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]>
151 lines
4.8 KiB
Python
151 lines
4.8 KiB
Python
# pylint: disable=unused-argument
|
|
# pylint: disable=redefined-outer-name
|
|
|
|
import pytest
|
|
|
|
from helpers.cluster import ClickHouseCluster
|
|
|
|
cluster = ClickHouseCluster(__file__)
|
|
|
|
node = cluster.add_instance("node", with_zookeeper=True)
|
|
|
|
|
|
@pytest.fixture(scope="module")
|
|
def start_cluster():
|
|
try:
|
|
cluster.start()
|
|
|
|
yield cluster
|
|
finally:
|
|
cluster.shutdown()
|
|
|
|
|
|
def get_counts():
|
|
src = int(node.query("SELECT count() FROM test"))
|
|
a = int(node.query("SELECT count() FROM test_mv_a"))
|
|
b = int(node.query("SELECT count() FROM test_mv_b"))
|
|
c = int(node.query("SELECT count() FROM test_mv_c"))
|
|
return src, a, b, c
|
|
|
|
|
|
def test_basic(start_cluster):
|
|
old_src, old_a, old_b, old_c = 0, 0, 0, 0
|
|
|
|
node.query(
|
|
"""
|
|
DROP TABLE IF EXISTS test_mv_c SYNC;
|
|
DROP TABLE IF EXISTS test_mv_b SYNC;
|
|
DROP TABLE IF EXISTS test_mv_a SYNC;
|
|
DROP TABLE IF EXISTS test SYNC;
|
|
"""
|
|
)
|
|
|
|
node.query(
|
|
"""
|
|
CREATE TABLE test (A Int64) ENGINE = ReplicatedMergeTree ('/clickhouse/test/tables/test','1') ORDER BY tuple();
|
|
CREATE MATERIALIZED VIEW test_mv_a Engine=ReplicatedMergeTree ('/clickhouse/test/tables/test_mv_a','1') order by tuple() AS SELECT A FROM test;
|
|
CREATE MATERIALIZED VIEW test_mv_b Engine=ReplicatedMergeTree ('/clickhouse/test/tables/test_mv_b','1') partition by A order by tuple() AS SELECT A FROM test;
|
|
CREATE MATERIALIZED VIEW test_mv_c Engine=ReplicatedMergeTree ('/clickhouse/test/tables/test_mv_c','1') order by tuple() AS SELECT A FROM test;
|
|
""")
|
|
|
|
node.query(
|
|
"""
|
|
SET deduplicate_blocks_in_dependent_materialized_views = 0;
|
|
INSERT INTO test values(999);
|
|
INSERT INTO test values(999);
|
|
"""
|
|
)
|
|
src, a, b, c = get_counts()
|
|
assert src == old_src + 1
|
|
assert a == old_a + 2
|
|
assert b == old_b + 2
|
|
assert c == old_c + 2
|
|
old_src, old_a, old_b, old_c = src, a, b, c
|
|
|
|
# that issert fails on test_mv_b due to partitions by A
|
|
node.query(
|
|
"""
|
|
SET max_partitions_per_insert_block = 3;
|
|
SET materialized_views_ignore_errors = 1;
|
|
SET deduplicate_blocks_in_dependent_materialized_views = 0;
|
|
INSERT INTO test SELECT number FROM numbers(10) ORDER BY ALL;
|
|
"""
|
|
)
|
|
src, a, b, c = get_counts()
|
|
assert src == old_src + 10
|
|
assert a == old_a + 10
|
|
assert b == old_b
|
|
assert c == old_c + 10
|
|
old_src, old_a, old_b, old_c = src, a, b, c
|
|
|
|
# deduplication only for src table
|
|
node.query(
|
|
"""
|
|
SET deduplicate_blocks_in_dependent_materialized_views = 0;
|
|
INSERT INTO test SELECT number FROM numbers(10) ORDER BY ALL
|
|
""")
|
|
src, a, b, c = get_counts()
|
|
assert src == old_src
|
|
assert a == old_a + 10
|
|
assert b == old_b + 10
|
|
assert c == old_c + 10
|
|
old_src, old_a, old_b, old_c = src, a, b, c
|
|
|
|
# deduplication for MV tables does not work, because previous inserts have not written their deduplications tokens to the log due to `deduplicate_blocks_in_dependent_materialized_views = 0`.
|
|
node.query(
|
|
"""
|
|
SET deduplicate_blocks_in_dependent_materialized_views = 1;
|
|
INSERT INTO test SELECT number FROM numbers(10) ORDER BY ALL;
|
|
"""
|
|
)
|
|
src, a, b, c = get_counts()
|
|
assert src == old_src
|
|
assert a == old_a + 10
|
|
assert b == old_b + 10
|
|
assert c == old_c + 10
|
|
old_src, old_a, old_b, old_c = src, a, b, c
|
|
|
|
# deduplication for all the tables
|
|
node.query(
|
|
"""
|
|
SET deduplicate_blocks_in_dependent_materialized_views = 1;
|
|
INSERT INTO test SELECT number FROM numbers(10) ORDER BY ALL;
|
|
"""
|
|
)
|
|
src, a, b, c = get_counts()
|
|
assert src == old_src
|
|
assert a == old_a
|
|
assert b == old_b
|
|
assert c == old_c
|
|
old_src, old_a, old_b, old_c = src, a, b, c
|
|
|
|
# that issert fails on test_mv_b due to partitions by A, it is an uniq data which is not deduplicated
|
|
node.query(
|
|
"""
|
|
SET max_partitions_per_insert_block = 3;
|
|
SET materialized_views_ignore_errors = 1;
|
|
SET deduplicate_blocks_in_dependent_materialized_views = 1;
|
|
INSERT INTO test SELECT number FROM numbers(100,10) ORDER BY ALL;
|
|
"""
|
|
)
|
|
src, a, b, c = get_counts()
|
|
assert src == old_src + 10
|
|
assert a == old_a + 10
|
|
assert b == old_b
|
|
assert c == old_c + 10
|
|
old_src, old_a, old_b, old_c = src, a, b, c
|
|
|
|
# deduplication for all tables, except test_mv_b. For test_mv_b it is an uniq data which is not deduplicated due to exception at previous insert
|
|
node.query(
|
|
"""
|
|
SET deduplicate_blocks_in_dependent_materialized_views = 1;
|
|
INSERT INTO test SELECT number FROM numbers(100,10) ORDER BY ALL;
|
|
"""
|
|
)
|
|
src, a, b, c = get_counts()
|
|
assert src == old_src
|
|
assert a == old_a
|
|
assert b == old_b + 10
|
|
assert c == old_c
|
|
old_src, old_a, old_b, old_c = src, a, b, c
|