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]>
166 lines
4.2 KiB
Python
166 lines
4.2 KiB
Python
import pytest
|
|
|
|
from helpers.cluster import ClickHouseCluster
|
|
from test_modify_engine_on_restart.common import check_flags_deleted, set_convert_flags
|
|
|
|
cluster = ClickHouseCluster(__file__)
|
|
ch1 = cluster.add_instance(
|
|
"ch1",
|
|
main_configs=[
|
|
"configs/config.d/clusters.xml",
|
|
"configs/config.d/distributed_ddl.xml",
|
|
],
|
|
with_zookeeper=True,
|
|
macros={"replica": "node1"},
|
|
stay_alive=True,
|
|
)
|
|
ch2 = cluster.add_instance(
|
|
"ch2",
|
|
main_configs=[
|
|
"configs/config.d/clusters.xml",
|
|
"configs/config.d/distributed_ddl.xml",
|
|
],
|
|
with_zookeeper=True,
|
|
macros={"replica": "node2"},
|
|
)
|
|
|
|
database_name = "modify_engine"
|
|
|
|
|
|
@pytest.fixture(scope="module")
|
|
def started_cluster():
|
|
try:
|
|
cluster.start()
|
|
yield cluster
|
|
|
|
finally:
|
|
cluster.shutdown()
|
|
|
|
|
|
def q(node, query):
|
|
return node.query(database=database_name, sql=query)
|
|
|
|
|
|
def create_tables():
|
|
# MergeTree table that will be converted
|
|
q(
|
|
ch1,
|
|
"CREATE TABLE rmt ( A Int64, D Date, S String ) ENGINE MergeTree() PARTITION BY toYYYYMM(D) ORDER BY A;",
|
|
)
|
|
|
|
q(ch1, "INSERT INTO rmt SELECT number, today(), '' FROM numbers(1e6);")
|
|
q(ch1, "INSERT INTO rmt SELECT number, today()-60, '' FROM numbers(1e5);")
|
|
|
|
# ReplacingMergeTree table that will be converted to check unusual engine kinds
|
|
q(
|
|
ch1,
|
|
"CREATE TABLE replacing ( A Int64, D Date, S String ) ENGINE ReplacingMergeTree() PARTITION BY toYYYYMM(D) ORDER BY A;",
|
|
)
|
|
|
|
q(ch1, "INSERT INTO replacing SELECT number, today(), '' FROM numbers(1e6);")
|
|
q(ch1, "INSERT INTO replacing SELECT number, today()-60, '' FROM numbers(1e5);")
|
|
|
|
# MergeTree table that will not be converted
|
|
q(
|
|
ch1,
|
|
"CREATE TABLE mt ( A Int64, D Date, S String ) ENGINE MergeTree() PARTITION BY toYYYYMM(D) ORDER BY A;",
|
|
)
|
|
|
|
# Not MergeTree table
|
|
q(ch1, "CREATE TABLE log ( A Int64, D Date, S String ) ENGINE Log;")
|
|
|
|
|
|
def check_tables(converted):
|
|
engine_prefix = ""
|
|
if converted:
|
|
engine_prefix = "Replicated"
|
|
|
|
# Check tables exists
|
|
assert (
|
|
q(
|
|
ch1,
|
|
"SHOW TABLES",
|
|
).strip()
|
|
== "log\nmt\nreplacing\nrmt"
|
|
)
|
|
|
|
# Check engines
|
|
assert (
|
|
q(
|
|
ch1,
|
|
f"SELECT name, engine FROM system.tables WHERE database = '{database_name}' AND (name != 'log' AND name != 'mt')",
|
|
).strip()
|
|
== f"replacing\t{engine_prefix}ReplacingMergeTree\nrmt\t{engine_prefix}MergeTree"
|
|
)
|
|
assert (
|
|
q(
|
|
ch1,
|
|
f"SELECT name, engine FROM system.tables WHERE database = '{database_name}' AND (name = 'log' OR name = 'mt')",
|
|
).strip()
|
|
== "log\tLog\nmt\tMergeTree"
|
|
)
|
|
|
|
# Check values
|
|
for table in ["rmt", "replacing"]:
|
|
assert (
|
|
q(
|
|
ch1,
|
|
f"SELECT count() FROM {table}",
|
|
).strip()
|
|
== "1100000"
|
|
)
|
|
|
|
|
|
def check_replica_added():
|
|
# Add replica to check if zookeeper path is correct and consistent with table uuid
|
|
|
|
uuid = q(
|
|
ch1,
|
|
f"SELECT uuid FROM system.tables WHERE table = 'rmt' AND database = '{database_name}'",
|
|
).strip()
|
|
|
|
q(
|
|
ch2,
|
|
f"CREATE TABLE rmt ( A Int64, D Date, S String ) ENGINE ReplicatedMergeTree('/clickhouse/tables/{uuid}/{{shard}}', '{{replica}}') PARTITION BY toYYYYMM(D) ORDER BY A",
|
|
)
|
|
|
|
ch2.query(database=database_name, sql="SYSTEM SYNC REPLICA rmt", timeout=20)
|
|
|
|
# Check values
|
|
assert (
|
|
q(
|
|
ch2,
|
|
"SELECT count() FROM rmt",
|
|
).strip()
|
|
== "1100000"
|
|
)
|
|
|
|
|
|
def test_modify_engine_on_restart(started_cluster):
|
|
ch1.query(f"DROP DATABASE IF EXISTS {database_name} ON CLUSTER cluster SYNC")
|
|
ch1.query(f"CREATE DATABASE {database_name} ON CLUSTER cluster")
|
|
|
|
create_tables()
|
|
|
|
check_tables(False)
|
|
|
|
ch1.restart_clickhouse()
|
|
|
|
check_tables(False)
|
|
|
|
set_convert_flags(ch1, database_name, ["rmt", "replacing", "log"])
|
|
|
|
ch1.restart_clickhouse()
|
|
|
|
check_flags_deleted(ch1, database_name, ["rmt", "replacing"])
|
|
|
|
check_tables(True)
|
|
|
|
check_replica_added()
|
|
|
|
ch1.restart_clickhouse()
|
|
|
|
check_tables(True)
|
|
|
|
ch1.query(f"DROP DATABASE IF EXISTS {database_name} ON CLUSTER cluster SYNC")
|