2019-10-16 11:23:46 +00:00
|
|
|
pub mod attr;
|
2021-02-13 17:42:43 +00:00
|
|
|
mod attr_wrapper;
|
2020-08-02 12:05:19 +00:00
|
|
|
mod diagnostics;
|
2019-08-11 11:14:30 +00:00
|
|
|
mod expr;
|
2020-08-02 12:05:19 +00:00
|
|
|
mod generics;
|
2019-08-11 16:34:42 +00:00
|
|
|
mod item;
|
2020-07-27 12:04:54 +00:00
|
|
|
mod nonterminal;
|
2019-12-22 22:42:04 +00:00
|
|
|
mod pat;
|
2019-08-11 17:59:27 +00:00
|
|
|
mod path;
|
2019-12-22 22:42:04 +00:00
|
|
|
mod stmt;
|
2024-12-04 04:55:06 +00:00
|
|
|
pub mod token_type;
|
2020-08-02 12:05:19 +00:00
|
|
|
mod ty;
|
2020-07-27 12:04:54 +00:00
|
|
|
|
2024-08-11 16:10:36 +00:00
|
|
|
use std::assert_matches::debug_assert_matches;
|
2024-07-28 22:13:50 +00:00
|
|
|
use std::ops::Range;
|
2025-02-03 03:44:41 +00:00
|
|
|
use std::sync::Arc;
|
2024-07-28 22:13:50 +00:00
|
|
|
use std::{fmt, mem, slice};
|
|
|
|
|
2024-08-06 07:16:40 +00:00
|
|
|
use attr_wrapper::{AttrWrapper, UsePreAttrPos};
|
2020-08-12 22:39:15 +00:00
|
|
|
pub use diagnostics::AttemptLocalParseRecovery;
|
2023-09-08 10:14:36 +00:00
|
|
|
pub(crate) use expr::ForbiddenLetReason;
|
2021-12-04 18:05:30 +00:00
|
|
|
pub(crate) use item::FnParseMode;
|
2022-01-12 20:43:24 +00:00
|
|
|
pub use pat::{CommaRecoveryMode, RecoverColon, RecoverComma};
|
2024-06-03 05:47:46 +00:00
|
|
|
use path::PathStyle;
|
2020-02-29 17:37:32 +00:00
|
|
|
use rustc_ast::ptr::P;
|
2024-04-17 22:58:06 +00:00
|
|
|
use rustc_ast::token::{
|
Remove `NtPat`.
The one notable test change is `tests/ui/macros/trace_faulty_macros.rs`.
This commit removes the complicated `Interpolated` handling in
`expected_expression_found` that results in a longer error message. But
I think the new, shorter message is actually an improvement.
The original complaint was in #71039, when the error message started
with "error: expected expression, found `1 + 1`". That was confusing
because `1 + 1` is an expression. Other than that, the reporter said
"the whole error message is not too bad if you ignore the first line".
Subsequently, extra complexity and wording was added to the error
message. But I don't think the extra wording actually helps all that
much. In particular, it still says of the `1+1` that "this is expected
to be expression". This repeats the problem from the original complaint!
This commit removes the extra complexity, reverting to a simpler error
message. This is primarily because the traversal is a pain without
`Interpolated` tokens. Nonetheless, I think the error message is
*improved*. It now starts with "expected expression, found `pat`
metavariable", which is much clearer and the real problem. It also
doesn't say anything specific about `1+1`, which is good, because the
`1+1` isn't really relevant to the error -- it's the `$e:pat` that's
important.
2024-04-18 02:44:11 +00:00
|
|
|
self, Delimiter, IdentIsRaw, InvisibleOrigin, MetaVarKind, Nonterminal, NtPatKind, Token,
|
|
|
|
TokenKind,
|
2024-04-17 22:58:06 +00:00
|
|
|
};
|
2024-12-10 08:18:44 +00:00
|
|
|
use rustc_ast::tokenstream::{AttrsTarget, Spacing, TokenStream, TokenTree};
|
2022-09-15 16:27:23 +00:00
|
|
|
use rustc_ast::util::case::Case;
|
2024-03-24 01:04:45 +00:00
|
|
|
use rustc_ast::{
|
2024-10-16 23:14:01 +00:00
|
|
|
self as ast, AnonConst, AttrArgs, AttrId, ByRef, Const, CoroutineKind, DUMMY_NODE_ID,
|
|
|
|
DelimArgs, Expr, ExprKind, Extern, HasAttrs, HasTokens, Mutability, Recovered, Safety, StrLit,
|
|
|
|
Visibility, VisibilityKind,
|
2024-03-24 01:04:45 +00:00
|
|
|
};
|
2020-01-11 16:02:46 +00:00
|
|
|
use rustc_ast_pretty::pprust;
|
2020-11-28 23:33:17 +00:00
|
|
|
use rustc_data_structures::fx::FxHashMap;
|
2024-05-09 08:44:40 +00:00
|
|
|
use rustc_errors::{Applicability, Diag, FatalError, MultiSpan, PResult};
|
2024-08-21 04:16:42 +00:00
|
|
|
use rustc_index::interval::IntervalSet;
|
2020-01-11 14:03:15 +00:00
|
|
|
use rustc_session::parse::ParseSess;
|
2024-12-12 23:29:23 +00:00
|
|
|
use rustc_span::{DUMMY_SP, Ident, Span, Symbol, kw, sym};
|
2022-11-23 00:55:16 +00:00
|
|
|
use thin_vec::ThinVec;
|
2024-12-04 04:55:06 +00:00
|
|
|
use token_type::TokenTypeSet;
|
|
|
|
pub use token_type::{ExpKeywordPair, ExpTokenPair, TokenType};
|
2022-11-23 00:55:16 +00:00
|
|
|
use tracing::debug;
|
2018-07-03 17:38:14 +00:00
|
|
|
|
2022-09-01 17:29:23 +00:00
|
|
|
use crate::errors::{
|
2023-04-27 00:53:06 +00:00
|
|
|
self, IncorrectVisibilityRestriction, MismatchedClosingDelimiter, NonStringAbiLiteral,
|
2022-09-01 17:29:23 +00:00
|
|
|
};
|
2024-12-04 04:55:06 +00:00
|
|
|
use crate::exp;
|
2024-07-28 22:13:50 +00:00
|
|
|
use crate::lexer::UnmatchedDelim;
|
2022-08-24 20:41:51 +00:00
|
|
|
|
2024-05-02 23:26:34 +00:00
|
|
|
#[cfg(test)]
|
|
|
|
mod tests;
|
|
|
|
|
|
|
|
// Ideally, these tests would be in `rustc_ast`. But they depend on having a
|
|
|
|
// parser, so they are here.
|
|
|
|
#[cfg(test)]
|
|
|
|
mod tokenstream {
|
|
|
|
mod tests;
|
|
|
|
}
|
|
|
|
#[cfg(test)]
|
|
|
|
mod mut_visit {
|
|
|
|
mod tests;
|
|
|
|
}
|
|
|
|
|
2019-02-06 17:33:01 +00:00
|
|
|
bitflags::bitflags! {
|
2024-05-05 19:44:40 +00:00
|
|
|
#[derive(Clone, Copy, Debug)]
|
2018-05-31 22:53:30 +00:00
|
|
|
struct Restrictions: u8 {
|
2017-09-08 19:08:01 +00:00
|
|
|
const STMT_EXPR = 1 << 0;
|
|
|
|
const NO_STRUCT_LITERAL = 1 << 1;
|
2020-10-03 18:30:32 +00:00
|
|
|
const CONST_EXPR = 1 << 2;
|
2022-08-01 01:13:16 +00:00
|
|
|
const ALLOW_LET = 1 << 3;
|
2023-10-03 21:21:02 +00:00
|
|
|
const IN_IF_GUARD = 1 << 4;
|
2024-01-28 15:12:21 +00:00
|
|
|
const IS_PAT = 1 << 5;
|
2014-09-16 05:22:12 +00:00
|
|
|
}
|
2011-12-21 04:12:52 +00:00
|
|
|
}
|
2011-01-24 23:26:10 +00:00
|
|
|
|
2018-03-20 22:58:25 +00:00
|
|
|
#[derive(Clone, Copy, PartialEq, Debug)]
|
2019-10-08 07:35:34 +00:00
|
|
|
enum SemiColonMode {
|
2016-02-10 03:11:27 +00:00
|
|
|
Break,
|
|
|
|
Ignore,
|
2019-01-20 08:37:06 +00:00
|
|
|
Comma,
|
2016-02-10 03:11:27 +00:00
|
|
|
}
|
|
|
|
|
2018-03-20 22:58:25 +00:00
|
|
|
#[derive(Clone, Copy, PartialEq, Debug)]
|
2019-10-08 07:35:34 +00:00
|
|
|
enum BlockMode {
|
2017-04-13 19:37:05 +00:00
|
|
|
Break,
|
|
|
|
Ignore,
|
|
|
|
}
|
|
|
|
|
2021-01-18 21:47:37 +00:00
|
|
|
/// Whether or not we should force collection of tokens for an AST node,
|
|
|
|
/// regardless of whether or not it has attributes
|
2024-05-05 19:44:40 +00:00
|
|
|
#[derive(Clone, Copy, Debug, PartialEq)]
|
2021-01-18 21:47:37 +00:00
|
|
|
pub enum ForceCollect {
|
|
|
|
Yes,
|
|
|
|
No,
|
|
|
|
}
|
|
|
|
|
2019-08-11 13:24:37 +00:00
|
|
|
#[macro_export]
|
2014-11-14 17:18:10 +00:00
|
|
|
macro_rules! maybe_whole {
|
2016-11-02 03:03:55 +00:00
|
|
|
($p:expr, $constructor:ident, |$x:ident| $e:expr) => {
|
2024-03-19 20:08:22 +00:00
|
|
|
if let token::Interpolated(nt) = &$p.token.kind
|
2024-04-22 06:29:27 +00:00
|
|
|
&& let token::$constructor(x) = &**nt
|
2024-03-19 20:08:22 +00:00
|
|
|
{
|
|
|
|
#[allow(unused_mut)]
|
|
|
|
let mut $x = x.clone();
|
|
|
|
$p.bump();
|
|
|
|
return Ok($e);
|
2013-07-02 19:47:32 +00:00
|
|
|
}
|
2016-11-02 03:03:55 +00:00
|
|
|
};
|
2014-11-14 17:18:10 +00:00
|
|
|
}
|
2012-07-04 01:39:37 +00:00
|
|
|
|
2019-03-09 14:41:01 +00:00
|
|
|
/// If the next tokens are ill-formed `$ty::` recover them as `<$ty>::`.
|
2019-08-11 11:14:30 +00:00
|
|
|
#[macro_export]
|
2019-03-09 14:41:01 +00:00
|
|
|
macro_rules! maybe_recover_from_interpolated_ty_qpath {
|
|
|
|
($self: expr, $allow_qpath_recovery: expr) => {
|
2022-02-28 10:49:56 +00:00
|
|
|
if $allow_qpath_recovery
|
2023-11-13 13:24:55 +00:00
|
|
|
&& $self.may_recover()
|
2025-02-21 05:47:07 +00:00
|
|
|
&& let Some(mv_kind) = $self.token.is_metavar_seq()
|
|
|
|
&& let token::MetaVarKind::Ty { .. } = mv_kind
|
2024-04-17 03:17:44 +00:00
|
|
|
&& $self.check_noexpect_past_close_delim(&token::PathSep)
|
2023-11-13 13:24:55 +00:00
|
|
|
{
|
2024-04-17 03:17:44 +00:00
|
|
|
// Reparse the type, then move to recovery.
|
|
|
|
let ty = $self
|
2025-02-21 05:47:07 +00:00
|
|
|
.eat_metavar_seq(mv_kind, |this| this.parse_ty_no_question_mark_recover())
|
2024-04-17 03:17:44 +00:00
|
|
|
.expect("metavar seq ty");
|
|
|
|
|
2023-11-13 13:24:55 +00:00
|
|
|
return $self.maybe_recover_from_bad_qpath_stage_2($self.prev_token.span, ty);
|
|
|
|
}
|
2019-12-22 22:42:04 +00:00
|
|
|
};
|
2019-03-09 14:41:01 +00:00
|
|
|
}
|
|
|
|
|
2024-05-05 19:44:40 +00:00
|
|
|
#[derive(Clone, Copy, Debug)]
|
2022-10-25 19:24:01 +00:00
|
|
|
pub enum Recovery {
|
|
|
|
Allowed,
|
|
|
|
Forbidden,
|
|
|
|
}
|
|
|
|
|
2017-06-15 03:42:24 +00:00
|
|
|
#[derive(Clone)]
|
2014-03-09 14:54:34 +00:00
|
|
|
pub struct Parser<'a> {
|
2024-03-04 05:31:49 +00:00
|
|
|
pub psess: &'a ParseSess,
|
2020-03-07 13:34:29 +00:00
|
|
|
/// The current token.
|
2020-02-24 10:04:13 +00:00
|
|
|
pub token: Token,
|
2023-08-08 01:43:44 +00:00
|
|
|
/// The spacing for the current token.
|
2024-06-03 05:47:46 +00:00
|
|
|
token_spacing: Spacing,
|
2020-03-07 13:34:29 +00:00
|
|
|
/// The previous token.
|
2020-02-24 10:04:13 +00:00
|
|
|
pub prev_token: Token,
|
2020-11-28 23:33:17 +00:00
|
|
|
pub capture_cfg: bool,
|
2018-05-31 22:53:30 +00:00
|
|
|
restrictions: Restrictions,
|
2024-12-04 04:55:06 +00:00
|
|
|
expected_token_types: TokenTypeSet,
|
2019-08-31 13:03:54 +00:00
|
|
|
token_cursor: TokenCursor,
|
2023-07-31 06:15:54 +00:00
|
|
|
// The number of calls to `bump`, i.e. the position in the token stream.
|
2024-07-02 06:31:24 +00:00
|
|
|
num_bump_calls: u32,
|
2024-09-19 09:32:17 +00:00
|
|
|
// 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
|
|
|
|
// process bypasses the normal capturing mechanism (e.g. `num_bump_calls`
|
|
|
|
// will not be incremented), since the "unglued" tokens due not exist in
|
|
|
|
// the original `TokenStream`.
|
2023-07-31 06:36:27 +00:00
|
|
|
//
|
2024-09-19 09:32:17 +00:00
|
|
|
// If we end up consuming all the component tokens, this is not an issue,
|
|
|
|
// because we'll end up capturing the single "glued" token.
|
2023-07-31 06:36:27 +00:00
|
|
|
//
|
2024-09-19 09:32:17 +00:00
|
|
|
// However, sometimes we may want to capture not all of the original
|
2023-07-31 06:36:27 +00:00
|
|
|
// token. For example, capturing the `Vec<u8>` in `Option<Vec<u8>>`
|
|
|
|
// requires us to unglue the trailing `>>` token. The `break_last_token`
|
2024-09-19 09:32:17 +00:00
|
|
|
// field is used to track these tokens. They get appended to the captured
|
2023-07-31 06:36:27 +00:00
|
|
|
// stream when we evaluate a `LazyAttrTokenStream`.
|
2024-09-19 09:32:17 +00:00
|
|
|
//
|
|
|
|
// This value is always 0, 1, or 2. It can only reach 2 when splitting
|
|
|
|
// `>>=` or `<<=`.
|
|
|
|
break_last_token: u32,
|
2019-01-23 01:35:13 +00:00
|
|
|
/// 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.
|
2023-10-24 22:22:52 +00:00
|
|
|
unmatched_angle_bracket_count: u16,
|
|
|
|
angle_bracket_nesting: u16,
|
2023-03-03 22:48:21 +00:00
|
|
|
|
2019-10-08 07:35:34 +00:00
|
|
|
last_unexpected_token_span: Option<Span>,
|
2019-05-22 05:17:53 +00:00
|
|
|
/// If present, this `Parser` is not parsing Rust code but rather a macro call.
|
2019-10-08 07:35:34 +00:00
|
|
|
subparser_name: Option<&'static str>,
|
2020-11-28 23:33:17 +00:00
|
|
|
capture_state: CaptureState,
|
2021-08-16 13:22:36 +00:00
|
|
|
/// This allows us to recover when the user forget to add braces around
|
|
|
|
/// multiple statements in the closure body.
|
2024-05-05 19:23:37 +00:00
|
|
|
current_closure: Option<ClosureSpans>,
|
2022-10-26 19:09:28 +00:00
|
|
|
/// Whether the parser is allowed to do recovery.
|
2022-10-25 19:24:01 +00:00
|
|
|
/// This is disabled when parsing macro arguments, see #103534
|
2024-06-03 05:47:46 +00:00
|
|
|
recovery: Recovery,
|
2021-08-16 13:22:36 +00:00
|
|
|
}
|
|
|
|
|
2024-12-19 09:06:44 +00:00
|
|
|
// This type is used a lot, e.g. it's cloned when matching many declarative macro rules with
|
2025-01-22 01:24:29 +00:00
|
|
|
// nonterminals. Make sure it doesn't unintentionally get bigger. We only check a few arches
|
|
|
|
// though, because `TokenTypeSet(u128)` alignment varies on others, changing the total size.
|
|
|
|
#[cfg(all(target_pointer_width = "64", any(target_arch = "aarch64", target_arch = "x86_64")))]
|
2024-08-21 04:16:42 +00:00
|
|
|
rustc_data_structures::static_assert_size!(Parser<'_>, 288);
|
2022-04-19 23:31:34 +00:00
|
|
|
|
2022-03-30 19:14:15 +00:00
|
|
|
/// Stores span information about a closure.
|
2024-05-05 19:44:40 +00:00
|
|
|
#[derive(Clone, Debug)]
|
2024-06-03 05:47:46 +00:00
|
|
|
struct ClosureSpans {
|
|
|
|
whole_closure: Span,
|
|
|
|
closing_pipe: Span,
|
|
|
|
body: Span,
|
2020-11-28 23:33:17 +00:00
|
|
|
}
|
|
|
|
|
2024-07-31 20:44:39 +00:00
|
|
|
/// A token range within a `Parser`'s full token stream.
|
|
|
|
#[derive(Clone, Debug)]
|
|
|
|
struct ParserRange(Range<u32>);
|
|
|
|
|
|
|
|
/// A token range within an individual AST node's (lazy) token stream, i.e.
|
|
|
|
/// relative to that node's first token. Distinct from `ParserRange` so the two
|
|
|
|
/// kinds of range can't be mixed up.
|
|
|
|
#[derive(Clone, Debug)]
|
|
|
|
struct NodeRange(Range<u32>);
|
|
|
|
|
|
|
|
/// Indicates a range of tokens that should be replaced by an `AttrsTarget`
|
|
|
|
/// (replacement) or be replaced by nothing (deletion). This is used in two
|
|
|
|
/// places during token collection.
|
|
|
|
///
|
|
|
|
/// 1. Replacement. During the parsing of an AST node that may have a
|
|
|
|
/// `#[derive]` attribute, when we parse a nested AST node that has `#[cfg]`
|
|
|
|
/// or `#[cfg_attr]`, we replace the entire inner AST node with
|
|
|
|
/// `FlatToken::AttrsTarget`. This lets us perform eager cfg-expansion on an
|
|
|
|
/// `AttrTokenStream`.
|
2020-11-28 23:33:17 +00:00
|
|
|
///
|
2024-07-31 20:44:39 +00:00
|
|
|
/// 2. Deletion. We delete inner attributes from all collected token streams,
|
|
|
|
/// and instead track them through the `attrs` field on the AST node. This
|
|
|
|
/// lets us manipulate them similarly to outer attributes. When we create a
|
|
|
|
/// `TokenStream`, the inner attributes are inserted into the proper place
|
|
|
|
/// in the token stream.
|
2020-11-28 23:33:17 +00:00
|
|
|
///
|
2024-07-31 20:44:39 +00:00
|
|
|
/// Each replacement starts off in `ParserReplacement` form but is converted to
|
|
|
|
/// `NodeReplacement` form when it is attached to a single AST node, via
|
|
|
|
/// `LazyAttrTokenStreamImpl`.
|
|
|
|
type ParserReplacement = (ParserRange, Option<AttrsTarget>);
|
|
|
|
|
|
|
|
/// See the comment on `ParserReplacement`.
|
|
|
|
type NodeReplacement = (NodeRange, Option<AttrsTarget>);
|
|
|
|
|
|
|
|
impl NodeRange {
|
|
|
|
// Converts a range within a parser's tokens to a range within a
|
|
|
|
// node's tokens beginning at `start_pos`.
|
|
|
|
//
|
|
|
|
// For example, imagine a parser with 50 tokens in its token stream, a
|
|
|
|
// function that spans `ParserRange(20..40)` and an inner attribute within
|
|
|
|
// that function that spans `ParserRange(30..35)`. We would find the inner
|
|
|
|
// attribute's range within the function's tokens by subtracting 20, which
|
|
|
|
// is the position of the function's start token. This gives
|
|
|
|
// `NodeRange(10..15)`.
|
|
|
|
fn new(ParserRange(parser_range): ParserRange, start_pos: u32) -> NodeRange {
|
2024-08-21 20:58:31 +00:00
|
|
|
assert!(!parser_range.is_empty());
|
|
|
|
assert!(parser_range.start >= start_pos);
|
2024-07-31 20:44:39 +00:00
|
|
|
NodeRange((parser_range.start - start_pos)..(parser_range.end - start_pos))
|
|
|
|
}
|
|
|
|
}
|
2020-11-28 23:33:17 +00:00
|
|
|
|
|
|
|
/// Controls how we capture tokens. Capturing can be expensive,
|
|
|
|
/// so we try to avoid performing capturing in cases where
|
2022-09-09 02:44:05 +00:00
|
|
|
/// we will never need an `AttrTokenStream`.
|
2024-05-05 19:44:40 +00:00
|
|
|
#[derive(Copy, Clone, Debug)]
|
2024-06-03 05:47:46 +00:00
|
|
|
enum Capturing {
|
2020-11-28 23:33:17 +00:00
|
|
|
/// We aren't performing any capturing - this is the default mode.
|
|
|
|
No,
|
|
|
|
/// We are capturing tokens
|
|
|
|
Yes,
|
|
|
|
}
|
|
|
|
|
2024-08-06 07:16:40 +00:00
|
|
|
// This state is used by `Parser::collect_tokens`.
|
2024-05-05 19:44:40 +00:00
|
|
|
#[derive(Clone, Debug)]
|
2020-11-28 23:33:17 +00:00
|
|
|
struct CaptureState {
|
|
|
|
capturing: Capturing,
|
2024-07-31 20:44:39 +00:00
|
|
|
parser_replacements: Vec<ParserReplacement>,
|
|
|
|
inner_attr_parser_ranges: FxHashMap<AttrId, ParserRange>,
|
2024-08-21 04:16:42 +00:00
|
|
|
// `IntervalSet` is good for perf because attrs are mostly added to this
|
|
|
|
// set in contiguous ranges.
|
|
|
|
seen_attrs: IntervalSet<AttrId>,
|
Make the parser’s ‘expected <foo>, found <bar>’ errors more accurate
As an example of what this changes, the following code:
let x: [int ..4];
Currently spits out ‘expected `]`, found `..`’. However, a comma would also be
valid there, as would a number of other tokens. This change adjusts the parser
to produce more accurate errors, so that that example now produces ‘expected one
of `(`, `+`, `,`, `::`, or `]`, found `..`’.
2014-12-03 09:47:53 +00:00
|
|
|
}
|
|
|
|
|
2024-12-10 08:18:44 +00:00
|
|
|
#[derive(Clone, Debug)]
|
|
|
|
struct TokenTreeCursor {
|
|
|
|
stream: TokenStream,
|
|
|
|
/// Points to the current token tree in the stream. In `TokenCursor::curr`,
|
|
|
|
/// this can be any token tree. In `TokenCursor::stack`, this is always a
|
|
|
|
/// `TokenTree::Delimited`.
|
|
|
|
index: usize,
|
|
|
|
}
|
|
|
|
|
|
|
|
impl TokenTreeCursor {
|
|
|
|
#[inline]
|
|
|
|
fn new(stream: TokenStream) -> Self {
|
|
|
|
TokenTreeCursor { stream, index: 0 }
|
|
|
|
}
|
|
|
|
|
|
|
|
#[inline]
|
|
|
|
fn curr(&self) -> Option<&TokenTree> {
|
|
|
|
self.stream.get(self.index)
|
|
|
|
}
|
|
|
|
|
|
|
|
#[inline]
|
|
|
|
fn bump(&mut self) {
|
|
|
|
self.index += 1;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
/// A `TokenStream` cursor that produces `Token`s. It's a bit odd that
|
2023-02-01 01:58:04 +00:00
|
|
|
/// we (a) lex tokens into a nice tree structure (`TokenStream`), and then (b)
|
|
|
|
/// use this type to emit them as a linear sequence. But a linear sequence is
|
|
|
|
/// what the parser expects, for the most part.
|
2024-05-05 19:44:40 +00:00
|
|
|
#[derive(Clone, Debug)]
|
2019-08-31 13:03:54 +00:00
|
|
|
struct TokenCursor {
|
2024-12-10 08:18:44 +00:00
|
|
|
// Cursor for the current (innermost) token stream. The index within the
|
|
|
|
// cursor can point to any token tree in the stream (or one past the end).
|
|
|
|
// The delimiters for this token stream are found in `self.stack.last()`;
|
|
|
|
// if that is `None` we are in the outermost token stream which never has
|
|
|
|
// delimiters.
|
|
|
|
curr: TokenTreeCursor,
|
|
|
|
|
|
|
|
// Token streams surrounding the current one. The index within each cursor
|
|
|
|
// always points to a `TokenTree::Delimited`.
|
|
|
|
stack: Vec<TokenTreeCursor>,
|
2017-02-20 05:44:06 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
impl TokenCursor {
|
2023-07-25 23:17:32 +00:00
|
|
|
fn next(&mut self) -> (Token, Spacing) {
|
|
|
|
self.inlined_next()
|
2022-03-07 04:55:39 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
/// This always-inlined version should only be used on hot code paths.
|
|
|
|
#[inline(always)]
|
2023-07-25 23:17:32 +00:00
|
|
|
fn inlined_next(&mut self) -> (Token, Spacing) {
|
2022-04-19 07:01:26 +00:00
|
|
|
loop {
|
2023-07-31 01:10:25 +00:00
|
|
|
// FIXME: we currently don't return `Delimiter::Invisible` open/close delims. To fix
|
|
|
|
// #67062 we will need to, whereupon the `delim != Delimiter::Invisible` conditions
|
|
|
|
// below can be removed.
|
2024-12-10 08:18:44 +00:00
|
|
|
if let Some(tree) = self.curr.curr() {
|
2022-04-20 02:22:42 +00:00
|
|
|
match tree {
|
2023-07-25 23:17:32 +00:00
|
|
|
&TokenTree::Token(ref token, spacing) => {
|
2023-07-30 07:16:20 +00:00
|
|
|
debug_assert!(!matches!(
|
|
|
|
token.kind,
|
|
|
|
token::OpenDelim(_) | token::CloseDelim(_)
|
|
|
|
));
|
2024-12-10 08:18:44 +00:00
|
|
|
let res = (token.clone(), spacing);
|
|
|
|
self.curr.bump();
|
|
|
|
return res;
|
2023-07-25 23:17:32 +00:00
|
|
|
}
|
2023-10-12 04:36:14 +00:00
|
|
|
&TokenTree::Delimited(sp, spacing, delim, ref tts) => {
|
2024-12-10 08:18:44 +00:00
|
|
|
let trees = TokenTreeCursor::new(tts.clone());
|
|
|
|
self.stack.push(mem::replace(&mut self.curr, trees));
|
2024-04-16 23:59:27 +00:00
|
|
|
if !delim.skip() {
|
2023-10-12 04:36:14 +00:00
|
|
|
return (Token::new(token::OpenDelim(delim), sp.open), spacing.open);
|
2022-04-20 02:22:42 +00:00
|
|
|
}
|
2022-08-18 02:13:37 +00:00
|
|
|
// No open delimiter to return; continue on to the next iteration.
|
2022-04-19 03:41:02 +00:00
|
|
|
}
|
2022-04-19 07:01:26 +00:00
|
|
|
};
|
2024-12-10 08:18:44 +00:00
|
|
|
} else if let Some(parent) = self.stack.pop() {
|
2023-02-01 01:43:13 +00:00
|
|
|
// We have exhausted this token stream. Move back to its parent token stream.
|
2024-12-10 08:18:44 +00:00
|
|
|
let Some(&TokenTree::Delimited(span, spacing, delim, _)) = parent.curr() else {
|
|
|
|
panic!("parent should be Delimited")
|
|
|
|
};
|
|
|
|
self.curr = parent;
|
|
|
|
self.curr.bump(); // move past the `Delimited`
|
2024-04-16 23:59:27 +00:00
|
|
|
if !delim.skip() {
|
2023-10-12 04:36:14 +00:00
|
|
|
return (Token::new(token::CloseDelim(delim), span.close), spacing.close);
|
2022-04-21 02:26:58 +00:00
|
|
|
}
|
|
|
|
// No close delimiter to return; continue on to the next iteration.
|
2017-02-20 05:44:06 +00:00
|
|
|
} else {
|
2023-08-08 01:43:44 +00:00
|
|
|
// We have exhausted the outermost token stream. The use of
|
|
|
|
// `Spacing::Alone` is arbitrary and immaterial, because the
|
|
|
|
// `Eof` token's spacing is never used.
|
2022-04-19 03:41:02 +00:00
|
|
|
return (Token::new(token::Eof, DUMMY_SP), Spacing::Alone);
|
2017-02-20 05:44:06 +00:00
|
|
|
}
|
2022-04-19 07:01:26 +00:00
|
|
|
}
|
|
|
|
}
|
2017-02-20 05:44:06 +00:00
|
|
|
}
|
|
|
|
|
2019-10-08 10:59:59 +00:00
|
|
|
/// A sequence separator.
|
2024-05-05 19:44:40 +00:00
|
|
|
#[derive(Debug)]
|
2024-12-04 04:55:06 +00:00
|
|
|
struct SeqSep<'a> {
|
2019-10-08 10:59:59 +00:00
|
|
|
/// The separator token.
|
2024-12-04 04:55:06 +00:00
|
|
|
sep: Option<ExpTokenPair<'a>>,
|
2019-10-08 10:59:59 +00:00
|
|
|
/// `true` if a trailing separator is allowed.
|
|
|
|
trailing_sep_allowed: bool,
|
|
|
|
}
|
|
|
|
|
2024-12-04 04:55:06 +00:00
|
|
|
impl<'a> SeqSep<'a> {
|
|
|
|
fn trailing_allowed(sep: ExpTokenPair<'a>) -> SeqSep<'a> {
|
|
|
|
SeqSep { sep: Some(sep), trailing_sep_allowed: true }
|
2019-10-08 10:59:59 +00:00
|
|
|
}
|
|
|
|
|
2024-12-04 04:55:06 +00:00
|
|
|
fn none() -> SeqSep<'a> {
|
2019-12-22 22:42:04 +00:00
|
|
|
SeqSep { sep: None, trailing_sep_allowed: false }
|
2019-10-08 10:59:59 +00:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2024-05-05 19:44:40 +00:00
|
|
|
#[derive(Debug)]
|
2019-12-22 22:42:04 +00:00
|
|
|
pub enum FollowedByType {
|
|
|
|
Yes,
|
|
|
|
No,
|
|
|
|
}
|
2019-11-07 10:26:36 +00:00
|
|
|
|
2024-02-13 23:48:23 +00:00
|
|
|
#[derive(Copy, Clone, Debug)]
|
2024-06-03 05:47:46 +00:00
|
|
|
enum Trailing {
|
2024-02-13 23:48:23 +00:00
|
|
|
No,
|
|
|
|
Yes,
|
|
|
|
}
|
|
|
|
|
2024-08-06 00:17:46 +00:00
|
|
|
impl From<bool> for Trailing {
|
|
|
|
fn from(b: bool) -> Trailing {
|
|
|
|
if b { Trailing::Yes } else { Trailing::No }
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2024-05-05 19:44:40 +00:00
|
|
|
#[derive(Clone, Copy, Debug, PartialEq, Eq)]
|
2024-06-03 05:47:46 +00:00
|
|
|
pub(super) enum TokenDescription {
|
2022-09-04 08:14:00 +00:00
|
|
|
ReservedIdentifier,
|
|
|
|
Keyword,
|
|
|
|
ReservedKeyword,
|
|
|
|
DocComment,
|
2024-04-17 22:58:06 +00:00
|
|
|
|
|
|
|
// 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),
|
2022-09-04 08:14:00 +00:00
|
|
|
}
|
|
|
|
|
2022-09-22 16:39:17 +00:00
|
|
|
impl TokenDescription {
|
2024-06-03 05:47:46 +00:00
|
|
|
pub(super) fn from_token(token: &Token) -> Option<Self> {
|
2022-09-22 16:39:17 +00:00
|
|
|
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),
|
2024-04-17 22:58:06 +00:00
|
|
|
token::OpenDelim(Delimiter::Invisible(InvisibleOrigin::MetaVar(kind))) => {
|
|
|
|
Some(TokenDescription::MetaVar(kind))
|
|
|
|
}
|
2022-09-22 16:39:17 +00:00
|
|
|
_ => None,
|
|
|
|
}
|
|
|
|
}
|
2019-12-07 02:07:35 +00:00
|
|
|
}
|
|
|
|
|
2024-04-17 07:08:58 +00:00
|
|
|
pub fn token_descr(token: &Token) -> String {
|
2024-04-17 22:58:06 +00:00
|
|
|
let s = pprust::token_to_string(token).to_string();
|
|
|
|
|
|
|
|
match (TokenDescription::from_token(token), &token.kind) {
|
|
|
|
(Some(TokenDescription::ReservedIdentifier), _) => format!("reserved identifier `{s}`"),
|
|
|
|
(Some(TokenDescription::Keyword), _) => format!("keyword `{s}`"),
|
|
|
|
(Some(TokenDescription::ReservedKeyword), _) => format!("reserved keyword `{s}`"),
|
|
|
|
(Some(TokenDescription::DocComment), _) => format!("doc comment `{s}`"),
|
|
|
|
// Deliberately doesn't print `s`, which is empty.
|
|
|
|
(Some(TokenDescription::MetaVar(kind)), _) => format!("`{kind}` metavariable"),
|
|
|
|
(None, TokenKind::NtIdent(..)) => format!("identifier `{s}`"),
|
|
|
|
(None, TokenKind::NtLifetime(..)) => format!("lifetime `{s}`"),
|
|
|
|
(None, TokenKind::Interpolated(node)) => format!("{} `{s}`", node.descr()),
|
|
|
|
(None, _) => format!("`{s}`"),
|
|
|
|
}
|
2019-12-07 02:07:35 +00:00
|
|
|
}
|
|
|
|
|
2014-03-09 14:54:34 +00:00
|
|
|
impl<'a> Parser<'a> {
|
2019-10-16 08:59:30 +00:00
|
|
|
pub fn new(
|
2024-03-04 05:31:49 +00:00
|
|
|
psess: &'a ParseSess,
|
2023-07-31 02:49:01 +00:00
|
|
|
stream: TokenStream,
|
2019-05-22 05:17:53 +00:00
|
|
|
subparser_name: Option<&'static str>,
|
2019-05-22 00:47:23 +00:00
|
|
|
) -> Self {
|
2016-11-03 07:43:29 +00:00
|
|
|
let mut parser = Parser {
|
2024-03-04 05:31:49 +00:00
|
|
|
psess,
|
2019-06-05 06:39:34 +00:00
|
|
|
token: Token::dummy(),
|
Rewrite `collect_tokens` implementations to use a flattened buffer
Instead of trying to collect tokens at each depth, we 'flatten' the
stream as we go allong, pushing open/close delimiters to our buffer
just like regular tokens. One capturing is complete, we reconstruct a
nested `TokenTree::Delimited` structure, producing a normal
`TokenStream`.
The reconstructed `TokenStream` is not created immediately - instead, it is
produced on-demand by a closure (wrapped in a new `LazyTokenStream` type). This
closure stores a clone of the original `TokenCursor`, plus a record of the
number of calls to `next()/next_desugared()`. This is sufficient to reconstruct
the tokenstream seen by the callback without storing any additional state. If
the tokenstream is never used (e.g. when a captured `macro_rules!` argument is
never passed to a proc macro), we never actually create a `TokenStream`.
This implementation has a number of advantages over the previous one:
* It is significantly simpler, with no edge cases around capturing the
start/end of a delimited group.
* It can be easily extended to allow replacing tokens an an arbitrary
'depth' by just using `Vec::splice` at the proper position. This is
important for PR #76130, which requires us to track information about
attributes along with tokens.
* The lazy approach to `TokenStream` construction allows us to easily
parse an AST struct, and then decide after the fact whether we need a
`TokenStream`. This will be useful when we start collecting tokens for
`Attribute` - we can discard the `LazyTokenStream` if the parsed
attribute doesn't need tokens (e.g. is a builtin attribute).
The performance impact seems to be neglibile (see
https://github.com/rust-lang/rust/pull/77250#issuecomment-703960604). There is a
small slowdown on a few benchmarks, but it only rises above 1% for incremental
builds, where it represents a larger fraction of the much smaller instruction
count. There a ~1% speedup on a few other incremental benchmarks - my guess is
that the speedups and slowdowns will usually cancel out in practice.
2020-09-27 01:56:29 +00:00
|
|
|
token_spacing: Spacing::Alone,
|
2020-02-09 14:54:38 +00:00
|
|
|
prev_token: Token::dummy(),
|
2020-11-28 23:33:17 +00:00
|
|
|
capture_cfg: false,
|
2015-04-29 21:58:43 +00:00
|
|
|
restrictions: Restrictions::empty(),
|
2024-12-04 04:55:06 +00:00
|
|
|
expected_token_types: TokenTypeSet::new(),
|
2024-12-10 08:18:44 +00:00
|
|
|
token_cursor: TokenCursor { curr: TokenTreeCursor::new(stream), stack: Vec::new() },
|
2023-07-31 06:15:54 +00:00
|
|
|
num_bump_calls: 0,
|
2024-09-19 09:32:17 +00:00
|
|
|
break_last_token: 0,
|
2019-01-23 01:35:13 +00:00
|
|
|
unmatched_angle_bracket_count: 0,
|
2023-10-24 22:22:52 +00:00
|
|
|
angle_bracket_nesting: 0,
|
2019-03-02 05:47:06 +00:00
|
|
|
last_unexpected_token_span: None,
|
2019-05-22 05:17:53 +00:00
|
|
|
subparser_name,
|
2020-11-28 23:33:17 +00:00
|
|
|
capture_state: CaptureState {
|
|
|
|
capturing: Capturing::No,
|
2024-07-31 20:44:39 +00:00
|
|
|
parser_replacements: Vec::new(),
|
|
|
|
inner_attr_parser_ranges: Default::default(),
|
2024-08-21 04:16:42 +00:00
|
|
|
seen_attrs: IntervalSet::new(u32::MAX as usize),
|
2020-11-28 23:33:17 +00:00
|
|
|
},
|
2021-08-16 13:22:36 +00:00
|
|
|
current_closure: None,
|
2022-10-25 19:24:01 +00:00
|
|
|
recovery: Recovery::Allowed,
|
2016-11-03 07:43:29 +00:00
|
|
|
};
|
|
|
|
|
2020-02-16 13:47:24 +00:00
|
|
|
// Make parser point to the first token.
|
|
|
|
parser.bump();
|
2017-05-17 22:37:24 +00:00
|
|
|
|
2024-07-17 07:59:05 +00:00
|
|
|
// Change this from 1 back to 0 after the bump. This eases debugging of
|
2024-08-06 07:16:40 +00:00
|
|
|
// `Parser::collect_tokens` because 0-indexed token positions are nicer
|
|
|
|
// than 1-indexed token positions.
|
2024-07-17 07:59:05 +00:00
|
|
|
parser.num_bump_calls = 0;
|
|
|
|
|
2016-11-03 07:43:29 +00:00
|
|
|
parser
|
|
|
|
}
|
|
|
|
|
2024-03-19 05:33:53 +00:00
|
|
|
#[inline]
|
2022-11-12 21:12:33 +00:00
|
|
|
pub fn recovery(mut self, recovery: Recovery) -> Self {
|
|
|
|
self.recovery = recovery;
|
2022-10-25 19:24:01 +00:00
|
|
|
self
|
|
|
|
}
|
|
|
|
|
2022-10-26 19:09:28 +00:00
|
|
|
/// 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.
|
|
|
|
///
|
2022-10-26 20:06:35 +00:00
|
|
|
/// Technically, this only needs to restrict eager recovery by doing lookahead at more tokens.
|
2022-10-26 19:09:28 +00:00
|
|
|
/// But making the distinction is very subtle, and simply forbidding all recovery is a lot simpler to uphold.
|
2024-03-19 05:33:53 +00:00
|
|
|
#[inline]
|
2022-10-25 19:24:01 +00:00
|
|
|
fn may_recover(&self) -> bool {
|
|
|
|
matches!(self.recovery, Recovery::Allowed)
|
|
|
|
}
|
|
|
|
|
2024-03-15 11:36:21 +00:00
|
|
|
/// Version of [`unexpected`](Parser::unexpected) that "returns" any type in the `Ok`
|
|
|
|
/// (both those functions never return "Ok", and so can lie like that in the type).
|
|
|
|
pub fn unexpected_any<T>(&mut self) -> PResult<'a, T> {
|
2015-03-28 21:58:51 +00:00
|
|
|
match self.expect_one_of(&[], &[]) {
|
2015-12-30 23:11:53 +00:00
|
|
|
Err(e) => Err(e),
|
2019-11-13 11:05:37 +00:00
|
|
|
// We can get `Ok(true)` from `recover_closing_delimiter`
|
|
|
|
// which is called in `expected_one_of_not_found`.
|
|
|
|
Ok(_) => FatalError.raise(),
|
2015-03-28 21:58:51 +00:00
|
|
|
}
|
2013-06-15 01:21:47 +00:00
|
|
|
}
|
|
|
|
|
2024-03-15 11:36:21 +00:00
|
|
|
pub fn unexpected(&mut self) -> PResult<'a, ()> {
|
|
|
|
self.unexpected_any()
|
|
|
|
}
|
|
|
|
|
2019-02-08 13:53:55 +00:00
|
|
|
/// Expects and consumes the token `t`. Signals an error if the next token is not `t`.
|
2024-12-04 04:55:06 +00:00
|
|
|
pub fn expect(&mut self, exp: ExpTokenPair<'_>) -> PResult<'a, Recovered> {
|
2024-12-03 09:09:29 +00:00
|
|
|
if self.expected_token_types.is_empty() {
|
2024-12-04 04:55:06 +00:00
|
|
|
if self.token == *exp.tok {
|
2015-12-30 23:11:53 +00:00
|
|
|
self.bump();
|
2024-02-13 23:44:33 +00:00
|
|
|
Ok(Recovered::No)
|
Make the parser’s ‘expected <foo>, found <bar>’ errors more accurate
As an example of what this changes, the following code:
let x: [int ..4];
Currently spits out ‘expected `]`, found `..`’. However, a comma would also be
valid there, as would a number of other tokens. This change adjusts the parser
to produce more accurate errors, so that that example now produces ‘expected one
of `(`, `+`, `,`, `::`, or `]`, found `..`’.
2014-12-03 09:47:53 +00:00
|
|
|
} else {
|
2024-12-04 04:55:06 +00:00
|
|
|
self.unexpected_try_recover(exp.tok)
|
Make the parser’s ‘expected <foo>, found <bar>’ errors more accurate
As an example of what this changes, the following code:
let x: [int ..4];
Currently spits out ‘expected `]`, found `..`’. However, a comma would also be
valid there, as would a number of other tokens. This change adjusts the parser
to produce more accurate errors, so that that example now produces ‘expected one
of `(`, `+`, `,`, `::`, or `]`, found `..`’.
2014-12-03 09:47:53 +00:00
|
|
|
}
|
2013-06-15 01:21:47 +00:00
|
|
|
} else {
|
2024-12-04 04:55:06 +00:00
|
|
|
self.expect_one_of(slice::from_ref(&exp), &[])
|
2013-06-15 01:21:47 +00:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2022-11-16 20:34:16 +00:00
|
|
|
/// Expect next token to be edible or inedible token. If edible,
|
2014-06-09 20:12:30 +00:00
|
|
|
/// then consume it; if inedible, then return without consuming
|
2022-11-16 20:34:16 +00:00
|
|
|
/// anything. Signal a fatal error if next token is unexpected.
|
2024-06-03 05:47:46 +00:00
|
|
|
fn expect_one_of(
|
2019-01-28 05:04:50 +00:00
|
|
|
&mut self,
|
2024-12-04 04:55:06 +00:00
|
|
|
edible: &[ExpTokenPair<'_>],
|
|
|
|
inedible: &[ExpTokenPair<'_>],
|
2024-02-13 23:44:33 +00:00
|
|
|
) -> PResult<'a, Recovered> {
|
2024-12-04 04:55:06 +00:00
|
|
|
if edible.iter().any(|exp| exp.tok == &self.token.kind) {
|
2015-12-30 23:11:53 +00:00
|
|
|
self.bump();
|
2024-02-13 23:44:33 +00:00
|
|
|
Ok(Recovered::No)
|
2024-12-04 04:55:06 +00:00
|
|
|
} else if inedible.iter().any(|exp| exp.tok == &self.token.kind) {
|
2013-08-05 20:18:29 +00:00
|
|
|
// leave it in the input
|
2024-02-13 23:44:33 +00:00
|
|
|
Ok(Recovered::No)
|
2024-08-09 07:44:47 +00:00
|
|
|
} else if self.token != token::Eof
|
2023-05-04 08:30:02 +00:00
|
|
|
&& self.last_unexpected_token_span == Some(self.token.span)
|
|
|
|
{
|
2019-03-02 05:47:06 +00:00
|
|
|
FatalError.raise();
|
2013-08-05 20:18:29 +00:00
|
|
|
} else {
|
2019-05-23 20:10:24 +00:00
|
|
|
self.expected_one_of_not_found(edible, inedible)
|
2024-07-04 23:19:15 +00:00
|
|
|
.map(|error_guaranteed| Recovered::Yes(error_guaranteed))
|
2013-08-05 20:18:29 +00:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2020-01-11 19:19:57 +00:00
|
|
|
// Public for rustfmt usage.
|
2020-04-19 11:00:18 +00:00
|
|
|
pub fn parse_ident(&mut self) -> PResult<'a, Ident> {
|
2018-01-06 22:43:20 +00:00
|
|
|
self.parse_ident_common(true)
|
|
|
|
}
|
|
|
|
|
2020-04-19 11:00:18 +00:00
|
|
|
fn parse_ident_common(&mut self, recover: bool) -> PResult<'a, Ident> {
|
2023-03-17 08:35:43 +00:00
|
|
|
let (ident, is_raw) = self.ident_or_err(recover)?;
|
2023-03-17 09:27:17 +00:00
|
|
|
|
2024-02-13 23:28:27 +00:00
|
|
|
if matches!(is_raw, IdentIsRaw::No) && ident.is_reserved() {
|
Make `DiagnosticBuilder::emit` consuming.
This works for most of its call sites. This is nice, because `emit` very
much makes sense as a consuming operation -- indeed,
`DiagnosticBuilderState` exists to ensure no diagnostic is emitted
twice, but it uses runtime checks.
For the small number of call sites where a consuming emit doesn't work,
the commit adds `DiagnosticBuilder::emit_without_consuming`. (This will
be removed in subsequent commits.)
Likewise, `emit_unless` becomes consuming. And `delay_as_bug` becomes
consuming, while `delay_as_bug_without_consuming` is added (which will
also be removed in subsequent commits.)
All this requires significant changes to `DiagnosticBuilder`'s chaining
methods. Currently `DiagnosticBuilder` method chaining uses a
non-consuming `&mut self -> &mut Self` style, which allows chaining to
be used when the chain ends in `emit()`, like so:
```
struct_err(msg).span(span).emit();
```
But it doesn't work when producing a `DiagnosticBuilder` value,
requiring this:
```
let mut err = self.struct_err(msg);
err.span(span);
err
```
This style of chaining won't work with consuming `emit` though. For
that, we need to use to a `self -> Self` style. That also would allow
`DiagnosticBuilder` production to be chained, e.g.:
```
self.struct_err(msg).span(span)
```
However, removing the `&mut self -> &mut Self` style would require that
individual modifications of a `DiagnosticBuilder` go from this:
```
err.span(span);
```
to this:
```
err = err.span(span);
```
There are *many* such places. I have a high tolerance for tedious
refactorings, but even I gave up after a long time trying to convert
them all.
Instead, this commit has it both ways: the existing `&mut self -> Self`
chaining methods are kept, and new `self -> Self` chaining methods are
added, all of which have a `_mv` suffix (short for "move"). Changes to
the existing `forward!` macro lets this happen with very little
additional boilerplate code. I chose to add the suffix to the new
chaining methods rather than the existing ones, because the number of
changes required is much smaller that way.
This doubled chainging is a bit clumsy, but I think it is worthwhile
because it allows a *lot* of good things to subsequently happen. In this
commit, there are many `mut` qualifiers removed in places where
diagnostics are emitted without being modified. In subsequent commits:
- chaining can be used more, making the code more concise;
- more use of chaining also permits the removal of redundant diagnostic
APIs like `struct_err_with_code`, which can be replaced easily with
`struct_err` + `code_mv`;
- `emit_without_diagnostic` can be removed, which simplifies a lot of
machinery, removing the need for `DiagnosticBuilderState`.
2024-01-03 01:17:35 +00:00
|
|
|
let err = self.expected_ident_found_err();
|
2020-09-16 21:10:05 +00:00
|
|
|
if recover {
|
|
|
|
err.emit();
|
|
|
|
} else {
|
|
|
|
return Err(err);
|
2013-06-15 01:21:47 +00:00
|
|
|
}
|
|
|
|
}
|
2020-09-16 21:10:05 +00:00
|
|
|
self.bump();
|
|
|
|
Ok(ident)
|
2013-06-15 01:21:47 +00:00
|
|
|
}
|
|
|
|
|
2024-02-13 23:28:27 +00:00
|
|
|
fn ident_or_err(&mut self, recover: bool) -> PResult<'a, (Ident, IdentIsRaw)> {
|
2023-12-27 20:16:29 +00:00
|
|
|
match self.token.ident() {
|
|
|
|
Some(ident) => Ok(ident),
|
|
|
|
None => self.expected_ident_found(recover),
|
|
|
|
}
|
2023-03-17 08:35:43 +00:00
|
|
|
}
|
|
|
|
|
2019-02-08 13:53:55 +00:00
|
|
|
/// Checks if the next token is `tok`, and returns `true` if so.
|
Make the parser’s ‘expected <foo>, found <bar>’ errors more accurate
As an example of what this changes, the following code:
let x: [int ..4];
Currently spits out ‘expected `]`, found `..`’. However, a comma would also be
valid there, as would a number of other tokens. This change adjusts the parser
to produce more accurate errors, so that that example now produces ‘expected one
of `(`, `+`, `,`, `::`, or `]`, found `..`’.
2014-12-03 09:47:53 +00:00
|
|
|
///
|
2024-12-03 09:09:29 +00:00
|
|
|
/// This method will automatically add `tok` to `expected_token_types` if `tok` is not
|
Make the parser’s ‘expected <foo>, found <bar>’ errors more accurate
As an example of what this changes, the following code:
let x: [int ..4];
Currently spits out ‘expected `]`, found `..`’. However, a comma would also be
valid there, as would a number of other tokens. This change adjusts the parser
to produce more accurate errors, so that that example now produces ‘expected one
of `(`, `+`, `,`, `::`, or `]`, found `..`’.
2014-12-03 09:47:53 +00:00
|
|
|
/// encountered.
|
2024-03-19 05:33:53 +00:00
|
|
|
#[inline]
|
2024-12-04 04:55:06 +00:00
|
|
|
fn check(&mut self, exp: ExpTokenPair<'_>) -> bool {
|
|
|
|
let is_present = self.token == *exp.tok;
|
2019-12-22 22:42:04 +00:00
|
|
|
if !is_present {
|
2024-12-04 04:55:06 +00:00
|
|
|
self.expected_token_types.insert(exp.token_type);
|
2019-12-22 22:42:04 +00:00
|
|
|
}
|
Make the parser’s ‘expected <foo>, found <bar>’ errors more accurate
As an example of what this changes, the following code:
let x: [int ..4];
Currently spits out ‘expected `]`, found `..`’. However, a comma would also be
valid there, as would a number of other tokens. This change adjusts the parser
to produce more accurate errors, so that that example now produces ‘expected one
of `(`, `+`, `,`, `::`, or `]`, found `..`’.
2014-12-03 09:47:53 +00:00
|
|
|
is_present
|
|
|
|
}
|
|
|
|
|
2024-03-19 05:33:53 +00:00
|
|
|
#[inline]
|
2024-07-30 01:21:15 +00:00
|
|
|
#[must_use]
|
2022-05-01 17:05:35 +00:00
|
|
|
fn check_noexpect(&self, tok: &TokenKind) -> bool {
|
|
|
|
self.token == *tok
|
|
|
|
}
|
|
|
|
|
2024-04-17 03:17:44 +00:00
|
|
|
// Check the first token after the delimiter that closes the current
|
|
|
|
// delimited sequence. (Panics if used in the outermost token stream, which
|
|
|
|
// has no delimiters.) It uses a clone of the relevant tree cursor to skip
|
|
|
|
// past the entire `TokenTree::Delimited` in a single step, avoiding the
|
|
|
|
// need for unbounded token lookahead.
|
|
|
|
//
|
|
|
|
// Primarily used when `self.token` matches
|
|
|
|
// `OpenDelim(Delimiter::Invisible(_))`, to look ahead through the current
|
|
|
|
// metavar expansion.
|
|
|
|
fn check_noexpect_past_close_delim(&self, tok: &TokenKind) -> bool {
|
|
|
|
let mut tree_cursor = self.token_cursor.stack.last().unwrap().clone();
|
|
|
|
tree_cursor.bump();
|
|
|
|
matches!(
|
|
|
|
tree_cursor.curr(),
|
|
|
|
Some(TokenTree::Token(token::Token { kind, .. }, _)) if kind == tok
|
|
|
|
)
|
|
|
|
}
|
|
|
|
|
2022-05-01 17:05:35 +00:00
|
|
|
/// Consumes a token 'tok' if it exists. Returns whether the given token was present.
|
|
|
|
///
|
|
|
|
/// the main purpose of this function is to reduce the cluttering of the suggestions list
|
|
|
|
/// which using the normal eat method could introduce in some cases.
|
2024-03-19 05:33:53 +00:00
|
|
|
#[inline]
|
2024-07-30 01:21:15 +00:00
|
|
|
#[must_use]
|
2024-06-03 05:47:46 +00:00
|
|
|
fn eat_noexpect(&mut self, tok: &TokenKind) -> bool {
|
2022-05-01 17:05:35 +00:00
|
|
|
let is_present = self.check_noexpect(tok);
|
|
|
|
if is_present {
|
|
|
|
self.bump()
|
|
|
|
}
|
|
|
|
is_present
|
|
|
|
}
|
|
|
|
|
2019-02-08 13:53:55 +00:00
|
|
|
/// Consumes a token 'tok' if it exists. Returns whether the given token was present.
|
2024-03-19 05:33:53 +00:00
|
|
|
#[inline]
|
2024-07-30 01:21:15 +00:00
|
|
|
#[must_use]
|
2024-12-04 04:55:06 +00:00
|
|
|
pub fn eat(&mut self, exp: ExpTokenPair<'_>) -> bool {
|
|
|
|
let is_present = self.check(exp);
|
2019-12-22 22:42:04 +00:00
|
|
|
if is_present {
|
|
|
|
self.bump()
|
|
|
|
}
|
2015-12-30 23:11:53 +00:00
|
|
|
is_present
|
2013-06-15 01:21:47 +00:00
|
|
|
}
|
|
|
|
|
2019-10-01 03:13:42 +00:00
|
|
|
/// If the next token is the given keyword, returns `true` without eating it.
|
|
|
|
/// An expectation is also added for diagnostics purposes.
|
2024-03-19 05:33:53 +00:00
|
|
|
#[inline]
|
2024-07-30 01:21:15 +00:00
|
|
|
#[must_use]
|
2024-12-04 04:55:06 +00:00
|
|
|
fn check_keyword(&mut self, exp: ExpKeywordPair) -> bool {
|
|
|
|
let is_keyword = self.token.is_keyword(exp.kw);
|
2024-12-04 04:36:49 +00:00
|
|
|
if !is_keyword {
|
2024-12-04 04:55:06 +00:00
|
|
|
self.expected_token_types.insert(exp.token_type);
|
2024-12-04 04:36:49 +00:00
|
|
|
}
|
|
|
|
is_keyword
|
2015-01-16 03:04:28 +00:00
|
|
|
}
|
|
|
|
|
2024-03-19 05:33:53 +00:00
|
|
|
#[inline]
|
2024-07-30 01:21:15 +00:00
|
|
|
#[must_use]
|
2024-12-04 04:55:06 +00:00
|
|
|
fn check_keyword_case(&mut self, exp: ExpKeywordPair, case: Case) -> bool {
|
|
|
|
if self.check_keyword(exp) {
|
2024-12-04 04:36:49 +00:00
|
|
|
true
|
|
|
|
} else if case == Case::Insensitive
|
2024-02-13 23:28:27 +00:00
|
|
|
&& let Some((ident, IdentIsRaw::No)) = self.token.ident()
|
2025-01-11 17:11:42 +00:00
|
|
|
// Do an ASCII case-insensitive match, because all keywords are ASCII.
|
2024-12-04 04:55:06 +00:00
|
|
|
&& ident.as_str().eq_ignore_ascii_case(exp.kw.as_str())
|
2023-10-13 08:58:33 +00:00
|
|
|
{
|
2022-09-13 18:48:29 +00:00
|
|
|
true
|
|
|
|
} else {
|
|
|
|
false
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2019-10-01 03:13:42 +00:00
|
|
|
/// If the next token is the given keyword, eats it and returns `true`.
|
|
|
|
/// Otherwise, returns `false`. An expectation is also added for diagnostics purposes.
|
2024-07-25 08:05:31 +00:00
|
|
|
// Public for rustc_builtin_macros and rustfmt usage.
|
2024-03-19 05:33:53 +00:00
|
|
|
#[inline]
|
2024-07-30 01:21:15 +00:00
|
|
|
#[must_use]
|
2024-12-04 04:55:06 +00:00
|
|
|
pub fn eat_keyword(&mut self, exp: ExpKeywordPair) -> bool {
|
|
|
|
let is_keyword = self.check_keyword(exp);
|
2024-12-04 04:36:49 +00:00
|
|
|
if is_keyword {
|
2015-12-30 23:11:53 +00:00
|
|
|
self.bump();
|
2015-01-16 03:04:28 +00:00
|
|
|
}
|
2024-12-04 04:36:49 +00:00
|
|
|
is_keyword
|
2015-01-16 03:04:28 +00:00
|
|
|
}
|
|
|
|
|
2022-07-29 19:06:13 +00:00
|
|
|
/// Eats a keyword, optionally ignoring the case.
|
|
|
|
/// If the case differs (and is ignored) an error is issued.
|
|
|
|
/// This is useful for recovery.
|
2024-03-19 05:33:53 +00:00
|
|
|
#[inline]
|
2024-07-30 01:21:15 +00:00
|
|
|
#[must_use]
|
2024-12-04 04:55:06 +00:00
|
|
|
fn eat_keyword_case(&mut self, exp: ExpKeywordPair, case: Case) -> bool {
|
|
|
|
if self.eat_keyword(exp) {
|
2024-12-04 04:36:49 +00:00
|
|
|
true
|
|
|
|
} else if case == Case::Insensitive
|
2024-02-13 23:28:27 +00:00
|
|
|
&& let Some((ident, IdentIsRaw::No)) = self.token.ident()
|
2025-01-11 17:11:42 +00:00
|
|
|
// Do an ASCII case-insensitive match, because all keywords are ASCII.
|
|
|
|
&& ident.as_str().eq_ignore_ascii_case(exp.kw.as_str())
|
2023-10-13 08:58:33 +00:00
|
|
|
{
|
2024-12-04 04:55:06 +00:00
|
|
|
self.dcx().emit_err(errors::KwBadCase { span: ident.span, kw: exp.kw.as_str() });
|
2022-07-29 19:06:13 +00:00
|
|
|
self.bump();
|
2024-12-04 04:36:49 +00:00
|
|
|
true
|
|
|
|
} else {
|
|
|
|
false
|
2022-07-29 19:06:13 +00:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2024-07-25 08:05:31 +00:00
|
|
|
/// If the next token is the given keyword, eats it and returns `true`.
|
|
|
|
/// Otherwise, returns `false`. No expectation is added.
|
|
|
|
// Public for rustc_builtin_macros usage.
|
2024-03-19 05:33:53 +00:00
|
|
|
#[inline]
|
2024-07-30 01:21:15 +00:00
|
|
|
#[must_use]
|
2024-07-25 08:05:31 +00:00
|
|
|
pub fn eat_keyword_noexpect(&mut self, kw: Symbol) -> bool {
|
2024-12-04 04:36:49 +00:00
|
|
|
let is_keyword = self.token.is_keyword(kw);
|
|
|
|
if is_keyword {
|
2015-12-30 23:11:53 +00:00
|
|
|
self.bump();
|
2014-08-28 04:34:03 +00:00
|
|
|
}
|
2024-12-04 04:36:49 +00:00
|
|
|
is_keyword
|
2013-06-15 01:21:47 +00:00
|
|
|
}
|
|
|
|
|
2019-02-08 13:53:55 +00:00
|
|
|
/// If the given word is not a keyword, signals an error.
|
|
|
|
/// If the next token is not the given word, signals an error.
|
|
|
|
/// Otherwise, eats it.
|
2024-12-04 04:55:06 +00:00
|
|
|
pub fn expect_keyword(&mut self, exp: ExpKeywordPair) -> PResult<'a, ()> {
|
|
|
|
if !self.eat_keyword(exp) { self.unexpected() } else { Ok(()) }
|
2013-06-15 01:21:47 +00:00
|
|
|
}
|
|
|
|
|
2024-04-17 02:17:09 +00:00
|
|
|
/// Consume a sequence produced by a metavar expansion, if present.
|
|
|
|
fn eat_metavar_seq<T>(
|
|
|
|
&mut self,
|
|
|
|
mv_kind: MetaVarKind,
|
|
|
|
f: impl FnMut(&mut Parser<'a>) -> PResult<'a, T>,
|
|
|
|
) -> Option<T> {
|
|
|
|
self.eat_metavar_seq_with_matcher(|mvk| mvk == mv_kind, f)
|
|
|
|
}
|
|
|
|
|
|
|
|
/// A slightly more general form of `eat_metavar_seq`, for use with the
|
|
|
|
/// `MetaVarKind` variants that have parameters, where an exact match isn't
|
|
|
|
/// desired.
|
|
|
|
fn eat_metavar_seq_with_matcher<T>(
|
|
|
|
&mut self,
|
|
|
|
match_mv_kind: impl Fn(MetaVarKind) -> bool,
|
|
|
|
mut f: impl FnMut(&mut Parser<'a>) -> PResult<'a, T>,
|
|
|
|
) -> Option<T> {
|
|
|
|
if let token::OpenDelim(delim) = self.token.kind
|
|
|
|
&& let Delimiter::Invisible(InvisibleOrigin::MetaVar(mv_kind)) = delim
|
|
|
|
&& match_mv_kind(mv_kind)
|
|
|
|
{
|
|
|
|
self.bump();
|
|
|
|
let res = f(self).expect("failed to reparse {mv_kind:?}");
|
|
|
|
if let token::CloseDelim(delim) = self.token.kind
|
|
|
|
&& let Delimiter::Invisible(InvisibleOrigin::MetaVar(mv_kind)) = delim
|
|
|
|
&& match_mv_kind(mv_kind)
|
|
|
|
{
|
|
|
|
self.bump();
|
|
|
|
Some(res)
|
|
|
|
} else {
|
|
|
|
panic!("no close delim when reparsing {mv_kind:?}");
|
|
|
|
}
|
|
|
|
} else {
|
|
|
|
None
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2020-02-01 05:18:10 +00:00
|
|
|
/// Is the given keyword `kw` followed by a non-reserved identifier?
|
|
|
|
fn is_kw_followed_by_ident(&self, kw: Symbol) -> bool {
|
|
|
|
self.token.is_keyword(kw) && self.look_ahead(1, |t| t.is_ident() && !t.is_reserved_ident())
|
|
|
|
}
|
|
|
|
|
2024-03-19 05:33:53 +00:00
|
|
|
#[inline]
|
2024-12-04 04:55:06 +00:00
|
|
|
fn check_or_expected(&mut self, ok: bool, token_type: TokenType) -> bool {
|
2024-12-04 04:36:49 +00:00
|
|
|
if !ok {
|
2024-12-04 04:55:06 +00:00
|
|
|
self.expected_token_types.insert(token_type);
|
2017-01-18 16:01:04 +00:00
|
|
|
}
|
2024-12-04 04:36:49 +00:00
|
|
|
ok
|
2017-01-18 16:01:04 +00:00
|
|
|
}
|
|
|
|
|
2019-10-08 07:35:34 +00:00
|
|
|
fn check_ident(&mut self) -> bool {
|
2019-10-01 03:55:28 +00:00
|
|
|
self.check_or_expected(self.token.is_ident(), TokenType::Ident)
|
2019-09-30 04:21:30 +00:00
|
|
|
}
|
|
|
|
|
2017-01-18 16:01:04 +00:00
|
|
|
fn check_path(&mut self) -> bool {
|
2019-10-01 03:55:28 +00:00
|
|
|
self.check_or_expected(self.token.is_path_start(), TokenType::Path)
|
2017-01-18 16:01:04 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
fn check_type(&mut self) -> bool {
|
2019-10-01 03:55:28 +00:00
|
|
|
self.check_or_expected(self.token.can_begin_type(), TokenType::Type)
|
2017-01-18 16:01:04 +00:00
|
|
|
}
|
|
|
|
|
2019-02-05 15:49:38 +00:00
|
|
|
fn check_const_arg(&mut self) -> bool {
|
2019-10-01 03:55:28 +00:00
|
|
|
self.check_or_expected(self.token.can_begin_const_arg(), TokenType::Const)
|
2019-09-30 04:21:30 +00:00
|
|
|
}
|
|
|
|
|
2022-12-20 16:15:55 +00:00
|
|
|
fn check_const_closure(&self) -> bool {
|
|
|
|
self.is_keyword_ahead(0, &[kw::Const])
|
|
|
|
&& self.look_ahead(1, |t| match &t.kind {
|
2023-02-01 05:55:48 +00:00
|
|
|
// async closures do not work with const closures, so we do not parse that here.
|
2025-02-16 15:20:53 +00:00
|
|
|
token::Ident(kw::Move | kw::Static, IdentIsRaw::No)
|
|
|
|
| token::OrOr
|
|
|
|
| token::BinOp(token::Or) => true,
|
2022-12-20 16:15:55 +00:00
|
|
|
_ => false,
|
|
|
|
})
|
|
|
|
}
|
|
|
|
|
2020-10-19 21:44:37 +00:00
|
|
|
fn check_inline_const(&self, dist: usize) -> bool {
|
|
|
|
self.is_keyword_ahead(dist, &[kw::Const])
|
2022-11-22 09:42:01 +00:00
|
|
|
&& self.look_ahead(dist + 1, |t| match &t.kind {
|
2024-04-22 06:29:27 +00:00
|
|
|
token::Interpolated(nt) => matches!(&**nt, token::NtBlock(..)),
|
2022-04-26 12:40:14 +00:00
|
|
|
token::OpenDelim(Delimiter::Brace) => true,
|
2020-10-19 19:57:04 +00:00
|
|
|
_ => false,
|
|
|
|
})
|
2020-09-21 20:55:58 +00:00
|
|
|
}
|
|
|
|
|
2019-09-30 04:21:30 +00:00
|
|
|
/// Checks to see if the next token is either `+` or `+=`.
|
|
|
|
/// Otherwise returns `false`.
|
2024-03-19 05:33:53 +00:00
|
|
|
#[inline]
|
2019-09-30 04:21:30 +00:00
|
|
|
fn check_plus(&mut self) -> bool {
|
2024-12-04 04:55:06 +00:00
|
|
|
self.check_or_expected(self.token.is_like_plus(), TokenType::Plus)
|
2019-02-05 15:49:38 +00:00
|
|
|
}
|
|
|
|
|
2020-02-22 13:22:38 +00:00
|
|
|
/// Eats the expected token if it's present possibly breaking
|
|
|
|
/// compound tokens like multi-character operators in process.
|
|
|
|
/// Returns `true` if the token was eaten.
|
2024-12-04 04:55:06 +00:00
|
|
|
fn break_and_eat(&mut self, exp: ExpTokenPair<'_>) -> bool {
|
|
|
|
if self.token == *exp.tok {
|
2020-02-22 13:22:38 +00:00
|
|
|
self.bump();
|
|
|
|
return true;
|
|
|
|
}
|
2024-09-19 09:32:17 +00:00
|
|
|
match self.token.kind.break_two_token_op(1) {
|
2024-12-04 04:55:06 +00:00
|
|
|
Some((first, second)) if first == *exp.tok => {
|
2024-03-04 05:31:49 +00:00
|
|
|
let first_span = self.psess.source_map().start_point(self.token.span);
|
2020-02-22 13:22:38 +00:00
|
|
|
let second_span = self.token.span.with_lo(first_span.hi());
|
2020-03-07 13:34:29 +00:00
|
|
|
self.token = Token::new(first, first_span);
|
2020-12-12 20:20:22 +00:00
|
|
|
// Keep track of this token - if we end token capturing now,
|
|
|
|
// we'll want to append this token to the captured stream.
|
|
|
|
//
|
|
|
|
// If we consume any additional tokens, then this token
|
|
|
|
// is not needed (we'll capture the entire 'glued' token),
|
2024-09-19 09:32:17 +00:00
|
|
|
// and `bump` will set this field to 0.
|
|
|
|
self.break_last_token += 1;
|
2023-08-08 01:43:44 +00:00
|
|
|
// Use the spacing of the glued token as the spacing of the
|
|
|
|
// unglued second token.
|
Rewrite `collect_tokens` implementations to use a flattened buffer
Instead of trying to collect tokens at each depth, we 'flatten' the
stream as we go allong, pushing open/close delimiters to our buffer
just like regular tokens. One capturing is complete, we reconstruct a
nested `TokenTree::Delimited` structure, producing a normal
`TokenStream`.
The reconstructed `TokenStream` is not created immediately - instead, it is
produced on-demand by a closure (wrapped in a new `LazyTokenStream` type). This
closure stores a clone of the original `TokenCursor`, plus a record of the
number of calls to `next()/next_desugared()`. This is sufficient to reconstruct
the tokenstream seen by the callback without storing any additional state. If
the tokenstream is never used (e.g. when a captured `macro_rules!` argument is
never passed to a proc macro), we never actually create a `TokenStream`.
This implementation has a number of advantages over the previous one:
* It is significantly simpler, with no edge cases around capturing the
start/end of a delimited group.
* It can be easily extended to allow replacing tokens an an arbitrary
'depth' by just using `Vec::splice` at the proper position. This is
important for PR #76130, which requires us to track information about
attributes along with tokens.
* The lazy approach to `TokenStream` construction allows us to easily
parse an AST struct, and then decide after the fact whether we need a
`TokenStream`. This will be useful when we start collecting tokens for
`Attribute` - we can discard the `LazyTokenStream` if the parsed
attribute doesn't need tokens (e.g. is a builtin attribute).
The performance impact seems to be neglibile (see
https://github.com/rust-lang/rust/pull/77250#issuecomment-703960604). There is a
small slowdown on a few benchmarks, but it only rises above 1% for incremental
builds, where it represents a larger fraction of the much smaller instruction
count. There a ~1% speedup on a few other incremental benchmarks - my guess is
that the speedups and slowdowns will usually cancel out in practice.
2020-09-27 01:56:29 +00:00
|
|
|
self.bump_with((Token::new(second, second_span), self.token_spacing));
|
2018-05-25 20:40:16 +00:00
|
|
|
true
|
|
|
|
}
|
2020-02-22 13:22:38 +00:00
|
|
|
_ => {
|
2024-12-04 04:55:06 +00:00
|
|
|
self.expected_token_types.insert(exp.token_type);
|
2020-02-22 13:22:38 +00:00
|
|
|
false
|
2018-05-25 20:40:16 +00:00
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
2018-05-25 21:36:23 +00:00
|
|
|
|
2020-02-22 13:22:38 +00:00
|
|
|
/// Eats `+` possibly breaking tokens like `+=` in process.
|
|
|
|
fn eat_plus(&mut self) -> bool {
|
2024-12-04 04:55:06 +00:00
|
|
|
self.break_and_eat(exp!(Plus))
|
2020-02-22 13:22:38 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
/// Eats `&` possibly breaking tokens like `&&` in process.
|
|
|
|
/// Signals an error if `&` is not eaten.
|
2015-12-20 21:00:43 +00:00
|
|
|
fn expect_and(&mut self) -> PResult<'a, ()> {
|
2024-12-04 04:55:06 +00:00
|
|
|
if self.break_and_eat(exp!(And)) { Ok(()) } else { self.unexpected() }
|
2014-04-17 08:35:31 +00:00
|
|
|
}
|
|
|
|
|
2020-02-22 13:22:38 +00:00
|
|
|
/// Eats `|` possibly breaking tokens like `||` in process.
|
|
|
|
/// Signals an error if `|` was not eaten.
|
2017-09-07 06:07:49 +00:00
|
|
|
fn expect_or(&mut self) -> PResult<'a, ()> {
|
2024-12-04 04:55:06 +00:00
|
|
|
if self.break_and_eat(exp!(Or)) { Ok(()) } else { self.unexpected() }
|
2017-09-07 06:07:49 +00:00
|
|
|
}
|
|
|
|
|
2020-02-22 13:22:38 +00:00
|
|
|
/// Eats `<` possibly breaking tokens like `<<` in process.
|
2015-12-30 23:11:53 +00:00
|
|
|
fn eat_lt(&mut self) -> bool {
|
2024-12-04 04:55:06 +00:00
|
|
|
let ate = self.break_and_eat(exp!(Lt));
|
2019-01-23 01:35:13 +00:00
|
|
|
if ate {
|
|
|
|
// See doc comment for `unmatched_angle_bracket_count`.
|
|
|
|
self.unmatched_angle_bracket_count += 1;
|
|
|
|
debug!("eat_lt: (increment) count={:?}", self.unmatched_angle_bracket_count);
|
2014-05-11 04:27:44 +00:00
|
|
|
}
|
2019-01-23 01:35:13 +00:00
|
|
|
ate
|
2014-05-11 04:27:44 +00:00
|
|
|
}
|
|
|
|
|
2020-02-22 13:22:38 +00:00
|
|
|
/// Eats `<` possibly breaking tokens like `<<` in process.
|
|
|
|
/// Signals an error if `<` was not eaten.
|
2015-12-20 21:00:43 +00:00
|
|
|
fn expect_lt(&mut self) -> PResult<'a, ()> {
|
2020-02-22 13:22:38 +00:00
|
|
|
if self.eat_lt() { Ok(()) } else { self.unexpected() }
|
2014-05-11 04:27:44 +00:00
|
|
|
}
|
|
|
|
|
2020-02-22 13:22:38 +00:00
|
|
|
/// Eats `>` possibly breaking tokens like `>>` in process.
|
|
|
|
/// Signals an error if `>` was not eaten.
|
2018-05-31 22:53:30 +00:00
|
|
|
fn expect_gt(&mut self) -> PResult<'a, ()> {
|
2024-12-04 04:55:06 +00:00
|
|
|
if self.break_and_eat(exp!(Gt)) {
|
2020-02-22 13:22:38 +00:00
|
|
|
// See doc comment for `unmatched_angle_bracket_count`.
|
|
|
|
if self.unmatched_angle_bracket_count > 0 {
|
|
|
|
self.unmatched_angle_bracket_count -= 1;
|
|
|
|
debug!("expect_gt: (decrement) count={:?}", self.unmatched_angle_bracket_count);
|
2019-12-22 22:42:04 +00:00
|
|
|
}
|
2020-02-22 13:22:38 +00:00
|
|
|
Ok(())
|
|
|
|
} else {
|
|
|
|
self.unexpected()
|
2013-06-15 01:21:47 +00:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2024-12-04 04:50:46 +00:00
|
|
|
/// Checks if the next token is contained within `closes`, and returns `true` if so.
|
2024-06-05 21:02:18 +00:00
|
|
|
fn expect_any_with_type(
|
|
|
|
&mut self,
|
2024-12-04 04:55:06 +00:00
|
|
|
closes_expected: &[ExpTokenPair<'_>],
|
2024-12-04 04:50:46 +00:00
|
|
|
closes_not_expected: &[&TokenKind],
|
2024-06-05 21:02:18 +00:00
|
|
|
) -> bool {
|
2024-12-04 04:55:06 +00:00
|
|
|
closes_expected.iter().any(|&close| self.check(close))
|
2024-12-04 04:50:46 +00:00
|
|
|
|| closes_not_expected.iter().any(|k| self.check_noexpect(k))
|
2019-07-09 08:27:07 +00:00
|
|
|
}
|
|
|
|
|
2023-12-28 13:06:51 +00:00
|
|
|
/// Parses a sequence until the specified delimiters. The function
|
|
|
|
/// `f` must consume tokens until reaching the next separator or
|
|
|
|
/// closing bracket.
|
2019-10-08 07:35:34 +00:00
|
|
|
fn parse_seq_to_before_tokens<T>(
|
2018-08-20 23:16:17 +00:00
|
|
|
&mut self,
|
2024-12-04 04:55:06 +00:00
|
|
|
closes_expected: &[ExpTokenPair<'_>],
|
2024-12-04 04:50:46 +00:00
|
|
|
closes_not_expected: &[&TokenKind],
|
2024-12-04 04:55:06 +00:00
|
|
|
sep: SeqSep<'_>,
|
2019-07-09 08:27:07 +00:00
|
|
|
mut f: impl FnMut(&mut Parser<'a>) -> PResult<'a, T>,
|
2024-02-13 23:48:23 +00:00
|
|
|
) -> PResult<'a, (ThinVec<T>, Trailing, Recovered)> {
|
2019-01-28 05:04:50 +00:00
|
|
|
let mut first = true;
|
2024-02-13 23:44:33 +00:00
|
|
|
let mut recovered = Recovered::No;
|
2024-02-13 23:48:23 +00:00
|
|
|
let mut trailing = Trailing::No;
|
2022-11-23 00:55:16 +00:00
|
|
|
let mut v = ThinVec::new();
|
2021-04-09 02:12:00 +00:00
|
|
|
|
2024-12-04 04:50:46 +00:00
|
|
|
while !self.expect_any_with_type(closes_expected, closes_not_expected) {
|
2019-07-09 08:27:07 +00:00
|
|
|
if let token::CloseDelim(..) | token::Eof = self.token.kind {
|
2019-12-22 22:42:04 +00:00
|
|
|
break;
|
2019-07-09 08:27:07 +00:00
|
|
|
}
|
2024-12-04 04:55:06 +00:00
|
|
|
if let Some(exp) = sep.sep {
|
2017-05-12 18:05:39 +00:00
|
|
|
if first {
|
2023-12-28 13:06:51 +00:00
|
|
|
// no separator for the first element
|
2017-05-12 18:05:39 +00:00
|
|
|
first = false;
|
|
|
|
} else {
|
2023-12-28 13:06:51 +00:00
|
|
|
// check for separator
|
2024-12-04 04:55:06 +00:00
|
|
|
match self.expect(exp) {
|
2024-02-13 23:44:33 +00:00
|
|
|
Ok(Recovered::No) => {
|
2021-08-16 13:22:36 +00:00
|
|
|
self.current_closure.take();
|
|
|
|
}
|
2024-05-09 08:44:40 +00:00
|
|
|
Ok(Recovered::Yes(guar)) => {
|
2021-08-16 13:22:36 +00:00
|
|
|
self.current_closure.take();
|
2024-05-09 08:44:40 +00:00
|
|
|
recovered = Recovered::Yes(guar);
|
2019-01-28 05:04:50 +00:00
|
|
|
break;
|
2017-10-24 13:04:01 +00:00
|
|
|
}
|
2019-11-24 21:33:00 +00:00
|
|
|
Err(mut expect_err) => {
|
2020-02-29 11:56:15 +00:00
|
|
|
let sp = self.prev_token.span.shrink_to_hi();
|
2024-12-04 04:55:06 +00:00
|
|
|
let token_str = pprust::token_kind_to_string(exp.tok);
|
2019-11-24 21:33:00 +00:00
|
|
|
|
2021-08-16 13:22:36 +00:00
|
|
|
match self.current_closure.take() {
|
2024-08-09 07:44:47 +00:00
|
|
|
Some(closure_spans) if self.token == TokenKind::Semi => {
|
2021-08-16 13:22:36 +00:00
|
|
|
// Finding a semicolon instead of a comma
|
|
|
|
// after a closure body indicates that the
|
|
|
|
// closure body may be a block but the user
|
|
|
|
// forgot to put braces around its
|
|
|
|
// statements.
|
|
|
|
|
|
|
|
self.recover_missing_braces_around_closure_body(
|
|
|
|
closure_spans,
|
|
|
|
expect_err,
|
|
|
|
)?;
|
|
|
|
|
|
|
|
continue;
|
|
|
|
}
|
|
|
|
|
|
|
|
_ => {
|
|
|
|
// Attempt to keep parsing if it was a similar separator.
|
2025-01-22 15:01:10 +00:00
|
|
|
if exp.tok.similar_tokens().contains(&self.token.kind) {
|
|
|
|
self.bump();
|
2021-08-16 13:22:36 +00:00
|
|
|
}
|
2019-01-28 05:04:50 +00:00
|
|
|
}
|
|
|
|
}
|
2019-11-24 21:33:00 +00:00
|
|
|
|
2020-05-27 18:09:54 +00:00
|
|
|
// If this was a missing `@` in a binding pattern
|
|
|
|
// bail with a suggestion
|
|
|
|
// https://github.com/rust-lang/rust/issues/72373
|
2024-08-09 07:44:47 +00:00
|
|
|
if self.prev_token.is_ident() && self.token == token::DotDot {
|
2020-05-27 18:09:54 +00:00
|
|
|
let msg = format!(
|
2023-11-06 19:56:45 +00:00
|
|
|
"if you meant to bind the contents of the rest of the array \
|
|
|
|
pattern into `{}`, use `@`",
|
2020-05-27 18:09:54 +00:00
|
|
|
pprust::token_to_string(&self.prev_token)
|
|
|
|
);
|
|
|
|
expect_err
|
2024-01-08 22:08:49 +00:00
|
|
|
.with_span_suggestion_verbose(
|
2020-05-27 18:09:54 +00:00
|
|
|
self.prev_token.span.shrink_to_hi().until(self.token.span),
|
Restrict `From<S>` for `{D,Subd}iagnosticMessage`.
Currently a `{D,Subd}iagnosticMessage` can be created from any type that
impls `Into<String>`. That includes `&str`, `String`, and `Cow<'static,
str>`, which are reasonable. It also includes `&String`, which is pretty
weird, and results in many places making unnecessary allocations for
patterns like this:
```
self.fatal(&format!(...))
```
This creates a string with `format!`, takes a reference, passes the
reference to `fatal`, which does an `into()`, which clones the
reference, doing a second allocation. Two allocations for a single
string, bleh.
This commit changes the `From` impls so that you can only create a
`{D,Subd}iagnosticMessage` from `&str`, `String`, or `Cow<'static,
str>`. This requires changing all the places that currently create one
from a `&String`. Most of these are of the `&format!(...)` form
described above; each one removes an unnecessary static `&`, plus an
allocation when executed. There are also a few places where the existing
use of `&String` was more reasonable; these now just use `clone()` at
the call site.
As well as making the code nicer and more efficient, this is a step
towards possibly using `Cow<'static, str>` in
`{D,Subd}iagnosticMessage::{Str,Eager}`. That would require changing
the `From<&'a str>` impls to `From<&'static str>`, which is doable, but
I'm not yet sure if it's worthwhile.
2023-04-20 03:26:58 +00:00
|
|
|
msg,
|
2022-04-26 05:17:33 +00:00
|
|
|
" @ ",
|
2020-05-27 18:09:54 +00:00
|
|
|
Applicability::MaybeIncorrect,
|
|
|
|
)
|
|
|
|
.emit();
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
|
2019-09-06 02:56:45 +00:00
|
|
|
// Attempt to keep parsing if it was an omitted separator.
|
2024-04-19 17:12:12 +00:00
|
|
|
self.last_unexpected_token_span = None;
|
2019-01-28 05:04:50 +00:00
|
|
|
match f(self) {
|
|
|
|
Ok(t) => {
|
2019-11-24 21:33:00 +00:00
|
|
|
// Parsed successfully, therefore most probably the code only
|
|
|
|
// misses a separator.
|
|
|
|
expect_err
|
2024-01-08 22:08:49 +00:00
|
|
|
.with_span_suggestion_short(
|
2020-12-19 10:29:56 +00:00
|
|
|
sp,
|
2023-07-25 20:00:13 +00:00
|
|
|
format!("missing `{token_str}`"),
|
2022-04-26 05:17:33 +00:00
|
|
|
token_str,
|
2019-11-24 21:33:00 +00:00
|
|
|
Applicability::MaybeIncorrect,
|
|
|
|
)
|
|
|
|
.emit();
|
|
|
|
|
2019-01-28 05:04:50 +00:00
|
|
|
v.push(t);
|
|
|
|
continue;
|
2019-12-22 22:42:04 +00:00
|
|
|
}
|
2022-01-26 03:39:14 +00:00
|
|
|
Err(e) => {
|
2019-11-24 21:33:00 +00:00
|
|
|
// Parsing failed, therefore it must be something more serious
|
|
|
|
// than just a missing separator.
|
2022-11-30 20:01:00 +00:00
|
|
|
for xx in &e.children {
|
2024-12-04 04:55:06 +00:00
|
|
|
// Propagate the help message from sub error `e` to main
|
|
|
|
// error `expect_err`.
|
2022-11-30 20:01:00 +00:00
|
|
|
expect_err.children.push(xx.clone());
|
|
|
|
}
|
2019-01-28 05:04:50 +00:00
|
|
|
e.cancel();
|
2022-11-16 20:46:06 +00:00
|
|
|
if self.token == token::Colon {
|
2024-12-04 04:55:06 +00:00
|
|
|
// We will try to recover in
|
|
|
|
// `maybe_recover_struct_lit_bad_delims`.
|
2022-11-16 20:46:06 +00:00
|
|
|
return Err(expect_err);
|
2024-12-04 04:55:06 +00:00
|
|
|
} else if let [exp] = closes_expected
|
|
|
|
&& exp.token_type == TokenType::CloseParen
|
2023-11-06 23:19:14 +00:00
|
|
|
{
|
|
|
|
return Err(expect_err);
|
2022-11-16 20:46:06 +00:00
|
|
|
} else {
|
|
|
|
expect_err.emit();
|
|
|
|
break;
|
|
|
|
}
|
2019-01-28 05:04:50 +00:00
|
|
|
}
|
2017-10-24 13:04:01 +00:00
|
|
|
}
|
|
|
|
}
|
2016-01-29 04:49:59 +00:00
|
|
|
}
|
|
|
|
}
|
2013-06-15 01:21:47 +00:00
|
|
|
}
|
2024-06-05 21:02:18 +00:00
|
|
|
if sep.trailing_sep_allowed
|
2024-12-04 04:50:46 +00:00
|
|
|
&& self.expect_any_with_type(closes_expected, closes_not_expected)
|
2024-06-05 21:02:18 +00:00
|
|
|
{
|
2024-02-13 23:48:23 +00:00
|
|
|
trailing = Trailing::Yes;
|
2016-01-31 19:39:50 +00:00
|
|
|
break;
|
|
|
|
}
|
2016-01-29 04:49:59 +00:00
|
|
|
|
2017-10-22 16:19:30 +00:00
|
|
|
let t = f(self)?;
|
|
|
|
v.push(t);
|
2013-06-15 01:21:47 +00:00
|
|
|
}
|
2023-03-14 23:10:59 +00:00
|
|
|
|
2019-07-09 08:27:07 +00:00
|
|
|
Ok((v, trailing, recovered))
|
2013-06-15 01:21:47 +00:00
|
|
|
}
|
|
|
|
|
2021-08-16 13:22:36 +00:00
|
|
|
fn recover_missing_braces_around_closure_body(
|
|
|
|
&mut self,
|
|
|
|
closure_spans: ClosureSpans,
|
2024-02-22 23:20:45 +00:00
|
|
|
mut expect_err: Diag<'_>,
|
2021-08-16 13:22:36 +00:00
|
|
|
) -> PResult<'a, ()> {
|
|
|
|
let initial_semicolon = self.token.span;
|
|
|
|
|
2024-12-04 04:55:06 +00:00
|
|
|
while self.eat(exp!(Semi)) {
|
2024-07-16 16:21:39 +00:00
|
|
|
let _ = self.parse_stmt_without_recovery(false, ForceCollect::No).unwrap_or_else(|e| {
|
|
|
|
e.cancel();
|
|
|
|
None
|
|
|
|
});
|
2021-08-16 13:22:36 +00:00
|
|
|
}
|
|
|
|
|
2023-12-23 22:08:41 +00:00
|
|
|
expect_err
|
|
|
|
.primary_message("closure bodies that contain statements must be surrounded by braces");
|
2021-08-16 13:22:36 +00:00
|
|
|
|
|
|
|
let preceding_pipe_span = closure_spans.closing_pipe;
|
|
|
|
let following_token_span = self.token.span;
|
|
|
|
|
|
|
|
let mut first_note = MultiSpan::from(vec![initial_semicolon]);
|
|
|
|
first_note.push_span_label(
|
|
|
|
initial_semicolon,
|
2022-06-29 12:16:43 +00:00
|
|
|
"this `;` turns the preceding closure into a statement",
|
2021-08-16 13:22:36 +00:00
|
|
|
);
|
|
|
|
first_note.push_span_label(
|
|
|
|
closure_spans.body,
|
2022-06-29 12:16:43 +00:00
|
|
|
"this expression is a statement because of the trailing semicolon",
|
2021-08-16 13:22:36 +00:00
|
|
|
);
|
|
|
|
expect_err.span_note(first_note, "statement found outside of a block");
|
|
|
|
|
|
|
|
let mut second_note = MultiSpan::from(vec![closure_spans.whole_closure]);
|
2022-06-29 12:16:43 +00:00
|
|
|
second_note.push_span_label(closure_spans.whole_closure, "this is the parsed closure...");
|
2021-08-16 13:22:36 +00:00
|
|
|
second_note.push_span_label(
|
|
|
|
following_token_span,
|
2022-06-29 12:16:43 +00:00
|
|
|
"...but likely you meant the closure to end here",
|
2021-08-16 13:22:36 +00:00
|
|
|
);
|
|
|
|
expect_err.span_note(second_note, "the closure body may be incorrectly delimited");
|
|
|
|
|
2023-12-23 22:08:41 +00:00
|
|
|
expect_err.span(vec![preceding_pipe_span, following_token_span]);
|
2021-08-16 13:22:36 +00:00
|
|
|
|
|
|
|
let opening_suggestion_str = " {".to_string();
|
|
|
|
let closing_suggestion_str = "}".to_string();
|
|
|
|
|
|
|
|
expect_err.multipart_suggestion(
|
|
|
|
"try adding braces",
|
|
|
|
vec![
|
|
|
|
(preceding_pipe_span.shrink_to_hi(), opening_suggestion_str),
|
|
|
|
(following_token_span.shrink_to_lo(), closing_suggestion_str),
|
|
|
|
],
|
|
|
|
Applicability::MaybeIncorrect,
|
|
|
|
);
|
|
|
|
|
|
|
|
expect_err.emit();
|
|
|
|
|
|
|
|
Ok(())
|
|
|
|
}
|
|
|
|
|
2023-12-28 13:06:51 +00:00
|
|
|
/// Parses a sequence, not including the delimiters. The function
|
2019-12-04 09:13:29 +00:00
|
|
|
/// `f` must consume tokens until reaching the next separator or
|
|
|
|
/// closing bracket.
|
|
|
|
fn parse_seq_to_before_end<T>(
|
|
|
|
&mut self,
|
2024-12-04 04:55:06 +00:00
|
|
|
close: ExpTokenPair<'_>,
|
|
|
|
sep: SeqSep<'_>,
|
2019-12-04 09:13:29 +00:00
|
|
|
f: impl FnMut(&mut Parser<'a>) -> PResult<'a, T>,
|
2024-02-13 23:48:23 +00:00
|
|
|
) -> PResult<'a, (ThinVec<T>, Trailing, Recovered)> {
|
2024-12-04 04:50:46 +00:00
|
|
|
self.parse_seq_to_before_tokens(&[close], &[], sep, f)
|
2019-12-04 09:13:29 +00:00
|
|
|
}
|
|
|
|
|
2023-12-28 13:06:51 +00:00
|
|
|
/// Parses a sequence, including only the closing delimiter. The function
|
2019-12-04 09:13:29 +00:00
|
|
|
/// `f` must consume tokens until reaching the next separator or
|
|
|
|
/// closing bracket.
|
|
|
|
fn parse_seq_to_end<T>(
|
|
|
|
&mut self,
|
2024-12-04 04:55:06 +00:00
|
|
|
close: ExpTokenPair<'_>,
|
|
|
|
sep: SeqSep<'_>,
|
2019-12-22 22:42:04 +00:00
|
|
|
f: impl FnMut(&mut Parser<'a>) -> PResult<'a, T>,
|
2024-02-13 23:48:23 +00:00
|
|
|
) -> PResult<'a, (ThinVec<T>, Trailing)> {
|
2024-12-04 04:50:46 +00:00
|
|
|
let (val, trailing, recovered) = self.parse_seq_to_before_end(close, sep, f)?;
|
|
|
|
if matches!(recovered, Recovered::No) && !self.eat(close) {
|
2024-07-30 01:21:15 +00:00
|
|
|
self.dcx().span_delayed_bug(
|
|
|
|
self.token.span,
|
2024-12-04 04:50:46 +00:00
|
|
|
"recovered but `parse_seq_to_before_end` did not give us the close token",
|
2024-07-30 01:21:15 +00:00
|
|
|
);
|
2019-12-04 09:13:29 +00:00
|
|
|
}
|
|
|
|
Ok((val, trailing))
|
|
|
|
}
|
|
|
|
|
2023-12-28 13:06:51 +00:00
|
|
|
/// Parses a sequence, including both delimiters. The function
|
2019-02-08 13:53:55 +00:00
|
|
|
/// `f` must consume tokens until reaching the next separator or
|
2014-06-09 20:12:30 +00:00
|
|
|
/// closing bracket.
|
2019-07-09 08:27:07 +00:00
|
|
|
fn parse_unspanned_seq<T>(
|
2019-01-28 05:04:50 +00:00
|
|
|
&mut self,
|
2024-12-04 04:55:06 +00:00
|
|
|
open: ExpTokenPair<'_>,
|
|
|
|
close: ExpTokenPair<'_>,
|
|
|
|
sep: SeqSep<'_>,
|
2019-07-09 08:27:07 +00:00
|
|
|
f: impl FnMut(&mut Parser<'a>) -> PResult<'a, T>,
|
2024-02-13 23:48:23 +00:00
|
|
|
) -> PResult<'a, (ThinVec<T>, Trailing)> {
|
2024-12-04 04:50:46 +00:00
|
|
|
self.expect(open)?;
|
|
|
|
self.parse_seq_to_end(close, sep, f)
|
2013-06-15 01:21:47 +00:00
|
|
|
}
|
|
|
|
|
2023-12-28 13:06:51 +00:00
|
|
|
/// Parses a comma-separated sequence, including both delimiters.
|
|
|
|
/// The function `f` must consume tokens until reaching the next separator or
|
|
|
|
/// closing bracket.
|
2019-07-09 08:31:24 +00:00
|
|
|
fn parse_delim_comma_seq<T>(
|
|
|
|
&mut self,
|
2024-12-04 04:55:06 +00:00
|
|
|
open: ExpTokenPair<'_>,
|
|
|
|
close: ExpTokenPair<'_>,
|
2019-07-09 08:31:24 +00:00
|
|
|
f: impl FnMut(&mut Parser<'a>) -> PResult<'a, T>,
|
2024-02-13 23:48:23 +00:00
|
|
|
) -> PResult<'a, (ThinVec<T>, Trailing)> {
|
2024-12-04 04:55:06 +00:00
|
|
|
self.parse_unspanned_seq(open, close, SeqSep::trailing_allowed(exp!(Comma)), f)
|
2019-07-09 08:31:24 +00:00
|
|
|
}
|
|
|
|
|
2023-12-28 13:06:51 +00:00
|
|
|
/// Parses a comma-separated sequence delimited by parentheses (e.g. `(x, y)`).
|
|
|
|
/// The function `f` must consume tokens until reaching the next separator or
|
|
|
|
/// closing bracket.
|
2019-07-09 08:31:24 +00:00
|
|
|
fn parse_paren_comma_seq<T>(
|
|
|
|
&mut self,
|
|
|
|
f: impl FnMut(&mut Parser<'a>) -> PResult<'a, T>,
|
2024-02-13 23:48:23 +00:00
|
|
|
) -> PResult<'a, (ThinVec<T>, Trailing)> {
|
2024-12-04 04:55:06 +00:00
|
|
|
self.parse_delim_comma_seq(exp!(OpenParen), exp!(CloseParen), f)
|
2019-07-09 08:31:24 +00:00
|
|
|
}
|
|
|
|
|
2020-02-22 13:22:38 +00:00
|
|
|
/// Advance the parser by one token using provided token as the next one.
|
2022-03-07 04:17:38 +00:00
|
|
|
fn bump_with(&mut self, next: (Token, Spacing)) {
|
|
|
|
self.inlined_bump_with(next)
|
|
|
|
}
|
|
|
|
|
|
|
|
/// This always-inlined version should only be used on hot code paths.
|
|
|
|
#[inline(always)]
|
|
|
|
fn inlined_bump_with(&mut self, (next_token, next_spacing): (Token, Spacing)) {
|
2020-02-09 14:54:38 +00:00
|
|
|
// Update the current and previous tokens.
|
2020-03-07 13:34:29 +00:00
|
|
|
self.prev_token = mem::replace(&mut self.token, next_token);
|
Rewrite `collect_tokens` implementations to use a flattened buffer
Instead of trying to collect tokens at each depth, we 'flatten' the
stream as we go allong, pushing open/close delimiters to our buffer
just like regular tokens. One capturing is complete, we reconstruct a
nested `TokenTree::Delimited` structure, producing a normal
`TokenStream`.
The reconstructed `TokenStream` is not created immediately - instead, it is
produced on-demand by a closure (wrapped in a new `LazyTokenStream` type). This
closure stores a clone of the original `TokenCursor`, plus a record of the
number of calls to `next()/next_desugared()`. This is sufficient to reconstruct
the tokenstream seen by the callback without storing any additional state. If
the tokenstream is never used (e.g. when a captured `macro_rules!` argument is
never passed to a proc macro), we never actually create a `TokenStream`.
This implementation has a number of advantages over the previous one:
* It is significantly simpler, with no edge cases around capturing the
start/end of a delimited group.
* It can be easily extended to allow replacing tokens an an arbitrary
'depth' by just using `Vec::splice` at the proper position. This is
important for PR #76130, which requires us to track information about
attributes along with tokens.
* The lazy approach to `TokenStream` construction allows us to easily
parse an AST struct, and then decide after the fact whether we need a
`TokenStream`. This will be useful when we start collecting tokens for
`Attribute` - we can discard the `LazyTokenStream` if the parsed
attribute doesn't need tokens (e.g. is a builtin attribute).
The performance impact seems to be neglibile (see
https://github.com/rust-lang/rust/pull/77250#issuecomment-703960604). There is a
small slowdown on a few benchmarks, but it only rises above 1% for incremental
builds, where it represents a larger fraction of the much smaller instruction
count. There a ~1% speedup on a few other incremental benchmarks - my guess is
that the speedups and slowdowns will usually cancel out in practice.
2020-09-27 01:56:29 +00:00
|
|
|
self.token_spacing = next_spacing;
|
2016-09-16 05:46:40 +00:00
|
|
|
|
2020-02-22 13:22:38 +00:00
|
|
|
// Diagnostics.
|
2024-12-03 09:09:29 +00:00
|
|
|
self.expected_token_types.clear();
|
2012-01-13 08:56:53 +00:00
|
|
|
}
|
2013-07-02 19:47:32 +00:00
|
|
|
|
2020-02-22 13:22:38 +00:00
|
|
|
/// Advance the parser by one token.
|
|
|
|
pub fn bump(&mut self) {
|
2022-04-20 06:34:33 +00:00
|
|
|
// Note: destructuring here would give nicer code, but it was found in #96210 to be slower
|
|
|
|
// than `.0`/`.1` access.
|
2023-07-25 23:17:32 +00:00
|
|
|
let mut next = self.token_cursor.inlined_next();
|
2023-07-31 06:15:54 +00:00
|
|
|
self.num_bump_calls += 1;
|
2024-09-19 09:32:17 +00:00
|
|
|
// We got a token from the underlying cursor and no longer need to
|
|
|
|
// worry about an unglued token. See `break_and_eat` for more details.
|
|
|
|
self.break_last_token = 0;
|
2022-04-20 06:34:33 +00:00
|
|
|
if next.0.span.is_dummy() {
|
2022-04-20 02:22:42 +00:00
|
|
|
// Tweak the location for better diagnostics, but keep syntactic context intact.
|
2022-04-20 04:04:22 +00:00
|
|
|
let fallback_span = self.token.span;
|
2022-04-20 06:34:33 +00:00
|
|
|
next.0.span = fallback_span.with_ctxt(next.0.span.ctxt());
|
2022-04-14 01:13:20 +00:00
|
|
|
}
|
2022-04-20 02:22:42 +00:00
|
|
|
debug_assert!(!matches!(
|
2022-04-20 06:34:33 +00:00
|
|
|
next.0.kind,
|
2024-04-16 23:59:27 +00:00
|
|
|
token::OpenDelim(delim) | token::CloseDelim(delim) if delim.skip()
|
2022-04-20 02:22:42 +00:00
|
|
|
));
|
2022-04-20 06:34:33 +00:00
|
|
|
self.inlined_bump_with(next)
|
2012-01-13 08:56:53 +00:00
|
|
|
}
|
2016-02-06 17:42:17 +00:00
|
|
|
|
2019-10-01 03:13:42 +00:00
|
|
|
/// Look-ahead `dist` tokens of `self.token` and get access to that token there.
|
2023-08-09 05:02:30 +00:00
|
|
|
/// When `dist == 0` then the current token is looked at. `Eof` will be
|
|
|
|
/// returned if the look-ahead is any distance past the end of the tokens.
|
2019-09-30 04:21:30 +00:00
|
|
|
pub fn look_ahead<R>(&self, dist: usize, looker: impl FnOnce(&Token) -> R) -> R {
|
2019-05-23 20:10:24 +00:00
|
|
|
if dist == 0 {
|
2019-09-30 04:21:30 +00:00
|
|
|
return looker(&self.token);
|
2019-05-23 20:10:24 +00:00
|
|
|
}
|
|
|
|
|
2024-07-12 03:20:24 +00:00
|
|
|
// Typically around 98% of the `dist > 0` cases have `dist == 1`, so we
|
|
|
|
// have a fast special case for that.
|
|
|
|
if dist == 1 {
|
|
|
|
// The index is zero because the tree cursor's index always points
|
|
|
|
// to the next token to be gotten.
|
2024-12-10 08:18:44 +00:00
|
|
|
match self.token_cursor.curr.curr() {
|
2024-07-12 03:20:24 +00:00
|
|
|
Some(tree) => {
|
|
|
|
// Indexing stayed within the current token tree.
|
2024-08-12 00:27:19 +00:00
|
|
|
match tree {
|
|
|
|
TokenTree::Token(token, _) => return looker(token),
|
|
|
|
&TokenTree::Delimited(dspan, _, delim, _) => {
|
2024-04-16 23:59:27 +00:00
|
|
|
if !delim.skip() {
|
2024-08-12 00:27:19 +00:00
|
|
|
return looker(&Token::new(token::OpenDelim(delim), dspan.open));
|
|
|
|
}
|
2024-07-12 03:20:24 +00:00
|
|
|
}
|
2024-12-10 08:18:44 +00:00
|
|
|
}
|
2024-07-12 03:20:24 +00:00
|
|
|
}
|
|
|
|
None => {
|
|
|
|
// The tree cursor lookahead went (one) past the end of the
|
|
|
|
// current token tree. Try to return a close delimiter.
|
2024-12-10 08:18:44 +00:00
|
|
|
if let Some(last) = self.token_cursor.stack.last()
|
|
|
|
&& let Some(&TokenTree::Delimited(span, _, delim, _)) = last.curr()
|
2024-04-16 23:59:27 +00:00
|
|
|
&& !delim.skip()
|
2024-07-12 03:20:24 +00:00
|
|
|
{
|
|
|
|
// We are not in the outermost token stream, so we have
|
|
|
|
// delimiters. Also, those delimiters are not skipped.
|
|
|
|
return looker(&Token::new(token::CloseDelim(delim), span.close));
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2024-07-12 02:56:58 +00:00
|
|
|
// Just clone the token cursor and use `next`, skipping delimiters as
|
|
|
|
// necessary. Slow but simple.
|
2021-04-12 15:15:38 +00:00
|
|
|
let mut cursor = self.token_cursor.clone();
|
|
|
|
let mut i = 0;
|
|
|
|
let mut token = Token::dummy();
|
|
|
|
while i < dist {
|
2023-07-25 23:17:32 +00:00
|
|
|
token = cursor.next().0;
|
2021-04-12 15:15:38 +00:00
|
|
|
if matches!(
|
|
|
|
token.kind,
|
2024-04-16 23:59:27 +00:00
|
|
|
token::OpenDelim(delim) | token::CloseDelim(delim) if delim.skip()
|
2021-04-12 15:15:38 +00:00
|
|
|
) {
|
|
|
|
continue;
|
|
|
|
}
|
|
|
|
i += 1;
|
2020-09-14 05:45:10 +00:00
|
|
|
}
|
2023-07-31 01:07:50 +00:00
|
|
|
looker(&token)
|
2019-05-23 20:10:24 +00:00
|
|
|
}
|
|
|
|
|
2019-05-29 15:58:44 +00:00
|
|
|
/// Returns whether any of the given keywords are `dist` tokens ahead of the current one.
|
2023-11-12 22:46:01 +00:00
|
|
|
pub(crate) fn is_keyword_ahead(&self, dist: usize, kws: &[Symbol]) -> bool {
|
2019-05-29 15:58:44 +00:00
|
|
|
self.look_ahead(dist, |t| kws.iter().any(|&kw| t.is_keyword(kw)))
|
|
|
|
}
|
|
|
|
|
2019-02-08 13:53:55 +00:00
|
|
|
/// Parses asyncness: `async` or nothing.
|
2023-12-05 21:45:01 +00:00
|
|
|
fn parse_coroutine_kind(&mut self, case: Case) -> Option<CoroutineKind> {
|
|
|
|
let span = self.token.uninterpolated_span();
|
2024-12-04 04:55:06 +00:00
|
|
|
if self.eat_keyword_case(exp!(Async), case) {
|
2023-12-05 21:45:01 +00:00
|
|
|
// FIXME(gen_blocks): Do we want to unconditionally parse `gen` and then
|
|
|
|
// error if edition <= 2024, like we do with async and edition <= 2018?
|
|
|
|
if self.token.uninterpolated_span().at_least_rust_2024()
|
2024-12-04 04:55:06 +00:00
|
|
|
&& self.eat_keyword_case(exp!(Gen), case)
|
2023-12-05 21:45:01 +00:00
|
|
|
{
|
|
|
|
let gen_span = self.prev_token.uninterpolated_span();
|
|
|
|
Some(CoroutineKind::AsyncGen {
|
|
|
|
span: span.to(gen_span),
|
|
|
|
closure_id: DUMMY_NODE_ID,
|
|
|
|
return_impl_trait_id: DUMMY_NODE_ID,
|
|
|
|
})
|
|
|
|
} else {
|
|
|
|
Some(CoroutineKind::Async {
|
|
|
|
span,
|
|
|
|
closure_id: DUMMY_NODE_ID,
|
|
|
|
return_impl_trait_id: DUMMY_NODE_ID,
|
|
|
|
})
|
|
|
|
}
|
|
|
|
} else if self.token.uninterpolated_span().at_least_rust_2024()
|
2024-12-04 04:55:06 +00:00
|
|
|
&& self.eat_keyword_case(exp!(Gen), case)
|
2023-12-05 21:45:01 +00:00
|
|
|
{
|
2023-12-01 00:39:56 +00:00
|
|
|
Some(CoroutineKind::Gen {
|
2023-11-30 22:54:39 +00:00
|
|
|
span,
|
|
|
|
closure_id: DUMMY_NODE_ID,
|
|
|
|
return_impl_trait_id: DUMMY_NODE_ID,
|
2023-12-01 00:39:56 +00:00
|
|
|
})
|
2023-10-05 11:30:55 +00:00
|
|
|
} else {
|
2023-12-01 00:39:56 +00:00
|
|
|
None
|
2023-10-05 11:30:55 +00:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2024-05-17 17:17:48 +00:00
|
|
|
/// Parses fn unsafety: `unsafe`, `safe` or nothing.
|
|
|
|
fn parse_safety(&mut self, case: Case) -> Safety {
|
2024-12-04 04:55:06 +00:00
|
|
|
if self.eat_keyword_case(exp!(Unsafe), case) {
|
2024-05-17 17:17:48 +00:00
|
|
|
Safety::Unsafe(self.prev_token.uninterpolated_span())
|
2024-12-04 04:55:06 +00:00
|
|
|
} else if self.eat_keyword_case(exp!(Safe), case) {
|
2024-05-23 13:01:05 +00:00
|
|
|
Safety::Safe(self.prev_token.uninterpolated_span())
|
2020-02-29 11:59:37 +00:00
|
|
|
} else {
|
2024-05-17 17:17:48 +00:00
|
|
|
Safety::Default
|
2020-02-29 11:59:37 +00:00
|
|
|
}
|
2020-01-30 01:42:33 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
/// Parses constness: `const` or nothing.
|
2022-09-15 16:27:23 +00:00
|
|
|
fn parse_constness(&mut self, case: Case) -> Const {
|
2023-02-01 05:55:48 +00:00
|
|
|
self.parse_constness_(case, false)
|
|
|
|
}
|
|
|
|
|
2023-03-11 21:29:15 +00:00
|
|
|
/// Parses constness for closures (case sensitive, feature-gated)
|
|
|
|
fn parse_closure_constness(&mut self) -> Const {
|
|
|
|
let constness = self.parse_constness_(Case::Sensitive, true);
|
|
|
|
if let Const::Yes(span) = constness {
|
2024-03-04 05:31:49 +00:00
|
|
|
self.psess.gated_spans.gate(sym::const_closures, span);
|
2023-03-11 21:29:15 +00:00
|
|
|
}
|
|
|
|
constness
|
2023-02-01 05:55:48 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
fn parse_constness_(&mut self, case: Case, is_closure: bool) -> Const {
|
|
|
|
// Avoid const blocks and const closures to be parsed as const items
|
|
|
|
if (self.check_const_closure() == is_closure)
|
2023-07-17 19:02:06 +00:00
|
|
|
&& !self
|
|
|
|
.look_ahead(1, |t| *t == token::OpenDelim(Delimiter::Brace) || t.is_whole_block())
|
2024-12-04 04:55:06 +00:00
|
|
|
&& self.eat_keyword_case(exp!(Const), case)
|
2020-09-21 20:55:58 +00:00
|
|
|
{
|
2020-03-04 21:34:57 +00:00
|
|
|
Const::Yes(self.prev_token.uninterpolated_span())
|
2020-02-29 11:59:37 +00:00
|
|
|
} else {
|
|
|
|
Const::No
|
|
|
|
}
|
2013-02-01 01:12:29 +00:00
|
|
|
}
|
2012-11-05 04:41:00 +00:00
|
|
|
|
2020-09-21 20:55:58 +00:00
|
|
|
/// Parses inline const expressions.
|
2021-11-22 16:25:28 +00:00
|
|
|
fn parse_const_block(&mut self, span: Span, pat: bool) -> PResult<'a, P<Expr>> {
|
|
|
|
if pat {
|
2024-03-04 05:31:49 +00:00
|
|
|
self.psess.gated_spans.gate(sym::inline_const_pat, span);
|
2021-11-22 16:25:28 +00:00
|
|
|
}
|
2024-12-04 04:55:06 +00:00
|
|
|
self.expect_keyword(exp!(Const))?;
|
2022-03-16 00:20:21 +00:00
|
|
|
let (attrs, blk) = self.parse_inner_attrs_and_block()?;
|
2024-06-03 09:11:58 +00:00
|
|
|
let anon_const = AnonConst {
|
|
|
|
id: DUMMY_NODE_ID,
|
|
|
|
value: self.mk_expr(blk.span, ExprKind::Block(blk, None)),
|
|
|
|
};
|
|
|
|
let blk_span = anon_const.value.span;
|
|
|
|
Ok(self.mk_expr_with_attrs(span.to(blk_span), ExprKind::ConstBlock(anon_const), attrs))
|
2020-09-21 20:55:58 +00:00
|
|
|
}
|
|
|
|
|
2019-02-08 13:53:55 +00:00
|
|
|
/// Parses mutability (`mut` or nothing).
|
2017-03-16 21:47:32 +00:00
|
|
|
fn parse_mutability(&mut self) -> Mutability {
|
2024-12-04 04:55:06 +00:00
|
|
|
if self.eat_keyword(exp!(Mut)) { Mutability::Mut } else { Mutability::Not }
|
2012-05-23 22:06:11 +00:00
|
|
|
}
|
2012-04-24 22:52:52 +00:00
|
|
|
|
2024-03-24 01:04:45 +00:00
|
|
|
/// Parses reference binding mode (`ref`, `ref mut`, or nothing).
|
|
|
|
fn parse_byref(&mut self) -> ByRef {
|
2024-12-04 04:55:06 +00:00
|
|
|
if self.eat_keyword(exp!(Ref)) { ByRef::Yes(self.parse_mutability()) } else { ByRef::No }
|
2024-03-24 01:04:45 +00:00
|
|
|
}
|
|
|
|
|
2019-09-30 00:36:08 +00:00
|
|
|
/// Possibly parses mutability (`const` or `mut`).
|
|
|
|
fn parse_const_or_mut(&mut self) -> Option<Mutability> {
|
2024-12-04 04:55:06 +00:00
|
|
|
if self.eat_keyword(exp!(Mut)) {
|
2019-12-16 16:28:40 +00:00
|
|
|
Some(Mutability::Mut)
|
2024-12-04 04:55:06 +00:00
|
|
|
} else if self.eat_keyword(exp!(Const)) {
|
2019-12-16 16:28:40 +00:00
|
|
|
Some(Mutability::Not)
|
2019-09-30 00:36:08 +00:00
|
|
|
} else {
|
|
|
|
None
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2018-05-31 22:53:30 +00:00
|
|
|
fn parse_field_name(&mut self) -> PResult<'a, Ident> {
|
2019-12-22 22:42:04 +00:00
|
|
|
if let token::Literal(token::Lit { kind: token::Integer, symbol, suffix }) = self.token.kind
|
|
|
|
{
|
2022-09-15 08:12:09 +00:00
|
|
|
if let Some(suffix) = suffix {
|
|
|
|
self.expect_no_tuple_index_suffix(self.token.span, suffix);
|
|
|
|
}
|
2016-07-29 20:47:55 +00:00
|
|
|
self.bump();
|
2020-02-29 11:56:15 +00:00
|
|
|
Ok(Ident::new(symbol, self.prev_token.span))
|
2016-07-29 20:47:55 +00:00
|
|
|
} else {
|
2021-01-21 02:49:11 +00:00
|
|
|
self.parse_ident_common(true)
|
2016-07-29 20:47:55 +00:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2022-11-18 00:24:21 +00:00
|
|
|
fn parse_delim_args(&mut self) -> PResult<'a, P<DelimArgs>> {
|
2024-03-15 11:36:21 +00:00
|
|
|
if let Some(args) = self.parse_delim_args_inner() {
|
|
|
|
Ok(P(args))
|
|
|
|
} else {
|
|
|
|
self.unexpected_any()
|
|
|
|
}
|
2019-11-30 23:25:32 +00:00
|
|
|
}
|
|
|
|
|
2022-11-18 00:24:21 +00:00
|
|
|
fn parse_attr_args(&mut self) -> PResult<'a, AttrArgs> {
|
|
|
|
Ok(if let Some(args) = self.parse_delim_args_inner() {
|
|
|
|
AttrArgs::Delimited(args)
|
2024-12-04 04:55:06 +00:00
|
|
|
} else if self.eat(exp!(Eq)) {
|
2024-09-11 21:23:56 +00:00
|
|
|
let eq_span = self.prev_token.span;
|
2024-10-16 23:14:01 +00:00
|
|
|
AttrArgs::Eq { eq_span, expr: self.parse_expr_force_collect()? }
|
2022-11-18 00:24:21 +00:00
|
|
|
} else {
|
2024-09-11 21:23:56 +00:00
|
|
|
AttrArgs::Empty
|
2022-11-18 00:24:21 +00:00
|
|
|
})
|
2019-11-30 23:25:32 +00:00
|
|
|
}
|
|
|
|
|
2022-11-18 00:24:21 +00:00
|
|
|
fn parse_delim_args_inner(&mut self) -> Option<DelimArgs> {
|
2024-12-04 04:55:06 +00:00
|
|
|
let delimited = self.check(exp!(OpenParen))
|
|
|
|
|| self.check(exp!(OpenBracket))
|
|
|
|
|| self.check(exp!(OpenBrace));
|
2023-02-15 11:43:41 +00:00
|
|
|
|
|
|
|
delimited.then(|| {
|
2023-10-12 04:36:14 +00:00
|
|
|
let TokenTree::Delimited(dspan, _, delim, tokens) = self.parse_token_tree() else {
|
2023-07-13 01:49:27 +00:00
|
|
|
unreachable!()
|
|
|
|
};
|
2023-08-01 23:56:26 +00:00
|
|
|
DelimArgs { dspan, delim, tokens }
|
2023-02-15 11:43:41 +00:00
|
|
|
})
|
2014-10-29 14:47:53 +00:00
|
|
|
}
|
|
|
|
|
2019-08-11 11:14:30 +00:00
|
|
|
/// Parses a single token tree from the input.
|
2023-07-31 05:51:08 +00:00
|
|
|
pub fn parse_token_tree(&mut self) -> TokenTree {
|
2019-08-11 11:14:30 +00:00
|
|
|
match self.token.kind {
|
|
|
|
token::OpenDelim(..) => {
|
2024-12-10 08:18:44 +00:00
|
|
|
// Clone the `TokenTree::Delimited` that we are currently
|
|
|
|
// within. That's what we are going to return.
|
|
|
|
let tree = self.token_cursor.stack.last().unwrap().curr().unwrap().clone();
|
|
|
|
debug_assert_matches!(tree, TokenTree::Delimited(..));
|
Rewrite `collect_tokens` implementations to use a flattened buffer
Instead of trying to collect tokens at each depth, we 'flatten' the
stream as we go allong, pushing open/close delimiters to our buffer
just like regular tokens. One capturing is complete, we reconstruct a
nested `TokenTree::Delimited` structure, producing a normal
`TokenStream`.
The reconstructed `TokenStream` is not created immediately - instead, it is
produced on-demand by a closure (wrapped in a new `LazyTokenStream` type). This
closure stores a clone of the original `TokenCursor`, plus a record of the
number of calls to `next()/next_desugared()`. This is sufficient to reconstruct
the tokenstream seen by the callback without storing any additional state. If
the tokenstream is never used (e.g. when a captured `macro_rules!` argument is
never passed to a proc macro), we never actually create a `TokenStream`.
This implementation has a number of advantages over the previous one:
* It is significantly simpler, with no edge cases around capturing the
start/end of a delimited group.
* It can be easily extended to allow replacing tokens an an arbitrary
'depth' by just using `Vec::splice` at the proper position. This is
important for PR #76130, which requires us to track information about
attributes along with tokens.
* The lazy approach to `TokenStream` construction allows us to easily
parse an AST struct, and then decide after the fact whether we need a
`TokenStream`. This will be useful when we start collecting tokens for
`Attribute` - we can discard the `LazyTokenStream` if the parsed
attribute doesn't need tokens (e.g. is a builtin attribute).
The performance impact seems to be neglibile (see
https://github.com/rust-lang/rust/pull/77250#issuecomment-703960604). There is a
small slowdown on a few benchmarks, but it only rises above 1% for incremental
builds, where it represents a larger fraction of the much smaller instruction
count. There a ~1% speedup on a few other incremental benchmarks - my guess is
that the speedups and slowdowns will usually cancel out in practice.
2020-09-27 01:56:29 +00:00
|
|
|
|
2022-04-21 02:26:58 +00:00
|
|
|
// Advance the token cursor through the entire delimited
|
|
|
|
// sequence. After getting the `OpenDelim` we are *within* the
|
|
|
|
// delimited sequence, i.e. at depth `d`. After getting the
|
|
|
|
// matching `CloseDelim` we are *after* the delimited sequence,
|
|
|
|
// i.e. at depth `d - 1`.
|
|
|
|
let target_depth = self.token_cursor.stack.len() - 1;
|
|
|
|
loop {
|
Rewrite `collect_tokens` implementations to use a flattened buffer
Instead of trying to collect tokens at each depth, we 'flatten' the
stream as we go allong, pushing open/close delimiters to our buffer
just like regular tokens. One capturing is complete, we reconstruct a
nested `TokenTree::Delimited` structure, producing a normal
`TokenStream`.
The reconstructed `TokenStream` is not created immediately - instead, it is
produced on-demand by a closure (wrapped in a new `LazyTokenStream` type). This
closure stores a clone of the original `TokenCursor`, plus a record of the
number of calls to `next()/next_desugared()`. This is sufficient to reconstruct
the tokenstream seen by the callback without storing any additional state. If
the tokenstream is never used (e.g. when a captured `macro_rules!` argument is
never passed to a proc macro), we never actually create a `TokenStream`.
This implementation has a number of advantages over the previous one:
* It is significantly simpler, with no edge cases around capturing the
start/end of a delimited group.
* It can be easily extended to allow replacing tokens an an arbitrary
'depth' by just using `Vec::splice` at the proper position. This is
important for PR #76130, which requires us to track information about
attributes along with tokens.
* The lazy approach to `TokenStream` construction allows us to easily
parse an AST struct, and then decide after the fact whether we need a
`TokenStream`. This will be useful when we start collecting tokens for
`Attribute` - we can discard the `LazyTokenStream` if the parsed
attribute doesn't need tokens (e.g. is a builtin attribute).
The performance impact seems to be neglibile (see
https://github.com/rust-lang/rust/pull/77250#issuecomment-703960604). There is a
small slowdown on a few benchmarks, but it only rises above 1% for incremental
builds, where it represents a larger fraction of the much smaller instruction
count. There a ~1% speedup on a few other incremental benchmarks - my guess is
that the speedups and slowdowns will usually cancel out in practice.
2020-09-27 01:56:29 +00:00
|
|
|
// Advance one token at a time, so `TokenCursor::next()`
|
|
|
|
// can capture these tokens if necessary.
|
|
|
|
self.bump();
|
2022-04-21 02:26:58 +00:00
|
|
|
if self.token_cursor.stack.len() == target_depth {
|
2024-08-11 16:10:36 +00:00
|
|
|
debug_assert_matches!(self.token.kind, token::CloseDelim(_));
|
2022-04-21 02:26:58 +00:00
|
|
|
break;
|
|
|
|
}
|
Rewrite `collect_tokens` implementations to use a flattened buffer
Instead of trying to collect tokens at each depth, we 'flatten' the
stream as we go allong, pushing open/close delimiters to our buffer
just like regular tokens. One capturing is complete, we reconstruct a
nested `TokenTree::Delimited` structure, producing a normal
`TokenStream`.
The reconstructed `TokenStream` is not created immediately - instead, it is
produced on-demand by a closure (wrapped in a new `LazyTokenStream` type). This
closure stores a clone of the original `TokenCursor`, plus a record of the
number of calls to `next()/next_desugared()`. This is sufficient to reconstruct
the tokenstream seen by the callback without storing any additional state. If
the tokenstream is never used (e.g. when a captured `macro_rules!` argument is
never passed to a proc macro), we never actually create a `TokenStream`.
This implementation has a number of advantages over the previous one:
* It is significantly simpler, with no edge cases around capturing the
start/end of a delimited group.
* It can be easily extended to allow replacing tokens an an arbitrary
'depth' by just using `Vec::splice` at the proper position. This is
important for PR #76130, which requires us to track information about
attributes along with tokens.
* The lazy approach to `TokenStream` construction allows us to easily
parse an AST struct, and then decide after the fact whether we need a
`TokenStream`. This will be useful when we start collecting tokens for
`Attribute` - we can discard the `LazyTokenStream` if the parsed
attribute doesn't need tokens (e.g. is a builtin attribute).
The performance impact seems to be neglibile (see
https://github.com/rust-lang/rust/pull/77250#issuecomment-703960604). There is a
small slowdown on a few benchmarks, but it only rises above 1% for incremental
builds, where it represents a larger fraction of the much smaller instruction
count. There a ~1% speedup on a few other incremental benchmarks - my guess is
that the speedups and slowdowns will usually cancel out in practice.
2020-09-27 01:56:29 +00:00
|
|
|
}
|
2022-04-21 02:26:58 +00:00
|
|
|
|
Rewrite `collect_tokens` implementations to use a flattened buffer
Instead of trying to collect tokens at each depth, we 'flatten' the
stream as we go allong, pushing open/close delimiters to our buffer
just like regular tokens. One capturing is complete, we reconstruct a
nested `TokenTree::Delimited` structure, producing a normal
`TokenStream`.
The reconstructed `TokenStream` is not created immediately - instead, it is
produced on-demand by a closure (wrapped in a new `LazyTokenStream` type). This
closure stores a clone of the original `TokenCursor`, plus a record of the
number of calls to `next()/next_desugared()`. This is sufficient to reconstruct
the tokenstream seen by the callback without storing any additional state. If
the tokenstream is never used (e.g. when a captured `macro_rules!` argument is
never passed to a proc macro), we never actually create a `TokenStream`.
This implementation has a number of advantages over the previous one:
* It is significantly simpler, with no edge cases around capturing the
start/end of a delimited group.
* It can be easily extended to allow replacing tokens an an arbitrary
'depth' by just using `Vec::splice` at the proper position. This is
important for PR #76130, which requires us to track information about
attributes along with tokens.
* The lazy approach to `TokenStream` construction allows us to easily
parse an AST struct, and then decide after the fact whether we need a
`TokenStream`. This will be useful when we start collecting tokens for
`Attribute` - we can discard the `LazyTokenStream` if the parsed
attribute doesn't need tokens (e.g. is a builtin attribute).
The performance impact seems to be neglibile (see
https://github.com/rust-lang/rust/pull/77250#issuecomment-703960604). There is a
small slowdown on a few benchmarks, but it only rises above 1% for incremental
builds, where it represents a larger fraction of the much smaller instruction
count. There a ~1% speedup on a few other incremental benchmarks - my guess is
that the speedups and slowdowns will usually cancel out in practice.
2020-09-27 01:56:29 +00:00
|
|
|
// Consume close delimiter
|
2019-08-11 11:14:30 +00:00
|
|
|
self.bump();
|
2024-12-10 08:18:44 +00:00
|
|
|
tree
|
2019-12-22 22:42:04 +00:00
|
|
|
}
|
2019-08-11 11:14:30 +00:00
|
|
|
token::CloseDelim(_) | token::Eof => unreachable!(),
|
|
|
|
_ => {
|
2023-08-08 01:43:44 +00:00
|
|
|
let prev_spacing = self.token_spacing;
|
2019-08-11 11:14:30 +00:00
|
|
|
self.bump();
|
2023-08-08 01:43:44 +00:00
|
|
|
TokenTree::Token(self.prev_token.clone(), prev_spacing)
|
2014-07-06 21:29:29 +00:00
|
|
|
}
|
2012-05-23 22:06:11 +00:00
|
|
|
}
|
2015-11-03 16:39:51 +00:00
|
|
|
}
|
|
|
|
|
2019-08-11 11:14:30 +00:00
|
|
|
pub fn parse_tokens(&mut self) -> TokenStream {
|
|
|
|
let mut result = Vec::new();
|
|
|
|
loop {
|
|
|
|
match self.token.kind {
|
|
|
|
token::Eof | token::CloseDelim(..) => break,
|
Remove `TreeAndSpacing`.
A `TokenStream` contains a `Lrc<Vec<(TokenTree, Spacing)>>`. But this is
not quite right. `Spacing` makes sense for `TokenTree::Token`, but does
not make sense for `TokenTree::Delimited`, because a
`TokenTree::Delimited` cannot be joined with another `TokenTree`.
This commit fixes this problem, by adding `Spacing` to `TokenTree::Token`,
changing `TokenStream` to contain a `Lrc<Vec<TokenTree>>`, and removing the
`TreeAndSpacing` typedef.
The commit removes these two impls:
- `impl From<TokenTree> for TokenStream`
- `impl From<TokenTree> for TreeAndSpacing`
These were useful, but also resulted in code with many `.into()` calls
that was hard to read, particularly for anyone not highly familiar with
the relevant types. This commit makes some other changes to compensate:
- `TokenTree::token()` becomes `TokenTree::token_{alone,joint}()`.
- `TokenStream::token_{alone,joint}()` are added.
- `TokenStream::delimited` is added.
This results in things like this:
```rust
TokenTree::token(token::Semi, stmt.span).into()
```
changing to this:
```rust
TokenStream::token_alone(token::Semi, stmt.span)
```
This makes the type of the result, and its spacing, clearer.
These changes also simplifies `Cursor` and `CursorRef`, because they no longer
need to distinguish between `next` and `next_with_spacing`.
2022-07-28 00:31:04 +00:00
|
|
|
_ => result.push(self.parse_token_tree()),
|
2019-04-15 00:09:03 +00:00
|
|
|
}
|
|
|
|
}
|
2019-08-11 11:14:30 +00:00
|
|
|
TokenStream::new(result)
|
2019-04-15 00:09:03 +00:00
|
|
|
}
|
|
|
|
|
2019-08-11 11:14:30 +00:00
|
|
|
/// Evaluates the closure with restrictions in place.
|
|
|
|
///
|
|
|
|
/// Afters the closure is evaluated, restrictions are reset.
|
2019-09-30 01:29:41 +00:00
|
|
|
fn with_res<T>(&mut self, res: Restrictions, f: impl FnOnce(&mut Self) -> T) -> T {
|
2019-08-11 11:14:30 +00:00
|
|
|
let old = self.restrictions;
|
2019-09-30 01:29:41 +00:00
|
|
|
self.restrictions = res;
|
|
|
|
let res = f(self);
|
2019-08-11 11:14:30 +00:00
|
|
|
self.restrictions = old;
|
2019-09-30 01:29:41 +00:00
|
|
|
res
|
2019-08-11 11:14:30 +00:00
|
|
|
}
|
2011-01-01 01:28:43 +00:00
|
|
|
|
2022-05-21 18:45:14 +00:00
|
|
|
/// Parses `pub` and `pub(in path)` plus shortcuts `pub(crate)` for `pub(in crate)`, `pub(self)`
|
|
|
|
/// for `pub(in self)` and `pub(super)` for `pub(in super)`.
|
2019-08-11 16:34:42 +00:00
|
|
|
/// If the following element can't be a tuple (i.e., it's a function definition), then
|
2021-10-17 10:04:01 +00:00
|
|
|
/// it's not a tuple struct field), and the contents within the parentheses aren't valid,
|
2019-08-11 16:34:42 +00:00
|
|
|
/// so emit a proper diagnostic.
|
2020-08-30 18:04:36 +00:00
|
|
|
// Public for rustfmt usage.
|
|
|
|
pub fn parse_visibility(&mut self, fbt: FollowedByType) -> PResult<'a, Visibility> {
|
2024-04-17 02:17:09 +00:00
|
|
|
if let Some(vis) = self
|
|
|
|
.eat_metavar_seq(MetaVarKind::Vis, |this| this.parse_visibility(FollowedByType::Yes))
|
|
|
|
{
|
|
|
|
return Ok(vis);
|
|
|
|
}
|
2012-08-16 00:10:23 +00:00
|
|
|
|
2024-12-04 04:55:06 +00:00
|
|
|
if !self.eat_keyword(exp!(Pub)) {
|
2019-08-11 16:34:42 +00:00
|
|
|
// We need a span for our `Spanned<VisibilityKind>`, but there's inherently no
|
|
|
|
// keyword to grab a span from for inherited visibility; an empty span at the
|
|
|
|
// beginning of the current token would seem to be the "Schelling span".
|
2020-08-21 23:11:00 +00:00
|
|
|
return Ok(Visibility {
|
|
|
|
span: self.token.span.shrink_to_lo(),
|
|
|
|
kind: VisibilityKind::Inherited,
|
|
|
|
tokens: None,
|
|
|
|
});
|
2019-08-11 16:34:42 +00:00
|
|
|
}
|
2020-02-29 11:56:15 +00:00
|
|
|
let lo = self.prev_token.span;
|
2017-03-07 23:50:13 +00:00
|
|
|
|
2024-12-04 04:55:06 +00:00
|
|
|
if self.check(exp!(OpenParen)) {
|
2017-03-18 04:13:00 +00:00
|
|
|
// We don't `self.bump()` the `(` yet because this might be a struct definition where
|
|
|
|
// `()` or a tuple might be allowed. For example, `struct Struct(pub (), pub (usize));`.
|
|
|
|
// Because of this, we only `bump` the `(` if we're assured it is appropriate to do so
|
|
|
|
// by the following tokens.
|
2022-05-21 18:45:14 +00:00
|
|
|
if self.is_keyword_ahead(1, &[kw::In]) {
|
2019-10-01 03:53:23 +00:00
|
|
|
// Parse `pub(in path)`.
|
|
|
|
self.bump(); // `(`
|
|
|
|
self.bump(); // `in`
|
|
|
|
let path = self.parse_path(PathStyle::Mod)?; // `path`
|
2024-12-04 04:55:06 +00:00
|
|
|
self.expect(exp!(CloseParen))?; // `)`
|
2022-08-10 03:31:45 +00:00
|
|
|
let vis = VisibilityKind::Restricted {
|
|
|
|
path: P(path),
|
|
|
|
id: ast::DUMMY_NODE_ID,
|
|
|
|
shorthand: false,
|
|
|
|
};
|
2020-08-21 23:11:00 +00:00
|
|
|
return Ok(Visibility {
|
|
|
|
span: lo.to(self.prev_token.span),
|
|
|
|
kind: vis,
|
|
|
|
tokens: None,
|
|
|
|
});
|
2022-04-26 12:40:14 +00:00
|
|
|
} else if self.look_ahead(2, |t| t == &token::CloseDelim(Delimiter::Parenthesis))
|
2022-05-21 18:45:14 +00:00
|
|
|
&& self.is_keyword_ahead(1, &[kw::Crate, kw::Super, kw::SelfLower])
|
2018-01-27 07:13:50 +00:00
|
|
|
{
|
2022-05-21 18:45:14 +00:00
|
|
|
// Parse `pub(crate)`, `pub(self)`, or `pub(super)`.
|
2019-10-01 03:53:23 +00:00
|
|
|
self.bump(); // `(`
|
2022-05-21 18:45:14 +00:00
|
|
|
let path = self.parse_path(PathStyle::Mod)?; // `crate`/`super`/`self`
|
2024-12-04 04:55:06 +00:00
|
|
|
self.expect(exp!(CloseParen))?; // `)`
|
2022-08-10 03:31:45 +00:00
|
|
|
let vis = VisibilityKind::Restricted {
|
|
|
|
path: P(path),
|
|
|
|
id: ast::DUMMY_NODE_ID,
|
|
|
|
shorthand: true,
|
|
|
|
};
|
2020-08-21 23:11:00 +00:00
|
|
|
return Ok(Visibility {
|
|
|
|
span: lo.to(self.prev_token.span),
|
|
|
|
kind: vis,
|
|
|
|
tokens: None,
|
|
|
|
});
|
2019-11-07 10:26:36 +00:00
|
|
|
} else if let FollowedByType::No = fbt {
|
|
|
|
// Provide this diagnostic if a type cannot follow;
|
|
|
|
// in particular, if this is not a tuple struct.
|
2019-09-30 04:42:56 +00:00
|
|
|
self.recover_incorrect_vis_restriction()?;
|
|
|
|
// Emit diagnostic, but continue with public visibility.
|
2016-04-23 05:40:55 +00:00
|
|
|
}
|
2016-04-11 00:39:35 +00:00
|
|
|
}
|
2017-03-07 23:50:13 +00:00
|
|
|
|
2020-08-21 23:11:00 +00:00
|
|
|
Ok(Visibility { span: lo, kind: VisibilityKind::Public, tokens: None })
|
2012-02-23 05:47:23 +00:00
|
|
|
}
|
2013-03-22 19:56:10 +00:00
|
|
|
|
2019-09-30 04:42:56 +00:00
|
|
|
/// Recovery for e.g. `pub(something) fn ...` or `struct X { pub(something) y: Z }`
|
|
|
|
fn recover_incorrect_vis_restriction(&mut self) -> PResult<'a, ()> {
|
|
|
|
self.bump(); // `(`
|
|
|
|
let path = self.parse_path(PathStyle::Mod)?;
|
2024-12-04 04:55:06 +00:00
|
|
|
self.expect(exp!(CloseParen))?; // `)`
|
2019-09-30 04:42:56 +00:00
|
|
|
|
2019-10-08 20:17:46 +00:00
|
|
|
let path_str = pprust::path_to_string(&path);
|
2023-12-18 10:14:02 +00:00
|
|
|
self.dcx()
|
|
|
|
.emit_err(IncorrectVisibilityRestriction { span: path.span, inner_str: path_str });
|
2019-09-30 04:42:56 +00:00
|
|
|
|
|
|
|
Ok(())
|
|
|
|
}
|
|
|
|
|
2019-10-27 23:29:23 +00:00
|
|
|
/// Parses `extern string_literal?`.
|
2022-09-15 16:27:23 +00:00
|
|
|
fn parse_extern(&mut self, case: Case) -> Extern {
|
2024-12-04 04:55:06 +00:00
|
|
|
if self.eat_keyword_case(exp!(Extern), case) {
|
2022-07-02 17:25:55 +00:00
|
|
|
let mut extern_span = self.prev_token.span;
|
|
|
|
let abi = self.parse_abi();
|
|
|
|
if let Some(abi) = abi {
|
|
|
|
extern_span = extern_span.to(abi.span);
|
|
|
|
}
|
|
|
|
Extern::from_abi(abi, extern_span)
|
|
|
|
} else {
|
|
|
|
Extern::None
|
|
|
|
}
|
2019-09-29 23:22:18 +00:00
|
|
|
}
|
|
|
|
|
2019-10-27 23:29:23 +00:00
|
|
|
/// Parses a string literal as an ABI spec.
|
2019-11-10 14:04:12 +00:00
|
|
|
fn parse_abi(&mut self) -> Option<StrLit> {
|
|
|
|
match self.parse_str_lit() {
|
|
|
|
Ok(str_lit) => Some(str_lit),
|
|
|
|
Err(Some(lit)) => match lit.kind {
|
2024-02-14 09:12:05 +00:00
|
|
|
ast::LitKind::Err(_) => None,
|
2019-10-27 23:29:23 +00:00
|
|
|
_ => {
|
2023-12-18 10:14:02 +00:00
|
|
|
self.dcx().emit_err(NonStringAbiLiteral { span: lit.span });
|
2019-11-10 14:04:12 +00:00
|
|
|
None
|
2019-10-27 23:29:23 +00:00
|
|
|
}
|
2019-12-22 22:42:04 +00:00
|
|
|
},
|
2019-11-10 14:04:12 +00:00
|
|
|
Err(None) => None,
|
2019-11-09 19:05:20 +00:00
|
|
|
}
|
2013-03-14 02:25:28 +00:00
|
|
|
}
|
|
|
|
|
2024-06-03 05:47:46 +00:00
|
|
|
fn collect_tokens_no_attrs<R: HasAttrs + HasTokens>(
|
2021-01-14 15:42:01 +00:00
|
|
|
&mut self,
|
|
|
|
f: impl FnOnce(&mut Self) -> PResult<'a, R>,
|
|
|
|
) -> PResult<'a, R> {
|
2021-01-22 18:28:08 +00:00
|
|
|
// The only reason to call `collect_tokens_no_attrs` is if you want tokens, so use
|
|
|
|
// `ForceCollect::Yes`
|
2024-08-06 07:16:40 +00:00
|
|
|
self.collect_tokens(None, AttrWrapper::empty(), ForceCollect::Yes, |this, _attrs| {
|
|
|
|
Ok((f(this)?, Trailing::No, UsePreAttrPos::No))
|
|
|
|
})
|
2021-01-14 15:42:01 +00:00
|
|
|
}
|
|
|
|
|
2024-09-21 17:07:52 +00:00
|
|
|
/// Checks for `::` or, potentially, `:::` and then look ahead after it.
|
|
|
|
fn check_path_sep_and_look_ahead(&mut self, looker: impl Fn(&Token) -> bool) -> bool {
|
2024-12-04 04:55:06 +00:00
|
|
|
if self.check(exp!(PathSep)) {
|
2024-09-21 17:07:52 +00:00
|
|
|
if self.may_recover() && self.look_ahead(1, |t| t.kind == token::Colon) {
|
|
|
|
debug_assert!(!self.look_ahead(1, &looker), "Looker must not match on colon");
|
|
|
|
self.look_ahead(2, looker)
|
|
|
|
} else {
|
|
|
|
self.look_ahead(1, looker)
|
|
|
|
}
|
|
|
|
} else {
|
|
|
|
false
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2018-03-10 15:44:44 +00:00
|
|
|
/// `::{` or `::*`
|
|
|
|
fn is_import_coupler(&mut self) -> bool {
|
2024-09-21 17:07:52 +00:00
|
|
|
self.check_path_sep_and_look_ahead(|t| {
|
|
|
|
matches!(t.kind, token::OpenDelim(Delimiter::Brace) | token::BinOp(token::Star))
|
|
|
|
})
|
2016-04-17 00:48:40 +00:00
|
|
|
}
|
2020-08-31 09:45:50 +00:00
|
|
|
|
2024-06-03 05:47:46 +00:00
|
|
|
// Debug view of the parser's token stream, up to `{lookahead}` tokens.
|
|
|
|
// Only used when debugging.
|
|
|
|
#[allow(unused)]
|
2025-02-20 18:58:46 +00:00
|
|
|
pub(crate) fn debug_lookahead(&self, lookahead: usize) -> impl fmt::Debug {
|
2025-01-23 19:48:54 +00:00
|
|
|
fmt::from_fn(move |f| {
|
|
|
|
let mut dbg_fmt = f.debug_struct("Parser"); // or at least, one view of
|
|
|
|
|
|
|
|
// we don't need N spans, but we want at least one, so print all of prev_token
|
|
|
|
dbg_fmt.field("prev_token", &self.prev_token);
|
|
|
|
let mut tokens = vec![];
|
|
|
|
for i in 0..lookahead {
|
|
|
|
let tok = self.look_ahead(i, |tok| tok.kind.clone());
|
|
|
|
let is_eof = tok == TokenKind::Eof;
|
|
|
|
tokens.push(tok);
|
|
|
|
if is_eof {
|
|
|
|
// Don't look ahead past EOF.
|
|
|
|
break;
|
2024-05-05 22:41:00 +00:00
|
|
|
}
|
2025-01-23 19:48:54 +00:00
|
|
|
}
|
|
|
|
dbg_fmt.field_with("tokens", |field| field.debug_list().entries(tokens).finish());
|
|
|
|
dbg_fmt.field("approx_token_stream_pos", &self.num_bump_calls);
|
2024-05-05 22:41:00 +00:00
|
|
|
|
2025-01-23 19:48:54 +00:00
|
|
|
// some fields are interesting for certain values, as they relate to macro parsing
|
|
|
|
if let Some(subparser) = self.subparser_name {
|
|
|
|
dbg_fmt.field("subparser_name", &subparser);
|
|
|
|
}
|
|
|
|
if let Recovery::Forbidden = self.recovery {
|
|
|
|
dbg_fmt.field("recovery", &self.recovery);
|
2024-05-05 22:41:00 +00:00
|
|
|
}
|
|
|
|
|
2025-01-23 19:48:54 +00:00
|
|
|
// imply there's "more to know" than this view
|
|
|
|
dbg_fmt.finish_non_exhaustive()
|
|
|
|
})
|
2024-05-05 22:41:00 +00:00
|
|
|
}
|
|
|
|
|
2024-12-03 09:09:29 +00:00
|
|
|
pub fn clear_expected_token_types(&mut self) {
|
|
|
|
self.expected_token_types.clear();
|
2020-08-31 09:45:50 +00:00
|
|
|
}
|
2022-12-11 20:46:30 +00:00
|
|
|
|
2024-07-02 06:31:24 +00:00
|
|
|
pub fn approx_token_stream_pos(&self) -> u32 {
|
2023-07-31 06:15:54 +00:00
|
|
|
self.num_bump_calls
|
2022-12-11 20:46:30 +00:00
|
|
|
}
|
2011-01-11 02:18:16 +00:00
|
|
|
}
|
2019-02-05 09:35:25 +00:00
|
|
|
|
2022-05-20 23:51:09 +00:00
|
|
|
pub(crate) fn make_unclosed_delims_error(
|
2023-02-21 14:51:19 +00:00
|
|
|
unmatched: UnmatchedDelim,
|
2024-03-04 05:31:49 +00:00
|
|
|
psess: &ParseSess,
|
2024-02-22 23:20:45 +00:00
|
|
|
) -> Option<Diag<'_>> {
|
2019-10-26 01:30:02 +00:00
|
|
|
// `None` here means an `Eof` was found. We already emit those errors elsewhere, we add them to
|
2023-02-21 14:51:19 +00:00
|
|
|
// `unmatched_delims` only for error recovery in the `Parser`.
|
2019-10-26 01:30:02 +00:00
|
|
|
let found_delim = unmatched.found_delim?;
|
2022-08-24 20:41:51 +00:00
|
|
|
let mut spans = vec![unmatched.found_span];
|
2019-10-26 01:30:02 +00:00
|
|
|
if let Some(sp) = unmatched.unclosed_span {
|
2022-08-24 20:41:51 +00:00
|
|
|
spans.push(sp);
|
|
|
|
};
|
2024-06-18 09:43:28 +00:00
|
|
|
let err = psess.dcx().create_err(MismatchedClosingDelimiter {
|
2022-08-24 20:41:51 +00:00
|
|
|
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,
|
2023-12-18 03:00:17 +00:00
|
|
|
});
|
2019-10-26 01:30:02 +00:00
|
|
|
Some(err)
|
|
|
|
}
|
|
|
|
|
2022-09-09 02:44:05 +00:00
|
|
|
/// A helper struct used when building an `AttrTokenStream` from
|
2022-09-09 07:15:53 +00:00
|
|
|
/// a `LazyAttrTokenStream`. Both delimiter and non-delimited tokens
|
2020-11-28 23:33:17 +00:00
|
|
|
/// are stored as `FlatToken::Token`. A vector of `FlatToken`s
|
2022-09-09 02:44:05 +00:00
|
|
|
/// is then 'parsed' to build up an `AttrTokenStream` with nested
|
|
|
|
/// `AttrTokenTree::Delimited` tokens.
|
2020-11-28 23:33:17 +00:00
|
|
|
#[derive(Debug, Clone)]
|
2024-06-03 05:47:46 +00:00
|
|
|
enum FlatToken {
|
2020-11-28 23:33:17 +00:00
|
|
|
/// A token - this holds both delimiter (e.g. '{' and '}')
|
|
|
|
/// and non-delimiter tokens
|
2024-07-08 09:32:21 +00:00
|
|
|
Token((Token, Spacing)),
|
2024-07-07 06:14:30 +00:00
|
|
|
/// Holds the `AttrsTarget` for an AST node. The `AttrsTarget` is inserted
|
|
|
|
/// directly into the constructed `AttrTokenStream` as an
|
|
|
|
/// `AttrTokenTree::AttrsTarget`.
|
|
|
|
AttrsTarget(AttrsTarget),
|
2020-11-28 23:33:17 +00:00
|
|
|
/// A special 'empty' token that is ignored during the conversion
|
2022-09-09 02:44:05 +00:00
|
|
|
/// to an `AttrTokenStream`. This is used to simplify the
|
2020-11-28 23:33:17 +00:00
|
|
|
/// handling of replace ranges.
|
|
|
|
Empty,
|
|
|
|
}
|
2022-03-25 01:39:12 +00:00
|
|
|
|
2024-03-19 02:33:33 +00:00
|
|
|
// Metavar captures of various kinds.
|
|
|
|
#[derive(Clone, Debug)]
|
2024-04-22 06:29:27 +00:00
|
|
|
pub enum ParseNtResult {
|
2022-03-25 01:39:12 +00:00
|
|
|
Tt(TokenTree),
|
2024-04-22 09:46:51 +00:00
|
|
|
Ident(Ident, IdentIsRaw),
|
2024-09-05 09:43:55 +00:00
|
|
|
Lifetime(Ident, IdentIsRaw),
|
Remove `NtPat`.
The one notable test change is `tests/ui/macros/trace_faulty_macros.rs`.
This commit removes the complicated `Interpolated` handling in
`expected_expression_found` that results in a longer error message. But
I think the new, shorter message is actually an improvement.
The original complaint was in #71039, when the error message started
with "error: expected expression, found `1 + 1`". That was confusing
because `1 + 1` is an expression. Other than that, the reporter said
"the whole error message is not too bad if you ignore the first line".
Subsequently, extra complexity and wording was added to the error
message. But I don't think the extra wording actually helps all that
much. In particular, it still says of the `1+1` that "this is expected
to be expression". This repeats the problem from the original complaint!
This commit removes the extra complexity, reverting to a simpler error
message. This is primarily because the traversal is a pain without
`Interpolated` tokens. Nonetheless, I think the error message is
*improved*. It now starts with "expected expression, found `pat`
metavariable", which is much clearer and the real problem. It also
doesn't say anything specific about `1+1`, which is good, because the
`1+1` isn't really relevant to the error -- it's the `$e:pat` that's
important.
2024-04-18 02:44:11 +00:00
|
|
|
Pat(P<ast::Pat>, NtPatKind),
|
2024-04-17 03:17:44 +00:00
|
|
|
Ty(P<ast::Ty>),
|
2024-04-18 06:22:02 +00:00
|
|
|
Meta(P<ast::AttrItem>),
|
2024-04-18 10:09:37 +00:00
|
|
|
Path(P<ast::Path>),
|
2024-04-17 02:17:09 +00:00
|
|
|
Vis(P<ast::Visibility>),
|
2024-04-22 09:46:51 +00:00
|
|
|
|
2024-04-17 02:17:09 +00:00
|
|
|
/// This variant will eventually be removed, along with `Token::Interpolate`.
|
2025-02-03 03:44:41 +00:00
|
|
|
Nt(Arc<Nonterminal>),
|
2022-03-25 01:39:12 +00:00
|
|
|
}
|