OpenMetadata/ingestion/tests/unit/test_usage_log.py
IceS2 e9c87c6adb
chore(ingestion): drop pylint, expand ruff (#27774)
* chore(ingestion): drop pylint, expand ruff to Stage 2c

Replace pylint with a coherent ruff-only stack (Stage 2c of the modernize
roadmap). Pylint is dropped from dev deps and CI workflows; ruff selected
ruleset expanded to ~22 families covering style, bug catchers, hygiene,
and the pylint port (PLE/PLC/PLW/PLR with the noisy "too-many-X"
complexity caps + magic-value disabled).

What's selected (with rationale in pyproject.toml):
  E, W, F, I, N         — style + correctness baseline + naming
  UP                    — pyupgrade (py>=3.10 modernizations)
  B, C4, C90, RET, SIM, TRY  — bug catchers
  PIE, ICN, T20, TC, TID, PTH, PERF  — hygiene
  PLE, PLC, PLW, PLR    — pylint port (PLR complexity caps ignored)
  RUF                   — ruff-native (incl. RUF100 unused-noqa)

What's removed:
  - .pylintrc (root) — duplicate of the ingestion pylint config
  - [tool.pylint.*] block in ingestion/pyproject.toml (~140 lines)
  - ingestion/plugins/{print_checker,import_checker}.py + tests + README
    (replaced by built-in T20 + TID251 banned-api respectively)
  - pylint dep from ingestion/setup.py and openmetadata-airflow-apis/pyproject.toml
  - `make lint` Makefile target + the pylint invocation in py_format_check
  - dead pylint TODO comment + ignored test entry in noxfile.py

Cwd-stable config: ruff is invoked both from the repo root (pre-commit,
CI) and from ingestion/ (`make py_format_check`). The `src`,
`extend-exclude`, and per-file-ignores entries are listed twice — once
relative to ingestion/ and once with the `ingestion/` prefix — so
first-party isort detection and exclusions match in both invocations.

Grandfathering: ran `ruff check --add-noqa` once + format-stable
iteration. ~12,130 noqa directives across ~1,400 files. Cleanup is
deferred to follow-up PRs that drop noqas one rule at a time.

Documentation sweep: replaced `make lint` references in CLAUDE.md,
AGENTS.md, DEVELOPER.md, copilot-instructions, and 6 SKILL files with
the apply+verify shape `make py_format && make py_format_check`.
`make py_format` is NOT a strict superset of pylint — it only applies
auto-fixable violations; `make py_format_check` catches the rest.

Basedpyright baseline regenerated: ruff format reflowed multi-line
signatures in ~70 files, shifting type-error column positions. The
basedpyright baseline matches by (file path, error code, range), so
column shifts caused 19 entries to mis-align. Net diff is small
(154 lines in/out of the 13MB baseline.json) — purely positional.

Verified locally:
  - make py_format_check         → All checks passed
  - nox --no-venv -s static-checks → 0 errors, 0 warnings, 0 notes

* chore(ingestion): finish ruff swap — nox lint session + skill docs

Three remaining stale-tooling references after Stage 2c:

  - `ingestion/noxfile.py` `lint` session was still calling `black --check`,
    `isort --check-only`, `pycln --diff`. Those tools aren't installed
    anywhere (we dropped them from dev deps). Replace with the ruff
    equivalents that mirror `make py_format_check`.
  - `skills/standards/code_style.md`: stack listed as `black + isort +
    pycln`; line length claimed 88 (black default). Both wrong: stack is
    ruff, line length is 120.
  - `skills/connector-building/SKILL.md`: `make py_format` comment said
    `# black + isort + pycln`. Same swap.

* chore(ingestion): keep main's baseline + globally ignore TRY400

Per gitar-bot's review on PR #27774:

1. Main's PR #27728 promoted ~60 `logger.warning()` → `logger.error()`
   inside `except` blocks. Those changes landed on main with their own
   baseline updates. Our PR doesn't promote anything — the merge from
   origin/main brought those `error` calls along with their baseline
   entries.

   The bot interpreted the `# noqa: TRY400` we added next to those lines
   as us silencing the rule case-by-case. Cleaner: globally ignore
   TRY400 in pyproject.toml, with a comment explaining why the codebase's
   `logger.error(...)` + separate `logger.debug(traceback.format_exc())`
   pattern is intentional. Strip ~430 per-line `# noqa: TRY400` markers
   from source.

2. Document that `S101` in `per-file-ignores` is a forward-looking
   entry — flake8-bandit (`S`) is not yet selected, so the rule is
   no-op today; the entry stays so when `S` lands later, tests don't
   immediately error.

Reverts the platform pin and Linux Docker–generated baseline. Keep
main's baseline intact and let CI surface the exact column-shifted
entries; the team will decide whether to fix in-place (revert format
on affected files) or add per-line `# pyright: ignore` markers.

* chore(ingestion): regen baseline for new connector type debt

Main's baseline was stale relative to recently-added connectors
(McpConnection, CustomDriveConnection) that lack common attributes
like `hostPort`, `database`, `catalog` etc. — all sites that access
those attributes via the union-typed `serviceConnection.root.config`
fire `reportAttributeAccessIssue` errors that aren't baselined.

71 errors + 58 warnings absorbed. Local macOS regen; pushing to see
CI's drift count. Per the basedpyright-baseline-and-ci PR experience,
macOS↔Linux column drift on this size of regen has historically been
1-7 residuals.
2026-04-28 07:21:59 +02:00

177 lines
6.4 KiB
Python

# Copyright 2025 Collate
# Licensed under the Collate Community License, Version 1.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
# https://github.com/open-metadata/OpenMetadata/blob/main/ingestion/LICENSE
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
# pylint: disable=line-too-long,unused-argument
"""
Usage via query logs tests
"""
from pathlib import Path
from unittest import TestCase
from unittest.mock import patch
from metadata.generated.schema.metadataIngestion.workflow import (
OpenMetadataWorkflowConfig,
)
from metadata.generated.schema.type.tableQuery import TableQuery
from metadata.ingestion.source.database.query.usage import QueryLogUsageSource
dataset = Path(__file__).parent / "resources/datasets/query_log.csv"
mock_query_log_config = {
"source": {
"type": "query-log-usage",
"serviceName": "local_glue",
"serviceConnection": {
"config": {
"type": "Glue",
"awsConfig": {
"awsAccessKeyId": "aws_access_key_id",
"awsSecretAccessKey": "aws_secret_access_key",
"awsRegion": "us-east-2",
"endPointURL": "https://endpoint.com/",
},
}
},
"sourceConfig": {"config": {"type": "DatabaseUsage", "queryLogFilePath": str(dataset)}},
},
"processor": {"type": "query-parser", "config": {}},
"stage": {"type": "table-usage", "config": {"filename": "/tmp/query_log_usage"}},
"bulkSink": {
"type": "metadata-usage",
"config": {"filename": "/tmp/query_log_usage"},
},
"workflowConfig": {
"openMetadataServerConfig": {
"hostPort": "http://localhost:8585/api",
"authProvider": "openmetadata",
"securityConfig": {
"jwtToken": "eyJraWQiOiJHYjM4OWEtOWY3Ni1nZGpzLWE5MmotMDI0MmJrOTQzNTYiLCJ0eXAiOiJKV1QiLCJhbGciOiJSUzI1NiJ9.eyJzdWIiOiJhZG1pbiIsImlzQm90IjpmYWxzZSwiaXNzIjoib3Blbi1tZXRhZGF0YS5vcmciLCJpYXQiOjE2NjM5Mzg0NjIsImVtYWlsIjoiYWRtaW5Ab3Blbm1ldGFkYXRhLm9yZyJ9.tS8um_5DKu7HgzGBzS1VTA5uUjKWOCU0B_j08WXBiEC0mr0zNREkqVfwFDD-d24HlNEbrqioLsBuFRiwIWKc1m_ZlVQbG7P36RUxhuv2vbSp80FKyNM-Tj93FDzq91jsyNmsQhyNv_fNr3TXfzzSPjHt8Go0FMMP66weoKMgW2PbXlhVKwEuXUHyakLLzewm9UMeQaEiRzhiTMU3UkLXcKbYEJJvfNFcLwSl9W8JCO_l0Yj3ud-qt_nQYEZwqW6u5nfdQllN133iikV4fM5QZsMCnm8Rq1mvLR0y9bmJiD7fwM1tmJ791TUWqmKaTnP49U493VanKpUAfzIiOiIbhg"
},
}
},
}
def custom_query_compare(self, other):
return (
self.query == other.query
and self.userName == other.userName
and self.startTime == other.startTime
and self.aborted == other.aborted
and self.serviceName == other.serviceName
and self.databaseName == other.databaseName
and self.databaseSchema == other.databaseSchema
and self.duration == other.duration
)
EXPECTED_QUERIES = [
TableQuery(
dialect="ansi",
query="select * from sales",
userName="",
startTime="",
endTime="",
aborted=False,
serviceName="local_glue",
databaseName="default",
databaseSchema="information_schema",
duration=None,
),
TableQuery(
dialect="ansi",
query="select * from marketing",
userName="",
startTime="",
endTime="",
aborted=False,
serviceName="local_glue",
databaseName="default",
databaseSchema="information_schema",
duration=None,
),
TableQuery(
dialect="ansi",
query="insert into marketing select * from sales",
userName="",
startTime="",
endTime="",
aborted=False,
serviceName="local_glue",
databaseName="default",
databaseSchema="information_schema",
duration=None,
),
]
EXPECTED_QUERIES_FILE_2 = [
TableQuery(
dialect="ansi",
query="select * from product_data",
userName="",
startTime="",
endTime="",
aborted=False,
serviceName="local_glue",
databaseName="default",
databaseSchema="information_schema",
duration=None,
),
TableQuery(
dialect="ansi",
query="select * from students where marks>=80",
userName="",
startTime="",
endTime="",
aborted=False,
serviceName="local_glue",
databaseName="default",
databaseSchema="information_schema",
duration=None,
),
]
class QueryLogSourceTest(TestCase):
"""
Implements the necessary unit tests for
Usage & Lineage via Query Log
"""
def __init__(self, methodName) -> None: # noqa: N803
super().__init__(methodName)
self.config = OpenMetadataWorkflowConfig.model_validate(mock_query_log_config)
with patch("metadata.ingestion.source.database.query.usage.QueryLogUsageSource.test_connection"):
self.source = QueryLogUsageSource.create(
mock_query_log_config["source"],
self.config.workflowConfig.openMetadataServerConfig,
)
def test_queries(self):
queries = list(self.source.get_table_query())
TableQuery.__eq__ = custom_query_compare
for index in range(len(queries[0].queries)):
assert queries[0].queries[index] == EXPECTED_QUERIES[index]
def test_multiple_file_queries(self):
dir_path = Path(__file__).parent / "resources/log_files"
self.source.config.sourceConfig.config.queryLogFilePath = dir_path
queries = list(self.source.get_table_query())
TableQuery.__eq__ = custom_query_compare
for single_file_queries in queries:
expected_queries_list = EXPECTED_QUERIES
if len(single_file_queries.queries) == 2:
# if no. of queries in any file = 2 then it should compare with 2nd file which has 2 queries.
# we don't know in which order the files are processed
expected_queries_list = EXPECTED_QUERIES_FILE_2
for index in range(len(single_file_queries.queries)):
assert single_file_queries.queries[index] == expected_queries_list[index]