Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Fix #19147 - Executable Test Suites #19221

Merged
merged 20 commits into from
Jan 7, 2025
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
26 changes: 25 additions & 1 deletion bootstrap/sql/migrations/native/1.6.2/mysql/schemaChanges.sql
Original file line number Diff line number Diff line change
@@ -1,2 +1,26 @@
-- add timestamp index for test case result reindex performance
ALTER TABLE data_quality_data_time_series ADD INDEX `idx_timestamp_desc` (timestamp DESC);
ALTER TABLE data_quality_data_time_series ADD INDEX `idx_timestamp_desc` (timestamp DESC);

-- rename executable -> basic for test suites
UPDATE test_suite
SET json = JSON_INSERT(
JSON_REMOVE(json, '$.executable'),
'$.basic',
JSON_EXTRACT(json, '$.executable')
)
WHERE JSON_EXTRACT(json, '$.executable') IS NOT NULL;

-- rename executableEntityReference -> basicEntityReference for test suites
UPDATE test_suite
SET json = JSON_INSERT(
JSON_REMOVE(json, '$.executableEntityReference'),
'$.basicEntityReference',
JSON_EXTRACT(json, '$.executableEntityReference')
)
WHERE JSON_EXTRACT(json, '$.executableEntityReference') IS NOT NULL;

-- clean up the testSuites
UPDATE test_case SET json = json_remove(json, '$.testSuites');

-- clean up the testSuites in the version history too
UPDATE entity_extension SET json = json_remove(json, '$.testSuites') WHERE jsonSchema = 'testCase';
26 changes: 26 additions & 0 deletions bootstrap/sql/migrations/native/1.6.2/postgres/schemaChanges.sql
Original file line number Diff line number Diff line change
@@ -1,2 +1,28 @@
-- add timestamp index for test case result reindex performance
CREATE INDEX idx_timestamp_desc ON data_quality_data_time_series (timestamp DESC);

-- rename executable -> basic for test suites
UPDATE test_suite
SET json = jsonb_set(
json::jsonb #- '{executable}',
'{basic}',
(json #> '{executable}')::jsonb,
true
)
WHERE json #>> '{executable}' IS NOT NULL;

-- rename executableEntityReference -> basicEntityReference for test suites
UPDATE test_suite
SET json = jsonb_set(
json::jsonb #- '{executableEntityReference}',
'{basicEntityReference}',
(json #> '{executableEntityReference}')::jsonb,
true
)
WHERE json #>> '{executableEntityReference}' IS NOT NULL;

-- clean up the testSuites
UPDATE test_case SET json = json::jsonb #- '{testSuites}';

-- clean up the testSuites in the version history too
UPDATE entity_extension SET json = json::jsonb #- '{testSuites}' WHERE jsonSchema = 'testCase';
4 changes: 4 additions & 0 deletions ingestion/src/metadata/data_quality/api/models.py
Original file line number Diff line number Diff line change
Expand Up @@ -23,6 +23,7 @@
from metadata.config.common import ConfigModel
from metadata.generated.schema.api.tests.createTestSuite import CreateTestSuiteRequest
from metadata.generated.schema.entity.data.table import Table
from metadata.generated.schema.entity.services.databaseService import DatabaseConnection
from metadata.generated.schema.tests.basic import TestCaseResult
from metadata.generated.schema.tests.testCase import TestCase, TestCaseParameterValue
from metadata.ingestion.models.custom_pydantic import BaseModel
Expand Down Expand Up @@ -63,6 +64,9 @@ class TableAndTests(BaseModel):
executable_test_suite: Optional[CreateTestSuiteRequest] = Field(
None, description="If no executable test suite is found, we'll create one"
)
service_connection: DatabaseConnection = Field(
..., description="Service connection for the given table"
)


class TestCaseResults(BaseModel):
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -27,6 +27,7 @@
from metadata.data_quality.runner.core import DataTestsRunner
from metadata.generated.schema.api.tests.createTestCase import CreateTestCaseRequest
from metadata.generated.schema.entity.data.table import Table
from metadata.generated.schema.entity.services.databaseService import DatabaseConnection
from metadata.generated.schema.entity.services.ingestionPipelines.status import (
StackTraceError,
)
Expand Down Expand Up @@ -93,7 +94,9 @@ def _run(self, record: TableAndTests) -> Either:
record.table, openmetadata_test_cases
)

test_suite_runner = self.get_test_suite_runner(record.table)
test_suite_runner = self.get_test_suite_runner(
record.table, record.service_connection
)

logger.debug(
f"Found {len(openmetadata_test_cases)} test cases for table {record.table.fullyQualifiedName.root}"
Expand Down Expand Up @@ -351,9 +354,9 @@ def filter_incompatible_test_cases(
result.append(tc)
return result

def get_test_suite_runner(self, table: Table):
def get_test_suite_runner(
self, table: Table, service_connection: DatabaseConnection
):
return BaseTestSuiteRunner(
self.config,
self.metadata,
table,
self.config, self.metadata, table, service_connection
).get_data_quality_runner()
Original file line number Diff line number Diff line change
Expand Up @@ -46,11 +46,12 @@ def __init__(
config: OpenMetadataWorkflowConfig,
ometa_client: OpenMetadata,
entity: Table,
service_connection: DatabaseConnection,
):
self.validator_builder_class = ValidatorBuilder
self._interface = None
self.entity = entity
self.service_conn_config = self._copy_service_config(config, self.entity.database) # type: ignore
self.service_conn_config = self._copy_service_config(service_connection, self.entity.database) # type: ignore
self._interface_type: str = self.service_conn_config.type.value.lower()

self.source_config = TestSuitePipeline.model_validate(
Expand All @@ -67,7 +68,7 @@ def interface(self, interface):
self._interface = interface

def _copy_service_config(
self, config: OpenMetadataWorkflowConfig, database: EntityReference
self, service_connection: DatabaseConnection, database: EntityReference
) -> DatabaseConnection:
"""Make a copy of the service config and update the database name

Expand All @@ -77,9 +78,7 @@ def _copy_service_config(
Returns:
DatabaseService.__config__
"""
config_copy = deepcopy(
config.source.serviceConnection.root.config # type: ignore
)
config_copy = deepcopy(service_connection.config) # type: ignore
if hasattr(
config_copy, # type: ignore
"supportsDatabase",
Expand Down
Loading
Loading