0fa60ebc45
* Rename archives to orgs and aid to oid on backend * Rename archive to org and aid to oid in frontend * Remove translation artifact * Rename team -> organization * Add database migrations and run once on startup * This commit also applies the new by_one_worker decorator to other asyncio tasks to prevent heavy tasks from being run in each worker. * Run black, pylint, and husky via pre-commit * Set db version and use in migrations * Update and prepare database in single task * Migrate k8s configmaps
99 lines
2.4 KiB
Python
99 lines
2.4 KiB
Python
import requests
|
|
import hashlib
|
|
import time
|
|
import io
|
|
import zipfile
|
|
|
|
from .conftest import API_PREFIX, HOST_PREFIX
|
|
|
|
wacz_path = None
|
|
wacz_size = None
|
|
wacz_hash = None
|
|
|
|
wacz_content = None
|
|
|
|
|
|
def test_list_orgs(admin_auth_headers, default_org_id):
|
|
r = requests.get(f"{API_PREFIX}/orgs", headers=admin_auth_headers)
|
|
data = r.json()
|
|
|
|
orgs = data["orgs"]
|
|
assert len(orgs) > 0
|
|
|
|
org_ids = []
|
|
for org in orgs:
|
|
org_ids.append(org["id"])
|
|
assert default_org_id in org_ids
|
|
|
|
|
|
def test_create_new_config(admin_auth_headers, default_org_id):
|
|
crawl_data = {
|
|
"runNow": True,
|
|
"name": "Test Crawl",
|
|
"config": {"seeds": ["https://webrecorder.net/"]},
|
|
}
|
|
r = requests.post(
|
|
f"{API_PREFIX}/orgs/{default_org_id}/crawlconfigs/",
|
|
headers=admin_auth_headers,
|
|
json=crawl_data,
|
|
)
|
|
|
|
assert r.status_code == 200
|
|
|
|
data = r.json()
|
|
assert data["added"]
|
|
assert data["run_now_job"]
|
|
|
|
|
|
def test_wait_for_complete(admin_auth_headers, default_org_id, admin_crawl_id):
|
|
r = requests.get(
|
|
f"{API_PREFIX}/orgs/{default_org_id}/crawls/{admin_crawl_id}/replay.json",
|
|
headers=admin_auth_headers,
|
|
)
|
|
data = r.json()
|
|
assert data["state"] == "complete"
|
|
|
|
assert len(data["resources"]) == 1
|
|
assert data["resources"][0]["path"]
|
|
|
|
assert data["tags"] == ["wr-test-1", "wr-test-2"]
|
|
|
|
global wacz_path
|
|
global wacz_size
|
|
global wacz_hash
|
|
wacz_path = data["resources"][0]["path"]
|
|
wacz_size = data["resources"][0]["size"]
|
|
wacz_hash = data["resources"][0]["hash"]
|
|
|
|
|
|
def test_crawl_info(admin_auth_headers, default_org_id, admin_crawl_id):
|
|
r = requests.get(
|
|
f"{API_PREFIX}/orgs/{default_org_id}/crawls/{admin_crawl_id}",
|
|
headers=admin_auth_headers,
|
|
)
|
|
data = r.json()
|
|
assert data["fileSize"] == wacz_size
|
|
|
|
|
|
def test_download_wacz():
|
|
r = requests.get(HOST_PREFIX + wacz_path)
|
|
assert r.status_code == 200
|
|
assert len(r.content) == wacz_size
|
|
|
|
h = hashlib.sha256()
|
|
h.update(r.content)
|
|
assert h.hexdigest() == wacz_hash, (h.hexdigest(), wacz_hash)
|
|
|
|
global wacz_content
|
|
wacz_content = r.content
|
|
|
|
|
|
def test_verify_wacz():
|
|
b = io.BytesIO(wacz_content)
|
|
z = zipfile.ZipFile(b)
|
|
|
|
assert "pages/pages.jsonl" in z.namelist()
|
|
|
|
pages = z.open("pages/pages.jsonl").read().decode("utf-8")
|
|
assert '"https://webrecorder.net/"' in pages
|