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

Encoding can only be set once #233

Merged
merged 1 commit into from
Nov 8, 2024
Merged

Encoding can only be set once #233

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
46 changes: 28 additions & 18 deletions src/rewriter/mod.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -266,21 +266,30 @@ impl<'h, O: OutputSink, H: HandlerTypes> Debug for HtmlRewriter<'h, O, H> {
fn handler_adjust_charset_on_meta_tag<'h, H: HandlerTypes>(
encoding: SharedEncoding,
) -> (Cow<'h, crate::Selector>, ElementContentHandlers<'h, H>) {
// HTML5 allows encoding to be set only once
let mut found = false;

let handler = move |el: &mut Element<'_, '_, H>| {
let attr_charset = el
.get_attribute("charset")
.and_then(|cs| Encoding::for_label_no_replacement(cs.as_bytes()))
.and_then(AsciiCompatibleEncoding::new);

let attr_http_equiv = el
.get_attribute("http-equiv")
.filter(|http_equiv| http_equiv.eq_ignore_ascii_case("Content-Type"))
.and_then(|_| el.get_attribute("content"))
.and_then(|ct| ct.parse::<Mime>().ok())
.as_ref()
.and_then(AsciiCompatibleEncoding::from_mimetype);

if let Some(charset) = attr_charset.or(attr_http_equiv) {
if found {
return Ok(());
}

let charset = el.get_attribute("charset").and_then(|cs| {
AsciiCompatibleEncoding::new(Encoding::for_label_no_replacement(cs.as_bytes())?)
});

let charset = charset.or_else(|| {
el.get_attribute("http-equiv")
.filter(|http_equiv| http_equiv.eq_ignore_ascii_case("Content-Type"))
.and_then(|_| {
AsciiCompatibleEncoding::from_mimetype(
&el.get_attribute("content")?.parse::<Mime>().ok()?,
)
})
});

if let Some(charset) = charset {
found = true;
encoding.set(charset);
}

Expand Down Expand Up @@ -739,10 +748,11 @@ mod tests {
};

let html: Vec<u8> = [
r#"<meta http-equiv="content-type" content="text/html; charset=windows-1251"><html><head></head><body>I love "#.as_bytes().to_vec(),
vec![0xd5, 0xec, 0xb3, 0xcb, 0xdc],
br"!</body></html>".to_vec(),
].into_iter().concat();
r#"<meta http-equiv="conTent-type" content="text/html; charset=windows-1251"><html><head>"#.as_bytes(),
br#"<meta charset="utf-8"></head><body>I love "#, // second one should be ignored
&[0xd5, 0xec, 0xb3, 0xcb, 0xdc],
br"!</body></html>",
].concat();

let expected: Vec<u8> = html
.iter()
Expand Down
Loading