OpenMetadata/ingestion/tests/cli_e2e/test_cli_bigquery.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

239 lines
7.6 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 Bigquery connector with CLI
"""
import random
from datetime import datetime
from typing import List, Tuple # noqa: UP035
import pytest
from ingestion.tests.cli_e2e.base.e2e_types import E2EType
from metadata.data_quality.api.models import TestCaseDefinition
from metadata.generated.schema.entity.data.table import (
ColumnProfile,
DmlOperationType,
SystemProfile,
TableProfilerConfig,
)
from metadata.generated.schema.tests.basic import TestCaseResult, TestCaseStatus
from metadata.generated.schema.tests.testCase import TestCaseParameterValue
from metadata.generated.schema.type.basic import ProfileSampleType, Timestamp
from .common.test_cli_db import CliCommonDB # noqa: TID252
from .common_e2e_sqa_mixins import SQACommonMethods # noqa: TID252
class BigqueryCliTest(CliCommonDB.TestSuite, SQACommonMethods):
create_table_query: str = """
CREATE TABLE `open-metadata-beta.exclude_me`.orders (
id int,
order_name string
)
"""
create_view_query: str = """
CREATE VIEW `open-metadata-beta.exclude_me.view_orders` AS
SELECT orders.id as id, orders.order_name as order_name
FROM `open-metadata-beta`.exclude_me.orders;
"""
insert_data_queries: List[str] = [ # noqa: RUF012, UP006
(
"INSERT INTO `open-metadata-beta.exclude_me`.orders (id, order_name) VALUES "
+ ",".join(
[
"(" + ",".join(values) + ")"
for values in [
(
str(i),
random.choice(["'PS'", "'XBOX'", "'NINTENDO'", "'SEGA'"]),
)
for i in range(1000)
]
]
)
+ ";"
),
"UPDATE `open-metadata-beta.exclude_me`.orders SET order_name = 'NINTENDO' WHERE id = 2",
]
drop_table_query: str = """
DROP TABLE IF EXISTS `open-metadata-beta.exclude_me`.orders;
"""
drop_view_query: str = """
DROP VIEW IF EXISTS `open-metadata-beta.exclude_me`.view_orders;
"""
def create_table_and_view(self) -> None:
SQACommonMethods.create_table_and_view(self)
def delete_table_and_view(self) -> None:
SQACommonMethods.delete_table_and_view(self)
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 "bigquery"
@staticmethod
def get_lineage_config_args() -> dict:
return {"processQueryLineage": True}
@staticmethod
def expected_tables() -> int:
return 2
def expected_sample_size(self) -> int:
return 50
def view_column_lineage_count(self) -> int:
return 2
def expected_lineage_node(self) -> str:
return "local_bigquery.open-metadata-beta.exclude_me.view_orders"
@staticmethod
def _expected_profiled_tables() -> int:
return 2
@staticmethod
def fqn_created_table() -> str:
return "local_bigquery.open-metadata-beta.exclude_me.orders"
@staticmethod
def get_includes_schemas() -> List[str]: # noqa: UP006
return ["exclude_me"]
@staticmethod
def get_includes_tables() -> List[str]: # noqa: UP006
return ["exclude_table"]
@staticmethod
def get_excludes_tables() -> List[str]: # noqa: UP006
return ["testtable"]
@staticmethod
def expected_filtered_schema_includes() -> int:
return 2
@staticmethod
def expected_filtered_schema_excludes() -> int:
return 1
@staticmethod
def expected_filtered_table_includes() -> int:
return 3
@staticmethod
def expected_filtered_table_excludes() -> int:
return 1
@staticmethod
def expected_filtered_mix() -> int:
return 2
@staticmethod
def delete_queries() -> List[str]: # noqa: UP006
return [
"""
DELETE FROM `open-metadata-beta.exclude_me`.orders WHERE id IN (1)
""",
]
@staticmethod
def update_queries() -> List[str]: # noqa: UP006
return [
"""
UPDATE `open-metadata-beta.exclude_me`.orders SET order_name = 'NINTENDO' WHERE id = 2
""",
]
def get_system_profile_cases(self) -> List[Tuple[str, List[SystemProfile]]]: # noqa: UP006
return [
(
"local_bigquery.open-metadata-beta.exclude_me.orders",
[
SystemProfile(
timestamp=Timestamp(root=0),
operation=DmlOperationType.INSERT,
rowsAffected=1000,
),
SystemProfile(
timestamp=Timestamp(root=1),
operation=DmlOperationType.UPDATE,
rowsAffected=1,
),
],
)
]
def add_table_profile_config(self):
self.openmetadata.create_or_update_table_profiler_config(
self.get_data_quality_table(),
TableProfilerConfig(
profileSampleType=ProfileSampleType.ROWS,
profileSample=100,
),
)
def get_data_quality_table(self):
return self.fqn_created_table()
def get_test_case_definitions(self) -> List[TestCaseDefinition]: # noqa: UP006
return [
TestCaseDefinition(
name="bigquery_data_diff",
testDefinitionName="tableDiff",
computePassedFailedRowCount=True,
parameterValues=[
TestCaseParameterValue(
name="table2",
value=self.get_data_quality_table(),
),
TestCaseParameterValue(
name="keyColumns",
value='["id"]',
),
],
)
]
def get_expected_test_case_results(self):
return [TestCaseResult(testCaseStatus=TestCaseStatus.Success, timestamp=0)]
@pytest.mark.order(9999)
def test_profiler_w_partition_table(self):
"""Test profiler sample for partitioned table"""
self.build_config_file(E2EType.INGEST_DB_FILTER_SCHEMA, {"includes": ["w_partition"]})
self.run_command()
self.build_config_file(E2EType.PROFILER, {"includes": ["w_partition"]})
start_ts = int(datetime.now().timestamp() * 1000)
self.run_command("profile")
end_ts = int(datetime.now().timestamp() * 1000)
column_profile = self.openmetadata.get_profile_data(
"local_bigquery.open-metadata-beta.w_partition.w_time_partition.id",
start_ts,
end_ts,
profile_type=ColumnProfile,
).entities[0]
# We ingest 1 row for each day and the profiler should default to the latest partition
assert column_profile.valuesCount == 1