Minor structural improvements

compiler/rustc_lexer/src/lib.rs

@@ -25,15 +25,13 @@
 #![deny(unstable_features)]
 // tidy-alphabetical-end
 
-mod cursor;
-
 #[cfg(test)]
 mod tests;
 
+use std::str::Chars;
+
 use LiteralKind::*;
 use TokenKind::*;
-use cursor::EOF_CHAR;
-pub use cursor::{Cursor, FrontmatterAllowed};
 pub use unicode_ident::UNICODE_VERSION;
 use unicode_properties::UnicodeEmoji;
 
@@ -407,7 +405,129 @@ pub fn is_ident(string: &str) -> bool {
     }
 }
 
-impl Cursor<'_> {
+pub enum FrontmatterAllowed {
+    Yes,
+    No,
+}
+
+/// Peekable iterator over a char sequence.
+///
+/// Next characters can be peeked via `first` method,
+/// and position can be shifted forward via `bump` method.
+pub struct Cursor<'a> {
+    len_remaining: usize,
+    /// Iterator over chars. Slightly faster than a &str.
+    chars: Chars<'a>,
+    pub(crate) frontmatter_allowed: FrontmatterAllowed,
+    #[cfg(debug_assertions)]
+    prev: char,
+}
+
+const EOF_CHAR: char = '\0';
+
+impl<'a> Cursor<'a> {
+    pub fn new(input: &'a str, frontmatter_allowed: FrontmatterAllowed) -> Cursor<'a> {
+        Cursor {
+            len_remaining: input.len(),
+            chars: input.chars(),
+            frontmatter_allowed,
+            #[cfg(debug_assertions)]
+            prev: EOF_CHAR,
+        }
+    }
+
+    pub fn as_str(&self) -> &'a str {
+        self.chars.as_str()
+    }
+
+    /// Returns the last eaten symbol (or `'\0'` in release builds).
+    /// (For debug assertions only.)
+    pub(crate) fn prev(&self) -> char {
+        #[cfg(debug_assertions)]
+        {
+            self.prev
+        }
+
+        #[cfg(not(debug_assertions))]
+        {
+            EOF_CHAR
+        }
+    }
+
+    /// Peeks the next symbol from the input stream without consuming it.
+    /// If requested position doesn't exist, `EOF_CHAR` is returned.
+    /// However, getting `EOF_CHAR` doesn't always mean actual end of file,
+    /// it should be checked with `is_eof` method.
+    pub fn first(&self) -> char {
+        // `.next()` optimizes better than `.nth(0)`
+        self.chars.clone().next().unwrap_or(EOF_CHAR)
+    }
+
+    /// Peeks the second symbol from the input stream without consuming it.
+    pub(crate) fn second(&self) -> char {
+        // `.next()` optimizes better than `.nth(1)`
+        let mut iter = self.chars.clone();
+        iter.next();
+        iter.next().unwrap_or(EOF_CHAR)
+    }
+
+    /// Peeks the third symbol from the input stream without consuming it.
+    pub fn third(&self) -> char {
+        // `.next()` optimizes better than `.nth(2)`
+        let mut iter = self.chars.clone();
+        iter.next();
+        iter.next();
+        iter.next().unwrap_or(EOF_CHAR)
+    }
+
+    /// Checks if there is nothing more to consume.
+    pub(crate) fn is_eof(&self) -> bool {
+        self.chars.as_str().is_empty()
+    }
+
+    /// Returns amount of already consumed symbols.
+    pub(crate) fn pos_within_token(&self) -> u32 {
+        (self.len_remaining - self.chars.as_str().len()) as u32
+    }
+
+    /// Resets the number of bytes consumed to 0.
+    pub(crate) fn reset_pos_within_token(&mut self) {
+        self.len_remaining = self.chars.as_str().len();
+    }
+
+    /// Moves to the next character.
+    pub(crate) fn bump(&mut self) -> Option<char> {
+        let c = self.chars.next()?;
+
+        #[cfg(debug_assertions)]
+        {
+            self.prev = c;
+        }
+
+        Some(c)
+    }
+
+    /// Moves to a substring by a number of bytes.
+    pub(crate) fn bump_bytes(&mut self, n: usize) {
+        self.chars = self.as_str()[n..].chars();
+    }
+
+    /// Eats symbols while predicate returns true or until the end of file is reached.
+    pub(crate) fn eat_while(&mut self, mut predicate: impl FnMut(char) -> bool) {
+        // It was tried making optimized version of this for eg. line comments, but
+        // LLVM can inline all of this and compile it down to fast iteration over bytes.
+        while predicate(self.first()) && !self.is_eof() {
+            self.bump();
+        }
+    }
+
+    pub(crate) fn eat_until(&mut self, byte: u8) {
+        self.chars = match memchr::memchr(byte, self.as_str().as_bytes()) {
+            Some(index) => self.as_str()[index..].chars(),
+            None => "".chars(),
+        }
+    }
+
     /// Parses a token from the input string.
     pub fn advance_token(&mut self) -> Token {
         let Some(first_char) = self.bump() else {

compiler/rustc_parse/src/errors.rs

@@ -3,7 +3,7 @@
 use std::borrow::Cow;
 use std::path::PathBuf;
 
-use rustc_ast::token::Token;
+use rustc_ast::token::{self, InvisibleOrigin, MetaVarKind, Token};
 use rustc_ast::util::parser::ExprPrecedence;
 use rustc_ast::{Path, Visibility};
 use rustc_errors::codes::*;
@@ -17,7 +17,6 @@ use rustc_span::edition::{Edition, LATEST_STABLE_EDITION};
 use rustc_span::{Ident, Span, Symbol};
 
 use crate::fluent_generated as fluent;
-use crate::parser::{ForbiddenLetReason, TokenDescription};
 
 #[derive(Diagnostic)]
 #[diag(parse_maybe_report_ambiguous_plus)]
@@ -3703,3 +3702,64 @@ pub(crate) struct StructLiteralWithoutPathLate {
     #[suggestion(applicability = "has-placeholders", code = "/* Type */ ", style = "verbose")]
     pub suggestion_span: Span,
 }
+
+/// Used to forbid `let` expressions in certain syntactic locations.
+#[derive(Clone, Copy, Subdiagnostic)]
+pub(crate) enum ForbiddenLetReason {
+    /// `let` is not valid and the source environment is not important
+    OtherForbidden,
+    /// A let chain with the `||` operator
+    #[note(parse_not_supported_or)]
+    NotSupportedOr(#[primary_span] Span),
+    /// A let chain with invalid parentheses
+    ///
+    /// For example, `let 1 = 1 && (expr && expr)` is allowed
+    /// but `(let 1 = 1 && (let 1 = 1 && (let 1 = 1))) && let a = 1` is not
+    #[note(parse_not_supported_parentheses)]
+    NotSupportedParentheses(#[primary_span] Span),
+}
+
+#[derive(Debug, rustc_macros::Subdiagnostic)]
+#[suggestion(
+    parse_misspelled_kw,
+    applicability = "machine-applicable",
+    code = "{similar_kw}",
+    style = "verbose"
+)]
+pub(crate) struct MisspelledKw {
+    // We use a String here because `Symbol::into_diag_arg` calls `Symbol::to_ident_string`, which
+    // prefix the keyword with a `r#` because it aims to print the symbol as an identifier.
+    pub similar_kw: String,
+    #[primary_span]
+    pub span: Span,
+    pub is_incorrect_case: bool,
+}
+
+#[derive(Clone, Copy, Debug, PartialEq, Eq)]
+pub(super) enum TokenDescription {
+    ReservedIdentifier,
+    Keyword,
+    ReservedKeyword,
+    DocComment,
+
+    // Expanded metavariables are wrapped in invisible delimiters which aren't
+    // pretty-printed. In error messages we must handle these specially
+    // otherwise we get confusing things in messages like "expected `(`, found
+    // ``". It's better to say e.g. "expected `(`, found type metavariable".
+    MetaVar(MetaVarKind),
+}
+
+impl TokenDescription {
+    pub(super) fn from_token(token: &Token) -> Option<Self> {
+        match token.kind {
+            _ if token.is_special_ident() => Some(TokenDescription::ReservedIdentifier),
+            _ if token.is_used_keyword() => Some(TokenDescription::Keyword),
+            _ if token.is_unused_keyword() => Some(TokenDescription::ReservedKeyword),
+            token::DocComment(..) => Some(TokenDescription::DocComment),
+            token::OpenInvisible(InvisibleOrigin::MetaVar(kind)) => {
+                Some(TokenDescription::MetaVar(kind))
+            }
+            _ => None,
+        }
+    }
+}

compiler/rustc_parse/src/parser/diagnostics.rs

@@ -35,10 +35,10 @@ use crate::errors::{
     ExpectedIdentifier, ExpectedSemi, ExpectedSemiSugg, GenericParamsWithoutAngleBrackets,
     GenericParamsWithoutAngleBracketsSugg, HelpIdentifierStartsWithNumber, HelpUseLatestEdition,
     InInTypo, IncorrectAwait, IncorrectSemicolon, IncorrectUseOfAwait, IncorrectUseOfUse,
-    PatternMethodParamWithoutBody, QuestionMarkInType, QuestionMarkInTypeSugg, SelfParamNotFirst,
-    StructLiteralBodyWithoutPath, StructLiteralBodyWithoutPathSugg, SuggAddMissingLetStmt,
-    SuggEscapeIdentifier, SuggRemoveComma, TernaryOperator, TernaryOperatorSuggestion,
-    UnexpectedConstInGenericParam, UnexpectedConstParamDeclaration,
+    MisspelledKw, PatternMethodParamWithoutBody, QuestionMarkInType, QuestionMarkInTypeSugg,
+    SelfParamNotFirst, StructLiteralBodyWithoutPath, StructLiteralBodyWithoutPathSugg,
+    SuggAddMissingLetStmt, SuggEscapeIdentifier, SuggRemoveComma, TernaryOperator,
+    TernaryOperatorSuggestion, UnexpectedConstInGenericParam, UnexpectedConstParamDeclaration,
     UnexpectedConstParamDeclarationSugg, UnmatchedAngleBrackets, UseEqInstead, WrapType,
 };
 use crate::parser::FnContext;
@@ -212,22 +212,6 @@ impl std::fmt::Display for UnaryFixity {
     }
 }
 
-#[derive(Debug, rustc_macros::Subdiagnostic)]
-#[suggestion(
-    parse_misspelled_kw,
-    applicability = "machine-applicable",
-    code = "{similar_kw}",
-    style = "verbose"
-)]
-struct MisspelledKw {
-    // We use a String here because `Symbol::into_diag_arg` calls `Symbol::to_ident_string`, which
-    // prefix the keyword with a `r#` because it aims to print the symbol as an identifier.
-    similar_kw: String,
-    #[primary_span]
-    span: Span,
-    is_incorrect_case: bool,
-}
-
 /// Checks if the given `lookup` identifier is similar to any keyword symbol in `candidates`.
 ///
 /// This is a specialized version of [`Symbol::find_similar`] that constructs an error when a