Skip to content

🔒 Fix missing timeout in query_databases.py urllib.request.urlopen calls #115

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
edithatogo wants to merge 1 commit into
base: main
Choose a base branch
from
Open

🔒 Fix missing timeout in query_databases.py urllib.request.urlopen calls #115

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
3 changes: 2 additions & 1 deletion scripts/review/query_databases.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,14 +6,15 @@
import sys

RAW_DATA_DIR = "data/raw"
TIMEOUT_SECONDS = 10

def fetch_url(url):
req = urllib.request.Request(
url,
headers={"User-Agent": "UOGTO-Scoping-Review-Agent/1.0 (mailto:uogto@example.org)"}
)
try:
with urllib.request.urlopen(req) as response:
with urllib.request.urlopen(req, timeout=TIMEOUT_SECONDS) as response:
return response.read()
except Exception as e:
print(f"Error fetching {url}: {e}", file=sys.stderr)
Expand Down
12 changes: 12 additions & 0 deletions tests/test_query_databases.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -77,3 +77,15 @@ def test_query_crossref(self, mock_fetch_url):
results = query_crossref("test", limit=1)
self.assertEqual(len(results), 1)
self.assertEqual(results[0]["title"], "Crossref Test Work")

@patch('urllib.request.urlopen')
def test_fetch_url_timeout(self, mock_urlopen):
import urllib.error
import socket
# Simulate a socket timeout exception
mock_urlopen.side_effect = urllib.error.URLError(socket.timeout("timed out"))

# Test that fetch_url handles the exception and returns None
from scripts.review.query_databases import fetch_url
result = fetch_url("http://example.com")
self.assertIsNone(result)
Loading