Skip to content

Commit aa3b075

Browse files
SimonSapinSimonSapin
committed
Remove the first rule if it’s @charset in "parse a stylesheet"
Per spec change https://drafts.csswg.org/css-syntax/#parse-stylesheet
1 parent e98fc6b commit aa3b075

File tree

6 files changed

+41
-26
lines changed

6 files changed

+41
-26
lines changed

‎Cargo.toml

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1,7 +1,7 @@
11
[package]
22

33
name = "cssparser"
4-
version = "0.5.7"
4+
version = "0.5.8"
55
authors = [ "Simon Sapin <simon.sapin@exyr.org>" ]
66

77
description = "Rust implementation of CSS Syntax Level 3"

‎src/css-parsing-tests/rule_list.json

Lines changed: 5 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -6,6 +6,11 @@
66

77
"@foo", [["at-rule", "foo", [], null]],
88

9+
"@charset; @foo", [
10+
["at-rule", "charset", [], null],
11+
["at-rule", "foo", [], null]
12+
],
13+
914
"@foo bar; \t/* comment */", [["at-rule", "foo", [" ", ["ident", "bar"]], null]],
1015

1116
" /**/ @foo bar{[(4", [["at-rule", "foo",

‎src/css-parsing-tests/stylesheet.json

Lines changed: 7 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -6,6 +6,13 @@
66

77
"@foo", [["at-rule", "foo", [], null]],
88

9+
"@charset 4 {} @foo", [["at-rule", "foo", [], null]],
10+
11+
"@foo; @charset 4 {}", [
12+
["at-rule", "foo", [], null],
13+
["at-rule", "charset", [" ", ["number", "4", 4, "integer"], " "], []]
14+
],
15+
916
"@foo bar; \t/* comment */", [["at-rule", "foo", [" ", ["ident", "bar"]], null]],
1017

1118
" /**/ @foo bar{[(4", [["at-rule", "foo",

‎src/css-parsing-tests/stylesheet_bytes.json

Lines changed: 12 additions & 24 deletions
Original file line numberDiff line numberDiff line change
@@ -41,32 +41,27 @@
4141

4242

4343
{"css_bytes": "@charset \"ISO-8859-5\"; @\u00E9"},
44-
[[["at-rule", "charset", [" ", ["string", "ISO-8859-5"]], null],
45-
["at-rule", "щ", [], null]],
44+
[[["at-rule", "щ", [], null]],
4645
"iso-8859-5"],
4746

4847
{"css_bytes": "@Charset \"ISO-8859-5\"; @\u00E9",
4948
"comment": "@charset has to match an exact byte pattern"},
50-
[[["at-rule", "Charset", [" ", ["string", "ISO-8859-5"]], null],
51-
["at-rule", "�", [], null]],
49+
[[["at-rule", "�", [], null]],
5250
"utf-8"],
5351

5452
{"css_bytes": "@charset \"ISO-8859-5\"; @\u00E9",
5553
"comment": "@charset has to match an exact byte pattern"},
56-
[[["at-rule", "charset", [" ", ["string", "ISO-8859-5"]], null],
57-
["at-rule", "�", [], null]],
54+
[[["at-rule", "�", [], null]],
5855
"utf-8"],
5956

6057
{"css_bytes": "@charset 'ISO-8859-5'; @\u00E9",
6158
"comment": "@charset has to match an exact byte pattern"},
62-
[[["at-rule", "charset", [" ", ["string", "ISO-8859-5"]], null],
63-
["at-rule", "�", [], null]],
59+
[[["at-rule", "�", [], null]],
6460
"utf-8"],
6561

6662
{"css_bytes": "@charset \"ISO-8859-5\" ; @\u00E9",
6763
"comment": "@charset has to match an exact byte pattern"},
68-
[[["at-rule", "charset", [" ", ["string", "ISO-8859-5"], " "], null],
69-
["at-rule", "�", [], null]],
64+
[[["at-rule", "�", [], null]],
7065
"utf-8"],
7166

7267

@@ -79,35 +74,30 @@
7974

8075
{"css_bytes": "@charset \"UTF-16LE\"; @\u00C3\u00A9",
8176
"comment": "@charset can only specify ASCII-compatible encodings"},
82-
[[["at-rule", "charset", [" ", ["string", "UTF-16LE"]], null],
83-
["at-rule", "é", [], null]],
77+
[[["at-rule", "é", [], null]],
8478
"utf-8"],
8579

8680

8781
{"css_bytes": "\u00EF\u00BB\u00BF @charset \"ISO-8859-5\"; @\u00E9",
8882
"comment": "BOM takes precedence over @charset"},
89-
[[["at-rule", "charset", [" ", ["string", "ISO-8859-5"]], null],
90-
["at-rule", "�", [], null]],
83+
[[["at-rule", "�", [], null]],
9184
"utf-8"],
9285

9386
{"css_bytes": "\u00EF\u00BB\u00BF @charset \"ISO-8859-5\"; @\u00C3\u00A9",
9487
"comment": "BOM takes precedence over @charset"},
95-
[[["at-rule", "charset", [" ", ["string", "ISO-8859-5"]], null],
96-
["at-rule", "é", [], null]],
88+
[[["at-rule", "é", [], null]],
9789
"utf-8"],
9890

9991
{"css_bytes": "@charset \"ISO-8859-5\"; @\u00E9",
10092
"protocol_encoding": " Iso-8859-2",
10193
"comment": "Protocol takes precedence over @charset"},
102-
[[["at-rule", "charset", [" ", ["string", "ISO-8859-5"]], null],
103-
["at-rule", "é", [], null]],
94+
[[["at-rule", "é", [], null]],
10495
"iso-8859-2"],
10596

10697
{"css_bytes": "@charset \"ISO-8859-5\"; @\u00E9",
10798
"protocol_encoding": "kamoulox",
10899
"comment": "Unknow protocol encoding falls back to @charset"},
109-
[[["at-rule", "charset", [" ", ["string", "ISO-8859-5"]], null],
110-
["at-rule", "щ", [], null]],
100+
[[["at-rule", "щ", [], null]],
111101
"iso-8859-5"],
112102

113103

@@ -120,15 +110,13 @@
120110
{"css_bytes": "@charset \"ISO-8859-5\"; @\u00E9",
121111
"environment_encoding": "ISO-8859-2",
122112
"comment": "@character takes precedence over environment"},
123-
[[["at-rule", "charset", [" ", ["string", "ISO-8859-5"]], null],
124-
["at-rule", "щ", [], null]],
113+
[[["at-rule", "щ", [], null]],
125114
"iso-8859-5"],
126115

127116
{"css_bytes": "@charset \"kamoulox\"; @\u00E9",
128117
"environment_encoding": "ISO-8859-2",
129118
"comment": "@character with unknown encoding falls back to environment encoding"},
130-
[[["at-rule", "charset", [" ", ["string", "kamoulox"]], null],
131-
["at-rule", "é", [], null]],
119+
[[["at-rule", "é", [], null]],
132120
"iso-8859-2"],
133121

134122
{"css_bytes": "@\u00E9",

‎src/parser.rs

Lines changed: 3 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -471,6 +471,9 @@ impl<'i, 't> Parser<'i, 't> {
471471
if next_byte.is_some() && !self.stop_before.contains(Delimiters::from_byte(next_byte)) {
472472
debug_assert!(delimiters.contains(Delimiters::from_byte(next_byte)));
473473
self.tokenizer.advance(1);
474+
if next_byte == Some(b'{') {
475+
consume_until_end_of_block(BlockType::CurlyBracket, &mut *self.tokenizer);
476+
}
474477
}
475478
result
476479
}

‎src/rules_and_declarations.rs

Lines changed: 13 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -4,6 +4,7 @@
44

55
// https://drafts.csswg.org/css-syntax/#parsing
66

7+
use std::ascii::AsciiExt;
78
use std::ops::Range;
89
use std::borrow::Cow;
910
use super::{Token, Parser, Delimiter, SourcePosition};
@@ -264,6 +265,7 @@ where P: QualifiedRuleParser<QualifiedRule = R> + AtRuleParser<AtRule = R> {
264265
pub parser: P,
265266

266267
is_stylesheet: bool,
268+
any_rule_so_far: bool,
267269
}
268270

269271

@@ -285,6 +287,7 @@ where P: QualifiedRuleParser<QualifiedRule = R> + AtRuleParser<AtRule = R> {
285287
input: input,
286288
parser: parser,
287289
is_stylesheet: true,
290+
any_rule_so_far: false,
288291
}
289292
}
290293

@@ -300,6 +303,7 @@ where P: QualifiedRuleParser<QualifiedRule = R> + AtRuleParser<AtRule = R> {
300303
input: input,
301304
parser: parser,
302305
is_stylesheet: false,
306+
any_rule_so_far: false,
303307
}
304308
}
305309
}
@@ -318,9 +322,17 @@ where P: QualifiedRuleParser<QualifiedRule = R> + AtRuleParser<AtRule = R> {
318322
Ok(Token::WhiteSpace(_)) | Ok(Token::Comment(_)) => {}
319323
Ok(Token::CDO) | Ok(Token::CDC) if self.is_stylesheet => {}
320324
Ok(Token::AtKeyword(name)) => {
321-
return Some(parse_at_rule(start_position, name, self.input, &mut self.parser))
325+
let first_stylesheet_rule = self.is_stylesheet && !self.any_rule_so_far;
326+
self.any_rule_so_far = true;
327+
if first_stylesheet_rule && name.eq_ignore_ascii_case("charset") {
328+
let delimiters = Delimiter::Semicolon | Delimiter::CurlyBracketBlock;
329+
let _ = self.input.parse_until_after(delimiters, |_input| Ok(()));
330+
} else {
331+
return Some(parse_at_rule(start_position, name, self.input, &mut self.parser))
332+
}
322333
}
323334
Ok(_) => {
335+
self.any_rule_so_far = true;
324336
self.input.reset(start_position);
325337
return Some(parse_qualified_rule(self.input, &mut self.parser)
326338
.map_err(|()| start_position..self.input.position()))

0 commit comments

Comments
 (0)