OpenMetadata/ingestion/tests/cli_e2e/common/test_cli_db.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

234 lines
10 KiB
Python

# Copyright 2022 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.
"""
Test database connectors which extend from `CommonDbSourceService` with CLI
"""
import os
from abc import ABC, abstractmethod
from pathlib import Path
from typing import Optional
from sqlalchemy.engine import Engine
from metadata.config.common import load_config_file
from metadata.generated.schema.entity.services.databaseService import DatabaseService
from metadata.generated.schema.metadataIngestion.workflow import (
OpenMetadataWorkflowConfig,
)
from metadata.ingestion.api.status import Status
from metadata.workflow.metadata import MetadataWorkflow # noqa: TC001
from ..base.test_cli import PATH_TO_RESOURCES # noqa: TID252
from ..base.test_cli_db import CliDBBase # noqa: TID252
class CliCommonDB:
class TestSuite(CliDBBase.TestSuite, ABC):
engine: Engine
@classmethod
def setUpClass(cls) -> None:
connector = cls.get_connector_name()
workflow: MetadataWorkflow = cls.get_workflow(connector, cls.get_test_type())
cls.engine = workflow.source.engine
cls.openmetadata = workflow.source.metadata
cls.set_ingestion_bot_jwt_token()
cls.config_file_path = str(Path(PATH_TO_RESOURCES + f"/database/{connector}/{connector}.yaml"))
cls.test_file_path = str(Path(PATH_TO_RESOURCES + f"/database/{connector}/test.yaml"))
@classmethod
def tearDownClass(cls):
workflow = OpenMetadataWorkflowConfig.model_validate(load_config_file(Path(cls.config_file_path)))
db_service: DatabaseService = cls.openmetadata.get_by_name(DatabaseService, workflow.source.serviceName)
if db_service and os.getenv("E2E_CLEAN_DB", "false") == "true":
cls.openmetadata.delete(DatabaseService, db_service.id, hard_delete=True, recursive=True)
def tearDown(self) -> None:
self.engine.dispose()
def assert_for_vanilla_ingestion(self, source_status: Status, sink_status: Status) -> None:
self.assertEqual(len(source_status.failures), 0)
self.assertEqual(len(source_status.warnings), 0)
self.assertEqual(len(source_status.filtered), 0)
self.assertGreaterEqual(
(len(source_status.records) + len(source_status.updated_records)),
self.expected_tables(),
)
self.assertEqual(len(sink_status.failures), 0)
self.assertEqual(len(sink_status.warnings), 0)
self.assertGreater(
(len(sink_status.records) + len(sink_status.updated_records)),
self.expected_tables(),
)
def assert_for_table_with_profiler(self, source_status: Status, sink_status: Status):
self.assertEqual(len(source_status.failures), 0)
self.assertGreaterEqual(
(len(source_status.records) + len(source_status.updated_records)),
self.expected_profiled_tables(),
)
self.assertEqual(len(sink_status.failures), 0)
self.assertGreaterEqual(
(len(sink_status.records) + len(sink_status.updated_records)),
self.expected_profiled_tables(),
)
# Since we removed view lineage from metadata workflow as part
# of https://github.com/open-metadata/OpenMetadata/pull/18558
# we need to introduce Lineage E2E base and add view lineage check there.
def assert_for_test_lineage(self, source_status: Status, sink_status: Status):
self.assertEqual(len(source_status.failures), 0)
self.assertEqual(len(source_status.warnings), 0)
self.assertEqual(len(sink_status.failures), 0)
self.assertEqual(len(sink_status.warnings), 0)
self.assertGreaterEqual(len(sink_status.records), 0)
lineage_data = self.retrieve_lineage(self.fqn_created_table())
retrieved_view_column_lineage_count = len(
lineage_data["downstreamEdges"][0]["lineageDetails"]["columnsLineage"]
)
self.assertEqual(retrieved_view_column_lineage_count, self.view_column_lineage_count())
retrieved_lineage_node = lineage_data["nodes"][0]["fullyQualifiedName"]
self.assertEqual(retrieved_lineage_node, self.expected_lineage_node())
def assert_auto_classification_sample_data(self, source_status: Status, sink_status: Status):
self.assertEqual(len(source_status.failures), 0)
self.assertGreaterEqual(
(len(source_status.records) + len(source_status.updated_records)),
self.expected_profiled_tables(),
)
sample_data = self.retrieve_sample_data(self.fqn_created_table()).sampleData
self.assertEqual(len(sample_data.rows), self.expected_sample_size())
def assert_for_table_with_profiler_time_partition(self, source_status: Status, sink_status: Status):
self.assertEqual(len(source_status.failures), 0)
self.assertEqual(len(sink_status.failures), 0)
profile = self.retrieve_profile(self.fqn_created_table())
expected_profiler_time_partition_results = self.get_profiler_time_partition_results()
if expected_profiler_time_partition_results:
table_profile = profile.profile.model_dump()
for key in expected_profiler_time_partition_results["table_profile"]:
self.assertEqual(
table_profile[key],
expected_profiler_time_partition_results["table_profile"][key],
)
for column in profile.columns:
expected_column_profile = next(
(
profile.get(column.name.root)
for profile in expected_profiler_time_partition_results["column_profile"]
if profile.get(column.name.root)
),
None,
)
if expected_column_profile:
column_profile = column.profile.model_dump()
for key in expected_column_profile: # type: ignore
if key == "nonParametricSkew":
self.assertEqual(
column_profile[key].__round__(10),
expected_column_profile[key].__round__(10),
)
continue
self.assertEqual(column_profile[key], expected_column_profile[key])
def assert_for_delete_table_is_marked_as_deleted(self, source_status: Status, sink_status: Status):
self.assertEqual(self.retrieve_table(self.fqn_deleted_table()), None)
def assert_filtered_schemas_includes(self, source_status: Status, sink_status: Status):
self.assertEqual(len(source_status.failures), 0)
self.assertGreaterEqual(len(source_status.filtered), self.expected_filtered_schema_includes())
def assert_filtered_schemas_excludes(self, source_status: Status, sink_status: Status):
self.assertEqual(len(source_status.failures), 0)
self.assertGreaterEqual(len(source_status.filtered), self.expected_filtered_schema_excludes())
def assert_filtered_tables_includes(self, source_status: Status, sink_status: Status):
self.assertEqual(len(source_status.failures), 0)
self.assertGreaterEqual(len(source_status.filtered), self.expected_filtered_table_includes())
def assert_filtered_tables_excludes(self, source_status: Status, sink_status: Status):
self.assertEqual(len(source_status.failures), 0)
self.assertGreaterEqual(len(source_status.filtered), self.expected_filtered_table_excludes())
def assert_filtered_mix(self, source_status: Status, sink_status: Status):
self.assertEqual(len(source_status.failures), 0)
self.assertGreaterEqual(len(source_status.filtered), self.expected_filtered_mix())
@staticmethod
@abstractmethod
def expected_tables() -> int:
raise NotImplementedError()
@abstractmethod
def expected_sample_size(self) -> int:
raise NotImplementedError()
@abstractmethod
def view_column_lineage_count(self) -> int:
raise NotImplementedError()
@abstractmethod
def expected_lineage_node(self) -> str:
raise NotImplementedError()
@staticmethod
@abstractmethod
def fqn_created_table() -> str:
raise NotImplementedError()
@staticmethod
def _fqn_deleted_table() -> Optional[str]: # noqa: UP045
return None
@staticmethod
def _expected_profiled_tables() -> int:
return None
def fqn_deleted_table(self) -> str:
if self._fqn_deleted_table() is None:
return self.fqn_created_table()
return self._fqn_deleted_table() # type: ignore
def expected_profiled_tables(self) -> int:
if self._expected_profiled_tables() is None:
return self.expected_tables()
return self._expected_profiled_tables()
@staticmethod
@abstractmethod
def expected_filtered_schema_includes() -> int:
raise NotImplementedError()
@staticmethod
@abstractmethod
def expected_filtered_schema_excludes() -> int:
raise NotImplementedError()
@staticmethod
@abstractmethod
def expected_filtered_table_includes() -> int:
raise NotImplementedError()
@staticmethod
@abstractmethod
def expected_filtered_table_excludes() -> int:
raise NotImplementedError()
@staticmethod
@abstractmethod
def expected_filtered_mix() -> int:
raise NotImplementedError()