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]>
103 lines
2.9 KiB
Python
103 lines
2.9 KiB
Python
import os
|
|
|
|
import pytest
|
|
from helpers.cluster import ClickHouseCluster
|
|
|
|
SCRIPT_DIR = os.path.dirname(os.path.realpath(__file__))
|
|
cluster = ClickHouseCluster(__file__)
|
|
node = cluster.add_instance("node", stay_alive=True)
|
|
|
|
|
|
@pytest.fixture(scope="module", autouse=True)
|
|
def started_cluster():
|
|
try:
|
|
cluster.start()
|
|
|
|
for i in range(1, 10):
|
|
node.exec_in_container(
|
|
[
|
|
"touch",
|
|
f"/var/lib/clickhouse/user_files/{i}.file",
|
|
]
|
|
)
|
|
|
|
node.exec_in_container(
|
|
[
|
|
"mkdir",
|
|
"/var/lib/clickhouse/user_files/yes",
|
|
]
|
|
)
|
|
|
|
for i in range(20, 30):
|
|
node.exec_in_container(
|
|
[
|
|
"touch",
|
|
f"/var/lib/clickhouse/user_files/yes/{i}.file",
|
|
]
|
|
)
|
|
|
|
# Create a controlled directory outside user_files for symlink testing.
|
|
# Using /var/log/clickhouse-server/ would include an unpredictable number of log files.
|
|
# Reset the directory to avoid stale entries from a reused container, which would
|
|
# break the exact row-count assertions below.
|
|
node.exec_in_container(["rm", "-rf", "/tmp/link_target"])
|
|
node.exec_in_container(["mkdir", "-p", "/tmp/link_target"])
|
|
node.exec_in_container(["touch", "/tmp/link_target/test.log"])
|
|
node.exec_in_container(
|
|
[
|
|
"ln",
|
|
"-s",
|
|
"/tmp/link_target/",
|
|
"/var/lib/clickhouse/user_files/link",
|
|
]
|
|
)
|
|
|
|
yield cluster
|
|
|
|
finally:
|
|
cluster.shutdown()
|
|
|
|
|
|
def test_full_path():
|
|
# Expected: root dir (1) + 9 files + yes dir (1) + 10 files in yes + link symlink (1) + test.log in link (1) = 23
|
|
assert (
|
|
node.query("SELECT count() FROM filesystem('/var/lib/clickhouse/user_files/')")
|
|
== "23\n"
|
|
)
|
|
|
|
|
|
def test_file_path():
|
|
assert node.query("SELECT count() FROM filesystem('yes')") == "11\n"
|
|
|
|
|
|
def test_no_path():
|
|
assert node.query("SELECT count() FROM filesystem('')") == "23\n"
|
|
assert (
|
|
node.query(
|
|
"SELECT * FROM filesystem('/var/lib/clickhouse/user_files/') EXCEPT SELECT * FROM filesystem('')"
|
|
)
|
|
== ""
|
|
)
|
|
|
|
|
|
def test_relative_path():
|
|
assert "DATABASE_ACCESS_DENIED" in node.query_and_get_error(
|
|
"SELECT * FROM filesystem('/var/lib/clickhouse/user_files/../')"
|
|
)
|
|
|
|
|
|
def test_escape_path():
|
|
assert (
|
|
node.query(
|
|
"SELECT count() FROM filesystem('/var/lib/clickhouse/user_files/link/test.log')"
|
|
)
|
|
== "1\n"
|
|
)
|
|
|
|
|
|
def test_direct_outside_path():
|
|
"""Direct access to a path outside user_files must be denied, even if the same file is reachable through a symlink inside user_files."""
|
|
assert "DATABASE_ACCESS_DENIED" in node.query_and_get_error(
|
|
"SELECT * FROM filesystem('/tmp/link_target/test.log')"
|
|
)
|