1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751
//! # Token Streams
//!
//! `TokenStream`s represent syntactic objects before they are converted into ASTs.
//! A `TokenStream` is, roughly speaking, a sequence of [`TokenTree`]s,
//! which are themselves a single [`Token`] or a `Delimited` subsequence of tokens.
//!
//! ## Ownership
//!
//! `TokenStream`s are persistent data structures constructed as ropes with reference
//! counted-children. In general, this means that calling an operation on a `TokenStream`
//! (such as `slice`) produces an entirely new `TokenStream` from the borrowed reference to
//! the original. This essentially coerces `TokenStream`s into "views" of their subparts,
//! and a borrowed `TokenStream` is sufficient to build an owned `TokenStream` without taking
//! ownership of the original.
use crate::ast::{AttrStyle, StmtKind};
use crate::ast_traits::{HasAttrs, HasSpan, HasTokens};
use crate::token::{self, Delimiter, Nonterminal, Token, TokenKind};
use crate::AttrVec;
use rustc_data_structures::stable_hasher::{HashStable, StableHasher};
use rustc_data_structures::sync::{self, Lrc};
use rustc_macros::HashStable_Generic;
use rustc_serialize::{Decodable, Decoder, Encodable, Encoder};
use rustc_span::{sym, Span, Symbol, DUMMY_SP};
use smallvec::{smallvec, SmallVec};
use std::borrow::Cow;
use std::{cmp, fmt, iter, mem};
/// When the main Rust parser encounters a syntax-extension invocation, it
/// parses the arguments to the invocation as a token tree. This is a very
/// loose structure, such that all sorts of different AST fragments can
/// be passed to syntax extensions using a uniform type.
///
/// If the syntax extension is an MBE macro, it will attempt to match its
/// LHS token tree against the provided token tree, and if it finds a
/// match, will transcribe the RHS token tree, splicing in any captured
/// `macro_parser::matched_nonterminals` into the `SubstNt`s it finds.
///
/// The RHS of an MBE macro is the only place `SubstNt`s are substituted.
/// Nothing special happens to misnamed or misplaced `SubstNt`s.
#[derive(Debug, Clone, PartialEq, Encodable, Decodable, HashStable_Generic)]
pub enum TokenTree {
/// A single token. Should never be `OpenDelim` or `CloseDelim`, because
/// delimiters are implicitly represented by `Delimited`.
Token(Token, Spacing),
/// A delimited sequence of token trees.
Delimited(DelimSpan, Delimiter, TokenStream),
}
// Ensure all fields of `TokenTree` are `DynSend` and `DynSync`.
#[cfg(parallel_compiler)]
fn _dummy()
where
Token: sync::DynSend + sync::DynSync,
Spacing: sync::DynSend + sync::DynSync,
DelimSpan: sync::DynSend + sync::DynSync,
Delimiter: sync::DynSend + sync::DynSync,
TokenStream: sync::DynSend + sync::DynSync,
{
}
impl TokenTree {
/// Checks if this `TokenTree` is equal to the other, regardless of span information.
pub fn eq_unspanned(&self, other: &TokenTree) -> bool {
match (self, other) {
(TokenTree::Token(token, _), TokenTree::Token(token2, _)) => token.kind == token2.kind,
(TokenTree::Delimited(_, delim, tts), TokenTree::Delimited(_, delim2, tts2)) => {
delim == delim2 && tts.eq_unspanned(tts2)
}
_ => false,
}
}
/// Retrieves the `TokenTree`'s span.
pub fn span(&self) -> Span {
match self {
TokenTree::Token(token, _) => token.span,
TokenTree::Delimited(sp, ..) => sp.entire(),
}
}
/// Modify the `TokenTree`'s span in-place.
pub fn set_span(&mut self, span: Span) {
match self {
TokenTree::Token(token, _) => token.span = span,
TokenTree::Delimited(dspan, ..) => *dspan = DelimSpan::from_single(span),
}
}
/// Create a `TokenTree::Token` with alone spacing.
pub fn token_alone(kind: TokenKind, span: Span) -> TokenTree {
TokenTree::Token(Token::new(kind, span), Spacing::Alone)
}
/// Create a `TokenTree::Token` with joint spacing.
pub fn token_joint(kind: TokenKind, span: Span) -> TokenTree {
TokenTree::Token(Token::new(kind, span), Spacing::Joint)
}
pub fn uninterpolate(&self) -> Cow<'_, TokenTree> {
match self {
TokenTree::Token(token, spacing) => match token.uninterpolate() {
Cow::Owned(token) => Cow::Owned(TokenTree::Token(token, *spacing)),
Cow::Borrowed(_) => Cow::Borrowed(self),
},
_ => Cow::Borrowed(self),
}
}
}
impl<CTX> HashStable<CTX> for TokenStream
where
CTX: crate::HashStableContext,
{
fn hash_stable(&self, hcx: &mut CTX, hasher: &mut StableHasher) {
for sub_tt in self.trees() {
sub_tt.hash_stable(hcx, hasher);
}
}
}
pub trait ToAttrTokenStream: sync::DynSend + sync::DynSync {
fn to_attr_token_stream(&self) -> AttrTokenStream;
}
impl ToAttrTokenStream for AttrTokenStream {
fn to_attr_token_stream(&self) -> AttrTokenStream {
self.clone()
}
}
/// A lazy version of [`TokenStream`], which defers creation
/// of an actual `TokenStream` until it is needed.
/// `Box` is here only to reduce the structure size.
#[derive(Clone)]
pub struct LazyAttrTokenStream(Lrc<Box<dyn ToAttrTokenStream>>);
impl LazyAttrTokenStream {
pub fn new(inner: impl ToAttrTokenStream + 'static) -> LazyAttrTokenStream {
LazyAttrTokenStream(Lrc::new(Box::new(inner)))
}
pub fn to_attr_token_stream(&self) -> AttrTokenStream {
self.0.to_attr_token_stream()
}
}
impl fmt::Debug for LazyAttrTokenStream {
fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
write!(f, "LazyAttrTokenStream({:?})", self.to_attr_token_stream())
}
}
impl<S: Encoder> Encodable<S> for LazyAttrTokenStream {
fn encode(&self, s: &mut S) {
// Used by AST json printing.
Encodable::encode(&self.to_attr_token_stream(), s);
}
}
impl<D: Decoder> Decodable<D> for LazyAttrTokenStream {
fn decode(_d: &mut D) -> Self {
panic!("Attempted to decode LazyAttrTokenStream");
}
}
impl<CTX> HashStable<CTX> for LazyAttrTokenStream {
fn hash_stable(&self, _hcx: &mut CTX, _hasher: &mut StableHasher) {
panic!("Attempted to compute stable hash for LazyAttrTokenStream");
}
}
/// An `AttrTokenStream` is similar to a `TokenStream`, but with extra
/// information about the tokens for attribute targets. This is used
/// during expansion to perform early cfg-expansion, and to process attributes
/// during proc-macro invocations.
#[derive(Clone, Debug, Default, Encodable, Decodable)]
pub struct AttrTokenStream(pub Lrc<Vec<AttrTokenTree>>);
/// Like `TokenTree`, but for `AttrTokenStream`.
#[derive(Clone, Debug, Encodable, Decodable)]
pub enum AttrTokenTree {
Token(Token, Spacing),
Delimited(DelimSpan, Delimiter, AttrTokenStream),
/// Stores the attributes for an attribute target,
/// along with the tokens for that attribute target.
/// See `AttributesData` for more information
Attributes(AttributesData),
}
impl AttrTokenStream {
pub fn new(tokens: Vec<AttrTokenTree>) -> AttrTokenStream {
AttrTokenStream(Lrc::new(tokens))
}
/// Converts this `AttrTokenStream` to a plain `TokenStream`.
/// During conversion, `AttrTokenTree::Attributes` get 'flattened'
/// back to a `TokenStream` of the form `outer_attr attr_target`.
/// If there are inner attributes, they are inserted into the proper
/// place in the attribute target tokens.
pub fn to_tokenstream(&self) -> TokenStream {
let trees: Vec<_> = self
.0
.iter()
.flat_map(|tree| match &tree {
AttrTokenTree::Token(inner, spacing) => {
smallvec![TokenTree::Token(inner.clone(), *spacing)].into_iter()
}
AttrTokenTree::Delimited(span, delim, stream) => {
smallvec![TokenTree::Delimited(*span, *delim, stream.to_tokenstream()),]
.into_iter()
}
AttrTokenTree::Attributes(data) => {
let idx = data
.attrs
.partition_point(|attr| matches!(attr.style, crate::AttrStyle::Outer));
let (outer_attrs, inner_attrs) = data.attrs.split_at(idx);
let mut target_tokens: Vec<_> = data
.tokens
.to_attr_token_stream()
.to_tokenstream()
.0
.iter()
.cloned()
.collect();
if !inner_attrs.is_empty() {
let mut found = false;
// Check the last two trees (to account for a trailing semi)
for tree in target_tokens.iter_mut().rev().take(2) {
if let TokenTree::Delimited(span, delim, delim_tokens) = tree {
// Inner attributes are only supported on extern blocks, functions,
// impls, and modules. All of these have their inner attributes
// placed at the beginning of the rightmost outermost braced group:
// e.g. fn foo() { #![my_attr} }
//
// Therefore, we can insert them back into the right location
// without needing to do any extra position tracking.
//
// Note: Outline modules are an exception - they can
// have attributes like `#![my_attr]` at the start of a file.
// Support for custom attributes in this position is not
// properly implemented - we always synthesize fake tokens,
// so we never reach this code.
let mut stream = TokenStream::default();
for inner_attr in inner_attrs {
stream.push_stream(inner_attr.tokens());
}
stream.push_stream(delim_tokens.clone());
*tree = TokenTree::Delimited(*span, *delim, stream);
found = true;
break;
}
}
assert!(
found,
"Failed to find trailing delimited group in: {target_tokens:?}"
);
}
let mut flat: SmallVec<[_; 1]> =
SmallVec::with_capacity(target_tokens.len() + outer_attrs.len());
for attr in outer_attrs {
flat.extend(attr.tokens().0.iter().cloned());
}
flat.extend(target_tokens);
flat.into_iter()
}
})
.collect();
TokenStream::new(trees)
}
}
/// Stores the tokens for an attribute target, along
/// with its attributes.
///
/// This is constructed during parsing when we need to capture
/// tokens.
///
/// For example, `#[cfg(FALSE)] struct Foo {}` would
/// have an `attrs` field containing the `#[cfg(FALSE)]` attr,
/// and a `tokens` field storing the (unparsed) tokens `struct Foo {}`
#[derive(Clone, Debug, Encodable, Decodable)]
pub struct AttributesData {
/// Attributes, both outer and inner.
/// These are stored in the original order that they were parsed in.
pub attrs: AttrVec,
/// The underlying tokens for the attribute target that `attrs`
/// are applied to
pub tokens: LazyAttrTokenStream,
}
/// A `TokenStream` is an abstract sequence of tokens, organized into [`TokenTree`]s.
///
/// The goal is for procedural macros to work with `TokenStream`s and `TokenTree`s
/// instead of a representation of the abstract syntax tree.
/// Today's `TokenTree`s can still contain AST via `token::Interpolated` for
/// backwards compatibility.
#[derive(Clone, Debug, Default, Encodable, Decodable)]
pub struct TokenStream(pub(crate) Lrc<Vec<TokenTree>>);
/// Similar to `proc_macro::Spacing`, but for tokens.
///
/// Note that all `ast::TokenTree::Token` instances have a `Spacing`, but when
/// we convert to `proc_macro::TokenTree` for proc macros only `Punct`
/// `TokenTree`s have a `proc_macro::Spacing`.
#[derive(Clone, Copy, Debug, PartialEq, Encodable, Decodable, HashStable_Generic)]
pub enum Spacing {
/// The token is not immediately followed by an operator token (as
/// determined by `Token::is_op`). E.g. a `+` token is `Alone` in `+ =`,
/// `+/*foo*/=`, `+ident`, and `+()`.
Alone,
/// The token is immediately followed by an operator token. E.g. a `+`
/// token is `Joint` in `+=` and `++`.
Joint,
}
impl TokenStream {
/// Given a `TokenStream` with a `Stream` of only two arguments, return a new `TokenStream`
/// separating the two arguments with a comma for diagnostic suggestions.
pub fn add_comma(&self) -> Option<(TokenStream, Span)> {
// Used to suggest if a user writes `foo!(a b);`
let mut suggestion = None;
let mut iter = self.0.iter().enumerate().peekable();
while let Some((pos, ts)) = iter.next() {
if let Some((_, next)) = iter.peek() {
let sp = match (&ts, &next) {
(_, TokenTree::Token(Token { kind: token::Comma, .. }, _)) => continue,
(
TokenTree::Token(token_left, Spacing::Alone),
TokenTree::Token(token_right, _),
) if ((token_left.is_ident() && !token_left.is_reserved_ident())
|| token_left.is_lit())
&& ((token_right.is_ident() && !token_right.is_reserved_ident())
|| token_right.is_lit()) =>
{
token_left.span
}
(TokenTree::Delimited(sp, ..), _) => sp.entire(),
_ => continue,
};
let sp = sp.shrink_to_hi();
let comma = TokenTree::token_alone(token::Comma, sp);
suggestion = Some((pos, comma, sp));
}
}
if let Some((pos, comma, sp)) = suggestion {
let mut new_stream = Vec::with_capacity(self.0.len() + 1);
let parts = self.0.split_at(pos + 1);
new_stream.extend_from_slice(parts.0);
new_stream.push(comma);
new_stream.extend_from_slice(parts.1);
return Some((TokenStream::new(new_stream), sp));
}
None
}
}
impl FromIterator<TokenTree> for TokenStream {
fn from_iter<I: IntoIterator<Item = TokenTree>>(iter: I) -> Self {
TokenStream::new(iter.into_iter().collect::<Vec<TokenTree>>())
}
}
impl Eq for TokenStream {}
impl PartialEq<TokenStream> for TokenStream {
fn eq(&self, other: &TokenStream) -> bool {
self.trees().eq(other.trees())
}
}
impl TokenStream {
pub fn new(streams: Vec<TokenTree>) -> TokenStream {
TokenStream(Lrc::new(streams))
}
pub fn is_empty(&self) -> bool {
self.0.is_empty()
}
pub fn len(&self) -> usize {
self.0.len()
}
pub fn trees(&self) -> RefTokenTreeCursor<'_> {
RefTokenTreeCursor::new(self)
}
pub fn into_trees(self) -> TokenTreeCursor {
TokenTreeCursor::new(self)
}
/// Compares two `TokenStream`s, checking equality without regarding span information.
pub fn eq_unspanned(&self, other: &TokenStream) -> bool {
let mut t1 = self.trees();
let mut t2 = other.trees();
for (t1, t2) in iter::zip(&mut t1, &mut t2) {
if !t1.eq_unspanned(t2) {
return false;
}
}
t1.next().is_none() && t2.next().is_none()
}
/// Applies the supplied function to each `TokenTree` and its index in `self`, returning a new `TokenStream`
///
/// It is equivalent to `TokenStream::new(self.trees().cloned().enumerate().map(|(i, tt)| f(i, tt)).collect())`.
pub fn map_enumerated_owned(
mut self,
mut f: impl FnMut(usize, TokenTree) -> TokenTree,
) -> TokenStream {
let owned = Lrc::make_mut(&mut self.0); // clone if necessary
// rely on vec's in-place optimizations to avoid another allocation
*owned = mem::take(owned).into_iter().enumerate().map(|(i, tree)| f(i, tree)).collect();
self
}
/// Create a token stream containing a single token with alone spacing.
pub fn token_alone(kind: TokenKind, span: Span) -> TokenStream {
TokenStream::new(vec![TokenTree::token_alone(kind, span)])
}
/// Create a token stream containing a single token with joint spacing.
pub fn token_joint(kind: TokenKind, span: Span) -> TokenStream {
TokenStream::new(vec![TokenTree::token_joint(kind, span)])
}
/// Create a token stream containing a single `Delimited`.
pub fn delimited(span: DelimSpan, delim: Delimiter, tts: TokenStream) -> TokenStream {
TokenStream::new(vec![TokenTree::Delimited(span, delim, tts)])
}
pub fn from_ast(node: &(impl HasAttrs + HasSpan + HasTokens + fmt::Debug)) -> TokenStream {
let Some(tokens) = node.tokens() else {
panic!("missing tokens for node at {:?}: {:?}", node.span(), node);
};
let attrs = node.attrs();
let attr_stream = if attrs.is_empty() {
tokens.to_attr_token_stream()
} else {
let attr_data =
AttributesData { attrs: attrs.iter().cloned().collect(), tokens: tokens.clone() };
AttrTokenStream::new(vec![AttrTokenTree::Attributes(attr_data)])
};
attr_stream.to_tokenstream()
}
pub fn from_nonterminal_ast(nt: &Nonterminal) -> TokenStream {
match nt {
Nonterminal::NtIdent(ident, is_raw) => {
TokenStream::token_alone(token::Ident(ident.name, *is_raw), ident.span)
}
Nonterminal::NtLifetime(ident) => {
TokenStream::token_alone(token::Lifetime(ident.name), ident.span)
}
Nonterminal::NtItem(item) => TokenStream::from_ast(item),
Nonterminal::NtBlock(block) => TokenStream::from_ast(block),
Nonterminal::NtStmt(stmt) if let StmtKind::Empty = stmt.kind => {
// FIXME: Properly collect tokens for empty statements.
TokenStream::token_alone(token::Semi, stmt.span)
}
Nonterminal::NtStmt(stmt) => TokenStream::from_ast(stmt),
Nonterminal::NtPat(pat) => TokenStream::from_ast(pat),
Nonterminal::NtTy(ty) => TokenStream::from_ast(ty),
Nonterminal::NtMeta(attr) => TokenStream::from_ast(attr),
Nonterminal::NtPath(path) => TokenStream::from_ast(path),
Nonterminal::NtVis(vis) => TokenStream::from_ast(vis),
Nonterminal::NtExpr(expr) | Nonterminal::NtLiteral(expr) => TokenStream::from_ast(expr),
}
}
fn flatten_token(token: &Token, spacing: Spacing) -> TokenTree {
match &token.kind {
token::Interpolated(nt) if let token::NtIdent(ident, is_raw) = **nt => {
TokenTree::Token(Token::new(token::Ident(ident.name, is_raw), ident.span), spacing)
}
token::Interpolated(nt) => TokenTree::Delimited(
DelimSpan::from_single(token.span),
Delimiter::Invisible,
TokenStream::from_nonterminal_ast(nt).flattened(),
),
_ => TokenTree::Token(token.clone(), spacing),
}
}
fn flatten_token_tree(tree: &TokenTree) -> TokenTree {
match tree {
TokenTree::Token(token, spacing) => TokenStream::flatten_token(token, *spacing),
TokenTree::Delimited(span, delim, tts) => {
TokenTree::Delimited(*span, *delim, tts.flattened())
}
}
}
#[must_use]
pub fn flattened(&self) -> TokenStream {
fn can_skip(stream: &TokenStream) -> bool {
stream.trees().all(|tree| match tree {
TokenTree::Token(token, _) => !matches!(token.kind, token::Interpolated(_)),
TokenTree::Delimited(_, _, inner) => can_skip(inner),
})
}
if can_skip(self) {
return self.clone();
}
self.trees().map(|tree| TokenStream::flatten_token_tree(tree)).collect()
}
// If `vec` is not empty, try to glue `tt` onto its last token. The return
// value indicates if gluing took place.
fn try_glue_to_last(vec: &mut Vec<TokenTree>, tt: &TokenTree) -> bool {
if let Some(TokenTree::Token(last_tok, Spacing::Joint)) = vec.last()
&& let TokenTree::Token(tok, spacing) = tt
&& let Some(glued_tok) = last_tok.glue(tok)
{
// ...then overwrite the last token tree in `vec` with the
// glued token, and skip the first token tree from `stream`.
*vec.last_mut().unwrap() = TokenTree::Token(glued_tok, *spacing);
true
} else {
false
}
}
/// Push `tt` onto the end of the stream, possibly gluing it to the last
/// token. Uses `make_mut` to maximize efficiency.
pub fn push_tree(&mut self, tt: TokenTree) {
let vec_mut = Lrc::make_mut(&mut self.0);
if Self::try_glue_to_last(vec_mut, &tt) {
// nothing else to do
} else {
vec_mut.push(tt);
}
}
/// Push `stream` onto the end of the stream, possibly gluing the first
/// token tree to the last token. (No other token trees will be glued.)
/// Uses `make_mut` to maximize efficiency.
pub fn push_stream(&mut self, stream: TokenStream) {
let vec_mut = Lrc::make_mut(&mut self.0);
let stream_iter = stream.0.iter().cloned();
if let Some(first) = stream.0.first() && Self::try_glue_to_last(vec_mut, first) {
// Now skip the first token tree from `stream`.
vec_mut.extend(stream_iter.skip(1));
} else {
// Append all of `stream`.
vec_mut.extend(stream_iter);
}
}
pub fn chunks(&self, chunk_size: usize) -> core::slice::Chunks<'_, TokenTree> {
self.0.chunks(chunk_size)
}
/// Desugar doc comments like `/// foo` in the stream into `#[doc =
/// r"foo"]`. Modifies the `TokenStream` via `Lrc::make_mut`, but as little
/// as possible.
pub fn desugar_doc_comments(&mut self) {
if let Some(desugared_stream) = desugar_inner(self.clone()) {
*self = desugared_stream;
}
// The return value is `None` if nothing in `stream` changed.
fn desugar_inner(mut stream: TokenStream) -> Option<TokenStream> {
let mut i = 0;
let mut modified = false;
while let Some(tt) = stream.0.get(i) {
match tt {
&TokenTree::Token(
Token { kind: token::DocComment(_, attr_style, data), span },
_spacing,
) => {
let desugared = desugared_tts(attr_style, data, span);
let desugared_len = desugared.len();
Lrc::make_mut(&mut stream.0).splice(i..i + 1, desugared);
modified = true;
i += desugared_len;
}
&TokenTree::Token(..) => i += 1,
&TokenTree::Delimited(sp, delim, ref delim_stream) => {
if let Some(desugared_delim_stream) = desugar_inner(delim_stream.clone()) {
let new_tt = TokenTree::Delimited(sp, delim, desugared_delim_stream);
Lrc::make_mut(&mut stream.0)[i] = new_tt;
modified = true;
}
i += 1;
}
}
}
if modified { Some(stream) } else { None }
}
fn desugared_tts(attr_style: AttrStyle, data: Symbol, span: Span) -> Vec<TokenTree> {
// Searches for the occurrences of `"#*` and returns the minimum number of `#`s
// required to wrap the text. E.g.
// - `abc d` is wrapped as `r"abc d"` (num_of_hashes = 0)
// - `abc "d"` is wrapped as `r#"abc "d""#` (num_of_hashes = 1)
// - `abc "##d##"` is wrapped as `r###"abc ##"d"##"###` (num_of_hashes = 3)
let mut num_of_hashes = 0;
let mut count = 0;
for ch in data.as_str().chars() {
count = match ch {
'"' => 1,
'#' if count > 0 => count + 1,
_ => 0,
};
num_of_hashes = cmp::max(num_of_hashes, count);
}
// `/// foo` becomes `doc = r"foo"`.
let delim_span = DelimSpan::from_single(span);
let body = TokenTree::Delimited(
delim_span,
Delimiter::Bracket,
[
TokenTree::token_alone(token::Ident(sym::doc, false), span),
TokenTree::token_alone(token::Eq, span),
TokenTree::token_alone(
TokenKind::lit(token::StrRaw(num_of_hashes), data, None),
span,
),
]
.into_iter()
.collect::<TokenStream>(),
);
if attr_style == AttrStyle::Inner {
vec![
TokenTree::token_alone(token::Pound, span),
TokenTree::token_alone(token::Not, span),
body,
]
} else {
vec![TokenTree::token_alone(token::Pound, span), body]
}
}
}
}
/// By-reference iterator over a [`TokenStream`], that produces `&TokenTree`
/// items.
#[derive(Clone)]
pub struct RefTokenTreeCursor<'t> {
stream: &'t TokenStream,
index: usize,
}
impl<'t> RefTokenTreeCursor<'t> {
fn new(stream: &'t TokenStream) -> Self {
RefTokenTreeCursor { stream, index: 0 }
}
pub fn look_ahead(&self, n: usize) -> Option<&TokenTree> {
self.stream.0.get(self.index + n)
}
}
impl<'t> Iterator for RefTokenTreeCursor<'t> {
type Item = &'t TokenTree;
fn next(&mut self) -> Option<&'t TokenTree> {
self.stream.0.get(self.index).map(|tree| {
self.index += 1;
tree
})
}
}
/// Owning by-value iterator over a [`TokenStream`], that produces `&TokenTree`
/// items.
///
/// Doesn't impl `Iterator` because Rust doesn't permit an owning iterator to
/// return `&T` from `next`; the need for an explicit lifetime in the `Item`
/// associated type gets in the way. Instead, use `next_ref` (which doesn't
/// involve associated types) for getting individual elements, or
/// `RefTokenTreeCursor` if you really want an `Iterator`, e.g. in a `for`
/// loop.
#[derive(Clone)]
pub struct TokenTreeCursor {
pub stream: TokenStream,
index: usize,
}
impl TokenTreeCursor {
fn new(stream: TokenStream) -> Self {
TokenTreeCursor { stream, index: 0 }
}
#[inline]
pub fn next_ref(&mut self) -> Option<&TokenTree> {
self.stream.0.get(self.index).map(|tree| {
self.index += 1;
tree
})
}
pub fn look_ahead(&self, n: usize) -> Option<&TokenTree> {
self.stream.0.get(self.index + n)
}
}
#[derive(Debug, Copy, Clone, PartialEq, Encodable, Decodable, HashStable_Generic)]
pub struct DelimSpan {
pub open: Span,
pub close: Span,
}
impl DelimSpan {
pub fn from_single(sp: Span) -> Self {
DelimSpan { open: sp, close: sp }
}
pub fn from_pair(open: Span, close: Span) -> Self {
DelimSpan { open, close }
}
pub fn dummy() -> Self {
Self::from_single(DUMMY_SP)
}
pub fn entire(self) -> Span {
self.open.with_hi(self.close.hi())
}
}
// Some types are used a lot. Make sure they don't unintentionally get bigger.
#[cfg(all(target_arch = "x86_64", target_pointer_width = "64"))]
mod size_asserts {
use super::*;
use rustc_data_structures::static_assert_size;
// tidy-alphabetical-start
static_assert_size!(AttrTokenStream, 8);
static_assert_size!(AttrTokenTree, 32);
static_assert_size!(LazyAttrTokenStream, 8);
static_assert_size!(TokenStream, 8);
static_assert_size!(TokenTree, 32);
// tidy-alphabetical-end
}