mirror of
https://github.com/hanzoai/datastore.git
synced 2026-09-26 13:55:07 +00:00
Alexey MilovidovandClaude Opus 4.8
295ced78d1
Follow-up to #105171, which added `ruff` with a deliberately narrow, bug-class-only rule set and left the unused-name and star-import rules off pending a dedicated cleanup pass. This enables that second batch in `pyproject.toml` and fixes every violation across the tree (the bulk in integration tests): - `F401` unused-import and `F841` unused-variable: removed, preserving any side-effecting right-hand side (e.g. `result = node.query(...)` becomes `node.query(...)`). Two `try: import ...` feature probes are kept with `# noqa: F401`. - `F541` f-string-missing-placeholders: dropped the redundant `f` prefix. - `F403`/`F405` star imports: every `from module import *` is expanded into explicit imports of the names actually used, taken from each name's real origin, so stdlib/third-party names import from their real source rather than through a test "convenience bundle". The now-empty `tests/integration/helpers/kafka/common_direct.py` bundle is removed and its three remaining consumers import `_VarintBytes`/`KafkaAdminClient` directly. Eliminating the star imports surfaced a real bug the wildcard had masked from `F821`: `generate_presets.py` in `test_prometheus_protocols` called an undefined `execute_instant_query_with_http_api`; fixed to the existing `execute_query_via_http_api`. No `black`/`isort` reformatting was applied (neither is enforced in the style check), so the diff is limited to the lint fixes themselves. Co-Authored-By: Claude Opus 4.8 (1M context) <[email protected]>
75 lines
2.9 KiB
Python
75 lines
2.9 KiB
Python
import pytest
|
|
from helpers.cluster import ClickHouseCluster
|
|
|
|
cluster = ClickHouseCluster(__file__)
|
|
node = cluster.add_instance("node", with_minio=False)
|
|
|
|
|
|
@pytest.fixture(scope="module")
|
|
def started_cluster():
|
|
try:
|
|
cluster.start()
|
|
yield cluster
|
|
finally:
|
|
cluster.shutdown()
|
|
|
|
def test_two_stage_ttl_group_by(started_cluster):
|
|
node = cluster.instances["node"]
|
|
|
|
node.query("DROP TABLE IF EXISTS test_ttl_group_by")
|
|
|
|
# Create table with two TTL GROUP BY rules:
|
|
# 1. After 13 seconds, aggregate by user_id, item_id using SUM
|
|
# 2. After 18 seconds, aggregate by user_id using SUM
|
|
node.query("""
|
|
CREATE TABLE test_ttl_group_by (
|
|
event_date DateTime,
|
|
user_id Int32,
|
|
item_id Int32,
|
|
val Float32,
|
|
rolled_by_item_id DateTime DEFAULT event_date,
|
|
rolled_by_user_id DateTime DEFAULT event_date
|
|
) ENGINE = MergeTree()
|
|
PRIMARY KEY (event_date, user_id, item_id)
|
|
TTL rolled_by_item_id + INTERVAL 13 SECOND
|
|
GROUP BY event_date, user_id, item_id
|
|
SET val = sum(val),
|
|
rolled_by_item_id = max(rolled_by_item_id) + INTERVAL 10 YEAR,
|
|
rolled_by_user_id + INTERVAL 18 SECOND
|
|
GROUP BY event_date, user_id
|
|
SET val = sum(val),
|
|
rolled_by_user_id = max(rolled_by_user_id) + INTERVAL 10 YEAR
|
|
SETTINGS merge_with_ttl_timeout = 0;
|
|
""")
|
|
|
|
# Insert 10 rows with current timestamp, evenly distributed across 2 user_ids and 3 items
|
|
node.query("""
|
|
INSERT INTO test_ttl_group_by
|
|
SELECT
|
|
now() AS event_date,
|
|
number % 2 AS user_id,
|
|
user_id * 10 + (number % 3) AS item_id,
|
|
1 AS val,
|
|
event_date AS rolled_by_item_id,
|
|
event_date AS rolled_by_user_id
|
|
FROM numbers(10);
|
|
""")
|
|
|
|
# Step 1: Ensure all 10 rows were inserted
|
|
node.query_with_retry("SELECT count() FROM test_ttl_group_by", check_callback=lambda res: int(res.strip()) == 10,
|
|
sleep_time=1, retry_count=10)
|
|
|
|
# Step 2: Wait for the first TTL (13 seconds) to apply — should reduce to 6 rows (one per item_id)
|
|
node.query_with_retry("SELECT count() FROM test_ttl_group_by", check_callback=lambda res: int(res.strip()) == 6,
|
|
sleep_time=1, retry_count=20)
|
|
|
|
# Step 3: Wait for second TTL (18 seconds since insert) to apply — should reduce to 2 rows (one per user_id)
|
|
node.query_with_retry("SELECT count() FROM test_ttl_group_by", check_callback=lambda res: int(res.strip()) == 2,
|
|
sleep_time=1, retry_count=10)
|
|
|
|
row_after_second_ttl = node.query_with_retry("SELECT user_id, val FROM test_ttl_group_by ORDER BY user_id FORMAT TSV")
|
|
|
|
rows = row_after_second_ttl.strip().splitlines()
|
|
for line in rows:
|
|
user_id_str, value_str = line.strip().split("\t")
|
|
assert int(value_str) == 5, "Invalid value after TTL aggregation" |