Skip to content

fix(scripts): correctly resolve internal absolute root site URLs to root index.html in check_links.py #709

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
yappermoar-boop wants to merge 3 commits into
base: main
Choose a base branch
from
Open

fix(scripts): correctly resolve internal absolute root site URLs to root index.html in check_links.py #709

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
7af933b
fix(scripts): correctly resolve internal absolute root site URLs to r…
Aug 11, 2026
9701524
refactor(scripts): refine internal link detection and path normalizat…
Aug 11, 2026
32c4f0f
fix(scripts): ignore versioned links if that version directory is not…
damaz91 Aug 11, 2026
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
34 changes: 30 additions & 4 deletions scripts/check_links.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -161,10 +161,24 @@ def get_file_ids(path):

parsed = urlparse(link)
if parsed.scheme and parsed.scheme in ("http", "https"):
if not link.startswith(SITE_URL):
parsed_site = urlparse(SITE_URL)
if parsed.hostname == parsed_site.hostname:
path = parsed.path if parsed.path else "/"
site_path = parsed_site.path
site_path_no_slash = site_path.rstrip("/")
if (path == site_path_no_slash) or path.startswith(site_path):
if path.startswith(site_path):
rel_link_path = "/" + path[len(site_path) :]
else:
rel_link_path = "/"
query_part = f"?{parsed.query}" if parsed.query else ""
fragment_part = f"#{parsed.fragment}" if parsed.fragment else ""
link = rel_link_path + query_part + fragment_part
parsed = urlparse(link)
else:
continue # External link
else:
continue # External link
# Internal absolute URL (e.g. https://ucp.dev/foo) -> /foo
link = link[len(SITE_URL) - 1 :] # Keep the leading slash

path_part = parsed.path
anchor_part = parsed.fragment
Expand All @@ -176,6 +190,7 @@ def get_file_ids(path):
path_part = "/" + path_part[len(SITE_BASE_PATH) :]

target_file = None
is_unbuilt_version = False

# Resolve Target File
if not path_part:
Expand All @@ -197,7 +212,14 @@ def get_file_ids(path):
)
and not (ROOT_DIR / parts[0]).exists()
):
rel_path = parts[1]
is_unbuilt_version = True
stripped_path = parts[1]
if (
(ROOT_DIR / stripped_path).exists()
or (ROOT_DIR / (stripped_path + ".html")).exists()
or (ROOT_DIR / stripped_path / "index.html").exists()
):
rel_path = stripped_path

target_file = ROOT_DIR / rel_path
else:
Expand All @@ -218,11 +240,15 @@ def get_file_ids(path):
if candidate.exists():
target_file = candidate
else:
if is_unbuilt_version:
continue
errors_by_version[version][str(file_path)].append(
f" Link: {original_link}\n Target: {target_file} (Not Found)"
)
continue
else:
if is_unbuilt_version:
continue
errors_by_version[version][str(file_path)].append(
f" Link: {original_link}\n Target: {target_file} (Not Found)"
)
Expand Down
Loading