Speed up Parser::expected_token_types
.
The parser pushes a `TokenType` to `Parser::expected_token_types` on every call to the various `check`/`eat` methods, and clears it on every call to `bump`. Some of those `TokenType` values are full tokens that require cloning and dropping. This is a *lot* of work for something that is only used in error messages and it accounts for a significant fraction of parsing execution time. This commit overhauls `TokenType` so that `Parser::expected_token_types` can be implemented as a bitset. This requires changing `TokenType` to a C-style parameterless enum, and adding `TokenTypeSet` which uses a `u128` for the bits. (The new `TokenType` has 105 variants.) The new types `ExpTokenPair` and `ExpKeywordPair` are now arguments to the `check`/`eat` methods. This is for maximum speed. The elements in the pairs are always statically known; e.g. a `token::BinOp(token::Star)` is always paired with a `TokenType::Star`. So we now compute `TokenType`s in advance and pass them in to `check`/`eat` rather than the current approach of constructing them on insertion into `expected_token_types`. Values of these pair types can be produced by the new `exp!` macro, which is used at every `check`/`eat` call site. The macro is for convenience, allowing any pair to be generated from a single identifier. The ident/keyword filtering in `expected_one_of_not_found` is no longer necessary. It was there to account for some sloppiness in `TokenKind`/`TokenType` comparisons. The existing `TokenType` is moved to a new file `token_type.rs`, and all its new infrastructure is added to that file. There is more boilerplate code than I would like, but I can't see how to make it shorter.
This commit is contained in:
parent
d5370d981f
commit
b9bf0b4b10
22 changed files with 1357 additions and 793 deletions
|
@ -2,9 +2,9 @@ use std::iter::once;
|
|||
use std::path::{self, Path, PathBuf};
|
||||
|
||||
use rustc_ast::ptr::P;
|
||||
use rustc_ast::{AttrVec, Attribute, Inline, Item, ModSpans, token};
|
||||
use rustc_ast::{AttrVec, Attribute, Inline, Item, ModSpans};
|
||||
use rustc_errors::{Diag, ErrorGuaranteed};
|
||||
use rustc_parse::{new_parser_from_file, unwrap_or_emit_fatal, validate_attr};
|
||||
use rustc_parse::{exp, new_parser_from_file, unwrap_or_emit_fatal, validate_attr};
|
||||
use rustc_session::Session;
|
||||
use rustc_session::parse::ParseSess;
|
||||
use rustc_span::{Ident, Span, sym};
|
||||
|
@ -70,7 +70,7 @@ pub(crate) fn parse_external_mod(
|
|||
let mut parser =
|
||||
unwrap_or_emit_fatal(new_parser_from_file(&sess.psess, &mp.file_path, Some(span)));
|
||||
let (inner_attrs, items, inner_span) =
|
||||
parser.parse_mod(&token::Eof).map_err(|err| ModError::ParserError(err))?;
|
||||
parser.parse_mod(exp!(Eof)).map_err(|err| ModError::ParserError(err))?;
|
||||
attrs.extend(inner_attrs);
|
||||
(items, inner_span, mp.file_path)
|
||||
};
|
||||
|
|
|
@ -15,7 +15,7 @@ use rustc_data_structures::sync::Lrc;
|
|||
use rustc_errors::{Diag, ErrorGuaranteed, MultiSpan, PResult};
|
||||
use rustc_parse::lexer::nfc_normalize;
|
||||
use rustc_parse::parser::Parser;
|
||||
use rustc_parse::{new_parser_from_source_str, source_str_to_stream, unwrap_or_emit_fatal};
|
||||
use rustc_parse::{exp, new_parser_from_source_str, source_str_to_stream, unwrap_or_emit_fatal};
|
||||
use rustc_session::parse::ParseSess;
|
||||
use rustc_span::def_id::CrateNum;
|
||||
use rustc_span::{BytePos, FileName, Pos, SourceFile, Span, Symbol, sym};
|
||||
|
@ -473,7 +473,7 @@ impl server::FreeFunctions for Rustc<'_, '_> {
|
|||
unwrap_or_emit_fatal(new_parser_from_source_str(self.psess(), name, s.to_owned()));
|
||||
|
||||
let first_span = parser.token.span.data();
|
||||
let minus_present = parser.eat(&token::BinOp(token::Minus));
|
||||
let minus_present = parser.eat(exp!(Minus));
|
||||
|
||||
let lit_span = parser.token.span.data();
|
||||
let token::Literal(mut lit) = parser.token.kind else {
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue