bjoernager/rust
bjoernager/rust
1
Fork 0
Code Activity

Rollup merge of #134161 - nnethercote:overhaul-token-cursors, r=spastorino

Browse source 
Overhaul token cursors

Some nice cleanups here.

r? `````@davidtwco`````
This commit is contained in:
许杰友 Jieyou Xu (Joe) 2024-12-18 22:56:53 +08:00 • committed by GitHub
commit 477f222b02
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
20 changed files with 199 additions and 210 deletions
Download patch file Download diff file Expand all files Collapse all files

4
compiler/rustc_parse/src/parser/expr.rs
View file

@ -8,6 +8,7 @@ use ast::token::IdentIsRaw;
use ast::{CoroutineKind, ForLoopKind, GenBlockKind, MatchKind, Pat, Path, PathSegment, Recovered};
use rustc_ast::ptr::P;
use rustc_ast::token::{self, Delimiter, Token, TokenKind};
use rustc_ast::tokenstream::TokenTree;
use rustc_ast::util::case::Case;
use rustc_ast::util::classify;
use rustc_ast::util::parser::{AssocOp, ExprPrecedence, Fixity, prec_let_scrutinee_needs_par};
@ -2392,7 +2393,8 @@ impl<'a> Parser<'a> {
}
if self.token == TokenKind::Semi
&& matches!(self.token_cursor.stack.last(), Some((.., Delimiter::Parenthesis)))
&& let Some(last) = self.token_cursor.stack.last()
&& let Some(TokenTree::Delimited(_, _, Delimiter::Parenthesis, _)) = last.curr()
&& self.may_recover()
{
// It is likely that the closure body is a block but where the

90
compiler/rustc_parse/src/parser/mod.rs
View file

@ -24,9 +24,7 @@ use rustc_ast::ptr::P;
use rustc_ast::token::{
self, Delimiter, IdentIsRaw, InvisibleOrigin, MetaVarKind, Nonterminal, Token, TokenKind,
};
use rustc_ast::tokenstream::{
AttrsTarget, DelimSpacing, DelimSpan, Spacing, TokenStream, TokenTree, TokenTreeCursor,
};
use rustc_ast::tokenstream::{AttrsTarget, Spacing, TokenStream, TokenTree};
use rustc_ast::util::case::Case;
use rustc_ast::{
self as ast, AnonConst, AttrArgs, AttrId, ByRef, Const, CoroutineKind, DUMMY_NODE_ID,
@ -272,21 +270,48 @@ struct CaptureState {
seen_attrs: IntervalSet<AttrId>,
}
/// Iterator over a `TokenStream` that produces `Token`s. It's a bit odd that
#[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
/// 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.
#[derive(Clone, Debug)]
struct TokenCursor {
// Cursor for the current (innermost) token stream. The delimiters for this
// token stream are found in `self.stack.last()`; when that is `None` then
// we are in the outermost token stream which never has delimiters.
tree_cursor: TokenTreeCursor,
// 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 delimiters for stack[n]'s
// tokens are in `stack[n-1]`. `stack[0]` (when present) has no delimiters
// because it's the outermost token stream which never has delimiters.
stack: Vec<(TokenTreeCursor, DelimSpan, DelimSpacing, Delimiter)>,
// Token streams surrounding the current one. The index within each cursor
// always points to a `TokenTree::Delimited`.
stack: Vec<TokenTreeCursor>,
}
impl TokenCursor {
@ -301,32 +326,33 @@ impl TokenCursor {
// 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.
if let Some(tree) = self.tree_cursor.next_ref() {
if let Some(tree) = self.curr.curr() {
match tree {
&TokenTree::Token(ref token, spacing) => {
debug_assert!(!matches!(
token.kind,
token::OpenDelim(_) | token::CloseDelim(_)
));
return (token.clone(), spacing);
let res = (token.clone(), spacing);
self.curr.bump();
return res;
}
&TokenTree::Delimited(sp, spacing, delim, ref tts) => {
let trees = tts.clone().into_trees();
self.stack.push((
mem::replace(&mut self.tree_cursor, trees),
sp,
spacing,
delim,
));
let trees = TokenTreeCursor::new(tts.clone());
self.stack.push(mem::replace(&mut self.curr, trees));
if !delim.skip() {
return (Token::new(token::OpenDelim(delim), sp.open), spacing.open);
}
// No open delimiter to return; continue on to the next iteration.
}
};
} else if let Some((tree_cursor, span, spacing, delim)) = self.stack.pop() {
} else if let Some(parent) = self.stack.pop() {
// We have exhausted this token stream. Move back to its parent token stream.
self.tree_cursor = tree_cursor;
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`
if !delim.skip() {
return (Token::new(token::CloseDelim(delim), span.close), spacing.close);
}
@ -465,7 +491,7 @@ impl<'a> Parser<'a> {
capture_cfg: false,
restrictions: Restrictions::empty(),
expected_tokens: Vec::new(),
token_cursor: TokenCursor { tree_cursor: stream.into_trees(), stack: Vec::new() },
token_cursor: TokenCursor { curr: TokenTreeCursor::new(stream), stack: Vec::new() },
num_bump_calls: 0,
break_last_token: 0,
unmatched_angle_bracket_count: 0,
@ -1191,7 +1217,7 @@ impl<'a> Parser<'a> {
if dist == 1 {
// The index is zero because the tree cursor's index always points
// to the next token to be gotten.
match self.token_cursor.tree_cursor.look_ahead(0) {
match self.token_cursor.curr.curr() {
Some(tree) => {
// Indexing stayed within the current token tree.
match tree {
@ -1201,12 +1227,13 @@ impl<'a> Parser<'a> {
return looker(&Token::new(token::OpenDelim(delim), dspan.open));
}
}
};
}
}
None => {
// The tree cursor lookahead went (one) past the end of the
// current token tree. Try to return a close delimiter.
if let Some(&(_, span, _, delim)) = self.token_cursor.stack.last()
if let Some(last) = self.token_cursor.stack.last()
&& let Some(&TokenTree::Delimited(span, _, delim, _)) = last.curr()
&& !delim.skip()
{
// We are not in the outermost token stream, so we have
@ -1398,9 +1425,10 @@ impl<'a> Parser<'a> {
pub fn parse_token_tree(&mut self) -> TokenTree {
match self.token.kind {
token::OpenDelim(..) => {
// Grab the tokens within the delimiters.
let stream = self.token_cursor.tree_cursor.stream.clone();
let (_, span, spacing, delim) = *self.token_cursor.stack.last().unwrap();
// 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(..));
// Advance the token cursor through the entire delimited
// sequence. After getting the `OpenDelim` we are *within* the
@ -1420,7 +1448,7 @@ impl<'a> Parser<'a> {
// Consume close delimiter
self.bump();
TokenTree::Delimited(span, spacing, delim, stream)
tree
}
token::CloseDelim(_) | token::Eof => unreachable!(),
_ => {

10
compiler/rustc_parse/src/parser/tests.rs
View file

@ -2286,7 +2286,7 @@ fn bad_path_expr_1() {
fn string_to_tts_macro() {
create_default_session_globals_then(|| {
let stream = string_to_stream("macro_rules! zip (($a)=>($a))".to_string());
let tts = &stream.trees().collect::<Vec<_>>()[..];
let tts = &stream.iter().collect::<Vec<_>>()[..];
match tts {
[
@ -2298,14 +2298,14 @@ fn string_to_tts_macro() {
TokenTree::Token(Token { kind: token::Ident(name_zip, IdentIsRaw::No), .. }, _),
TokenTree::Delimited(.., macro_delim, macro_tts),
] if name_macro_rules == &kw::MacroRules && name_zip.as_str() == "zip" => {
let tts = &macro_tts.trees().collect::<Vec<_>>();
let tts = &macro_tts.iter().collect::<Vec<_>>();
match &tts[..] {
[
TokenTree::Delimited(.., first_delim, first_tts),
TokenTree::Token(Token { kind: token::FatArrow, .. }, _),
TokenTree::Delimited(.., second_delim, second_tts),
] if macro_delim == &Delimiter::Parenthesis => {
let tts = &first_tts.trees().collect::<Vec<_>>();
let tts = &first_tts.iter().collect::<Vec<_>>();
match &tts[..] {
[
TokenTree::Token(Token { kind: token::Dollar, .. }, _),
@ -2317,7 +2317,7 @@ fn string_to_tts_macro() {
}
_ => panic!("value 3: {:?} {:?}", first_delim, first_tts),
}
let tts = &second_tts.trees().collect::<Vec<_>>();
let tts = &second_tts.iter().collect::<Vec<_>>();
match &tts[..] {
[
TokenTree::Token(Token { kind: token::Dollar, .. }, _),
@ -2545,7 +2545,7 @@ fn ttdelim_span() {
.unwrap();
let ast::ExprKind::MacCall(mac) = &expr.kind else { panic!("not a macro") };
let span = mac.args.tokens.trees().last().unwrap().span();
let span = mac.args.tokens.iter().last().unwrap().span();
match psess.source_map().span_to_snippet(span) {
Ok(s) => assert_eq!(&s[..], "{ body }"),

8
compiler/rustc_parse/src/parser/tokenstream/tests.rs
View file

@ -23,8 +23,8 @@ fn test_concat() {
let mut eq_res = TokenStream::default();
eq_res.push_stream(test_fst);
eq_res.push_stream(test_snd);
assert_eq!(test_res.trees().count(), 5);
assert_eq!(eq_res.trees().count(), 5);
assert_eq!(test_res.iter().count(), 5);
assert_eq!(eq_res.iter().count(), 5);
assert_eq!(test_res.eq_unspanned(&eq_res), true);
})
}
@ -33,7 +33,7 @@ fn test_concat() {
fn test_to_from_bijection() {
create_default_session_globals_then(|| {
let test_start = string_to_ts("foo::bar(baz)");
let test_end = test_start.trees().cloned().collect();
let test_end = test_start.iter().cloned().collect();
assert_eq!(test_start, test_end)
})
}
@ -105,6 +105,6 @@ fn test_dotdotdot() {
stream.push_tree(TokenTree::token_joint(token::Dot, sp(1, 2)));
stream.push_tree(TokenTree::token_alone(token::Dot, sp(2, 3)));
assert!(stream.eq_unspanned(&string_to_ts("...")));
assert_eq!(stream.trees().count(), 1);
assert_eq!(stream.iter().count(), 1);
})
}