The_Great_Archive/ArchiveBox
1
0
Fork 0
mirror of https://github.com/ArchiveBox/ArchiveBox.git synced 2026-09-14 11:06:13 +05:00
Code Issues Actions Packages Projects Releases Wiki Activity

Wait for all CLI import snapshots before restart

Browse Source
This commit is contained in:
Nick Sweeting 2026-06-21 08:26:10 -07:00
parent 8bd69a0f0e
commit 75d5c53d36
No known key found for this signature in database
1 changed files with 7 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
archivebox/tests/test_cli_add.py
View File

@ -162,13 +162,17 @@ def wait_for_import_processing(cwd: Path, expected_urls: set[str], *, timeout: f
import time
deadline = time.time() + timeout
counts = {url: 0 for url in expected_urls}
while time.time() < deadline:
with use_archivebox_db(cwd):
snapshot_started = Snapshot.objects.filter(url__in=expected_urls).exists()
if snapshot_started:
rows = list(Snapshot.objects.filter(url__in=expected_urls).values_list("url", flat=True))
counts = {url: 0 for url in expected_urls}
for url in rows:
counts[url] += 1
if all(count >= 1 for count in counts.values()):
return
time.sleep(1)
raise AssertionError("timed out waiting for import crawl processing to start")
raise AssertionError(f"timed out waiting for import crawl processing to start, got counts={counts}")
def wait_for_expected_import_snapshots(cwd: Path, expected_urls: set[str], *, timeout: float = 180.0) -> None: