Skip to content

Fix extracting links after <pre><code></code></pre> #1911

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

Merged
mre merged 1 commit into from
Nov 11, 2025
Merged

Fix extracting links after <pre><code></code></pre> #1911

Show file tree
Hide file tree
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
36 changes: 36 additions & 0 deletions lychee-lib/src/extract/html/html5ever.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -583,4 +583,40 @@ mod tests {
let uris = extract_html(input, false);
assert!(uris.is_empty());
}

#[test]
fn test_extract_links_after_empty_verbatim_block() {
// Test that links are correctly extracted after empty <pre><code> blocks
let input = r#"
<body>
<div>
See <a href="https://example.com/1">First</a>
</div>
<pre>
<code></code>
</pre>
<div>
See <a href="https://example.com/2">Second</a>
</div>
</body>
"#;

let expected = vec![
RawUri {
text: "https://example.com/1".to_string(),
element: Some("a".to_string()),
attribute: Some("href".to_string()),
span: span_line(4),
},
RawUri {
text: "https://example.com/2".to_string(),
element: Some("a".to_string()),
attribute: Some("href".to_string()),
span: span_line(10),
},
];

let uris = extract_html(input, false);
assert_eq!(uris, expected);
}
}
43 changes: 40 additions & 3 deletions lychee-lib/src/extract/html/html5gum.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -278,14 +278,15 @@ impl<S: SpanProvider> Callback<(), usize> for &mut LinkExtractor<S> {
self.verbatim_stack.pop();
}
}
CallbackEvent::EndTag { .. } => {
CallbackEvent::EndTag { name } => {
let tag_name = String::from_utf8_lossy(name);
// Update the current verbatim element name.
//
// Keeps track of the last verbatim element name, so that we can
// properly handle nested verbatim blocks.
if self.filter_verbatim_here()
if !self.include_verbatim
&& let Some(last_verbatim) = self.verbatim_stack.last()
&& last_verbatim == &self.current_element
&& last_verbatim == tag_name.as_ref()
{
self.verbatim_stack.pop();
}
Expand Down Expand Up @@ -726,4 +727,40 @@ mod tests {
let actual = extract_html_fragments(input);
assert_eq!(actual, expected);
}

#[test]
fn test_extract_links_after_empty_verbatim_block() {
// Test that links are correctly extracted after empty <pre><code> blocks
let input = r#"
<body>
<div>
See <a href="https://example.com/1">First</a>
</div>
<pre>
<code></code>
</pre>
<div>
See <a href="https://example.com/2">Second</a>
</div>
</body>
"#;

let expected = vec![
RawUri {
text: "https://example.com/1".to_string(),
element: Some("a".to_string()),
attribute: Some("href".to_string()),
span: span(4, 30),
},
RawUri {
text: "https://example.com/2".to_string(),
element: Some("a".to_string()),
attribute: Some("href".to_string()),
span: span(10, 30),
},
];

let uris = extract_html(input, false);
assert_eq!(uris, expected);
}
}
Loading