Skip to content

fix(ingestion): match navigation "header" by class token, not substring #241

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

Open
detail-app wants to merge 1 commit into
base: dev
Choose a base branch
from
Open

fix(ingestion): match navigation "header" by class token, not substring #241

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
5 changes: 4 additions & 1 deletion src/main/java/com/williamcallahan/javachat/service/HtmlContentExtractor.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -222,13 +222,16 @@ private void appendTableContent(Element table, StringBuilder sb) {
*/
private boolean isNavigationElement(Element element) {
String className = AsciiTextNormalizer.toLowerAscii(element.className());
Set<String> classTokens = element.classNames().stream()
.map(AsciiTextNormalizer::toLowerAscii)
.collect(Collectors.toSet());
String id = AsciiTextNormalizer.toLowerAscii(element.id());
String text = AsciiTextNormalizer.toLowerAscii(element.text());

return className.contains("nav")
|| className.contains("menu")
|| className.contains("sidebar")
|| className.contains("header")
|| classTokens.contains("header")
|| className.contains("footer")
|| id.contains("nav")
|| id.contains("menu")
Expand Down
54 changes: 54 additions & 0 deletions src/test/java/com/williamcallahan/javachat/service/HtmlContentExtractorTest.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -267,4 +267,58 @@ void retainsPackagePagesAsUnanchoredJavaApiOverviews() {
assertTrue(extraction.anchoredSections().isEmpty());
assertTrue(document.selectFirst("nav") != null, "Extraction must use a clone before removing navigation");
}

@Test
void pageHeaderWrapperRetainsNestedHeading() {
Document document = Jsoup.parse("""
<html><body><main>
<div class="page-header"><h1>Important Page Title</h1></div>
<p>Body text that should always remain.</p>
</main></body></html>
""");
HtmlContentExtractor extractor = new HtmlContentExtractor();

String extractedText = extractor.extractCleanContent(document);

assertTrue(extractedText.contains("Important Page Title"), "nested h1 in page-header must survive");
assertTrue(extractedText.contains("Body text that should always remain."), "sibling body text must survive");
}

@Test
void exactHeaderClassTokenIsStillRemoved() {
Document document = Jsoup.parse("""
<html><body><main>
<div class="header"><h1>Site Header Title</h1></div>
<p>Body text that should always remain.</p>
</main></body></html>
""");
HtmlContentExtractor extractor = new HtmlContentExtractor();

String extractedText = extractor.extractCleanContent(document);

assertFalse(extractedText.contains("Site Header Title"), "exact header class token must still be removed");
assertTrue(extractedText.contains("Body text that should always remain."), "sibling body text must survive");
}

@Test
void compositeNavClassesAreStillRemoved() {
Document document = Jsoup.parse("""
<html><body><main>
<div class="top-nav"><a href="/">Home</a></div>
<div class="main-nav"><a href="/about">About</a></div>
<div class="header-nav"><a href="/docs">Docs</a></div>
<div class="primary-nav"><a href="/blog">Blog</a></div>
<p>Body text that should always remain.</p>
</main></body></html>
""");
HtmlContentExtractor extractor = new HtmlContentExtractor();

String extractedText = extractor.extractCleanContent(document);

assertFalse(extractedText.contains("Home"), "top-nav must still be removed");
assertFalse(extractedText.contains("About"), "main-nav must still be removed");
assertFalse(extractedText.contains("Docs"), "header-nav must still be removed");
assertFalse(extractedText.contains("Blog"), "primary-nav must still be removed");
assertTrue(extractedText.contains("Body text that should always remain."), "body text must survive");
}
}