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]>
117 lines
3.7 KiB
Python
117 lines
3.7 KiB
Python
import time
|
|
|
|
import pytest
|
|
|
|
from helpers.cluster import ClickHouseCluster
|
|
from helpers.test_tools import wait_condition
|
|
|
|
cluster = ClickHouseCluster(__file__)
|
|
node1 = cluster.add_instance("node1", stay_alive=True, with_zookeeper=True)
|
|
node2 = cluster.add_instance("node2", with_zookeeper=True)
|
|
|
|
instance = node1
|
|
q = node1.query
|
|
|
|
path_to_data = "/var/lib/clickhouse/"
|
|
|
|
|
|
@pytest.fixture(scope="module")
|
|
def started_cluster():
|
|
try:
|
|
cluster.start()
|
|
yield cluster
|
|
finally:
|
|
cluster.shutdown()
|
|
|
|
|
|
def wait_merged_part(table, part_name, retries=100):
|
|
for i in range(retries):
|
|
q("OPTIMIZE TABLE {}".format(table))
|
|
result = q(
|
|
"SELECT name FROM system.parts where table='{}' AND name='{}' AND active".format(
|
|
table, part_name
|
|
)
|
|
)
|
|
if result:
|
|
return True
|
|
time.sleep(0.5)
|
|
else:
|
|
return False
|
|
|
|
|
|
def test_make_clone_covered_by_broken_detached_dir_exists(started_cluster):
|
|
q("DROP TABLE IF EXISTS test_make_clone_cvbdde SYNC")
|
|
|
|
q(
|
|
"CREATE TABLE test_make_clone_cvbdde(n int, m String) ENGINE=ReplicatedMergeTree('/test_make_clone_cvbdde', '1') ORDER BY n SETTINGS old_parts_lifetime=3600, min_age_to_force_merge_seconds=1, min_age_to_force_merge_on_partition_only=0"
|
|
)
|
|
|
|
data_path = node1.query(
|
|
"SELECT arrayElement(data_paths, 1) FROM system.tables WHERE database='default' AND name='test_make_clone_cvbdde'"
|
|
).strip()
|
|
|
|
q("INSERT INTO test_make_clone_cvbdde VALUES (0, 'hbl')")
|
|
|
|
q("INSERT INTO test_make_clone_cvbdde VALUES (1, 'hbl')")
|
|
if not (wait_merged_part("test_make_clone_cvbdde", "all_0_1_1")):
|
|
assert False, "Part all_0_1_1 doesn't appeared in system.parts"
|
|
|
|
q("INSERT INTO test_make_clone_cvbdde VALUES (2, 'hbl')")
|
|
if not (wait_merged_part("test_make_clone_cvbdde", "all_0_2_2")):
|
|
assert False, "Part all_0_2_2 doesn't appeared in system.parts"
|
|
|
|
q("INSERT INTO test_make_clone_cvbdde VALUES (3, 'hbl')")
|
|
if not (wait_merged_part("test_make_clone_cvbdde", "all_0_3_3")):
|
|
assert False, "Part all_0_3_3 doesn't appeared in system.parts"
|
|
|
|
str(instance.exec_in_container(["ls", data_path]).strip().split("\n"))
|
|
|
|
# broke the merged parts
|
|
instance.exec_in_container(
|
|
[
|
|
"bash",
|
|
"-c",
|
|
"echo 'broken' > {}".format(data_path + "all_0_1_1/data.bin"),
|
|
]
|
|
)
|
|
|
|
instance.exec_in_container(
|
|
[
|
|
"bash",
|
|
"-c",
|
|
"echo 'broken' > {}".format(data_path + "all_0_2_2/data.bin"),
|
|
]
|
|
)
|
|
|
|
instance.exec_in_container(
|
|
[
|
|
"bash",
|
|
"-c",
|
|
"echo 'broken' > {}".format(data_path + "all_0_3_3/data.bin"),
|
|
]
|
|
)
|
|
|
|
instance.restart_clickhouse(kill=True)
|
|
|
|
# Sometimes,though rare, there seems to be a slight delay on ci and the parts don't become
|
|
# available immediately after restarting the server. In this case, the test fails. So, sleep
|
|
# for a second and then try to assert with retries to ensure that the test is not flaky.
|
|
time.sleep(1)
|
|
|
|
def assert_detached_parts(): # check that the broken parts are not in system.parts
|
|
return [
|
|
"broken-on-start_all_0_1_1",
|
|
"broken-on-start_all_0_2_2",
|
|
"broken-on-start_all_0_3_3",
|
|
"covered-by-broken_all_0_0_0",
|
|
"covered-by-broken_all_1_1_0",
|
|
"covered-by-broken_all_2_2_0",
|
|
"covered-by-broken_all_3_3_0",
|
|
] == sorted(
|
|
instance.exec_in_container(["ls", data_path + "detached/"])
|
|
.strip()
|
|
.split("\n")
|
|
)
|
|
|
|
wait_condition(assert_detached_parts, lambda x: x, max_attempts=10, delay=0.2)
|