swc_ecma_parser: Unexpected escape sequence in reserved word (2)

[sebastiano-barrera]

Describe the bug

Have swc_ecma_parser parse this test262 case: test/language/import/import-assertions/json-extensibility-array.js (others also exhibit this behavior).

(This is a re-post of #9214, this time with a proper reproduction link that works on the latest parser version, 0.147.0)

Input code

var obj = ({ bre\u0061k: 42 });

Config

(I'm only using swc_ecma_parser in my toy/learning JS impl; I'm not using the full swc and I don't have an .swcrc)

fwiw:
Syntax::Es(Default::default())
EsVersion::Es2015

Playground link (or link to the minimal reproduction)

https://play.swc.rs/?version=1.6.7&code=H4sIAAAAAAAAAytLLFLIT8pSsFXQqFZIKkqNKTUwMDPMtlIwMVKo1bTmAgDLr8KQIAAAAA%3D%3D&config=H4sIAAAAAAAAA1VPSQ7CMAy89xWRzxwACQ78gUdYwa1SZVMcJKKqfyfNUujNs3nsZRACZpbwEEseM%2FAYmMKOM8PJRvxkBkgaZBmUj3Dq6sybNKJmKtRaFYgYJoolxdfz5dYSoJ1j6onGGWXVmP47pTM%2BEPPRuFnRTpqOjUNrBeNe7yK2X2LyVC%2B4w8%2FUy%2FbFoPjZk3Xt%2BgVne8%2FLGAEAAA%3D%3D

SWC Info output

No response

Expected behavior

The above code is parsed as an object literal with property "var" (which is legal JS). This works in node.

Actual behavior

The following error is reported:

error: Unexpected escape sequence in reserved word: var
  --> <anon>:37:14
   |
37 | var obj = ({ v\u0061r: 42 });
   |              ^^^^^^^^

Version

0.147.0

Additional context

The relevant code that calls the parser is the following (just an extract; the original with full context is here):

use swc_ecma_ast::EsVersion;
use swc_ecma_parser::{lexer::Lexer, Parser, StringInput, Syntax};

// ...
// content: String
let source_file = source_map.new_source_file(swc_common::FileName::Anon, content);
let input = StringInput::from(source_file.as_ref());

// ...

let lexer = Lexer::new(
    Syntax::Es(Default::default()),
    EsVersion::Es2015,
    input,
    None,
);
let mut parser = Parser::new_from(lexer);

// ...

let script_ast = parser
    .parse_script()
    .map_err(|e| {
        e.into_diagnostic(&err_handler).emit();
        error!("parse error")
    });

[kdy1]

GFI guide

37 | var obj = ({ v\u0061r: 42 });

This is about an object lieral, and the relevant code lives at

swc/crates/swc_ecma_parser/src/parser/object.rs

Lines 183 to 212 in 1ec68cb

	let key = self.parse_prop_name()?;
	if self.input.syntax().typescript()
	&& !is_one_of!(self, '(', '[', ':', ',', '?', '=', '*', IdentName, Str, Num)
	&& !(self.input.syntax().typescript() && is!(self, '<'))
	&& !(is!(self, '}') && matches!(key, PropName::Ident(..)))
	{
	trace_cur!(self, parse_object_prop_error);
	self.emit_err(self.input.cur_span(), SyntaxError::TS1005);
	return Ok(PropOrSpread::Prop(Box::new(Prop::KeyValue(KeyValueProp {
	key,
	value: Invalid {
	span: span!(self, start),
	}
	.into(),
	}))));
	}
	//
	// {[computed()]: a,}
	// { 'a': a, }
	// { 0: 1, }
	// { a: expr, }
	if eat!(self, ':') {
	let value = self.include_in_expr(true).parse_assignment_expr()?;
	return Ok(PropOrSpread::Prop(Box::new(Prop::KeyValue(KeyValueProp {
	key,
	value,
	}))));
	}

It seems like parse_prop_name has a bug.

parse_prop_name is declared as

swc/crates/swc_ecma_parser/src/parser/object.rs

Lines 43 to 122 in 1ec68cb

	pub(super) fn parse_prop_name(&mut self) -> PResult<PropName> {
	trace_cur!(self, parse_prop_name);
	let ctx = self.ctx();
	self.with_ctx(Context {
	in_property_name: true,
	..ctx
	})
	.parse_with(|p| {
	let start = cur_pos!(p);
	let v = match *cur!(p, true) {
	Token::Str { .. } => match bump!(p) {
	Token::Str { value, raw } => PropName::Str(Str {
	span: span!(p, start),
	value,
	raw: Some(raw),
	}),
	_ => unreachable!(),
	},
	Token::Num { .. } => match bump!(p) {
	Token::Num { value, raw } => PropName::Num(Number {
	span: span!(p, start),
	value,
	raw: Some(raw),
	}),
	_ => unreachable!(),
	},
	Token::BigInt { .. } => match bump!(p) {
	Token::BigInt { value, raw } => PropName::BigInt(BigInt {
	span: span!(p, start),
	value,
	raw: Some(raw),
	}),
	_ => unreachable!(),
	},
	Word(..) => match bump!(p) {
	Word(w) => PropName::Ident(IdentName::new(w.into(), span!(p, start))),
	_ => unreachable!(),
	},
	tok!('[') => {
	bump!(p);
	let inner_start = cur_pos!(p);
	let mut expr = p.include_in_expr(true).parse_assignment_expr()?;
	if p.syntax().typescript() && is!(p, ',') {
	let mut exprs = vec![expr];
	while eat!(p, ',') {
	exprs.push(p.include_in_expr(true).parse_assignment_expr()?);
	}
	p.emit_err(span!(p, inner_start), SyntaxError::TS1171);
	expr = Box::new(
	SeqExpr {
	span: span!(p, inner_start),
	exprs,
	}
	.into(),
	);
	}
	expect!(p, ']');
	PropName::Computed(ComputedPropName {
	span: span!(p, start),
	expr,
	})
	}
	_ => unexpected!(
	p,
	"identifier, string literal, numeric literal or [ for the computed key"
	),
	};
	Ok(v)
	})
	}

But there's no relevant error reporting logic so my guess is that the error is from lexer. The relevant error reporting logic is at

swc/crates/swc_ecma_parser/src/lexer/mod.rs

Lines 777 to 780 in 1ec68cb

	self.error(
	start,
	SyntaxError::EscapeInReservedWord { word: word.into() },
	)?

We need to patch this logic to allow escapes in reserved word in property names.

[sebastiano-barrera]

I'm going to take a stab at it