Rollup merge of #151171 - issue-141436, r=davidtwco

Do not recover from `Trait()` if generic list is unterminated

If we encounter `fn foo<T: Trait()`, the recovery logic would it as if `Trait` was intended to use the Fn-like trait syntax, but if we don't know for certain that we've parsed a full trait bound (`fn foo<T: Trait()>`), we bail from the recovery as more likely there could have been a missing closing `>` and the `(` corresponds to the start of the fn parameter list.

Fix rust-lang/rust#141436.

compiler/rustc_ast/src/token.rs

@@ -625,12 +625,12 @@ impl TokenKind {
 }
 
 impl Token {
-    pub fn new(kind: TokenKind, span: Span) -> Self {
+    pub const fn new(kind: TokenKind, span: Span) -> Self {
         Token { kind, span }
     }
 
     /// Some token that will be thrown away later.
-    pub fn dummy() -> Self {
+    pub const fn dummy() -> Self {
         Token::new(TokenKind::Question, DUMMY_SP)
     }
 

compiler/rustc_parse/src/parser/generics.rs

@@ -204,9 +204,11 @@ impl<'a> Parser<'a> {
     pub(super) fn parse_generic_params(&mut self) -> PResult<'a, ThinVec<ast::GenericParam>> {
         let mut params = ThinVec::new();
         let mut done = false;
+        let prev = self.parsing_generics;
+        self.parsing_generics = true;
         while !done {
             let attrs = self.parse_outer_attributes()?;
-            let param = self.collect_tokens(None, attrs, ForceCollect::No, |this, attrs| {
+            let param = match self.collect_tokens(None, attrs, ForceCollect::No, |this, attrs| {
                 if this.eat_keyword_noexpect(kw::SelfUpper) {
                     // `Self` as a generic param is invalid. Here we emit the diagnostic and continue parsing
                     // as if `Self` never existed.
@@ -288,7 +290,13 @@ impl<'a> Parser<'a> {
                 }
                 // We just ate the comma, so no need to capture the trailing token.
                 Ok((param, Trailing::No, UsePreAttrPos::No))
-            })?;
+            }) {
+                Ok(param) => param,
+                Err(err) => {
+                    self.parsing_generics = prev;
+                    return Err(err);
+                }
+            };
 
             if let Some(param) = param {
                 params.push(param);
@@ -296,6 +304,7 @@ impl<'a> Parser<'a> {
                 break;
             }
         }
+        self.parsing_generics = prev;
         Ok(params)
     }
 

compiler/rustc_parse/src/parser/mod.rs

@@ -175,17 +175,17 @@ pub enum Recovery {
 pub struct Parser<'a> {
     pub psess: &'a ParseSess,
     /// The current token.
-    pub token: Token,
+    pub token: Token = Token::dummy(),
     /// The spacing for the current token.
-    token_spacing: Spacing,
+    token_spacing: Spacing = Spacing::Alone,
     /// The previous token.
-    pub prev_token: Token,
-    pub capture_cfg: bool,
-    restrictions: Restrictions,
-    expected_token_types: TokenTypeSet,
+    pub prev_token: Token = Token::dummy(),
+    pub capture_cfg: bool = false,
+    restrictions: Restrictions = Restrictions::empty(),
+    expected_token_types: TokenTypeSet = TokenTypeSet::new(),
     token_cursor: TokenCursor,
     // The number of calls to `bump`, i.e. the position in the token stream.
-    num_bump_calls: u32,
+    num_bump_calls: u32 = 0,
     // During parsing we may sometimes need to "unglue" a glued token into two
     // or three component tokens (e.g. `>>` into `>` and `>`, or `>>=` into `>`
     // and `>` and `=`), so the parser can consume them one at a time. This
@@ -204,25 +204,27 @@ pub struct Parser<'a> {
     //
     // This value is always 0, 1, or 2. It can only reach 2 when splitting
     // `>>=` or `<<=`.
-    break_last_token: u32,
+    break_last_token: u32 = 0,
     /// This field is used to keep track of how many left angle brackets we have seen. This is
     /// required in order to detect extra leading left angle brackets (`<` characters) and error
     /// appropriately.
     ///
     /// See the comments in the `parse_path_segment` function for more details.
-    unmatched_angle_bracket_count: u16,
-    angle_bracket_nesting: u16,
+    unmatched_angle_bracket_count: u16 = 0,
+    angle_bracket_nesting: u16 = 0,
+    /// Keep track of when we're within `<...>` for proper error recovery.
+    parsing_generics: bool = false,
 
-    last_unexpected_token_span: Option<Span>,
+    last_unexpected_token_span: Option<Span> = None,
     /// If present, this `Parser` is not parsing Rust code but rather a macro call.
     subparser_name: Option<&'static str>,
     capture_state: CaptureState,
     /// This allows us to recover when the user forget to add braces around
     /// multiple statements in the closure body.
-    current_closure: Option<ClosureSpans>,
+    current_closure: Option<ClosureSpans> = None,
     /// Whether the parser is allowed to do recovery.
     /// This is disabled when parsing macro arguments, see #103534
-    recovery: Recovery,
+    recovery: Recovery = Recovery::Allowed,
 }
 
 // This type is used a lot, e.g. it's cloned when matching many declarative macro rules with
@@ -351,18 +353,7 @@ impl<'a> Parser<'a> {
     ) -> Self {
         let mut parser = Parser {
             psess,
-            token: Token::dummy(),
-            token_spacing: Spacing::Alone,
-            prev_token: Token::dummy(),
-            capture_cfg: false,
-            restrictions: Restrictions::empty(),
-            expected_token_types: TokenTypeSet::new(),
             token_cursor: TokenCursor { curr: TokenTreeCursor::new(stream), stack: Vec::new() },
-            num_bump_calls: 0,
-            break_last_token: 0,
-            unmatched_angle_bracket_count: 0,
-            angle_bracket_nesting: 0,
-            last_unexpected_token_span: None,
             subparser_name,
             capture_state: CaptureState {
                 capturing: Capturing::No,
@@ -370,8 +361,7 @@ impl<'a> Parser<'a> {
                 inner_attr_parser_ranges: Default::default(),
                 seen_attrs: IntervalSet::new(u32::MAX as usize),
             },
-            current_closure: None,
-            recovery: Recovery::Allowed,
+            ..
         };
 
         // Make parser point to the first token.

compiler/rustc_parse/src/parser/token_type.rs

@@ -585,7 +585,7 @@ macro_rules! exp {
 pub(super) struct TokenTypeSet(u128);
 
 impl TokenTypeSet {
-    pub(super) fn new() -> TokenTypeSet {
+    pub(super) const fn new() -> TokenTypeSet {
         TokenTypeSet(0)
     }
 

compiler/rustc_parse/src/parser/ty.rs

@@ -1488,14 +1488,44 @@ impl<'a> Parser<'a> {
             return Ok(());
         }
 
+        let snapshot = if self.parsing_generics {
+            // The snapshot is only relevant if we're parsing the generics of an `fn` to avoid
+            // incorrect recovery.
+            Some(self.create_snapshot_for_diagnostic())
+        } else {
+            None
+        };
         // Parse `(T, U) -> R`.
         let inputs_lo = self.token.span;
         let mode =
             FnParseMode { req_name: |_, _| false, context: FnContext::Free, req_body: false };
-        let inputs: ThinVec<_> =
-            self.parse_fn_params(&mode)?.into_iter().map(|input| input.ty).collect();
+        let params = match self.parse_fn_params(&mode) {
+            Ok(params) => params,
+            Err(err) => {
+                if let Some(snapshot) = snapshot {
+                    self.restore_snapshot(snapshot);
+                    err.cancel();
+                    return Ok(());
+                } else {
+                    return Err(err);
+                }
+            }
+        };
+        let inputs: ThinVec<_> = params.into_iter().map(|input| input.ty).collect();
         let inputs_span = inputs_lo.to(self.prev_token.span);
-        let output = self.parse_ret_ty(AllowPlus::No, RecoverQPath::No, RecoverReturnSign::No)?;
+        let output = match self.parse_ret_ty(AllowPlus::No, RecoverQPath::No, RecoverReturnSign::No)
+        {
+            Ok(output) => output,
+            Err(err) => {
+                if let Some(snapshot) = snapshot {
+                    self.restore_snapshot(snapshot);
+                    err.cancel();
+                    return Ok(());
+                } else {
+                    return Err(err);
+                }
+            }
+        };
         let args = ast::ParenthesizedArgs {
             span: fn_path_segment.span().to(self.prev_token.span),
             inputs,
@@ -1503,6 +1533,17 @@ impl<'a> Parser<'a> {
             output,
         }
         .into();
+
+        if let Some(snapshot) = snapshot
+            && ![token::Comma, token::Gt, token::Plus].contains(&self.token.kind)
+        {
+            // We would expect another bound or the end of type params by now. Most likely we've
+            // encountered a `(` *not* representing `Trait()`, but rather the start of the `fn`'s
+            // argument list where the generic param list wasn't properly closed.
+            self.restore_snapshot(snapshot);
+            return Ok(());
+        }
+
         *fn_path_segment = ast::PathSegment {
             ident: fn_path_segment.ident,
             args: Some(args),

tests/ui/parser/missing-closing-generics-bracket.fixed

@@ -0,0 +1,10 @@
+// Issue #141436
+//@ run-rustfix
+#![allow(dead_code)]
+
+trait Trait<'a> {}
+
+fn foo<T: Trait<'static>>() {}
+//~^ ERROR expected one of
+
+fn main() {}

tests/ui/parser/missing-closing-generics-bracket.rs

@@ -0,0 +1,10 @@
+// Issue #141436
+//@ run-rustfix
+#![allow(dead_code)]
+
+trait Trait<'a> {}
+
+fn foo<T: Trait<'static>() {}
+//~^ ERROR expected one of
+
+fn main() {}

tests/ui/parser/missing-closing-generics-bracket.stderr

@@ -0,0 +1,13 @@
+error: expected one of `+`, `,`, `::`, `=`, or `>`, found `(`
+  --> $DIR/missing-closing-generics-bracket.rs:7:25
+   |
+LL | fn foo<T: Trait<'static>() {}
+   |                         ^ expected one of `+`, `,`, `::`, `=`, or `>`
+   |
+help: you might have meant to end the type parameters here
+   |
+LL | fn foo<T: Trait<'static>>() {}
+   |                         +
+
+error: aborting due to 1 previous error
+