66b4532321
Related to https://github.com/webrecorder/browsertrix-cloud/issues/1620 Follow-up to https://github.com/webrecorder/browsertrix-cloud/pull/1621, which didn't seem to fix the problem. I'm giving it much more time here in the hopes that it solves it (since it's a nightly test, time shouldn't be such a pressing issue).
83 lines
2.3 KiB
Python
83 lines
2.3 KiB
Python
import requests
|
|
import time
|
|
|
|
from .conftest import API_PREFIX
|
|
from .utils import verify_file_replicated
|
|
|
|
|
|
def test_crawl_timeout(admin_auth_headers, default_org_id, timeout_crawl):
|
|
# Verify that crawl has started
|
|
r = requests.get(
|
|
f"{API_PREFIX}/orgs/{default_org_id}/crawls/{timeout_crawl}/replay.json",
|
|
headers=admin_auth_headers,
|
|
)
|
|
assert r.status_code == 200
|
|
data = r.json()
|
|
assert data["state"] in ("starting", "running")
|
|
|
|
attempts = 0
|
|
while True:
|
|
# Try for 10 minutes before failing
|
|
if attempts > 30:
|
|
assert False
|
|
|
|
r = requests.get(
|
|
f"{API_PREFIX}/orgs/{default_org_id}/crawls/{timeout_crawl}/replay.json",
|
|
headers=admin_auth_headers,
|
|
)
|
|
if r.json()["state"] == "complete":
|
|
break
|
|
time.sleep(20)
|
|
attempts += 1
|
|
|
|
|
|
def test_crawl_files_replicated(admin_auth_headers, default_org_id, timeout_crawl):
|
|
time.sleep(20)
|
|
|
|
# Verify replication job was successful
|
|
r = requests.get(
|
|
f"{API_PREFIX}/orgs/{default_org_id}/jobs?sortBy=started&sortDirection=1&jobType=create-replica",
|
|
headers=admin_auth_headers,
|
|
)
|
|
assert r.status_code == 200
|
|
latest_job = r.json()["items"][0]
|
|
assert latest_job["type"] == "create-replica"
|
|
job_id = latest_job["id"]
|
|
|
|
attempts = 0
|
|
while attempts < 5:
|
|
r = requests.get(
|
|
f"{API_PREFIX}/orgs/{default_org_id}/jobs/{job_id}",
|
|
headers=admin_auth_headers,
|
|
)
|
|
assert r.status_code == 200
|
|
job = r.json()
|
|
finished = latest_job.get("finished")
|
|
if not finished:
|
|
attempts += 1
|
|
time.sleep(10)
|
|
continue
|
|
|
|
assert job["success"]
|
|
break
|
|
|
|
# Assert file was updated
|
|
r = requests.get(
|
|
f"{API_PREFIX}/orgs/{default_org_id}/crawls/{timeout_crawl}/replay.json",
|
|
headers=admin_auth_headers,
|
|
)
|
|
assert r.status_code == 200
|
|
data = r.json()
|
|
files = data.get("resources")
|
|
assert files
|
|
for file_ in files:
|
|
assert file_["numReplicas"] == 1
|
|
|
|
# Verify replica is stored
|
|
r = requests.get(
|
|
f"{API_PREFIX}/orgs/{default_org_id}/jobs/{job_id}", headers=admin_auth_headers
|
|
)
|
|
assert r.status_code == 200
|
|
data = r.json()
|
|
verify_file_replicated(data["file_path"])
|