OpenMetadata/ingestion/tests/cli_e2e/test_cli_redshift.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

271 lines
9 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.
"""
Redshift E2E tests
"""
from typing import List, Tuple # noqa: UP035
import pytest
from sqlalchemy import text
from metadata.generated.schema.entity.data.table import DmlOperationType, SystemProfile
from metadata.generated.schema.type.basic import Timestamp
from metadata.ingestion.api.status import Status
from .common.test_cli_db import CliCommonDB # noqa: TID252
from .common_e2e_sqa_mixins import SQACommonMethods # noqa: TID252
class RedshiftCliTest(CliCommonDB.TestSuite, SQACommonMethods):
create_table_query: str = """
CREATE TABLE IF NOT EXISTS e2e_cli_tests.dbt_jaffle.persons (
person_id int,
full_name varchar(255),
birthdate date,
bigint_col bigint
)
"""
create_view_query: str = """
CREATE OR REPLACE VIEW e2e_cli_tests.dbt_jaffle.view_persons AS
SELECT *
FROM e2e_cli_tests.dbt_jaffle.persons;
"""
insert_data_queries: List[str] = [ # noqa: RUF012, UP006
"""
INSERT INTO e2e_cli_tests.dbt_jaffle.persons (person_id, full_name, birthdate, bigint_col) VALUES
(1,'Peter Parker', '2004-08-10', 9223372036854775807),
(2,'Bruce Banner', '1988-12-18', 9223372036854775807),
(3,'Steve Rogers', '1988-07-04', 9223372036854775807),
(4,'Natasha Romanoff', '1997-12-03', 9223372036854775807),
(5,'Wanda Maximoff', '1998-02-10', 9223372036854775807),
(6,'Diana Prince', '1976-03-17', 9000000000000000007);
"""
]
drop_table_query: str = """
DROP TABLE IF EXISTS "e2e_cli_tests"."dbt_jaffle"."persons";
"""
drop_view_query: str = """
DROP VIEW IF EXISTS "e2e_cli_tests"."dbt_jaffle"."view_persons";
"""
def setUp(self) -> None:
self.create_table_and_view()
def tearDown(self) -> None:
self.delete_table_and_view()
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), 1)
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 create_table_and_view(self) -> None:
SQACommonMethods.create_table_and_view(self)
def delete_table_and_view(self) -> None:
from sqlalchemy.exc import OperationalError
max_retries = 3
for attempt in range(max_retries):
try:
self.engine.dispose()
with self.engine.begin() as connection:
connection.execute(text(self.drop_view_query))
connection.execute(text(self.drop_table_query))
break
except OperationalError as e:
if "server closed the connection" in str(e) and attempt < max_retries - 1:
continue
raise
def delete_table_rows(self) -> None:
SQACommonMethods.run_delete_queries(self)
def update_table_row(self) -> None:
SQACommonMethods.run_update_queries(self)
@staticmethod
def get_connector_name() -> str:
return "redshift"
@staticmethod
def expected_tables() -> int:
return 5
def expected_sample_size(self) -> int:
return 50
def view_column_lineage_count(self) -> int:
"""
Gives us the lineage for the view_listing
"""
return 9
def expected_lineage_node(self) -> str:
return "e2e_redshift.e2e_cli_tests.dbt_jaffle.view_listing"
@staticmethod
def fqn_created_table() -> str:
return "e2e_redshift.e2e_cli_tests.dbt_jaffle.listing"
@staticmethod
def _fqn_deleted_table() -> str:
return "e2e_redshift.e2e_cli_tests.dbt_jaffle.persons"
@staticmethod
def get_profiler_time_partition() -> dict:
return {
"fullyQualifiedName": "e2e_redshift.e2e_cli_tests.dbt_jaffle.listing",
"partitionConfig": {
"enablePartitioning": True,
"partitionColumnName": "date",
"partitionIntervalType": "TIME-UNIT",
"partitionInterval": 5,
"partitionIntervalUnit": "YEAR",
},
}
@staticmethod
def get_includes_schemas() -> List[str]: # noqa: UP006
return ["dbt_jaffle"]
@classmethod
def get_excludes_schemas(cls) -> List[str]: # noqa: UP006
return ["dbt_jaffle", "information_schema"]
@staticmethod
def get_includes_tables() -> List[str]: # noqa: UP006
return ["customer", "listing"]
@staticmethod
def get_excludes_tables() -> List[str]: # noqa: UP006
return ["foo"]
@staticmethod
def expected_filtered_schema_includes() -> int:
return 3
@staticmethod
def expected_filtered_schema_excludes() -> int:
return 2
@staticmethod
def expected_filtered_table_includes() -> int:
return 6
@staticmethod
def expected_filtered_table_excludes() -> int:
return 3
@staticmethod
def expected_filtered_mix() -> int:
return 8
@staticmethod
def get_profiler_time_partition_results() -> dict:
return {
"table_profile": {
"columnCount": 9.0,
"rowCount": 101.0,
},
"column_profile": [
{
"totalprice": {
"distinctCount": 21.0,
"distinctProportion": 1.0,
"duplicateCount": None,
"firstQuartile": -430.13,
"histogram": {
"boundaries": [
"-999.630 to -669.291",
"-669.291 to -338.952",
"-338.952 to -8.613",
"-8.613 to 321.726",
"321.726 to 652.065",
"652.065 and up",
],
"frequencies": [3, 6, 6, 1, 1, 4],
},
"interQuartileRange": 455.69,
"max": 856.41,
"maxLength": None,
"mean": -137.0,
"median": -275.85,
"min": -999.63,
"minLength": None,
"missingCount": None,
"missingPercentage": None,
"nonParametricSkew": 0.26190566403449345,
"nullCount": 0.0,
"nullProportion": 0.0,
"stddev": 530.152719345975,
"sum": -2882.0,
"thirdQuartile": 25.56,
"uniqueCount": 21.0,
"uniqueProportion": 1.0,
"validCount": None,
"valuesCount": 21.0,
"valuesPercentage": None,
"variance": None,
}
}
],
}
@staticmethod
def delete_queries() -> List[str]: # noqa: UP006
return [
"""
DELETE FROM e2e_cli_tests.dbt_jaffle.persons WHERE person_id IN (1,2)
""",
]
@staticmethod
def update_queries() -> List[str]: # noqa: UP006
return [
"""
UPDATE e2e_cli_tests.dbt_jaffle.persons SET full_name = 'Bruce Wayne' WHERE person_id = 3
""",
]
@pytest.mark.skip(reason="Skipped due to Redshift instance issue")
def test_profiler_with_time_partition(self) -> None:
pass
def get_system_profile_cases(self) -> List[Tuple[str, List[SystemProfile]]]: # noqa: UP006
return [
(
"e2e_redshift.e2e_cli_tests.dbt_jaffle.persons",
[
SystemProfile(
timestamp=Timestamp(root=0),
operation=DmlOperationType.INSERT,
rowsAffected=6,
)
],
)
]