oblachno-oss/grm
3
0
Fork 0
Code Issues 20 Pull Requests Actions Packages Projects Releases 14 Wiki Activity

GRM-40: fix: wiki links, add --strict integrity check for wiki sync (#34)

Browse Source
This commit is contained in:
emil
2026-06-21 21:14:17 +00:00
parent 945344f960
commit 0c54efbf6b
4 changed files with 241 additions and 30 deletions
Download Patch File Download Diff File Expand all files Collapse all files
scripts/ci/sync_wiki.py
+93 -22
View File
@@ -130,7 +130,9 @@ def sync_page(
return "created"
def verify_wiki_page(client: GiteaClient, page_title: str, expected_content: str, existing_pages: dict[str, str]) -> bool:
def verify_wiki_page(
client: GiteaClient, page_title: str, expected_content: str, existing_pages: dict[str, str]
) -> bool:
"""Verify that a wiki page has non-empty content matching the docs.
Returns True if the page content matches, False otherwise.
@@ -142,6 +144,54 @@ def verify_wiki_page(client: GiteaClient, page_title: str, expected_content: str
return actual.strip() == expected_content.strip()
def verify_wiki_integrity(
client: GiteaClient,
mapping: dict[str, str],
synced: dict[str, str],
) -> list[str]:
"""Comprehensive wiki verification.
Checks:
1. Every mapped page exists in the wiki
2. Every mapped page has non-empty content
3. Every mapped page's content matches the docs
4. No stale pages exist in the wiki (pages not in mapping)
5. Page count matches
Returns a list of failure messages (empty if all checks pass).
"""
failures: list[str] = []
existing_pages = list_wiki_pages(client)
expected_titles = set(mapping.values())
# Check 1: Page count
if len(existing_pages) != len(expected_titles):
failures.append(f"Page count mismatch: wiki has {len(existing_pages)}, mapping has {len(expected_titles)}")
# Check 2: Missing pages (in mapping but not in wiki)
missing = expected_titles - set(existing_pages.keys())
for title in sorted(missing):
failures.append(f"Missing page: {title}")
# Check 3: Stale pages (in wiki but not in mapping)
stale = set(existing_pages.keys()) - expected_titles
for title in sorted(stale):
failures.append(f"Stale page (not in mapping): {title}")
# Check 4: Content verification
for page_title, expected_content in sorted(synced.items()):
ok = verify_wiki_page(client, page_title, expected_content, existing_pages)
if not ok:
sub_url = existing_pages.get(page_title, "?")
actual = fetch_page_content(client, sub_url)
if not actual.strip():
failures.append(f"Empty content: {page_title}")
else:
failures.append(f"Content mismatch: {page_title}")
return failures
@click.command()
@click.option("--dry-run", is_flag=True, default=False, help="Show what would happen without making changes.")
@click.option("--repo", default=None, help="Repository in owner/name format (auto-detected if omitted).")
@@ -151,7 +201,13 @@ def verify_wiki_page(client: GiteaClient, page_title: str, expected_content: str
default=False,
help="After syncing, verify each page has non-empty content. Exit 1 if any page is empty or mismatched.",
)
def main(dry_run: bool, repo: str | None, verify: bool) -> None:
@click.option(
"--strict",
is_flag=True,
default=False,
help="Full integrity check: verify page count, missing pages, stale pages, and content. Implies --verify.",
)
def main(dry_run: bool, repo: str | None, verify: bool, strict: bool) -> None:
token = os.environ.get("REPO_TOKEN", "")
if not token:
raise click.ClickException(_("ERROR: REPO_TOKEN is not set."))
@@ -213,27 +269,42 @@ def main(dry_run: bool, repo: str | None, verify: bool) -> None:
)
)
if verify and not dry_run:
click.echo(_("\nVerifying wiki pages have content..."))
# Re-fetch the page list to get updated sub_urls
existing_pages = list_wiki_pages(client)
failures = 0
for page_title, expected_content in sorted(synced.items()):
ok = verify_wiki_page(client, page_title, expected_content, existing_pages)
if ok:
click.echo(_(" OK: {title} ({chars} chars)", title=page_title, chars=len(expected_content)))
else:
click.echo(_(" FAIL: {title} — content mismatch or empty!", title=page_title))
failures += 1
if failures > 0:
click.echo(
_(
"\nVerification FAILED: {failures} page(s) have empty or mismatched content!",
failures=failures,
# --strict implies --verify
do_verify = verify or strict
if do_verify and not dry_run:
if strict:
click.echo(_("\nRunning full wiki integrity check..."))
failures = verify_wiki_integrity(client, mapping, synced)
if failures:
click.echo(_("\nIntegrity check FAILED ({count} issues):", count=len(failures)))
for f in failures:
click.echo(f" - {f}")
raise click.ClickException(_("Wiki integrity check failed — {count} issue(s)", count=len(failures)))
click.echo(_("\nIntegrity check passed — all {count} pages verified.", count=len(synced)))
else:
click.echo(_("\nVerifying wiki pages have content..."))
# Re-fetch the page list to get updated sub_urls
existing_pages = list_wiki_pages(client)
failures = 0
for page_title, expected_content in sorted(synced.items()):
ok = verify_wiki_page(client, page_title, expected_content, existing_pages)
if ok:
click.echo(_(" OK: {title} ({chars} chars)", title=page_title, chars=len(expected_content)))
else:
click.echo(_(" FAIL: {title} — content mismatch or empty!", title=page_title))
failures += 1
if failures > 0:
click.echo(
_(
"\nVerification FAILED: {failures} page(s) have empty or mismatched content!",
failures=failures,
)
)
)
raise click.ClickException(_("Wiki verification failed — {failures} page(s) empty or mismatched", failures=failures))
click.echo(_("\nVerification passed — all wiki pages have correct content."))
raise click.ClickException(
_("Wiki verification failed — {failures} page(s) empty or mismatched", failures=failures)
)
click.echo(_("\nVerification passed — all wiki pages have correct content."))
if __name__ == "__main__": # pragma: no cover