diff options
Diffstat (limited to '')
| -rw-r--r-- | compiler/rustc_parse/src/parser/mod.rs | 196 |
1 files changed, 116 insertions, 80 deletions
diff --git a/compiler/rustc_parse/src/parser/mod.rs b/compiler/rustc_parse/src/parser/mod.rs index 0c523ad22..5fe29062b 100644 --- a/compiler/rustc_parse/src/parser/mod.rs +++ b/compiler/rustc_parse/src/parser/mod.rs @@ -13,7 +13,6 @@ mod ty; use crate::lexer::UnmatchedBrace; pub use attr_wrapper::AttrWrapper; pub use diagnostics::AttemptLocalParseRecovery; -use diagnostics::Error; pub(crate) use item::FnParseMode; pub use pat::{CommaRecoveryMode, RecoverColon, RecoverComma}; pub use path::PathStyle; @@ -32,16 +31,20 @@ use rustc_ast_pretty::pprust; use rustc_data_structures::fx::FxHashMap; use rustc_errors::PResult; use rustc_errors::{ - struct_span_err, Applicability, DiagnosticBuilder, ErrorGuaranteed, FatalError, MultiSpan, + Applicability, DiagnosticBuilder, ErrorGuaranteed, FatalError, IntoDiagnostic, MultiSpan, }; use rustc_session::parse::ParseSess; use rustc_span::source_map::{Span, DUMMY_SP}; use rustc_span::symbol::{kw, sym, Ident, Symbol}; -use tracing::debug; use std::ops::Range; use std::{cmp, mem, slice}; +use crate::errors::{ + DocCommentDoesNotDocumentAnything, IncorrectVisibilityRestriction, MismatchedClosingDelimiter, + NonStringAbiLiteral, +}; + bitflags::bitflags! { struct Restrictions: u8 { const STMT_EXPR = 1 << 0; @@ -76,6 +79,7 @@ pub enum ForceCollect { pub enum TrailingToken { None, Semi, + Gt, /// If the trailing token is a comma, then capture it /// Otherwise, ignore the trailing token MaybeComma, @@ -111,6 +115,12 @@ macro_rules! maybe_recover_from_interpolated_ty_qpath { }; } +#[derive(Clone, Copy)] +pub enum Recovery { + Allowed, + Forbidden, +} + #[derive(Clone)] pub struct Parser<'a> { pub sess: &'a ParseSess, @@ -148,12 +158,15 @@ pub struct Parser<'a> { /// This allows us to recover when the user forget to add braces around /// multiple statements in the closure body. pub current_closure: Option<ClosureSpans>, + /// Whether the parser is allowed to do recovery. + /// This is disabled when parsing macro arguments, see #103534 + pub recovery: Recovery, } -// This type is used a lot, e.g. it's cloned when matching many declarative macro rules. Make sure +// This type is used a lot, e.g. it's cloned when matching many declarative macro rules with nonterminals. Make sure // it doesn't unintentionally get bigger. #[cfg(all(target_arch = "x86_64", target_pointer_width = "64"))] -rustc_data_structures::static_assert_size!(Parser<'_>, 328); +rustc_data_structures::static_assert_size!(Parser<'_>, 336); /// Stores span information about a closure. #[derive(Clone)] @@ -171,7 +184,7 @@ pub struct ClosureSpans { /// attribute, we parse a nested AST node that has `#[cfg]` or `#[cfg_attr]` /// In this case, we use a `ReplaceRange` to replace the entire inner AST node /// with `FlatToken::AttrTarget`, allowing us to perform eager cfg-expansion -/// on an `AttrAnnotatedTokenStream` +/// on an `AttrTokenStream`. /// /// 2. When we parse an inner attribute while collecting tokens. We /// remove inner attributes from the token stream entirely, and @@ -184,7 +197,7 @@ pub type ReplaceRange = (Range<u32>, Vec<(FlatToken, Spacing)>); /// Controls how we capture tokens. Capturing can be expensive, /// so we try to avoid performing capturing in cases where -/// we will never need an `AttrAnnotatedTokenStream` +/// we will never need an `AttrTokenStream`. #[derive(Copy, Clone)] pub enum Capturing { /// We aren't performing any capturing - this is the default mode. @@ -238,7 +251,7 @@ struct TokenCursor { // the trailing `>>` token. The `break_last_token` // field is used to track this token - it gets // appended to the captured stream when - // we evaluate a `LazyTokenStream` + // we evaluate a `LazyAttrTokenStream`. break_last_token: bool, } @@ -281,7 +294,7 @@ impl TokenCursor { if delim != Delimiter::Invisible { return (Token::new(token::OpenDelim(delim), sp.open), Spacing::Alone); } - // No open delimeter to return; continue on to the next iteration. + // No open delimiter to return; continue on to the next iteration. } }; } else if let Some(frame) = self.stack.pop() { @@ -299,7 +312,10 @@ impl TokenCursor { fn desugar(&mut self, attr_style: AttrStyle, data: Symbol, span: Span) -> (Token, Spacing) { // Searches for the occurrences of `"#*` and returns the minimum number of `#`s - // required to wrap the text. + // required to wrap the text. E.g. + // - `abc d` is wrapped as `r"abc d"` (num_of_hashes = 0) + // - `abc "d"` is wrapped as `r#"abc "d""#` (num_of_hashes = 1) + // - `abc "##d##"` is wrapped as `r###"abc "d""###` (num_of_hashes = 3) let mut num_of_hashes = 0; let mut count = 0; for ch in data.as_str().chars() { @@ -311,6 +327,7 @@ impl TokenCursor { num_of_hashes = cmp::max(num_of_hashes, count); } + // `/// foo` becomes `doc = r"foo". let delim_span = DelimSpan::from_single(span); let body = TokenTree::Delimited( delim_span, @@ -407,24 +424,39 @@ pub enum FollowedByType { No, } -fn token_descr_opt(token: &Token) -> Option<&'static str> { - Some(match token.kind { - _ if token.is_special_ident() => "reserved identifier", - _ if token.is_used_keyword() => "keyword", - _ if token.is_unused_keyword() => "reserved keyword", - token::DocComment(..) => "doc comment", - _ => return None, - }) +#[derive(Clone, Copy, PartialEq, Eq)] +pub enum TokenDescription { + ReservedIdentifier, + Keyword, + ReservedKeyword, + DocComment, } -pub(super) fn token_descr(token: &Token) -> String { - let token_str = pprust::token_to_string(token); - match token_descr_opt(token) { - Some(prefix) => format!("{} `{}`", prefix, token_str), - _ => format!("`{}`", token_str), +impl TokenDescription { + pub 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), + _ => None, + } } } +pub(super) fn token_descr(token: &Token) -> String { + let name = pprust::token_to_string(token).to_string(); + + let kind = TokenDescription::from_token(token).map(|kind| match kind { + TokenDescription::ReservedIdentifier => "reserved identifier", + TokenDescription::Keyword => "keyword", + TokenDescription::ReservedKeyword => "reserved keyword", + TokenDescription::DocComment => "doc comment", + }); + + if let Some(kind) = kind { format!("{} `{}`", kind, name) } else { format!("`{}`", name) } +} + impl<'a> Parser<'a> { pub fn new( sess: &'a ParseSess, @@ -460,6 +492,7 @@ impl<'a> Parser<'a> { inner_attr_ranges: Default::default(), }, current_closure: None, + recovery: Recovery::Allowed, }; // Make parser point to the first token. @@ -468,6 +501,22 @@ impl<'a> Parser<'a> { parser } + pub fn forbid_recovery(mut self) -> Self { + self.recovery = Recovery::Forbidden; + self + } + + /// Whether the parser is allowed to recover from broken code. + /// + /// If this returns false, recovering broken code into valid code (especially if this recovery does lookahead) + /// is not allowed. All recovery done by the parser must be gated behind this check. + /// + /// Technically, this only needs to restrict eager recovery by doing lookahead at more tokens. + /// But making the distinction is very subtle, and simply forbidding all recovery is a lot simpler to uphold. + fn may_recover(&self) -> bool { + matches!(self.recovery, Recovery::Allowed) + } + pub fn unexpected<T>(&mut self) -> PResult<'a, T> { match self.expect_one_of(&[], &[]) { Err(e) => Err(e), @@ -519,9 +568,11 @@ impl<'a> Parser<'a> { fn ident_or_err(&mut self) -> PResult<'a, (Ident, /* is_raw */ bool)> { self.token.ident().ok_or_else(|| match self.prev_token.kind { - TokenKind::DocComment(..) => { - self.span_err(self.prev_token.span, Error::UselessDocComment) + TokenKind::DocComment(..) => DocCommentDoesNotDocumentAnything { + span: self.prev_token.span, + missing_comma: None, } + .into_diagnostic(&self.sess.span_diagnostic), _ => self.expected_ident_found(), }) } @@ -1116,10 +1167,14 @@ impl<'a> Parser<'a> { let (attrs, blk) = self.parse_inner_attrs_and_block()?; let anon_const = AnonConst { id: DUMMY_NODE_ID, - value: self.mk_expr(blk.span, ExprKind::Block(blk, None), AttrVec::new()), + value: self.mk_expr(blk.span, ExprKind::Block(blk, None)), }; let blk_span = anon_const.value.span; - Ok(self.mk_expr(span.to(blk_span), ExprKind::ConstBlock(anon_const), AttrVec::from(attrs))) + Ok(self.mk_expr_with_attrs( + span.to(blk_span), + ExprKind::ConstBlock(anon_const), + AttrVec::from(attrs), + )) } /// Parses mutability (`mut` or nothing). @@ -1141,7 +1196,9 @@ impl<'a> Parser<'a> { fn parse_field_name(&mut self) -> PResult<'a, Ident> { if let token::Literal(token::Lit { kind: token::Integer, symbol, suffix }) = self.token.kind { - self.expect_no_suffix(self.token.span, "a tuple index", suffix); + if let Some(suffix) = suffix { + self.expect_no_tuple_index_suffix(self.token.span, suffix); + } self.bump(); Ok(Ident::new(symbol, self.prev_token.span)) } else { @@ -1295,7 +1352,11 @@ impl<'a> Parser<'a> { self.bump(); // `in` let path = self.parse_path(PathStyle::Mod)?; // `path` self.expect(&token::CloseDelim(Delimiter::Parenthesis))?; // `)` - let vis = VisibilityKind::Restricted { path: P(path), id: ast::DUMMY_NODE_ID }; + let vis = VisibilityKind::Restricted { + path: P(path), + id: ast::DUMMY_NODE_ID, + shorthand: false, + }; return Ok(Visibility { span: lo.to(self.prev_token.span), kind: vis, @@ -1308,7 +1369,11 @@ impl<'a> Parser<'a> { self.bump(); // `(` let path = self.parse_path(PathStyle::Mod)?; // `crate`/`super`/`self` self.expect(&token::CloseDelim(Delimiter::Parenthesis))?; // `)` - let vis = VisibilityKind::Restricted { path: P(path), id: ast::DUMMY_NODE_ID }; + let vis = VisibilityKind::Restricted { + path: P(path), + id: ast::DUMMY_NODE_ID, + shorthand: true, + }; return Ok(Visibility { span: lo.to(self.prev_token.span), kind: vis, @@ -1331,23 +1396,8 @@ impl<'a> Parser<'a> { let path = self.parse_path(PathStyle::Mod)?; self.expect(&token::CloseDelim(Delimiter::Parenthesis))?; // `)` - let msg = "incorrect visibility restriction"; - let suggestion = r##"some possible visibility restrictions are: -`pub(crate)`: visible only on the current crate -`pub(super)`: visible only in the current module's parent -`pub(in path::to::module)`: visible only on the specified path"##; - let path_str = pprust::path_to_string(&path); - - struct_span_err!(self.sess.span_diagnostic, path.span, E0704, "{}", msg) - .help(suggestion) - .span_suggestion( - path.span, - &format!("make this visible only to module `{}` with `in`", path_str), - format!("in {}", path_str), - Applicability::MachineApplicable, - ) - .emit(); + self.sess.emit_err(IncorrectVisibilityRestriction { span: path.span, inner_str: path_str }); Ok(()) } @@ -1371,16 +1421,9 @@ impl<'a> Parser<'a> { match self.parse_str_lit() { Ok(str_lit) => Some(str_lit), Err(Some(lit)) => match lit.kind { - ast::LitKind::Err(_) => None, + ast::LitKind::Err => None, _ => { - self.struct_span_err(lit.span, "non-string ABI literal") - .span_suggestion( - lit.span, - "specify the ABI with a string literal", - "\"C\"", - Applicability::MaybeIncorrect, - ) - .emit(); + self.sess.emit_err(NonStringAbiLiteral { span: lit.span }); None } }, @@ -1421,25 +1464,18 @@ pub(crate) fn make_unclosed_delims_error( // `None` here means an `Eof` was found. We already emit those errors elsewhere, we add them to // `unmatched_braces` only for error recovery in the `Parser`. let found_delim = unmatched.found_delim?; - let span: MultiSpan = if let Some(sp) = unmatched.unclosed_span { - vec![unmatched.found_span, sp].into() - } else { - unmatched.found_span.into() - }; - let mut err = sess.span_diagnostic.struct_span_err( - span, - &format!( - "mismatched closing delimiter: `{}`", - pprust::token_kind_to_string(&token::CloseDelim(found_delim)), - ), - ); - err.span_label(unmatched.found_span, "mismatched closing delimiter"); - if let Some(sp) = unmatched.candidate_span { - err.span_label(sp, "closing delimiter possibly meant for this"); - } + let mut spans = vec![unmatched.found_span]; if let Some(sp) = unmatched.unclosed_span { - err.span_label(sp, "unclosed delimiter"); - } + spans.push(sp); + }; + let err = MismatchedClosingDelimiter { + spans, + delimiter: pprust::token_kind_to_string(&token::CloseDelim(found_delim)).to_string(), + unmatched: unmatched.found_span, + opening_candidate: unmatched.candidate_span, + unclosed: unmatched.unclosed_span, + } + .into_diagnostic(&sess.span_diagnostic); Some(err) } @@ -1453,11 +1489,11 @@ pub fn emit_unclosed_delims(unclosed_delims: &mut Vec<UnmatchedBrace>, sess: &Pa } } -/// A helper struct used when building an `AttrAnnotatedTokenStream` from -/// a `LazyTokenStream`. Both delimiter and non-delimited tokens +/// A helper struct used when building an `AttrTokenStream` from +/// a `LazyAttrTokenStream`. Both delimiter and non-delimited tokens /// are stored as `FlatToken::Token`. A vector of `FlatToken`s -/// is then 'parsed' to build up an `AttrAnnotatedTokenStream` with nested -/// `AttrAnnotatedTokenTree::Delimited` tokens +/// is then 'parsed' to build up an `AttrTokenStream` with nested +/// `AttrTokenTree::Delimited` tokens. #[derive(Debug, Clone)] pub enum FlatToken { /// A token - this holds both delimiter (e.g. '{' and '}') @@ -1465,11 +1501,11 @@ pub enum FlatToken { Token(Token), /// Holds the `AttributesData` for an AST node. The /// `AttributesData` is inserted directly into the - /// constructed `AttrAnnotatedTokenStream` as - /// an `AttrAnnotatedTokenTree::Attributes` + /// constructed `AttrTokenStream` as + /// an `AttrTokenTree::Attributes`. AttrTarget(AttributesData), /// A special 'empty' token that is ignored during the conversion - /// to an `AttrAnnotatedTokenStream`. This is used to simplify the + /// to an `AttrTokenStream`. This is used to simplify the /// handling of replace ranges. Empty, } |