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]>
141 lines
4.2 KiB
Python
141 lines
4.2 KiB
Python
import logging
|
|
|
|
import pytest
|
|
|
|
from helpers.cluster import ClickHouseCluster
|
|
from helpers.blobs import wait_blobs_count_synchronization
|
|
|
|
|
|
@pytest.fixture(scope="module")
|
|
def cluster():
|
|
try:
|
|
cluster = ClickHouseCluster(__file__)
|
|
cluster.add_instance(
|
|
"node",
|
|
main_configs=["configs/minio.xml", "configs/ssl.xml"],
|
|
with_minio=True,
|
|
stay_alive=True,
|
|
)
|
|
logging.info("Starting cluster...")
|
|
cluster.start()
|
|
|
|
logging.info("Cluster started")
|
|
|
|
yield cluster
|
|
finally:
|
|
cluster.shutdown()
|
|
|
|
|
|
def test_set_s3(cluster):
|
|
node = cluster.instances["node"]
|
|
|
|
node.query("CREATE TABLE testLocalSet (n UInt64) Engine = Set")
|
|
node.query("CREATE TABLE testS3Set (n UInt64) Engine = Set SETTINGS disk='s3'")
|
|
|
|
node.query("INSERT INTO TABLE testLocalSet VALUES (1)")
|
|
node.query("INSERT INTO TABLE testS3Set VALUES (1)")
|
|
|
|
assert (
|
|
node.query(
|
|
"SELECT number in testLocalSet, number in testS3Set FROM system.numbers LIMIT 3"
|
|
)
|
|
== "0\t0\n1\t1\n0\t0\n"
|
|
)
|
|
wait_blobs_count_synchronization(cluster.minio_client, 1)
|
|
|
|
node.query("INSERT INTO TABLE testLocalSet VALUES (2)")
|
|
node.query("INSERT INTO TABLE testS3Set VALUES (2)")
|
|
|
|
assert (
|
|
node.query(
|
|
"SELECT number in testLocalSet, number in testS3Set FROM system.numbers LIMIT 3"
|
|
)
|
|
== "0\t0\n1\t1\n1\t1\n"
|
|
)
|
|
wait_blobs_count_synchronization(cluster.minio_client, 2)
|
|
|
|
node.restart_clickhouse()
|
|
assert (
|
|
node.query(
|
|
"SELECT number in testLocalSet, number in testS3Set FROM system.numbers LIMIT 3"
|
|
)
|
|
== "0\t0\n1\t1\n1\t1\n"
|
|
)
|
|
|
|
node.query("TRUNCATE TABLE testLocalSet")
|
|
node.query("TRUNCATE TABLE testS3Set")
|
|
|
|
assert (
|
|
node.query(
|
|
"SELECT number in testLocalSet, number in testS3Set FROM system.numbers LIMIT 3"
|
|
)
|
|
== "0\t0\n0\t0\n0\t0\n"
|
|
)
|
|
wait_blobs_count_synchronization(cluster.minio_client, 0)
|
|
|
|
node.query("DROP TABLE testLocalSet")
|
|
node.query("DROP TABLE testS3Set")
|
|
|
|
|
|
def test_join_s3(cluster):
|
|
node = cluster.instances["node"]
|
|
|
|
node.query(
|
|
"CREATE TABLE testLocalJoin(`id` UInt64, `val` String) ENGINE = Join(ANY, LEFT, id)"
|
|
)
|
|
node.query(
|
|
"CREATE TABLE testS3Join(`id` UInt64, `val` String) ENGINE = Join(ANY, LEFT, id) SETTINGS disk='s3', join_any_take_last_row = 1"
|
|
)
|
|
|
|
node.query("INSERT INTO testLocalJoin VALUES (1, 'a')")
|
|
for i in range(1, 10):
|
|
c = chr(ord("a") + i)
|
|
node.query(f"INSERT INTO testLocalJoin VALUES (1, '{c}')")
|
|
|
|
# because of `join_any_take_last_row = 1` we expect the last row with 'a' value
|
|
for i in range(1, 10):
|
|
c = chr(ord("a") + i)
|
|
node.query(f"INSERT INTO testS3Join VALUES (1, '{c}')")
|
|
node.query("INSERT INTO testS3Join VALUES (1, 'a')")
|
|
|
|
assert (
|
|
node.query(
|
|
"SELECT joinGet('testLocalJoin', 'val', number) as local, joinGet('testS3Join', 'val', number) as s3 FROM system.numbers LIMIT 3"
|
|
)
|
|
== "\t\na\ta\n\t\n"
|
|
)
|
|
wait_blobs_count_synchronization(cluster.minio_client, 10)
|
|
|
|
node.query("INSERT INTO testLocalJoin VALUES (2, 'b')")
|
|
node.query("INSERT INTO testS3Join VALUES (2, 'b')")
|
|
|
|
assert (
|
|
node.query(
|
|
"SELECT joinGet('testLocalJoin', 'val', number) as local, joinGet('testS3Join', 'val', number) as s3 FROM system.numbers LIMIT 3"
|
|
)
|
|
== "\t\na\ta\nb\tb\n"
|
|
)
|
|
wait_blobs_count_synchronization(cluster.minio_client, 11)
|
|
|
|
node.restart_clickhouse()
|
|
assert (
|
|
node.query(
|
|
"SELECT joinGet('testLocalJoin', 'val', number) as local, joinGet('testS3Join', 'val', number) as s3 FROM system.numbers LIMIT 3"
|
|
)
|
|
== "\t\na\ta\nb\tb\n"
|
|
)
|
|
|
|
node.query("TRUNCATE TABLE testLocalJoin")
|
|
node.query("TRUNCATE TABLE testS3Join")
|
|
|
|
assert (
|
|
node.query(
|
|
"SELECT joinGet('testLocalJoin', 'val', number) as local, joinGet('testS3Join', 'val', number) as s3 FROM system.numbers LIMIT 3"
|
|
)
|
|
== "\t\n\t\n\t\n"
|
|
)
|
|
wait_blobs_count_synchronization(cluster.minio_client, 0)
|
|
|
|
node.query("DROP TABLE testLocalJoin")
|
|
node.query("DROP TABLE testS3Join")
|