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]>
99 lines
3.0 KiB
Python
99 lines
3.0 KiB
Python
import pytest
|
|
import logging
|
|
import pyspark
|
|
import subprocess
|
|
|
|
|
|
from helpers.cluster import ClickHouseCluster, minio_access_key, minio_secret_key
|
|
from helpers.s3_tools import (
|
|
prepare_s3_bucket,
|
|
)
|
|
from helpers.spark_tools import ResilientSparkSession, write_spark_log_config
|
|
|
|
def check_spark(spark):
|
|
p = subprocess.run(["echo", "hello world!"], capture_output=True, text=True)
|
|
logging.info(f"Java version: {p.stdout}")
|
|
|
|
|
|
spark.sql(
|
|
"""
|
|
DROP DATABASE IF EXISTS spark_catalog.db CASCADE
|
|
"""
|
|
)
|
|
|
|
spark.sql(
|
|
"""
|
|
CREATE DATABASE spark_catalog.db
|
|
"""
|
|
)
|
|
|
|
spark.sql(
|
|
"""
|
|
CREATE TABLE IF NOT EXISTS spark_catalog.db.lol2 (order_number bigint) USING iceberg OPTIONS ('format-version'='1');
|
|
"""
|
|
)
|
|
|
|
spark.sql(
|
|
"""
|
|
INSERT INTO spark_catalog.db.lol2 (order_number) VALUES (123), (456), (789);
|
|
"""
|
|
)
|
|
|
|
logging.info(f"Dataframe: {spark.sql('SELECT * FROM spark_catalog.db.lol2').show()}")
|
|
|
|
def get_spark(cluster : ClickHouseCluster):
|
|
|
|
builder = (
|
|
pyspark.sql.SparkSession.builder \
|
|
.appName("IcebergS3Example") \
|
|
.config("spark.sql.extensions", "org.apache.iceberg.spark.extensions.IcebergSparkSessionExtensions") \
|
|
.config("spark.sql.catalog.spark_catalog", "org.apache.iceberg.spark.SparkSessionCatalog") \
|
|
.config("spark.sql.catalog.spark_catalog.type", "hadoop") \
|
|
.config("spark.sql.catalog.spark_catalog.warehouse", "s3a://root/var/lib/clickhouse/user_files/iceberg_data") \
|
|
.config("spark.hadoop.fs.s3a.endpoint", f"http://{cluster.minio_ip}:{cluster.minio_port}/") \
|
|
.config("spark.hadoop.fs.s3a.access.key", minio_access_key) \
|
|
.config("spark.hadoop.fs.s3a.secret.key", minio_secret_key) \
|
|
.config("spark.hadoop.fs.s3a.path.style.access", "true") \
|
|
.config("spark.hadoop.fs.s3a.impl", "org.apache.hadoop.fs.s3a.S3AFileSystem")
|
|
.master("local")
|
|
)
|
|
|
|
props_path = write_spark_log_config(cluster.instances_dir)
|
|
builder = builder.config(
|
|
"spark.driver.extraJavaOptions",
|
|
f"-Dlog4j2.configurationFile=file:{props_path}",
|
|
)
|
|
|
|
return builder.getOrCreate()
|
|
|
|
@pytest.fixture(scope="package")
|
|
def started_cluster_iceberg():
|
|
try:
|
|
cluster = ClickHouseCluster(__file__, with_spark=True)
|
|
cluster.add_instance(
|
|
"node1",
|
|
main_configs=[
|
|
"configs/config.d/named_collections.xml",
|
|
"configs/config.d/log_level_override.xml",
|
|
],
|
|
user_configs=["configs/users.d/users.xml"],
|
|
with_minio=True,
|
|
stay_alive=True,
|
|
mem_limit='15g',
|
|
cpu_limit=False,
|
|
)
|
|
|
|
logging.info("Starting cluster...")
|
|
cluster.start()
|
|
|
|
prepare_s3_bucket(cluster)
|
|
|
|
cluster.spark_session = ResilientSparkSession(lambda: get_spark(cluster))
|
|
|
|
# check_spark(cluster.spark_session)
|
|
|
|
yield cluster
|
|
|
|
finally:
|
|
cluster.shutdown()
|