Skip to content

feat: mediaWiki change dump dir! #23

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
amindadgar merged 2 commits into from
Apr 15, 2025
Merged

feat: mediaWiki change dump dir! #23

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
8576181
feat: mediaWiki change dump dir!
amindadgar Apr 15, 2025
f414749
feat: update test cases to match the new changes!
amindadgar Apr 15, 2025
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: 1 addition & 1 deletion hivemind_etl/mediawiki/etl.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -25,7 +25,7 @@ def __init__(
community_id, namespaces=namespaces, proxy_url=self.proxy_url
)

self.dump_dir = f"dump_{self.community_id}"
self.dump_dir = f"dumps/{self.community_id}"
self.delete_dump_after_load = delete_dump_after_load

def extract(self, api_url: str, dump_dir: str | None = None) -> None:
Expand Down
11 changes: 6 additions & 5 deletions tests/unit/test_mediawiki_etl.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,20 +15,21 @@ def setUp(self):
self.namespaces = [0, 1] # Main and Talk namespaces

# Create a temporary dumps directory
os.makedirs(f"dump_{self.community_id}", exist_ok=True)
os.makedirs("dumps", exist_ok=True)
os.makedirs(f"dumps/{self.community_id}", exist_ok=True)

def tearDown(self):
# Clean up any created files
if os.path.exists(f"dump_{self.community_id}"):
shutil.rmtree(f"dump_{self.community_id}")
if os.path.exists(f"dumps/{self.community_id}"):
shutil.rmtree(f"dumps/{self.community_id}")
if os.path.exists(self.custom_path):
shutil.rmtree(self.custom_path)

def test_mediawiki_etl_initialization(self):
etl = MediawikiETL(community_id=self.community_id, namespaces=self.namespaces)
self.assertEqual(etl.community_id, self.community_id)
self.assertTrue(etl.delete_dump_after_load)
self.assertEqual(etl.dump_dir, f"dump_{self.community_id}")
self.assertEqual(etl.dump_dir, f"dumps/{self.community_id}")

etl = MediawikiETL(
community_id=self.community_id,
Expand All @@ -45,7 +46,7 @@ def test_extract_with_default_path(self):
etl.extract(self.api_url)

etl.wikiteam_crawler.crawl.assert_called_once_with(
self.api_url, f"dump_{self.community_id}"
self.api_url, f"dumps/{self.community_id}"
)

def test_extract_with_custom_path(self):
Expand Down