Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

fix(html/parser): cdata parsing + tests #6534

Merged
merged 7 commits into from Nov 29, 2022
Merged

fix(html/parser): cdata parsing + tests #6534

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
232ae6c
test: cdata
alexander-akait Nov 28, 2022
e1688a1
test: cdata in svg
alexander-akait Nov 28, 2022
b7c5d5c
test: cdata in svg
alexander-akait Nov 28, 2022
e1fb82b
fix: cdata parsing
alexander-akait Nov 28, 2022
182fdd4
fix: cdata parsing
alexander-akait Nov 29, 2022
b5d5abd
test: more
alexander-akait Nov 29, 2022
cc1ac0e
test: more
alexander-akait Nov 29, 2022
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Jump to
Jump to file
Failed to load files.
Diff view
Diff view
11 changes: 11 additions & 0 deletions crates/swc_html_codegen/tests/fixture/cdata/input.html
View file
Open in desktop
@@ -0,0 +1,11 @@
<!doctype html>
<html lang="en">
<head>
<title>Document</title>
</head>
<body>
<svg viewBox="0 0 100 100">
<text><![CDATA[content]]></text>
</svg>
</body>
</html>
11 changes: 11 additions & 0 deletions crates/swc_html_codegen/tests/fixture/cdata/output.html
View file
Open in desktop
@@ -0,0 +1,11 @@
<!DOCTYPE html>
<html lang="en">
<head>
<title>Document</title>
</head>
<body>
<svg viewBox="0 0 100 100">
<text>content</text>
</svg>

</body></html>
8 changes: 8 additions & 0 deletions crates/swc_html_codegen/tests/fixture/cdata/output.min.html
View file
Open in desktop
@@ -0,0 +1,8 @@
<!doctype html><html lang=en><head>
<title>Document</title>
</head>
<body>
<svg viewBox="0 0 100 100">
<text>content</text>
</svg>

64 changes: 30 additions & 34 deletions crates/swc_html_parser/src/lexer/mod.rs
View file
Open in desktop
Expand Up @@ -134,8 +134,6 @@ struct Comment {

pub(crate) type LexResult<T> = Result<T, ErrorKind>;

// TODO improve `raw` for all tokens (linting + better codegen)

pub struct Lexer<I>
where
I: Input,
Expand Down Expand Up @@ -2682,37 +2680,35 @@ where
// error. Create a comment token whose data is the "[CDATA[" string.
// Switch to the bogus comment state.
Some('[') => match self.consume_next_char() {
Some(c @ 'c' | c @ 'C') => match self.consume_next_char() {
Some(d @ 'd' | d @ 'D') => match self.consume_next_char() {
Some(a1 @ 'a' | a1 @ 'A') => match self.consume_next_char() {
Some(t @ 't' | t @ 'T') => match self.consume_next_char() {
Some(a2 @ 'a' | a2 @ 'A') => {
match self.consume_next_char() {
Some('[') => {
if let Some(false) = self.is_adjusted_current_node_is_element_in_html_namespace {
self.state = State::CdataSection;
} else {
self.emit_error(
ErrorKind::CdataInHtmlContent,
);
let mut data = String::with_capacity(7);

data.push('[');
data.push(c);
data.push(d);
data.push(a1);
data.push(t);
data.push(a2);
data.push('[');

self.create_comment_token(Some(data), "<!");
self.state = State::BogusComment;
}
}
_ => {
anything_else(self);
Some(c @ 'C') => match self.consume_next_char() {
Some(d @ 'D') => match self.consume_next_char() {
Some(a1 @ 'A') => match self.consume_next_char() {
Some(t @ 'T') => match self.consume_next_char() {
Some(a2 @ 'A') => match self.consume_next_char() {
Some('[') => {
if let Some(false) = self.is_adjusted_current_node_is_element_in_html_namespace {
self.state = State::CdataSection;
} else {
self.emit_error(
ErrorKind::CdataInHtmlContent,
);
let mut data = String::with_capacity(7);

data.push('[');
data.push(c);
data.push(d);
data.push(a1);
data.push(t);
data.push(a2);
data.push('[');

self.create_comment_token(Some(data), "<!");
self.state = State::BogusComment;
}
}
_ => {
anything_else(self);
}
}
_ => {
anything_else(self);
Expand All @@ -2725,15 +2721,15 @@ where
_ => {
anything_else(self);
}
},
}
_ => {
anything_else(self);
}
},
}
_ => {
anything_else(self);
}
},
}
// Anything else
// This is an incorrectly-opened-comment parse error. Create a comment token
// whose data is the empty string. Switch to the bogus comment state (don't
Expand Down
12 changes: 7 additions & 5 deletions crates/swc_html_parser/src/parser/mod.rs
View file
Open in desktop
Expand Up @@ -508,7 +508,7 @@ where
}
Data::Text { data, raw } => {
let span = if let Some(end_span) = node.end_span.take() {
swc_common::Span::new(start_span.lo(), end_span.hi(), Default::default())
Span::new(start_span.lo(), end_span.hi(), Default::default())
} else {
start_span
};
Expand All @@ -533,7 +533,12 @@ where
fn run(&mut self) -> PResult<()> {
while !self.stopped {
let adjusted_current_node = self.get_adjusted_current_node();
let is_element_in_html_namespace = is_element_in_html_namespace(adjusted_current_node);
let is_element_in_html_namespace =
if is_element_in_html_namespace(adjusted_current_node) {
true
} else {
is_html_integration_point(adjusted_current_node)
};

self.input
.set_adjusted_current_node_to_html_namespace(is_element_in_html_namespace);
Expand Down Expand Up @@ -625,9 +630,6 @@ where
let is_mathml_annotation_xml = is_mathml_annotation_xml(adjusted_current_node);
let is_html_integration_point = is_html_integration_point(adjusted_current_node);

self.input
.set_adjusted_current_node_to_html_namespace(is_element_in_html_namespace);

if self.open_elements_stack.items.is_empty()
|| is_element_in_html_namespace
|| (is_mathml_text_integration_point
Expand Down
112 changes: 112 additions & 0 deletions crates/swc_html_parser/tests/fixture/text/cdata-svg/dom.rust-debug
View file
Open in desktop
@@ -0,0 +1,112 @@
| <!DOCTYPE html>
| <html>
| lang="en-US"
| <head>
| "
"
| <meta>
| charset="utf-8"
| "
"
| <title>
| "SVG Demo"
| "
"
| <meta>
| content="width=device-width"
| name="viewport"
| "
"
| "
"
| <body>
| "
"
| <svg svg>
| viewBox="0 0 100 100"
| "
"
| <svg title>
| "A gradient"
| "
"
| <svg linearGradient>
| id="gradient"
| "
"
| <svg stop>
| class="begin"
| offset="0%"
| "
"
| <svg stop>
| class="end"
| offset="100%"
| "
"
| "
"
| <svg rect>
| height="100"
| style="fill:url(#gradient)"
| width="100"
| x="0"
| y="0"
| "
"
| <svg circle>
| cx="50"
| cy="50"
| r="30"
| style="fill:url(#gradient)"
| "
"
| <svg text>
| class="empty"
| "
"
| <svg text>
| "content"
| "
"
| <svg text>
| "&amping"
| "
"
| <svg text>
| "&amping ]"
| "
"
| <svg text>
| "&amping]] "
| "
"
| <svg text>
| "<message>text</message>"
| "
"
| <svg text>
| "</this is malformed!</malformed</malformed & worse>"
| "
"
| <svg text>
| "12"
| "
"
| <svg text>
| "
data
"
| "
"
| <svg text>
| "bracket ]after"
| "
"
| <svg text>
| "abracket ]afterb"
| "
"
| "

"
32 changes: 32 additions & 0 deletions crates/swc_html_parser/tests/fixture/text/cdata-svg/input.html
View file
Open in desktop
@@ -0,0 +1,32 @@
<!DOCTYPE html>
<html lang="en-US">
<head>
<meta charset="utf-8" />
<title>SVG Demo</title>
<meta name="viewport" content="width=device-width" />
</head>
<body>
<svg viewBox="0 0 100 100">
<title>A gradient</title>
<linearGradient id="gradient">
<stop class="begin" offset="0%" />
<stop class="end" offset="100%" />
</linearGradient>
<rect x="0" y="0" width="100" height="100" style="fill:url(#gradient)" />
<circle cx="50" cy="50" r="30" style="fill:url(#gradient)" />
<text class="empty"><![CDATA[]]></text>
<text><![CDATA[content]]></text>
<text><![CDATA[&amping]]></text>
<text><![CDATA[&amping ]]]></text>
<text><![CDATA[&amping]] ]]></text>
<text><![CDATA[<message>text</message>]]></text>
<text><![CDATA[</this is malformed!</malformed</malformed & worse>]]></text>
<text><![CDATA[1]]><![CDATA[2]]></text>
<text>
<![CDATA[data]]>
</text>
<text><![CDATA[bracket ]after]]></text>
<text>a<![CDATA[bracket ]after]]>b</text>
</svg>
</body>
</html>