Skip to content

fix(search-core): skip shop sitemap urls #14

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
lurkshark merged 1 commit into from
Mar 5, 2026
Merged

fix(search-core): skip shop sitemap urls #14

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
2 changes: 2 additions & 0 deletions packages/search-core/src/grogbot_search/service.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -718,6 +718,8 @@ def create_documents_from_sitemap(self, sitemap_url: str, bootstrap: bool = Fals
documents: List[Document] = []
for page_url in unique_urls:
canonical_url = _canonicalize_url(page_url)
if "/shop/" in urlparse(canonical_url).path:
continue
if bootstrap:
existing = self.connection.execute(
"SELECT 1 FROM documents WHERE canonical_url = ? LIMIT 1",
Expand Down
22 changes: 22 additions & 0 deletions packages/search-core/tests/conftest.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -114,6 +114,21 @@ def log_message(self, format, *args): # noqa: A003 - match base signature
</html>
"""

responses["/shop/product"] = f"""
<html>
<head>
<title>Shop Product</title>
<link rel="canonical" href="{base_url}/shop/product" />
</head>
<body>
<article>
<h1>Shop Product Heading</h1>
<p>Shop product details.</p>
</article>
</body>
</html>
"""

responses["/article-no-canonical"] = """
<html>
<head>
Expand Down Expand Up @@ -360,6 +375,13 @@ def log_message(self, format, *args): # noqa: A003 - match base signature
</urlset>
"""

responses["/sitemap-shop-skip.xml"] = f"""<?xml version="1.0" encoding="UTF-8"?>
<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9">
<url><loc>{base_url}/shop/product</loc></url>
<url><loc>{base_url}/article</loc></url>
</urlset>
"""

responses["/invalid-sitemap.xml"] = "<urlset><url><loc>"

responses["/sitemap-bootstrap-skip.xml"] = f"""<?xml version="1.0" encoding="UTF-8"?>
Expand Down
7 changes: 7 additions & 0 deletions packages/search-core/tests/test_service.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -800,6 +800,13 @@ def test_create_documents_from_sitemap_deduplicates_urls(service: SearchService,
assert documents[0].canonical_url == f"{http_server}/canonical"


def test_create_documents_from_sitemap_skips_shop_paths(service: SearchService, http_server):
documents = service.create_documents_from_sitemap(f"{http_server}/sitemap-shop-skip.xml")

assert len(documents) == 1
assert documents[0].canonical_url == f"{http_server}/canonical"


def test_create_documents_from_sitemap_invalid_xml_raises_value_error(service: SearchService, http_server):
with pytest.raises(ValueError, match="Invalid sitemap XML"):
service.create_documents_from_sitemap(f"{http_server}/invalid-sitemap.xml")
Expand Down