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

Handle sealed crawl pause race in API test

Browse Source
This commit is contained in:
Nick Sweeting 2026-06-21 06:49:38 -07:00
parent be9c77320c
commit fee4bf13cb
No known key found for this signature in database
1 changed files with 5 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
archivebox/tests/test_api_v1_crawls_crawl_crawl_id.py
View File

@ -475,11 +475,14 @@ def test_update_index_only_runs_paused_search_rows_and_resume_later_runs_crawl(t
if snapshot_finished_before_pause:
indexed_state = get_crawl_runtime_state(tmp_path, crawl_id)
assert indexed_state["crawl_status"] == "paused"
assert indexed_state["crawl_retry_at"] == indexed_state["retry_at_max"]
assert indexed_state["snapshots"][0]["status"] == "sealed"
wget_results = [result for result in indexed_state["results"] if result["plugin"] == "wget"]
assert any(result["status"] == "succeeded" and result["output_size"] > 0 for result in wget_results)
if indexed_state["crawl_status"] == "paused":
assert indexed_state["crawl_retry_at"] == indexed_state["retry_at_max"]
else:
assert indexed_state["crawl_status"] == "sealed"
assert all(result["status"] not in {"queued", "started", "paused"} for result in indexed_state["results"])
captured_text = wait_for_snapshot_capture(tmp_path, recursive_test_site["root_url"], timeout=60)
assert "Root" in captured_text
assert "About" in captured_text