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]>
212 lines
6.9 KiB
Python
212 lines
6.9 KiB
Python
import logging
|
|
|
|
import pytest
|
|
|
|
from helpers.cluster import ClickHouseCluster
|
|
from helpers.test_tools import TSV
|
|
|
|
logging.getLogger().setLevel(logging.INFO)
|
|
logging.getLogger().addHandler(logging.StreamHandler())
|
|
|
|
|
|
@pytest.fixture(scope="module")
|
|
def started_cluster():
|
|
try:
|
|
cluster = ClickHouseCluster(__file__)
|
|
cluster.add_instance(
|
|
"s0_0_0",
|
|
main_configs=["configs/cluster.xml"],
|
|
user_configs=["configs/users.xml"],
|
|
macros={"replica": "node1", "shard": "shard1"},
|
|
with_zookeeper=True,
|
|
)
|
|
cluster.add_instance(
|
|
"s0_0_1",
|
|
main_configs=["configs/cluster.xml"],
|
|
user_configs=["configs/users.xml"],
|
|
macros={"replica": "replica2", "shard": "shard1"},
|
|
with_zookeeper=True,
|
|
)
|
|
cluster.add_instance(
|
|
"s0_1_0",
|
|
main_configs=["configs/cluster.xml"],
|
|
user_configs=["configs/users.xml"],
|
|
macros={"replica": "replica1", "shard": "shard2"},
|
|
with_zookeeper=True,
|
|
)
|
|
|
|
logging.info("Starting cluster...")
|
|
cluster.start()
|
|
logging.info("Cluster started")
|
|
|
|
for node_name in ("s0_0_0", "s0_0_1", "s0_1_0"):
|
|
for i in range(1, 3):
|
|
cluster.instances[node_name].query(
|
|
f"""
|
|
INSERT INTO TABLE FUNCTION file(
|
|
'file{i}.csv', 'CSV', 's String, i UInt32') VALUES ('file{i}',{i})
|
|
"""
|
|
)
|
|
|
|
yield cluster
|
|
finally:
|
|
cluster.shutdown()
|
|
|
|
|
|
def get_query(select: str, cluster: bool, files_nums: str, order_by="ORDER BY (i, s)"):
|
|
if cluster:
|
|
return f"SELECT {select} from fileCluster('my_cluster', 'file{{{files_nums}}}.csv', 'CSV', 's String, i UInt32') {order_by}"
|
|
else:
|
|
return f"SELECT {select} from file('file{{{files_nums}}}.csv', 'CSV', 's String, i UInt32') {order_by}"
|
|
|
|
|
|
def test_select_all(started_cluster):
|
|
node = started_cluster.instances["s0_0_0"]
|
|
|
|
local = node.query(get_query("*", False, "1,2"))
|
|
distributed = node.query(get_query("*", True, "1,2"))
|
|
|
|
assert TSV(local) == TSV(distributed)
|
|
|
|
|
|
def test_count(started_cluster):
|
|
node = started_cluster.instances["s0_0_0"]
|
|
|
|
local = node.query(get_query("count(*)", False, "1,2", ""))
|
|
distributed = node.query(get_query("count(*)", True, "1,2", ""))
|
|
|
|
assert TSV(local) == TSV(distributed)
|
|
|
|
|
|
def test_non_existent_cluster(started_cluster):
|
|
node = started_cluster.instances["s0_0_0"]
|
|
error = node.query_and_get_error(
|
|
"""
|
|
SELECT count(*) from fileCluster(
|
|
'non_existent_cluster', 'file{1,2}.csv', 'CSV', 's String, i UInt32')
|
|
UNION ALL
|
|
SELECT count(*) from fileCluster(
|
|
'non_existent_cluster', 'file{1,2}.csv', 'CSV', 's String, i UInt32')
|
|
"""
|
|
)
|
|
|
|
assert "not found" in error
|
|
|
|
|
|
def test_missing_file(started_cluster):
|
|
"""
|
|
Select from a list of files, _some_ of them don't exist
|
|
"""
|
|
node = started_cluster.instances["s0_0_0"]
|
|
|
|
local_with_missing_file = node.query(get_query("*", False, "1,2,3"))
|
|
local_wo_missing_file = node.query(get_query("*", False, "1,2"))
|
|
|
|
distributed_with_missing_file = node.query(get_query("*", True, "1,2,3"))
|
|
distributed_wo_missing_file = node.query(get_query("*", True, "1,2"))
|
|
|
|
assert TSV(local_with_missing_file) == TSV(distributed_with_missing_file)
|
|
assert TSV(local_wo_missing_file) == TSV(distributed_wo_missing_file)
|
|
assert TSV(local_with_missing_file) == TSV(distributed_wo_missing_file)
|
|
assert TSV(local_wo_missing_file) == TSV(distributed_with_missing_file)
|
|
|
|
|
|
def test_no_such_files(started_cluster):
|
|
"""
|
|
Select from a list of files, _none_ of them don't exist
|
|
"""
|
|
node = started_cluster.instances["s0_0_0"]
|
|
|
|
local = node.query(get_query("*", False, "3,4"))
|
|
distributed = node.query(get_query("*", True, "3,4"))
|
|
|
|
assert TSV(local) == TSV(distributed)
|
|
|
|
|
|
def test_schema_inference(started_cluster):
|
|
node = started_cluster.instances["s0_0_0"]
|
|
|
|
expected_result = node.query(
|
|
"select * from file('file*.csv', 'CSV', 's String, i UInt32') ORDER BY (i, s)"
|
|
)
|
|
result = node.query(
|
|
"select * from fileCluster('my_cluster', 'file*.csv') ORDER BY (c1, c2)"
|
|
)
|
|
assert result == expected_result
|
|
|
|
result = node.query(
|
|
"select * from fileCluster('my_cluster', 'file*.csv', auto) ORDER BY (c1, c2)"
|
|
)
|
|
assert result == expected_result
|
|
|
|
result = node.query(
|
|
"select * from fileCluster('my_cluster', 'file*.csv', CSV) ORDER BY (c1, c2)"
|
|
)
|
|
assert result == expected_result
|
|
|
|
result = node.query(
|
|
"select * from fileCluster('my_cluster', 'file*.csv', auto, auto) ORDER BY (c1, c2)"
|
|
)
|
|
assert result == expected_result
|
|
|
|
result = node.query(
|
|
"select * from fileCluster('my_cluster', 'file*.csv', CSV, auto) ORDER BY (c1, c2)"
|
|
)
|
|
assert result == expected_result
|
|
|
|
result = node.query(
|
|
"select * from fileCluster('my_cluster', 'file*.csv', auto, auto, auto) ORDER BY (c1, c2)"
|
|
)
|
|
assert result == expected_result
|
|
|
|
result = node.query(
|
|
"select * from fileCluster('my_cluster', 'file*.csv', CSV, auto, auto) ORDER BY (c1, c2)"
|
|
)
|
|
assert result == expected_result
|
|
|
|
|
|
def test_format_detection(started_cluster):
|
|
for node_name in ("s0_0_0", "s0_0_1", "s0_1_0"):
|
|
for i in range(1, 3):
|
|
started_cluster.instances[node_name].query(
|
|
f"""
|
|
INSERT INTO TABLE FUNCTION file(
|
|
'file_for_format_detection_{i}', 'CSV', 's String, i UInt32') VALUES ('file{i}',{i})
|
|
"""
|
|
)
|
|
|
|
node = started_cluster.instances["s0_0_0"]
|
|
expected_result = node.query(
|
|
"select * from file('file_for_format_detection*', 'CSV', 's String, i UInt32') ORDER BY (i, s)"
|
|
)
|
|
|
|
result = node.query(
|
|
"select * from fileCluster('my_cluster', 'file_for_format_detection*') ORDER BY (c1, c2)"
|
|
)
|
|
assert result == expected_result
|
|
|
|
result = node.query(
|
|
"select * from fileCluster('my_cluster', 'file_for_format_detection*', auto) ORDER BY (c1, c2)"
|
|
)
|
|
assert result == expected_result
|
|
|
|
result = node.query(
|
|
"select * from fileCluster('my_cluster', 'file_for_format_detection*', auto, auto) ORDER BY (c1, c2)"
|
|
)
|
|
assert result == expected_result
|
|
|
|
result = node.query(
|
|
"select * from fileCluster('my_cluster', 'file_for_format_detection*', auto, 's String, i UInt32') ORDER BY (i, s)"
|
|
)
|
|
assert result == expected_result
|
|
|
|
result = node.query(
|
|
"select * from fileCluster('my_cluster', 'file_for_format_detection*', auto, auto, auto) ORDER BY (c1, c2)"
|
|
)
|
|
assert result == expected_result
|
|
|
|
result = node.query(
|
|
"select * from fileCluster('my_cluster', 'file_for_format_detection*', auto, 's String, i UInt32', auto) ORDER BY (i, s)"
|
|
)
|
|
assert result == expected_result
|