apunkt/webclaw
1
0
Fork 0
mirror of https://github.com/0xMassi/webclaw.git synced 2026-06-07 22:15:12 +02:00
Code Issues Projects Releases Packages Wiki Activity

chore: bump to 0.3.9, fix formatting from #14

Browse source 
Version bump for layout table, stack overflow, and noise filter fixes
contributed by @devnen. Also fixes cargo fmt issues that caused CI lint
failure on the merge commit.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
Valerio 2026-04-04 15:24:17 +02:00
parent 87ecf4241f
commit 3cf9dbaf2a
7 changed files with 137 additions and 39 deletions
Download patch file Download diff file Expand all files Collapse all files

14
crates/webclaw-core/src/lib.rs
View file

@ -562,9 +562,14 @@ mod tests {
let html = include_str!("../testdata/express_test.html");
let result = extract(
html,
Some("https://www.express.co.uk/news/world/2189934/iran-live-donald-trump-uae-dubai-kuwait-attacks"),
Some(
"https://www.express.co.uk/news/world/2189934/iran-live-donald-trump-uae-dubai-kuwait-attacks",
),
);
assert!(
result.is_ok(),
"Should not stack overflow on Express.co.uk live blog"
);
assert!(result.is_ok(), "Should not stack overflow on Express.co.uk live blog");
let result = result.unwrap();
assert!(
result.metadata.word_count > 100,
@ -588,7 +593,10 @@ mod tests {
html.push_str("</body></html>");
let result = extract(&html, None);
assert!(result.is_ok(), "Should not stack overflow on deeply nested HTML");
assert!(
result.is_ok(),
"Should not stack overflow on deeply nested HTML"
);
let result = result.unwrap();
assert!(
result.content.markdown.contains("Deep content"),