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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946
//! # Authoring Parse Rules
//!
//! This is a short, or not so short, guide to implement parse rules using the Biome parser infrastructure.
//!
//! ## Naming
//! The convention is to prefix your parse rule with `parse_` and then use the name defined in the grammar file.
//!
//! For example, `parse_for_statement` or `parse_expression`.
//!
//! ## Signature
//! Most parse rules take a `&mut` reference to the parser as their only parameter and return a `ParsedSyntax`.
//!
//! ```rust,ignore
//! fn parse_rule_name(&mut: Parser) -> ParsedSyntax {}
//! ```
//!
//! You're free to add additional parameters to your function if needed. There are rare cases where you want to consider returning `ConditionalParsedSyntax` as explained in [conditional syntax](#conditional-syntax)
//!
//!
//! ## Parsing a single node
//!
//! Let's assume you want to parse the JS `if` statement:
//!
//! ```js
//! JsIfStatement =
//! if
//! (
//! test: JsAnyExpression
//! )
//! consequent: JsBlockStatement
//! else_clause: JsElseClause?
//! ```
//!
//! ### Presence Test
//!
//! Now, the parsing function must first test if the parser is positioned at an `if` statement and return `Absent` if that's not the case.
//!
//! ```rust, ignore
//! if !p.at(T![if]) {
//! return ParsedSyntax::Absent;
//! }
//! ```
//!
//! Why return `ParsedSyntax::Absent`? The function must return `ParsedSyntax::Absent` if the rule can't predict by the next token(s) if they form the expected node or not. Doing so allows the calling rule to decide if this is an error and perform an error recovery if necessary. The second reason is to ensure that the rule doesn't return a node where all children are missing.
//!
//! Your rule implementation may want to consider more than just the first child to determine if it can parse at least some of the expected children.
//! For example, the if statement rule could test if the parser is located at an `else` clause and then create an `if` statement where all children are missing except the `else` clause:
//!
//! ```rust, ignore
//! if !p.at(T![if]) && !p.at(T![else]){
//! return Absent
//! }
//! ```
//!
//! Your implementation can also call into another parsing rule if the first child is a node and not a token.
//!
//! ```rust, ignore
//! let assignment_target = parse_assignment_target(p);
//!
//! if assignment_target.is_absent() {
//! return Absent;
//! }
//!
//! let my_node = assignment_target.precede_or_missing();
//! ```
//!
//! But be careful with calling other rules. Your rule mustn't progress the parser - meaning that it can't
//! advance in the parsing process and consume tokens - if it returns `Absent`.
//!
//!
//! ### Parse children
//! The parse rules will guide you in how to write your implementation and the parser infrastructure provides the following convenience APIs:
//!
//! * Optional token `'ident'?`: Use `p.eat(token)`. It eats the next token if it matches the passed-in token.
//! * Required token `'ident'`: Use`p.expect(token)`. It eats the next token if it matches the passed-in token.
//! It adds an `Expected 'x' but found 'y' instead` error and a missing marker if the token isn't present in the source code.
//! * Optional node `body: JsBlockStatement?`: Use`parse_block_statement(p).or_missing(p)`. It parses the block if it is present in the source code and adds a missing marker if it isn't.
//! * Required node `body: JsBlockStatement`: Use `parse_block_statement(p).or_missing_with_error(p, error_builder)`:
//! it parses the block statement if it is present in the source code and adds a missing marker and an error if not.
//!
//! Using the above-described rules result in the following implementation for the `if` statement rule.
//!
//! ```rust, ignore
//! fn parse_if_statement(p: &mut Parser) -> ParsedSyntax {
//! if !p.at(T![if]) {
//! return Absent;
//! }
//!
//! let m = p.start();
//!
//! p.expect(T![if]);
//! p.expect(T!['(']);
//! parse_any_expression(p).or_add_diagnostic(p, js_parse_errors::expeced_if_statement);
//! p.expect(T![')']);
//! parse_block_statement(p).or_add_diagnostic(p, js_parse_errors::expected_block_statement);
//! // the else block is optional, handle the marker by using `ok`
//! parse_else_clause(p).ok();
//!
//! Present(m.complete(p, JS_IF_STATEMENT));
//! }
//! ```
//!
//! Hold on, what are these *missing* markers? Biome's AST facade uses fixed offsets to retrieve a particular child from a node.
//! For example, the 3rd child of the if statement is the condition. However, the condition would become the second element
//! if the opening parentheses `(` isn't present in the source text. That's where missing elements come into play.
//!
//! ## Parsing Lists & Error Recovery
//!
//! Parsing lists is different from parsing single elements with a fixed set of children because it requires looping until
//! the parser reaches a terminal token (or the end of the file).
//!
//! You may remember that `parse_*` methods shouldn't progress parsing if they return `Absent`.
//! Not progressing the parser is problematic inside `while` loops because it inevitably results in an infinite loop.
//!
//! That's why you must do error recovery when parsing lists. Luckily, the parser comes with the infrastructure to make error recovery a piece of cake.
//! The general structure for parsing a list is (yes, that's something the parser infrastructure should provide for you):
//!
//!
//! Let's try to parse an array:
//!
//! ```js
//! [ 1, 3, 6 ]
//! ```
//!
//! We will use `ParseSeparatedList` in order to achieve that
//!
//! ```rust, ignore
//! struct ArrayElementsList;
//!
//! impl ParseSeparatedList for ArrayElementsList {
//! type ParsedElement = CompletedMarker;
//!
//! fn parse_element(&mut self, p: &mut Parser) -> ParsedSyntax<Self::ParsedElement> {
//! parse_array_element(p)
//! }
//!
//! fn is_at_list_end(&self, p: &mut Parser) -> bool {
//! p.at_ts(token_set![T![default], T![case], T!['}']])
//! }
//!
//! fn recover(
//! &mut self,
//! p: &mut Parser,
//! parsed_element: ParsedSyntax<Self::ParsedElement>,
//! ) -> parser::RecoveryResult {
//! parsed_element.or_recover(
//! p,
//! &ParseRecovery::new(JS_BOGUS_STATEMENT, STMT_RECOVERY_SET),
//! js_parse_error::expected_case,
//! )
//! }
//! };
//! ```
//!
//! Let's run through this step by step:
//!
//! ```rust, ignore
//! parsed_element.or_recover(
//! p,
//! &ParseRecovery::new(JS_BOGUS_STATEMENT, STMT_RECOVERY_SET),
//! js_parse_error::expected_case,
//! )
//! ```
//!
//! The `or_recover` performs an error recovery if the `parse_array_element` method returns `Absent`;
//! there's no array element in the source text.
//!
//! The recovery eats all tokens until it finds one of the tokens specified in the `token_set`,
//! a line break (if you called `enable_recovery_on_line_break`) or the end of the file.
//!
//! The recovery doesn't throw the tokens away but instead wraps them inside a `JS_BOGUS_EXPRESSION` node (first parameter).
//! There exist multiple `BOGUS_*` nodes. You must consult the grammar to understand which `BOGUS*` node is supported in your case.
//!
//! > You usually want to include the terminal token ending your list, the element separator token, and the token terminating a statement in your recovery set.
//!
//!
//! Now, the problem with recovery is that it can fail, and there are two reasons:
//!
//! - the parser reached the end of the file;
//! - the next token is one of the tokens specified in the recovery set, meaning there is nothing to recover from;
//!
//! In these cases the `ParseSeparatedList` and `ParseNodeList` will recover the parser for you.
//!
//! ## Conditional Syntax
//!
//! The conditional syntax allows you to express that some syntax may not be valid in all source files. Some use cases are:
//!
//! * syntax that is only supported in strict or sloppy mode: for example, `with` statements is not valid when a JavaScript file uses `"use strict"` or is a module;
//! * syntax that is only supported in certain file types: Typescript, JSX, modules;
//! * syntax that is only available in specific language versions: experimental features, different versions of the language e.g. (ECMA versions for JavaScript);
//!
//! The idea is that the parser always parses the syntax regardless of whatever it is supported in this specific file or context.
//! The main motivation behind doing so is that this gives us perfect error recovery and allows us to use the same code regardless of whether the syntax is supported.
//!
//! However, conditional syntax must be handled because we want to add a diagnostic if the syntax isn't supported for the current file, and the parsed tokens must be attached somewhere.
//!
//! Let's have a look at the `with` statement that is only allowed in loose mode/sloppy mode:
//!
//! ```rust, ignore
//! fn parse_with_statement(p: &mut Parser) -> ParsedSyntax {
//! if !p.at(T![with]) {
//! return Absent;
//! }
//!
//! let m = p.start();
//! p.bump(T![with]); // with
//! parenthesized_expression(p).or_add_diagnostic(p, js_errors::expected_parenthesized_expression);
//! parse_statement(p).or_add_diagnostic(p, js_error::expected_statement);
//! let with_stmt = m.complete(p, JS_WITH_STATEMENT);
//!
//! let conditional = StrictMode.excluding_syntax(p, with_stmt, |p, marker| {
//! p.err_builder("`with` statements are not allowed in strict mode", marker.range(p))
//! });
//!
//!
//! }
//! ```
//!
//! The start of the rule is the same as for any other rule. The exciting bits start with
//!
//! ```rust, ignore
//! let conditional = StrictMode.excluding_syntax(p, with_stmt, |p, marker| {
//! p.err_builder("`with` statements are not allowed in strict mode", marker.range(p))
//! });
//! ```
//!
//! The `StrictMode.excluding_syntax` converts the parsed syntax to a bogus node and uses the diagnostic builder to create a diagnostic if the feature is not supported.
//!
//! You can convert the `ConditionalParsedSyntax` to a regular `ParsedSyntax` by calling `or_invalid_to_bogus`, which wraps the whole parsed `with` statement in an `BOGUS` node if the parser is in strict mode and otherwise returns the unchanged `with` statement.
//!
//! What if there's no `BOGUS` node matching the node of your parse rule? You must then return the `ConditionalParsedSyntax` without making the `or_invalid_to_bogus` recovery. It's then up to the caller to recover the potentially invalid syntax.
//!
//!
//! ## Summary
//!
//! * Parse rules are named `parse_rule_name`
//! * The parse rules should return a `ParsedSyntax`
//! * The rule must return `Present` if it consumes any token and, therefore, can parse the node with at least some of its children.
//! * It returns `Absent` otherwise and must not progress parsing nor add any errors.
//! * Lists must perform error recovery to avoid infinite loops.
//! * Consult the grammar to identify the `BOGUS` node that is valid in the context of your rule.
//!
use crate::diagnostic::{expected_token, ParseDiagnostic, ToDiagnostic};
use crate::event::Event;
use crate::event::Event::Token;
use crate::token_source::{BumpWithContext, NthToken, TokenSource};
use biome_console::fmt::Display;
use biome_diagnostics::location::AsSpan;
use biome_rowan::{
AnyFileSource, AstNode, FileSource, FileSourceError, Language, SendNode, SyntaxKind,
SyntaxNode, TextRange, TextSize,
};
use std::any::type_name;
use std::path::Path;
pub mod diagnostic;
pub mod event;
pub mod lexer;
mod marker;
pub mod parse_lists;
pub mod parse_recovery;
pub mod parsed_syntax;
pub mod prelude;
pub mod token_set;
pub mod token_source;
pub mod tree_sink;
use crate::parsed_syntax::ParsedSyntax;
use crate::parsed_syntax::ParsedSyntax::{Absent, Present};
use biome_diagnostics::serde::Diagnostic;
pub use marker::{CompletedMarker, Marker};
pub use token_set::TokenSet;
pub struct ParserContext<K: SyntaxKind> {
events: Vec<Event<K>>,
skipping: bool,
diagnostics: Vec<ParseDiagnostic>,
}
impl<K: SyntaxKind> Default for ParserContext<K> {
fn default() -> Self {
Self::new()
}
}
impl<K: SyntaxKind> ParserContext<K> {
pub fn new() -> Self {
Self {
skipping: false,
events: Vec::new(),
diagnostics: Vec::new(),
}
}
/// Returns the slice with the parse events
pub fn events(&self) -> &[Event<K>] {
&self.events
}
/// Returns a slice with the parse diagnostics
pub fn diagnostics(&self) -> &[ParseDiagnostic] {
&self.diagnostics
}
/// Drops all diagnostics after `at`.
pub fn truncate_diagnostics(&mut self, at: usize) {
self.diagnostics.truncate(at);
}
/// Pushes a new token event
pub fn push_token(&mut self, kind: K, end: TextSize) {
self.push_event(Token { kind, end });
}
/// Pushes a parse event
pub fn push_event(&mut self, event: Event<K>) {
self.events.push(event)
}
/// Returns `true` if the parser is skipping a token as skipped token trivia.
pub fn is_skipping(&self) -> bool {
self.skipping
}
/// Splits the events into two at the given `position`. Returns a newly allocated vector containing the
/// elements from `[position;len]`.
///
/// ## Safety
/// The method is marked as `unsafe` to discourage its usage. Removing events can lead to
/// corrupted events if not done carefully.
pub unsafe fn split_off_events(&mut self, position: usize) -> Vec<Event<K>> {
self.events.split_off(position)
}
/// Get the current index of the last event
fn cur_event_pos(&self) -> usize {
self.events.len().saturating_sub(1)
}
/// Remove `amount` events from the parser
fn drain_events(&mut self, amount: usize) {
self.events.truncate(self.events.len() - amount);
}
/// Rewind the parser back to a previous position in time
pub fn rewind(&mut self, checkpoint: ParserContextCheckpoint) {
let ParserContextCheckpoint {
event_pos,
errors_pos,
} = checkpoint;
self.drain_events(self.cur_event_pos() - event_pos);
self.diagnostics.truncate(errors_pos as usize);
}
/// Get a checkpoint representing the progress of the parser at this point of time
#[must_use]
pub fn checkpoint(&self) -> ParserContextCheckpoint {
ParserContextCheckpoint {
event_pos: self.cur_event_pos(),
errors_pos: self.diagnostics.len() as u32,
}
}
pub fn finish(self) -> (Vec<Event<K>>, Vec<ParseDiagnostic>) {
(self.events, self.diagnostics)
}
}
/// A structure signifying the Parser progress at one point in time
#[derive(Debug)]
pub struct ParserContextCheckpoint {
event_pos: usize,
/// The length of the errors list at the time the checkpoint was created.
/// Safety: The parser only supports files <= 4Gb. Storing a `u32` is sufficient to store one error
/// for each single character in the file, which should be sufficient for any realistic file.
errors_pos: u32,
}
impl ParserContextCheckpoint {
pub fn event_position(&self) -> usize {
self.event_pos
}
}
pub trait Parser: Sized {
type Kind: SyntaxKind;
type Source: TokenSource<Kind = Self::Kind>;
/// Returns a reference to the [`ParserContext`](ParserContext)
fn context(&self) -> &ParserContext<Self::Kind>;
/// Returns a mutable reference to the [`ParserContext`](ParserContext).
fn context_mut(&mut self) -> &mut ParserContext<Self::Kind>;
/// Returns a reference to the [`TokenSource``](TokenSource]
fn source(&self) -> &Self::Source;
/// Returns a mutable reference to the [`TokenSource`](TokenSource)
fn source_mut(&mut self) -> &mut Self::Source;
/// Returns `true` if the parser is trying to parse some syntax but only if it has no errors.
///
/// Returning `true` disables more involved error recovery.
fn is_speculative_parsing(&self) -> bool {
false
}
/// Gets the source text of a range
///
/// # Panics
///
/// If the range is out of bounds
fn text(&self, span: TextRange) -> &str {
&self.source().text()[span]
}
/// Gets the current token kind of the parser
fn cur(&self) -> Self::Kind {
self.source().current()
}
/// Gets the range of the current token
fn cur_range(&self) -> TextRange {
self.source().current_range()
}
/// Tests if there's a line break before the current token (between the last and current)
fn has_preceding_line_break(&self) -> bool {
self.source().has_preceding_line_break()
}
/// Get the source code of the parser's current token.
fn cur_text(&self) -> &str {
&self.source().text()[self.cur_range()]
}
/// Checks if the parser is currently at a specific token
fn at(&self, kind: Self::Kind) -> bool {
self.cur() == kind
}
/// Check if the parser's current token is contained in a token set
fn at_ts(&self, kinds: TokenSet<Self::Kind>) -> bool {
kinds.contains(self.cur())
}
/// Look ahead at a token and get its kind.
fn nth(&mut self, n: usize) -> Self::Kind
where
Self::Source: NthToken,
{
self.source_mut().nth(n)
}
/// Checks if a token lookahead is something
fn nth_at(&mut self, n: usize, kind: Self::Kind) -> bool
where
Self::Source: NthToken,
{
self.nth(n) == kind
}
/// Tests if there's a line break before the nth token.
#[inline]
fn has_nth_preceding_line_break(&mut self, n: usize) -> bool
where
Self::Source: NthToken,
{
self.source_mut().has_nth_preceding_line_break(n)
}
/// Consume the current token if `kind` matches.
fn bump(&mut self, kind: Self::Kind) {
assert_eq!(
kind,
self.cur(),
"expected {:?} but at {:?}",
kind,
self.cur()
);
self.do_bump(kind)
}
/// Consume the current token if `kind` matches.
fn bump_ts(&mut self, kinds: TokenSet<Self::Kind>) {
assert!(
kinds.contains(self.cur()),
"expected {:?} but at {:?}",
kinds,
self.cur()
);
self.bump_any()
}
/// Consume any token but cast it as a different kind using the specified `context.
fn bump_remap_with_context(
&mut self,
kind: Self::Kind,
context: <Self::Source as BumpWithContext>::Context,
) where
Self::Source: BumpWithContext,
{
self.do_bump_with_context(kind, context);
}
/// Consume any token but cast it as a different kind
fn bump_remap(&mut self, kind: Self::Kind) {
self.do_bump(kind);
}
/// Bumps the current token regardless of its kind and advances to the next token.
fn bump_any(&mut self) {
let kind = self.cur();
assert_ne!(kind, Self::Kind::EOF);
self.do_bump(kind);
}
/// Consumes the current token if `kind` matches and lexes the next token using the
/// specified `context.
fn bump_with_context(
&mut self,
kind: Self::Kind,
context: <Self::Source as BumpWithContext>::Context,
) where
Self::Source: BumpWithContext,
{
assert_eq!(
kind,
self.cur(),
"expected {:?} but at {:?}",
kind,
self.cur()
);
self.do_bump_with_context(kind, context);
}
#[doc(hidden)]
fn do_bump_with_context(
&mut self,
kind: Self::Kind,
context: <Self::Source as BumpWithContext>::Context,
) where
Self::Source: BumpWithContext,
{
let end = self.cur_range().end();
self.context_mut().push_token(kind, end);
if self.context().skipping {
self.source_mut().skip_as_trivia_with_context(context);
} else {
self.source_mut().bump_with_context(context);
}
}
#[doc(hidden)]
fn do_bump(&mut self, kind: Self::Kind) {
let end = self.cur_range().end();
self.context_mut().push_token(kind, end);
if self.context().skipping {
self.source_mut().skip_as_trivia();
} else {
self.source_mut().bump();
}
}
/// Consume the next token if `kind` matches using the specified `context.
fn eat_with_context(
&mut self,
kind: Self::Kind,
context: <Self::Source as BumpWithContext>::Context,
) -> bool
where
Self::Source: BumpWithContext,
{
if !self.at(kind) {
return false;
}
self.do_bump_with_context(kind, context);
true
}
/// Consume the next token if `kind` matches.
fn eat(&mut self, kind: Self::Kind) -> bool {
if !self.at(kind) {
return false;
}
self.do_bump(kind);
true
}
/// Consume the next token if token set matches.
fn eat_ts(&mut self, kinds: TokenSet<Self::Kind>) -> bool {
if !self.at_ts(kinds) {
return false;
}
self.do_bump(self.cur());
true
}
/// Consume the next token if token set matches using the specified `context.
fn eat_ts_with_context(
&mut self,
kinds: TokenSet<Self::Kind>,
context: <Self::Source as BumpWithContext>::Context,
) -> bool
where
Self::Source: BumpWithContext,
{
if !self.at_ts(kinds) {
return false;
}
self.do_bump_with_context(self.cur(), context);
true
}
/// Try to eat a specific token kind, if the kind is not there then adds an error to the events stack
/// using the specified `context.
fn expect_with_context(
&mut self,
kind: Self::Kind,
context: <Self::Source as BumpWithContext>::Context,
) -> bool
where
Self::Source: BumpWithContext,
{
if self.eat_with_context(kind, context) {
true
} else {
self.error(expected_token(kind));
false
}
}
/// Try to eat a specific token kind, if the kind is not there then adds an error to the events stack.
fn expect(&mut self, kind: Self::Kind) -> bool {
if self.eat(kind) {
true
} else {
self.error(expected_token(kind));
false
}
}
/// Allows parsing an unsupported syntax as skipped trivia tokens.
fn parse_as_skipped_trivia_tokens<P>(&mut self, parse: P)
where
P: FnOnce(&mut Self),
{
let events_pos = self.context().events.len();
self.context_mut().skipping = true;
parse(self);
self.context_mut().skipping = false;
// Truncate any start/finish events
self.context_mut().events.truncate(events_pos);
}
/// Add a diagnostic
fn error(&mut self, err: impl ToDiagnostic<Self>) {
let err = err.into_diagnostic(self);
// Don't report another diagnostic if the last diagnostic is at the same position of the current one
if let Some(previous) = self.context().diagnostics.last() {
match (&err.diagnostic_range(), &previous.diagnostic_range()) {
(Some(err_range), Some(previous_range))
if err_range.start() == previous_range.start() =>
{
return;
}
_ => {}
}
}
self.context_mut().diagnostics.push(err)
}
/// Creates a new diagnostic. Pass the message and the range where the error occurred
#[must_use]
fn err_builder(&self, message: impl Display, span: impl AsSpan) -> ParseDiagnostic {
ParseDiagnostic::new(message, span)
}
/// Bump and add an error event
fn err_and_bump(&mut self, err: impl ToDiagnostic<Self>, unknown_syntax_kind: Self::Kind) {
let m = self.start();
self.bump_any();
m.complete(self, unknown_syntax_kind);
self.error(err);
}
/// Returns the kind of the last bumped token.
fn last(&self) -> Option<Self::Kind> {
self.context()
.events
.iter()
.rev()
.find_map(|event| match event {
Token { kind, .. } => Some(*kind),
_ => None,
})
}
/// Returns the end offset of the last bumped token.
fn last_end(&self) -> Option<TextSize> {
self.context()
.events
.iter()
.rev()
.find_map(|event| match event {
Token { end, .. } => Some(*end),
_ => None,
})
}
/// Starts a new node in the syntax tree. All nodes and tokens
/// consumed between the `start` and the corresponding `Marker::complete`
/// belong to the same node.
fn start(&mut self) -> Marker {
let pos = self.context().events.len() as u32;
let start = self.source().position();
self.context_mut().push_event(Event::tombstone());
Marker::new(pos, start)
}
}
/// Captures the progress of the parser and allows to test if the parsing is still making progress
#[derive(Debug, Eq, Ord, PartialOrd, PartialEq, Hash, Default)]
pub struct ParserProgress(Option<TextSize>);
impl ParserProgress {
/// Returns true if the current parser position is passed this position
#[inline]
pub fn has_progressed<P>(&self, p: &P) -> bool
where
P: Parser,
{
match self.0 {
None => true,
Some(pos) => pos < p.source().position(),
}
}
/// Asserts that the parsing is still making progress.
///
/// # Panics
///
/// Panics if the parser is still at this position
#[inline]
pub fn assert_progressing<P>(&mut self, p: &P)
where
P: Parser,
{
assert!(
self.has_progressed(p),
"The parser is no longer progressing. Stuck at '{}' {:?}:{:?}",
p.cur_text(),
p.cur(),
p.cur_range(),
);
self.0 = Some(p.source().position());
}
}
/// A syntax feature that may or may not be supported depending on the file type and parser configuration
pub trait SyntaxFeature: Sized {
type Parser<'source>: Parser;
/// Returns `true` if the current parsing context supports this syntax feature.
fn is_supported(&self, p: &Self::Parser<'_>) -> bool;
/// Returns `true` if the current parsing context doesn't support this syntax feature.
fn is_unsupported(&self, p: &Self::Parser<'_>) -> bool {
!self.is_supported(p)
}
/// Adds a diagnostic and changes the kind of the node to [SyntaxKind::to_bogus] if this feature isn't
/// supported.
///
/// Returns the parsed syntax.
fn exclusive_syntax<'source, S, E, D>(
&self,
p: &mut Self::Parser<'source>,
syntax: S,
error_builder: E,
) -> ParsedSyntax
where
S: Into<ParsedSyntax>,
E: FnOnce(&Self::Parser<'source>, &CompletedMarker) -> D,
D: ToDiagnostic<Self::Parser<'source>>,
{
syntax.into().map(|mut syntax| {
if self.is_unsupported(p) {
let error = error_builder(p, &syntax);
p.error(error);
syntax.change_to_bogus(p);
syntax
} else {
syntax
}
})
}
/// Parses a syntax and adds a diagnostic and changes the kind of the node to [SyntaxKind::to_bogus] if this feature isn't
/// supported.
///
/// Returns the parsed syntax.
fn parse_exclusive_syntax<'source, P, E>(
&self,
p: &mut Self::Parser<'source>,
parse: P,
error_builder: E,
) -> ParsedSyntax
where
P: FnOnce(&mut Self::Parser<'source>) -> ParsedSyntax,
E: FnOnce(&Self::Parser<'source>, &CompletedMarker) -> ParseDiagnostic,
{
if self.is_supported(p) {
parse(p)
} else {
let diagnostics_checkpoint = p.context().diagnostics().len();
let syntax = parse(p);
p.context_mut().truncate_diagnostics(diagnostics_checkpoint);
match syntax {
Present(mut syntax) => {
let diagnostic = error_builder(p, &syntax);
p.error(diagnostic);
syntax.change_to_bogus(p);
Present(syntax)
}
_ => Absent,
}
}
}
/// Adds a diagnostic and changes the kind of the node to [SyntaxKind::to_bogus] if this feature is
/// supported.
///
/// Returns the parsed syntax.
fn excluding_syntax<'source, S, E>(
&self,
p: &mut Self::Parser<'source>,
syntax: S,
error_builder: E,
) -> ParsedSyntax
where
S: Into<ParsedSyntax>,
E: FnOnce(&Self::Parser<'source>, &CompletedMarker) -> ParseDiagnostic,
{
syntax.into().map(|mut syntax| {
if self.is_unsupported(p) {
syntax
} else {
let error = error_builder(p, &syntax);
p.error(error);
syntax.change_to_bogus(p);
syntax
}
})
}
}
/// Language-independent cache entry for a parsed file
///
/// This struct holds a handle to the root node of the parsed syntax tree,
/// along with the list of diagnostics emitted by the parser while generating
/// this entry.
///
/// It can be dynamically downcast into a concrete [SyntaxNode] or [AstNode] of
/// the corresponding language, generally through a language-specific capability
#[derive(Clone)]
pub struct AnyParse {
pub(crate) root: SendNode,
pub(crate) diagnostics: Vec<ParseDiagnostic>,
pub(crate) file_source: AnyFileSource,
}
impl AnyParse {
pub fn new(
root: SendNode,
diagnostics: Vec<ParseDiagnostic>,
file_source: AnyFileSource,
) -> AnyParse {
AnyParse {
root,
diagnostics,
file_source,
}
}
pub fn syntax<L>(&self) -> SyntaxNode<L>
where
L: Language + 'static,
{
self.root.clone().into_node().unwrap_or_else(|| {
panic!(
"could not downcast root node to language {}",
type_name::<L>()
)
})
}
pub fn file_source<'a, F, L>(&self, path: &'a Path) -> Result<F, FileSourceError>
where
F: FileSource<'a, L> + 'static,
L: Language + 'static,
{
self.file_source.unwrap_cast_from_path(path)
}
pub fn tree<N>(&self) -> N
where
N: AstNode,
N::Language: 'static,
{
N::unwrap_cast(self.syntax::<N::Language>())
}
/// This function transforms diagnostics coming from the parser into serializable diagnostics
pub fn into_diagnostics(self) -> Vec<Diagnostic> {
self.diagnostics.into_iter().map(Diagnostic::new).collect()
}
/// Get the diagnostics which occurred when parsing
pub fn diagnostics(&self) -> &[ParseDiagnostic] {
&self.diagnostics
}
pub fn has_errors(&self) -> bool {
self.diagnostics.iter().any(|diag| diag.is_error())
}
}