {
+                rustc_lexer::TokenKind::Lifetime { starts_with_number, has_emoji } => {
                     // Include the leading `'` in the real identifier, for macro
                     // expansion purposes. See #12512 for the gory details of why
                     // this is necessary.
                     let lifetime_name = nfc_normalize(self.str_from(start));
                     self.last_lifetime = Some(self.mk_sp(start, start + BytePos(1)));
+                    let span = self.mk_sp(start, self.pos);
                     if starts_with_number {
-                        let span = self.mk_sp(start, self.pos);
                         self.dcx()
                             .struct_err("lifetimes cannot start with a number")
                             .with_span(span)
                             .stash(span, StashKey::LifetimeIsChar);
                     }
+                    if has_emoji {
+                        self.dcx().struct_span_err(span, "lifetimes cannot contain emoji").emit();
+                    }
                     token::Lifetime(lifetime_name, IdentIsRaw::No)
                 }
                 rustc_lexer::TokenKind::RawLifetime => {

tests/ui/lexer/emoji-in-lifetime.rs

@@ -0,0 +1,9 @@
+// #141081
+fn bad_lifetime_name<'🐛🐛🐛family👨‍👩‍👧‍👦>(_: &'🐛🐛🐛family👨‍👩‍👧‍👦 ()) {}
+//~^ ERROR: lifetimes cannot contain emoji
+//~| ERROR: lifetimes cannot contain emoji
+fn main() {
+    '🐛: { //~ ERROR: lifetimes cannot contain emoji
+        todo!();  
+    };
+}

tests/ui/lexer/emoji-in-lifetime.stderr

@@ -0,0 +1,20 @@
+error: lifetimes cannot contain emoji
+  --> $DIR/emoji-in-lifetime.rs:2:22
+   |
+LL | fn bad_lifetime_name<'🐛🐛🐛family👨👩👧👦>(_: &'🐛🐛🐛family👨👩👧👦 ()) {}
+   |                      ^^^^^^^^^^^^^^^^^^^^^
+
+error: lifetimes cannot contain emoji
+  --> $DIR/emoji-in-lifetime.rs:2:45
+   |
+LL | fn bad_lifetime_name<'🐛🐛🐛family👨👩👧👦>(_: &'🐛🐛🐛family👨👩👧👦 ()) {}
+   |                                                 ^^^^^^^^^^^^^^^^^^^^^
+
+error: lifetimes cannot contain emoji
+  --> $DIR/emoji-in-lifetime.rs:6:5
+   |
+LL |     '🐛: {
+   |     ^^^
+
+error: aborting due to 3 previous errors
+