diff --git a/datahub-graphql-core/src/main/java/com/linkedin/datahub/graphql/GmsGraphQLEngine.java b/datahub-graphql-core/src/main/java/com/linkedin/datahub/graphql/GmsGraphQLEngine.java index ebb5c7d62c7d3..b99f712034fe0 100644 --- a/datahub-graphql-core/src/main/java/com/linkedin/datahub/graphql/GmsGraphQLEngine.java +++ b/datahub-graphql-core/src/main/java/com/linkedin/datahub/graphql/GmsGraphQLEngine.java @@ -1292,7 +1292,8 @@ private void configureCorpUserResolvers(final RuntimeWiring.Builder builder) { */ private void configureCorpGroupResolvers(final RuntimeWiring.Builder builder) { builder.type("CorpGroup", typeWiring -> typeWiring - .dataFetcher("relationships", new EntityRelationshipsResultResolver(graphClient))); + .dataFetcher("relationships", new EntityRelationshipsResultResolver(graphClient)) + .dataFetcher("exists", new EntityExistsResolver(entityService))); builder.type("CorpGroupInfo", typeWiring -> typeWiring .dataFetcher("admins", new LoadableTypeBatchResolver<>(corpUserType, diff --git a/datahub-graphql-core/src/main/resources/entity.graphql b/datahub-graphql-core/src/main/resources/entity.graphql index 0b15d7b875a9c..b37a8f34fa056 100644 --- a/datahub-graphql-core/src/main/resources/entity.graphql +++ b/datahub-graphql-core/src/main/resources/entity.graphql @@ -3788,6 +3788,11 @@ type CorpGroup implements Entity { Additional read only info about the group """ info: CorpGroupInfo @deprecated + + """ + Whether or not this entity exists on DataHub + """ + exists: Boolean } """ diff --git a/datahub-web-react/src/app/entity/group/GroupProfile.tsx b/datahub-web-react/src/app/entity/group/GroupProfile.tsx index d5e284af931df..53d2062277dec 100644 --- a/datahub-web-react/src/app/entity/group/GroupProfile.tsx +++ b/datahub-web-react/src/app/entity/group/GroupProfile.tsx @@ -11,6 +11,7 @@ import { RoutedTabs } from '../../shared/RoutedTabs'; import GroupInfoSidebar from './GroupInfoSideBar'; import { GroupAssets } from './GroupAssets'; import { ErrorSection } from '../../shared/error/ErrorSection'; +import NonExistentEntityPage from '../shared/entity/NonExistentEntityPage'; const messageStyle = { marginTop: '10%' }; @@ -110,6 +111,9 @@ export default function GroupProfile() { urn, }; + if (data?.corpGroup?.exists === false) { + return ; + } return ( <> {error && } diff --git a/datahub-web-react/src/graphql/group.graphql b/datahub-web-react/src/graphql/group.graphql index 9aa6e2b005f16..1007721e51a4e 100644 --- a/datahub-web-react/src/graphql/group.graphql +++ b/datahub-web-react/src/graphql/group.graphql @@ -3,6 +3,7 @@ query getGroup($urn: String!, $membersCount: Int!) { urn type name + exists origin { type externalType diff --git a/docs/how/updating-datahub.md b/docs/how/updating-datahub.md index 5d0ad5eaf8f7e..9cd4ad5c6f02d 100644 --- a/docs/how/updating-datahub.md +++ b/docs/how/updating-datahub.md @@ -7,6 +7,8 @@ This file documents any backwards-incompatible changes in DataHub and assists pe ### Breaking Changes - #8810 - Removed support for SQLAlchemy 1.3.x. Only SQLAlchemy 1.4.x is supported now. +- #8942 - Removed `urn:li:corpuser:datahub` owner for the `Measure`, `Dimension` and `Temporal` tags emitted + by Looker and LookML source connectors. - #8853 - The Airflow plugin no longer supports Airflow 2.0.x or Python 3.7. See the docs for more details. - #8853 - Introduced the Airflow plugin v2. If you're using Airflow 2.3+, the v2 plugin will be enabled by default, and so you'll need to switch your requirements to include `pip install 'acryl-datahub-airflow-plugin[plugin-v2]'`. To continue using the v1 plugin, set the `DATAHUB_AIRFLOW_PLUGIN_USE_V1_PLUGIN` environment variable to `true`. - #8943 The Unity Catalog ingestion source has a new option `include_metastore`, which will cause all urns to be changed when disabled. diff --git a/metadata-ingestion/src/datahub/ingestion/api/common.py b/metadata-ingestion/src/datahub/ingestion/api/common.py index 778bd119615e2..a6761a3c77d5e 100644 --- a/metadata-ingestion/src/datahub/ingestion/api/common.py +++ b/metadata-ingestion/src/datahub/ingestion/api/common.py @@ -2,6 +2,7 @@ from dataclasses import dataclass from typing import TYPE_CHECKING, Dict, Generic, Iterable, Optional, Tuple, TypeVar +from datahub.configuration.common import ConfigurationError from datahub.emitter.mce_builder import set_dataset_urn_to_lower from datahub.ingestion.api.committable import Committable from datahub.ingestion.graph.client import DataHubGraph @@ -75,3 +76,11 @@ def register_checkpointer(self, committable: Committable) -> None: def get_committables(self) -> Iterable[Tuple[str, Committable]]: yield from self.checkpointers.items() + + def require_graph(self, operation: Optional[str] = None) -> DataHubGraph: + if not self.graph: + raise ConfigurationError( + f"{operation or 'This operation'} requires a graph, but none was provided. " + "To provide one, either use the datahub-rest sink or set the top-level datahub_api config in the recipe." + ) + return self.graph diff --git a/metadata-ingestion/src/datahub/ingestion/source/csv_enricher.py b/metadata-ingestion/src/datahub/ingestion/source/csv_enricher.py index 7cb487a86d931..611f0c5c52cc6 100644 --- a/metadata-ingestion/src/datahub/ingestion/source/csv_enricher.py +++ b/metadata-ingestion/src/datahub/ingestion/source/csv_enricher.py @@ -129,11 +129,9 @@ def __init__(self, config: CSVEnricherConfig, ctx: PipelineContext): # Map from entity urn to a list of SubResourceRow. self.editable_schema_metadata_map: Dict[str, List[SubResourceRow]] = {} self.should_overwrite: bool = self.config.write_semantics == "OVERRIDE" - if not self.should_overwrite and not self.ctx.graph: - raise ConfigurationError( - "With PATCH semantics, the csv-enricher source requires a datahub_api to connect to. " - "Consider using the datahub-rest sink or provide a datahub_api: configuration on your ingestion recipe." - ) + + if not self.should_overwrite: + self.ctx.require_graph(operation="The csv-enricher's PATCH semantics flag") def get_resource_glossary_terms_work_unit( self, diff --git a/metadata-ingestion/src/datahub/ingestion/source/dbt/dbt_cloud.py b/metadata-ingestion/src/datahub/ingestion/source/dbt/dbt_cloud.py index af9769bc9d94c..da1ea8ecb4678 100644 --- a/metadata-ingestion/src/datahub/ingestion/source/dbt/dbt_cloud.py +++ b/metadata-ingestion/src/datahub/ingestion/source/dbt/dbt_cloud.py @@ -20,9 +20,8 @@ DBTCommonConfig, DBTNode, DBTSourceBase, - DBTTest, - DBTTestResult, ) +from datahub.ingestion.source.dbt.dbt_tests import DBTTest, DBTTestResult logger = logging.getLogger(__name__) diff --git a/metadata-ingestion/src/datahub/ingestion/source/dbt/dbt_common.py b/metadata-ingestion/src/datahub/ingestion/source/dbt/dbt_common.py index 0f5c08eb6ac54..48d2118a9b091 100644 --- a/metadata-ingestion/src/datahub/ingestion/source/dbt/dbt_common.py +++ b/metadata-ingestion/src/datahub/ingestion/source/dbt/dbt_common.py @@ -1,11 +1,10 @@ -import json import logging import re from abc import abstractmethod from dataclasses import dataclass, field from datetime import datetime from enum import auto -from typing import Any, Callable, ClassVar, Dict, Iterable, List, Optional, Tuple, Union +from typing import Any, Dict, Iterable, List, Optional, Tuple import pydantic from pydantic import root_validator, validator @@ -34,6 +33,12 @@ from datahub.ingestion.api.source import MetadataWorkUnitProcessor from datahub.ingestion.api.workunit import MetadataWorkUnit from datahub.ingestion.source.common.subtypes import DatasetSubTypes +from datahub.ingestion.source.dbt.dbt_tests import ( + DBTTest, + DBTTestResult, + make_assertion_from_test, + make_assertion_result_from_test, +) from datahub.ingestion.source.sql.sql_types import ( ATHENA_SQL_TYPES_MAP, BIGQUERY_TYPES_MAP, @@ -81,20 +86,7 @@ TimeTypeClass, ) from datahub.metadata.schema_classes import ( - AssertionInfoClass, - AssertionResultClass, - AssertionResultTypeClass, - AssertionRunEventClass, - AssertionRunStatusClass, - AssertionStdAggregationClass, - AssertionStdOperatorClass, - AssertionStdParameterClass, - AssertionStdParametersClass, - AssertionStdParameterTypeClass, - AssertionTypeClass, DataPlatformInstanceClass, - DatasetAssertionInfoClass, - DatasetAssertionScopeClass, DatasetPropertiesClass, GlobalTagsClass, GlossaryTermsClass, @@ -551,134 +543,6 @@ def get_column_type( return SchemaFieldDataType(type=TypeClass()) -@dataclass -class AssertionParams: - scope: Union[DatasetAssertionScopeClass, str] - operator: Union[AssertionStdOperatorClass, str] - aggregation: Union[AssertionStdAggregationClass, str] - parameters: Optional[Callable[[Dict[str, str]], AssertionStdParametersClass]] = None - logic_fn: Optional[Callable[[Dict[str, str]], Optional[str]]] = None - - -def _get_name_for_relationship_test(kw_args: Dict[str, str]) -> Optional[str]: - """ - Try to produce a useful string for the name of a relationship constraint. - Return None if we fail to - """ - destination_ref = kw_args.get("to") - source_ref = kw_args.get("model") - column_name = kw_args.get("column_name") - dest_field_name = kw_args.get("field") - if not destination_ref or not source_ref or not column_name or not dest_field_name: - # base assertions are violated, bail early - return None - m = re.match(r"^ref\(\'(.*)\'\)$", destination_ref) - if m: - destination_table = m.group(1) - else: - destination_table = destination_ref - m = re.search(r"ref\(\'(.*)\'\)", source_ref) - if m: - source_table = m.group(1) - else: - source_table = source_ref - return f"{source_table}.{column_name} referential integrity to {destination_table}.{dest_field_name}" - - -@dataclass -class DBTTest: - qualified_test_name: str - column_name: Optional[str] - kw_args: dict - - TEST_NAME_TO_ASSERTION_MAP: ClassVar[Dict[str, AssertionParams]] = { - "not_null": AssertionParams( - scope=DatasetAssertionScopeClass.DATASET_COLUMN, - operator=AssertionStdOperatorClass.NOT_NULL, - aggregation=AssertionStdAggregationClass.IDENTITY, - ), - "unique": AssertionParams( - scope=DatasetAssertionScopeClass.DATASET_COLUMN, - operator=AssertionStdOperatorClass.EQUAL_TO, - aggregation=AssertionStdAggregationClass.UNIQUE_PROPOTION, - parameters=lambda _: AssertionStdParametersClass( - value=AssertionStdParameterClass( - value="1.0", - type=AssertionStdParameterTypeClass.NUMBER, - ) - ), - ), - "accepted_values": AssertionParams( - scope=DatasetAssertionScopeClass.DATASET_COLUMN, - operator=AssertionStdOperatorClass.IN, - aggregation=AssertionStdAggregationClass.IDENTITY, - parameters=lambda kw_args: AssertionStdParametersClass( - value=AssertionStdParameterClass( - value=json.dumps(kw_args.get("values")), - type=AssertionStdParameterTypeClass.SET, - ), - ), - ), - "relationships": AssertionParams( - scope=DatasetAssertionScopeClass.DATASET_COLUMN, - operator=AssertionStdOperatorClass._NATIVE_, - aggregation=AssertionStdAggregationClass.IDENTITY, - parameters=lambda kw_args: AssertionStdParametersClass( - value=AssertionStdParameterClass( - value=json.dumps(kw_args.get("values")), - type=AssertionStdParameterTypeClass.SET, - ), - ), - logic_fn=_get_name_for_relationship_test, - ), - "dbt_expectations.expect_column_values_to_not_be_null": AssertionParams( - scope=DatasetAssertionScopeClass.DATASET_COLUMN, - operator=AssertionStdOperatorClass.NOT_NULL, - aggregation=AssertionStdAggregationClass.IDENTITY, - ), - "dbt_expectations.expect_column_values_to_be_between": AssertionParams( - scope=DatasetAssertionScopeClass.DATASET_COLUMN, - operator=AssertionStdOperatorClass.BETWEEN, - aggregation=AssertionStdAggregationClass.IDENTITY, - parameters=lambda x: AssertionStdParametersClass( - minValue=AssertionStdParameterClass( - value=str(x.get("min_value", "unknown")), - type=AssertionStdParameterTypeClass.NUMBER, - ), - maxValue=AssertionStdParameterClass( - value=str(x.get("max_value", "unknown")), - type=AssertionStdParameterTypeClass.NUMBER, - ), - ), - ), - "dbt_expectations.expect_column_values_to_be_in_set": AssertionParams( - scope=DatasetAssertionScopeClass.DATASET_COLUMN, - operator=AssertionStdOperatorClass.IN, - aggregation=AssertionStdAggregationClass.IDENTITY, - parameters=lambda kw_args: AssertionStdParametersClass( - value=AssertionStdParameterClass( - value=json.dumps(kw_args.get("value_set")), - type=AssertionStdParameterTypeClass.SET, - ), - ), - ), - } - - -@dataclass -class DBTTestResult: - invocation_id: str - - status: str - execution_time: datetime - - native_results: Dict[str, str] - - -def string_map(input_map: Dict[str, Any]) -> Dict[str, str]: - return {k: str(v) for k, v in input_map.items()} - - @platform_name("dbt") @config_class(DBTCommonConfig) @support_status(SupportStatus.CERTIFIED) @@ -750,7 +614,7 @@ def create_test_entity_mcps( for upstream_urn in sorted(upstream_urns): if self.config.entities_enabled.can_emit_node_type("test"): - yield self._make_assertion_from_test( + yield make_assertion_from_test( custom_props, node, assertion_urn, @@ -759,133 +623,17 @@ def create_test_entity_mcps( if node.test_result: if self.config.entities_enabled.can_emit_test_results: - yield self._make_assertion_result_from_test( - node, assertion_urn, upstream_urn + yield make_assertion_result_from_test( + node, + assertion_urn, + upstream_urn, + test_warnings_are_errors=self.config.test_warnings_are_errors, ) else: logger.debug( f"Skipping test result {node.name} emission since it is turned off." ) - def _make_assertion_from_test( - self, - extra_custom_props: Dict[str, str], - node: DBTNode, - assertion_urn: str, - upstream_urn: str, - ) -> MetadataWorkUnit: - assert node.test_info - qualified_test_name = node.test_info.qualified_test_name - column_name = node.test_info.column_name - kw_args = node.test_info.kw_args - - if qualified_test_name in DBTTest.TEST_NAME_TO_ASSERTION_MAP: - assertion_params = DBTTest.TEST_NAME_TO_ASSERTION_MAP[qualified_test_name] - assertion_info = AssertionInfoClass( - type=AssertionTypeClass.DATASET, - customProperties=extra_custom_props, - datasetAssertion=DatasetAssertionInfoClass( - dataset=upstream_urn, - scope=assertion_params.scope, - operator=assertion_params.operator, - fields=[ - mce_builder.make_schema_field_urn(upstream_urn, column_name) - ] - if ( - assertion_params.scope - == DatasetAssertionScopeClass.DATASET_COLUMN - and column_name - ) - else [], - nativeType=node.name, - aggregation=assertion_params.aggregation, - parameters=assertion_params.parameters(kw_args) - if assertion_params.parameters - else None, - logic=assertion_params.logic_fn(kw_args) - if assertion_params.logic_fn - else None, - nativeParameters=string_map(kw_args), - ), - ) - elif column_name: - # no match with known test types, column-level test - assertion_info = AssertionInfoClass( - type=AssertionTypeClass.DATASET, - customProperties=extra_custom_props, - datasetAssertion=DatasetAssertionInfoClass( - dataset=upstream_urn, - scope=DatasetAssertionScopeClass.DATASET_COLUMN, - operator=AssertionStdOperatorClass._NATIVE_, - fields=[ - mce_builder.make_schema_field_urn(upstream_urn, column_name) - ], - nativeType=node.name, - logic=node.compiled_code or node.raw_code, - aggregation=AssertionStdAggregationClass._NATIVE_, - nativeParameters=string_map(kw_args), - ), - ) - else: - # no match with known test types, default to row-level test - assertion_info = AssertionInfoClass( - type=AssertionTypeClass.DATASET, - customProperties=extra_custom_props, - datasetAssertion=DatasetAssertionInfoClass( - dataset=upstream_urn, - scope=DatasetAssertionScopeClass.DATASET_ROWS, - operator=AssertionStdOperatorClass._NATIVE_, - logic=node.compiled_code or node.raw_code, - nativeType=node.name, - aggregation=AssertionStdAggregationClass._NATIVE_, - nativeParameters=string_map(kw_args), - ), - ) - - wu = MetadataChangeProposalWrapper( - entityUrn=assertion_urn, - aspect=assertion_info, - ).as_workunit() - - return wu - - def _make_assertion_result_from_test( - self, - node: DBTNode, - assertion_urn: str, - upstream_urn: str, - ) -> MetadataWorkUnit: - assert node.test_result - test_result = node.test_result - - assertionResult = AssertionRunEventClass( - timestampMillis=int(test_result.execution_time.timestamp() * 1000.0), - assertionUrn=assertion_urn, - asserteeUrn=upstream_urn, - runId=test_result.invocation_id, - result=AssertionResultClass( - type=AssertionResultTypeClass.SUCCESS - if test_result.status == "pass" - or ( - not self.config.test_warnings_are_errors - and test_result.status == "warn" - ) - else AssertionResultTypeClass.FAILURE, - nativeResults=test_result.native_results, - ), - status=AssertionRunStatusClass.COMPLETE, - ) - - event = MetadataChangeProposalWrapper( - entityUrn=assertion_urn, - aspect=assertionResult, - ) - wu = MetadataWorkUnit( - id=f"{assertion_urn}-assertionRunEvent-{upstream_urn}", - mcp=event, - ) - return wu - @abstractmethod def load_nodes(self) -> Tuple[List[DBTNode], Dict[str, Optional[str]]]: # return dbt nodes + global custom properties diff --git a/metadata-ingestion/src/datahub/ingestion/source/dbt/dbt_core.py b/metadata-ingestion/src/datahub/ingestion/source/dbt/dbt_core.py index c08295ed1dc59..dc3a84847beb2 100644 --- a/metadata-ingestion/src/datahub/ingestion/source/dbt/dbt_core.py +++ b/metadata-ingestion/src/datahub/ingestion/source/dbt/dbt_core.py @@ -26,9 +26,8 @@ DBTNode, DBTSourceBase, DBTSourceReport, - DBTTest, - DBTTestResult, ) +from datahub.ingestion.source.dbt.dbt_tests import DBTTest, DBTTestResult logger = logging.getLogger(__name__) diff --git a/metadata-ingestion/src/datahub/ingestion/source/dbt/dbt_tests.py b/metadata-ingestion/src/datahub/ingestion/source/dbt/dbt_tests.py new file mode 100644 index 0000000000000..721769d214d9e --- /dev/null +++ b/metadata-ingestion/src/datahub/ingestion/source/dbt/dbt_tests.py @@ -0,0 +1,261 @@ +import json +import re +from dataclasses import dataclass +from datetime import datetime +from typing import TYPE_CHECKING, Any, Callable, Dict, Optional, Union + +from datahub.emitter import mce_builder +from datahub.emitter.mcp import MetadataChangeProposalWrapper +from datahub.ingestion.api.workunit import MetadataWorkUnit +from datahub.metadata.schema_classes import ( + AssertionInfoClass, + AssertionResultClass, + AssertionResultTypeClass, + AssertionRunEventClass, + AssertionRunStatusClass, + AssertionStdAggregationClass, + AssertionStdOperatorClass, + AssertionStdParameterClass, + AssertionStdParametersClass, + AssertionStdParameterTypeClass, + AssertionTypeClass, + DatasetAssertionInfoClass, + DatasetAssertionScopeClass, +) + +if TYPE_CHECKING: + from datahub.ingestion.source.dbt.dbt_common import DBTNode + + +@dataclass +class DBTTest: + qualified_test_name: str + column_name: Optional[str] + kw_args: dict + + +@dataclass +class DBTTestResult: + invocation_id: str + + status: str + execution_time: datetime + + native_results: Dict[str, str] + + +def _get_name_for_relationship_test(kw_args: Dict[str, str]) -> Optional[str]: + """ + Try to produce a useful string for the name of a relationship constraint. + Return None if we fail to + """ + destination_ref = kw_args.get("to") + source_ref = kw_args.get("model") + column_name = kw_args.get("column_name") + dest_field_name = kw_args.get("field") + if not destination_ref or not source_ref or not column_name or not dest_field_name: + # base assertions are violated, bail early + return None + m = re.match(r"^ref\(\'(.*)\'\)$", destination_ref) + if m: + destination_table = m.group(1) + else: + destination_table = destination_ref + m = re.search(r"ref\(\'(.*)\'\)", source_ref) + if m: + source_table = m.group(1) + else: + source_table = source_ref + return f"{source_table}.{column_name} referential integrity to {destination_table}.{dest_field_name}" + + +@dataclass +class AssertionParams: + scope: Union[DatasetAssertionScopeClass, str] + operator: Union[AssertionStdOperatorClass, str] + aggregation: Union[AssertionStdAggregationClass, str] + parameters: Optional[Callable[[Dict[str, str]], AssertionStdParametersClass]] = None + logic_fn: Optional[Callable[[Dict[str, str]], Optional[str]]] = None + + +_DBT_TEST_NAME_TO_ASSERTION_MAP: Dict[str, AssertionParams] = { + "not_null": AssertionParams( + scope=DatasetAssertionScopeClass.DATASET_COLUMN, + operator=AssertionStdOperatorClass.NOT_NULL, + aggregation=AssertionStdAggregationClass.IDENTITY, + ), + "unique": AssertionParams( + scope=DatasetAssertionScopeClass.DATASET_COLUMN, + operator=AssertionStdOperatorClass.EQUAL_TO, + aggregation=AssertionStdAggregationClass.UNIQUE_PROPOTION, + parameters=lambda _: AssertionStdParametersClass( + value=AssertionStdParameterClass( + value="1.0", + type=AssertionStdParameterTypeClass.NUMBER, + ) + ), + ), + "accepted_values": AssertionParams( + scope=DatasetAssertionScopeClass.DATASET_COLUMN, + operator=AssertionStdOperatorClass.IN, + aggregation=AssertionStdAggregationClass.IDENTITY, + parameters=lambda kw_args: AssertionStdParametersClass( + value=AssertionStdParameterClass( + value=json.dumps(kw_args.get("values")), + type=AssertionStdParameterTypeClass.SET, + ), + ), + ), + "relationships": AssertionParams( + scope=DatasetAssertionScopeClass.DATASET_COLUMN, + operator=AssertionStdOperatorClass._NATIVE_, + aggregation=AssertionStdAggregationClass.IDENTITY, + parameters=lambda kw_args: AssertionStdParametersClass( + value=AssertionStdParameterClass( + value=json.dumps(kw_args.get("values")), + type=AssertionStdParameterTypeClass.SET, + ), + ), + logic_fn=_get_name_for_relationship_test, + ), + "dbt_expectations.expect_column_values_to_not_be_null": AssertionParams( + scope=DatasetAssertionScopeClass.DATASET_COLUMN, + operator=AssertionStdOperatorClass.NOT_NULL, + aggregation=AssertionStdAggregationClass.IDENTITY, + ), + "dbt_expectations.expect_column_values_to_be_between": AssertionParams( + scope=DatasetAssertionScopeClass.DATASET_COLUMN, + operator=AssertionStdOperatorClass.BETWEEN, + aggregation=AssertionStdAggregationClass.IDENTITY, + parameters=lambda x: AssertionStdParametersClass( + minValue=AssertionStdParameterClass( + value=str(x.get("min_value", "unknown")), + type=AssertionStdParameterTypeClass.NUMBER, + ), + maxValue=AssertionStdParameterClass( + value=str(x.get("max_value", "unknown")), + type=AssertionStdParameterTypeClass.NUMBER, + ), + ), + ), + "dbt_expectations.expect_column_values_to_be_in_set": AssertionParams( + scope=DatasetAssertionScopeClass.DATASET_COLUMN, + operator=AssertionStdOperatorClass.IN, + aggregation=AssertionStdAggregationClass.IDENTITY, + parameters=lambda kw_args: AssertionStdParametersClass( + value=AssertionStdParameterClass( + value=json.dumps(kw_args.get("value_set")), + type=AssertionStdParameterTypeClass.SET, + ), + ), + ), +} + + +def _string_map(input_map: Dict[str, Any]) -> Dict[str, str]: + return {k: str(v) for k, v in input_map.items()} + + +def make_assertion_from_test( + extra_custom_props: Dict[str, str], + node: "DBTNode", + assertion_urn: str, + upstream_urn: str, +) -> MetadataWorkUnit: + assert node.test_info + qualified_test_name = node.test_info.qualified_test_name + column_name = node.test_info.column_name + kw_args = node.test_info.kw_args + + if qualified_test_name in _DBT_TEST_NAME_TO_ASSERTION_MAP: + assertion_params = _DBT_TEST_NAME_TO_ASSERTION_MAP[qualified_test_name] + assertion_info = AssertionInfoClass( + type=AssertionTypeClass.DATASET, + customProperties=extra_custom_props, + datasetAssertion=DatasetAssertionInfoClass( + dataset=upstream_urn, + scope=assertion_params.scope, + operator=assertion_params.operator, + fields=[mce_builder.make_schema_field_urn(upstream_urn, column_name)] + if ( + assertion_params.scope == DatasetAssertionScopeClass.DATASET_COLUMN + and column_name + ) + else [], + nativeType=node.name, + aggregation=assertion_params.aggregation, + parameters=assertion_params.parameters(kw_args) + if assertion_params.parameters + else None, + logic=assertion_params.logic_fn(kw_args) + if assertion_params.logic_fn + else None, + nativeParameters=_string_map(kw_args), + ), + ) + elif column_name: + # no match with known test types, column-level test + assertion_info = AssertionInfoClass( + type=AssertionTypeClass.DATASET, + customProperties=extra_custom_props, + datasetAssertion=DatasetAssertionInfoClass( + dataset=upstream_urn, + scope=DatasetAssertionScopeClass.DATASET_COLUMN, + operator=AssertionStdOperatorClass._NATIVE_, + fields=[mce_builder.make_schema_field_urn(upstream_urn, column_name)], + nativeType=node.name, + logic=node.compiled_code or node.raw_code, + aggregation=AssertionStdAggregationClass._NATIVE_, + nativeParameters=_string_map(kw_args), + ), + ) + else: + # no match with known test types, default to row-level test + assertion_info = AssertionInfoClass( + type=AssertionTypeClass.DATASET, + customProperties=extra_custom_props, + datasetAssertion=DatasetAssertionInfoClass( + dataset=upstream_urn, + scope=DatasetAssertionScopeClass.DATASET_ROWS, + operator=AssertionStdOperatorClass._NATIVE_, + logic=node.compiled_code or node.raw_code, + nativeType=node.name, + aggregation=AssertionStdAggregationClass._NATIVE_, + nativeParameters=_string_map(kw_args), + ), + ) + + return MetadataChangeProposalWrapper( + entityUrn=assertion_urn, + aspect=assertion_info, + ).as_workunit() + + +def make_assertion_result_from_test( + node: "DBTNode", + assertion_urn: str, + upstream_urn: str, + test_warnings_are_errors: bool, +) -> MetadataWorkUnit: + assert node.test_result + test_result = node.test_result + + assertionResult = AssertionRunEventClass( + timestampMillis=int(test_result.execution_time.timestamp() * 1000.0), + assertionUrn=assertion_urn, + asserteeUrn=upstream_urn, + runId=test_result.invocation_id, + result=AssertionResultClass( + type=AssertionResultTypeClass.SUCCESS + if test_result.status == "pass" + or (not test_warnings_are_errors and test_result.status == "warn") + else AssertionResultTypeClass.FAILURE, + nativeResults=test_result.native_results, + ), + status=AssertionRunStatusClass.COMPLETE, + ) + + return MetadataChangeProposalWrapper( + entityUrn=assertion_urn, + aspect=assertionResult, + ).as_workunit() diff --git a/metadata-ingestion/src/datahub/ingestion/source/looker/looker_common.py b/metadata-ingestion/src/datahub/ingestion/source/looker/looker_common.py index 89b1e45695c57..30c38720dd96c 100644 --- a/metadata-ingestion/src/datahub/ingestion/source/looker/looker_common.py +++ b/metadata-ingestion/src/datahub/ingestion/source/looker/looker_common.py @@ -81,9 +81,6 @@ EnumTypeClass, FineGrainedLineageClass, GlobalTagsClass, - OwnerClass, - OwnershipClass, - OwnershipTypeClass, SchemaMetadataClass, StatusClass, SubTypesClass, @@ -453,17 +450,9 @@ def _get_schema( @staticmethod def _get_tag_mce_for_urn(tag_urn: str) -> MetadataChangeEvent: assert tag_urn in LookerUtil.tag_definitions - ownership = OwnershipClass( - owners=[ - OwnerClass( - owner="urn:li:corpuser:datahub", - type=OwnershipTypeClass.DATAOWNER, - ) - ] - ) return MetadataChangeEvent( proposedSnapshot=TagSnapshotClass( - urn=tag_urn, aspects=[ownership, LookerUtil.tag_definitions[tag_urn]] + urn=tag_urn, aspects=[LookerUtil.tag_definitions[tag_urn]] ) ) diff --git a/metadata-ingestion/src/datahub/ingestion/source/snowflake/snowflake_profiler.py b/metadata-ingestion/src/datahub/ingestion/source/snowflake/snowflake_profiler.py index 24275dcdff34d..8e18d85d6f3ca 100644 --- a/metadata-ingestion/src/datahub/ingestion/source/snowflake/snowflake_profiler.py +++ b/metadata-ingestion/src/datahub/ingestion/source/snowflake/snowflake_profiler.py @@ -86,7 +86,7 @@ def get_batch_kwargs( # Fixed-size sampling can be slower than equivalent fraction-based sampling # as per https://docs.snowflake.com/en/sql-reference/constructs/sample#performance-considerations sample_pc = 100 * self.config.profiling.sample_size / table.rows_count - custom_sql = f'select * from "{db_name}"."{schema_name}"."{table.name}" TABLESAMPLE ({sample_pc:.3f})' + custom_sql = f'select * from "{db_name}"."{schema_name}"."{table.name}" TABLESAMPLE ({sample_pc:.8f})' return { **super().get_batch_kwargs(table, schema_name, db_name), # Lowercase/Mixedcase table names in Snowflake do not work by default. diff --git a/metadata-ingestion/src/datahub/ingestion/source/sql/postgres.py b/metadata-ingestion/src/datahub/ingestion/source/sql/postgres.py index ba8655b83446d..a6a9d8e2c8597 100644 --- a/metadata-ingestion/src/datahub/ingestion/source/sql/postgres.py +++ b/metadata-ingestion/src/datahub/ingestion/source/sql/postgres.py @@ -217,14 +217,15 @@ def _get_view_lineage_elements( key = (lineage.dependent_view, lineage.dependent_schema) # Append the source table to the list. lineage_elements[key].append( - mce_builder.make_dataset_urn( - self.platform, - self.get_identifier( + mce_builder.make_dataset_urn_with_platform_instance( + platform=self.platform, + name=self.get_identifier( schema=lineage.source_schema, entity=lineage.source_table, inspector=inspector, ), - self.config.env, + platform_instance=self.config.platform_instance, + env=self.config.env, ) ) @@ -244,12 +245,13 @@ def _get_view_lineage_workunits( dependent_view, dependent_schema = key # Construct a lineage object. - urn = mce_builder.make_dataset_urn( - self.platform, - self.get_identifier( + urn = mce_builder.make_dataset_urn_with_platform_instance( + platform=self.platform, + name=self.get_identifier( schema=dependent_schema, entity=dependent_view, inspector=inspector ), - self.config.env, + platform_instance=self.config.platform_instance, + env=self.config.env, ) # use the mce_builder to ensure that the change proposal inherits diff --git a/metadata-ingestion/src/datahub/utilities/sqlglot_lineage.py b/metadata-ingestion/src/datahub/utilities/sqlglot_lineage.py index 81c43884fdf7d..349eb40a5e865 100644 --- a/metadata-ingestion/src/datahub/utilities/sqlglot_lineage.py +++ b/metadata-ingestion/src/datahub/utilities/sqlglot_lineage.py @@ -5,12 +5,13 @@ import logging import pathlib from collections import defaultdict -from typing import Dict, List, Optional, Set, Tuple, Union +from typing import Any, Dict, List, Optional, Set, Tuple, Union import pydantic.dataclasses import sqlglot import sqlglot.errors import sqlglot.lineage +import sqlglot.optimizer.annotate_types import sqlglot.optimizer.qualify import sqlglot.optimizer.qualify_columns from pydantic import BaseModel @@ -23,7 +24,17 @@ from datahub.ingestion.api.closeable import Closeable from datahub.ingestion.graph.client import DataHubGraph from datahub.ingestion.source.bigquery_v2.bigquery_audit import BigqueryTableIdentifier -from datahub.metadata.schema_classes import OperationTypeClass, SchemaMetadataClass +from datahub.metadata.schema_classes import ( + ArrayTypeClass, + BooleanTypeClass, + DateTypeClass, + NumberTypeClass, + OperationTypeClass, + SchemaFieldDataTypeClass, + SchemaMetadataClass, + StringTypeClass, + TimeTypeClass, +) from datahub.utilities.file_backed_collections import ConnectionWrapper, FileBackedDict from datahub.utilities.urns.dataset_urn import DatasetUrn @@ -90,8 +101,18 @@ def get_query_type_of_sql(expression: sqlglot.exp.Expression) -> QueryType: return QueryType.UNKNOWN +class _ParserBaseModel( + BaseModel, + arbitrary_types_allowed=True, + json_encoders={ + SchemaFieldDataTypeClass: lambda v: v.to_obj(), + }, +): + pass + + @functools.total_ordering -class _FrozenModel(BaseModel, frozen=True): +class _FrozenModel(_ParserBaseModel, frozen=True): def __lt__(self, other: "_FrozenModel") -> bool: for field in self.__fields__: self_v = getattr(self, field) @@ -146,29 +167,42 @@ class _ColumnRef(_FrozenModel): column: str -class ColumnRef(BaseModel): +class ColumnRef(_ParserBaseModel): table: Urn column: str -class _DownstreamColumnRef(BaseModel): +class _DownstreamColumnRef(_ParserBaseModel): table: Optional[_TableName] column: str + column_type: Optional[sqlglot.exp.DataType] -class DownstreamColumnRef(BaseModel): +class DownstreamColumnRef(_ParserBaseModel): table: Optional[Urn] column: str + column_type: Optional[SchemaFieldDataTypeClass] + native_column_type: Optional[str] + + @pydantic.validator("column_type", pre=True) + def _load_column_type( + cls, v: Optional[Union[dict, SchemaFieldDataTypeClass]] + ) -> Optional[SchemaFieldDataTypeClass]: + if v is None: + return None + if isinstance(v, SchemaFieldDataTypeClass): + return v + return SchemaFieldDataTypeClass.from_obj(v) -class _ColumnLineageInfo(BaseModel): +class _ColumnLineageInfo(_ParserBaseModel): downstream: _DownstreamColumnRef upstreams: List[_ColumnRef] logic: Optional[str] -class ColumnLineageInfo(BaseModel): +class ColumnLineageInfo(_ParserBaseModel): downstream: DownstreamColumnRef upstreams: List[ColumnRef] @@ -176,7 +210,7 @@ class ColumnLineageInfo(BaseModel): logic: Optional[str] = pydantic.Field(default=None, exclude=True) -class SqlParsingDebugInfo(BaseModel, arbitrary_types_allowed=True): +class SqlParsingDebugInfo(_ParserBaseModel): confidence: float = 0.0 tables_discovered: int = 0 @@ -190,7 +224,7 @@ def error(self) -> Optional[Exception]: return self.table_error or self.column_error -class SqlParsingResult(BaseModel): +class SqlParsingResult(_ParserBaseModel): query_type: QueryType = QueryType.UNKNOWN in_tables: List[Urn] @@ -541,6 +575,15 @@ def _schema_aware_fuzzy_column_resolve( ) from e logger.debug("Qualified sql %s", statement.sql(pretty=True, dialect=dialect)) + # Try to figure out the types of the output columns. + try: + statement = sqlglot.optimizer.annotate_types.annotate_types( + statement, schema=sqlglot_db_schema + ) + except sqlglot.errors.OptimizeError as e: + # This is not a fatal error, so we can continue. + logger.debug("sqlglot failed to annotate types: %s", e) + column_lineage = [] try: @@ -553,7 +596,6 @@ def _schema_aware_fuzzy_column_resolve( logger.debug("output columns: %s", [col[0] for col in output_columns]) output_col: str for output_col, original_col_expression in output_columns: - # print(f"output column: {output_col}") if output_col == "*": # If schema information is available, the * will be expanded to the actual columns. # Otherwise, we can't process it. @@ -613,12 +655,19 @@ def _schema_aware_fuzzy_column_resolve( output_col = _schema_aware_fuzzy_column_resolve(output_table, output_col) + # Guess the output column type. + output_col_type = None + if original_col_expression.type: + output_col_type = original_col_expression.type + if not direct_col_upstreams: logger.debug(f' "{output_col}" has no upstreams') column_lineage.append( _ColumnLineageInfo( downstream=_DownstreamColumnRef( - table=output_table, column=output_col + table=output_table, + column=output_col, + column_type=output_col_type, ), upstreams=sorted(direct_col_upstreams), # logic=column_logic.sql(pretty=True, dialect=dialect), @@ -673,6 +722,42 @@ def _try_extract_select( return statement +def _translate_sqlglot_type( + sqlglot_type: sqlglot.exp.DataType.Type, +) -> Optional[SchemaFieldDataTypeClass]: + TypeClass: Any + if sqlglot_type in sqlglot.exp.DataType.TEXT_TYPES: + TypeClass = StringTypeClass + elif sqlglot_type in sqlglot.exp.DataType.NUMERIC_TYPES or sqlglot_type in { + sqlglot.exp.DataType.Type.DECIMAL, + }: + TypeClass = NumberTypeClass + elif sqlglot_type in { + sqlglot.exp.DataType.Type.BOOLEAN, + sqlglot.exp.DataType.Type.BIT, + }: + TypeClass = BooleanTypeClass + elif sqlglot_type in { + sqlglot.exp.DataType.Type.DATE, + }: + TypeClass = DateTypeClass + elif sqlglot_type in sqlglot.exp.DataType.TEMPORAL_TYPES: + TypeClass = TimeTypeClass + elif sqlglot_type in { + sqlglot.exp.DataType.Type.ARRAY, + }: + TypeClass = ArrayTypeClass + elif sqlglot_type in { + sqlglot.exp.DataType.Type.UNKNOWN, + }: + return None + else: + logger.debug("Unknown sqlglot type: %s", sqlglot_type) + return None + + return SchemaFieldDataTypeClass(type=TypeClass()) + + def _translate_internal_column_lineage( table_name_urn_mapping: Dict[_TableName, str], raw_column_lineage: _ColumnLineageInfo, @@ -684,6 +769,16 @@ def _translate_internal_column_lineage( downstream=DownstreamColumnRef( table=downstream_urn, column=raw_column_lineage.downstream.column, + column_type=_translate_sqlglot_type( + raw_column_lineage.downstream.column_type.this + ) + if raw_column_lineage.downstream.column_type + else None, + native_column_type=raw_column_lineage.downstream.column_type.sql() + if raw_column_lineage.downstream.column_type + and raw_column_lineage.downstream.column_type.this + != sqlglot.exp.DataType.Type.UNKNOWN + else None, ), upstreams=[ ColumnRef( diff --git a/metadata-ingestion/tests/integration/looker/golden_looker_mces.json b/metadata-ingestion/tests/integration/looker/golden_looker_mces.json index dee85b40bb7a8..1da42b94e320c 100644 --- a/metadata-ingestion/tests/integration/looker/golden_looker_mces.json +++ b/metadata-ingestion/tests/integration/looker/golden_looker_mces.json @@ -533,20 +533,6 @@ "com.linkedin.pegasus2avro.metadata.snapshot.TagSnapshot": { "urn": "urn:li:tag:Dimension", "aspects": [ - { - "com.linkedin.pegasus2avro.common.Ownership": { - "owners": [ - { - "owner": "urn:li:corpuser:datahub", - "type": "DATAOWNER" - } - ], - "lastModified": { - "time": 0, - "actor": "urn:li:corpuser:unknown" - } - } - }, { "com.linkedin.pegasus2avro.tag.TagProperties": { "name": "Dimension", @@ -566,20 +552,6 @@ "com.linkedin.pegasus2avro.metadata.snapshot.TagSnapshot": { "urn": "urn:li:tag:Temporal", "aspects": [ - { - "com.linkedin.pegasus2avro.common.Ownership": { - "owners": [ - { - "owner": "urn:li:corpuser:datahub", - "type": "DATAOWNER" - } - ], - "lastModified": { - "time": 0, - "actor": "urn:li:corpuser:unknown" - } - } - }, { "com.linkedin.pegasus2avro.tag.TagProperties": { "name": "Temporal", @@ -599,20 +571,6 @@ "com.linkedin.pegasus2avro.metadata.snapshot.TagSnapshot": { "urn": "urn:li:tag:Measure", "aspects": [ - { - "com.linkedin.pegasus2avro.common.Ownership": { - "owners": [ - { - "owner": "urn:li:corpuser:datahub", - "type": "DATAOWNER" - } - ], - "lastModified": { - "time": 0, - "actor": "urn:li:corpuser:unknown" - } - } - }, { "com.linkedin.pegasus2avro.tag.TagProperties": { "name": "Measure", diff --git a/metadata-ingestion/tests/integration/looker/golden_test_allow_ingest.json b/metadata-ingestion/tests/integration/looker/golden_test_allow_ingest.json index 72db36e63daf7..685a606a57c33 100644 --- a/metadata-ingestion/tests/integration/looker/golden_test_allow_ingest.json +++ b/metadata-ingestion/tests/integration/looker/golden_test_allow_ingest.json @@ -327,20 +327,6 @@ "com.linkedin.pegasus2avro.metadata.snapshot.TagSnapshot": { "urn": "urn:li:tag:Dimension", "aspects": [ - { - "com.linkedin.pegasus2avro.common.Ownership": { - "owners": [ - { - "owner": "urn:li:corpuser:datahub", - "type": "DATAOWNER" - } - ], - "lastModified": { - "time": 0, - "actor": "urn:li:corpuser:unknown" - } - } - }, { "com.linkedin.pegasus2avro.tag.TagProperties": { "name": "Dimension", @@ -360,20 +346,6 @@ "com.linkedin.pegasus2avro.metadata.snapshot.TagSnapshot": { "urn": "urn:li:tag:Temporal", "aspects": [ - { - "com.linkedin.pegasus2avro.common.Ownership": { - "owners": [ - { - "owner": "urn:li:corpuser:datahub", - "type": "DATAOWNER" - } - ], - "lastModified": { - "time": 0, - "actor": "urn:li:corpuser:unknown" - } - } - }, { "com.linkedin.pegasus2avro.tag.TagProperties": { "name": "Temporal", @@ -393,20 +365,6 @@ "com.linkedin.pegasus2avro.metadata.snapshot.TagSnapshot": { "urn": "urn:li:tag:Measure", "aspects": [ - { - "com.linkedin.pegasus2avro.common.Ownership": { - "owners": [ - { - "owner": "urn:li:corpuser:datahub", - "type": "DATAOWNER" - } - ], - "lastModified": { - "time": 0, - "actor": "urn:li:corpuser:unknown" - } - } - }, { "com.linkedin.pegasus2avro.tag.TagProperties": { "name": "Measure", diff --git a/metadata-ingestion/tests/integration/looker/golden_test_external_project_view_mces.json b/metadata-ingestion/tests/integration/looker/golden_test_external_project_view_mces.json index e5508bdb06b9e..069788cb088ac 100644 --- a/metadata-ingestion/tests/integration/looker/golden_test_external_project_view_mces.json +++ b/metadata-ingestion/tests/integration/looker/golden_test_external_project_view_mces.json @@ -327,20 +327,6 @@ "com.linkedin.pegasus2avro.metadata.snapshot.TagSnapshot": { "urn": "urn:li:tag:Dimension", "aspects": [ - { - "com.linkedin.pegasus2avro.common.Ownership": { - "owners": [ - { - "owner": "urn:li:corpuser:datahub", - "type": "DATAOWNER" - } - ], - "lastModified": { - "time": 0, - "actor": "urn:li:corpuser:unknown" - } - } - }, { "com.linkedin.pegasus2avro.tag.TagProperties": { "name": "Dimension", @@ -360,20 +346,6 @@ "com.linkedin.pegasus2avro.metadata.snapshot.TagSnapshot": { "urn": "urn:li:tag:Temporal", "aspects": [ - { - "com.linkedin.pegasus2avro.common.Ownership": { - "owners": [ - { - "owner": "urn:li:corpuser:datahub", - "type": "DATAOWNER" - } - ], - "lastModified": { - "time": 0, - "actor": "urn:li:corpuser:unknown" - } - } - }, { "com.linkedin.pegasus2avro.tag.TagProperties": { "name": "Temporal", @@ -393,20 +365,6 @@ "com.linkedin.pegasus2avro.metadata.snapshot.TagSnapshot": { "urn": "urn:li:tag:Measure", "aspects": [ - { - "com.linkedin.pegasus2avro.common.Ownership": { - "owners": [ - { - "owner": "urn:li:corpuser:datahub", - "type": "DATAOWNER" - } - ], - "lastModified": { - "time": 0, - "actor": "urn:li:corpuser:unknown" - } - } - }, { "com.linkedin.pegasus2avro.tag.TagProperties": { "name": "Measure", diff --git a/metadata-ingestion/tests/integration/looker/golden_test_file_path_ingest.json b/metadata-ingestion/tests/integration/looker/golden_test_file_path_ingest.json index b0f66e7b245c9..f1c932ebd5a70 100644 --- a/metadata-ingestion/tests/integration/looker/golden_test_file_path_ingest.json +++ b/metadata-ingestion/tests/integration/looker/golden_test_file_path_ingest.json @@ -335,20 +335,6 @@ "com.linkedin.pegasus2avro.metadata.snapshot.TagSnapshot": { "urn": "urn:li:tag:Dimension", "aspects": [ - { - "com.linkedin.pegasus2avro.common.Ownership": { - "owners": [ - { - "owner": "urn:li:corpuser:datahub", - "type": "DATAOWNER" - } - ], - "lastModified": { - "time": 0, - "actor": "urn:li:corpuser:unknown" - } - } - }, { "com.linkedin.pegasus2avro.tag.TagProperties": { "name": "Dimension", @@ -369,20 +355,6 @@ "com.linkedin.pegasus2avro.metadata.snapshot.TagSnapshot": { "urn": "urn:li:tag:Temporal", "aspects": [ - { - "com.linkedin.pegasus2avro.common.Ownership": { - "owners": [ - { - "owner": "urn:li:corpuser:datahub", - "type": "DATAOWNER" - } - ], - "lastModified": { - "time": 0, - "actor": "urn:li:corpuser:unknown" - } - } - }, { "com.linkedin.pegasus2avro.tag.TagProperties": { "name": "Temporal", @@ -403,20 +375,6 @@ "com.linkedin.pegasus2avro.metadata.snapshot.TagSnapshot": { "urn": "urn:li:tag:Measure", "aspects": [ - { - "com.linkedin.pegasus2avro.common.Ownership": { - "owners": [ - { - "owner": "urn:li:corpuser:datahub", - "type": "DATAOWNER" - } - ], - "lastModified": { - "time": 0, - "actor": "urn:li:corpuser:unknown" - } - } - }, { "com.linkedin.pegasus2avro.tag.TagProperties": { "name": "Measure", diff --git a/metadata-ingestion/tests/integration/looker/golden_test_independent_look_ingest.json b/metadata-ingestion/tests/integration/looker/golden_test_independent_look_ingest.json index 91e13debfa028..9521c9af4bbdc 100644 --- a/metadata-ingestion/tests/integration/looker/golden_test_independent_look_ingest.json +++ b/metadata-ingestion/tests/integration/looker/golden_test_independent_look_ingest.json @@ -550,20 +550,6 @@ "com.linkedin.pegasus2avro.metadata.snapshot.TagSnapshot": { "urn": "urn:li:tag:Dimension", "aspects": [ - { - "com.linkedin.pegasus2avro.common.Ownership": { - "owners": [ - { - "owner": "urn:li:corpuser:datahub", - "type": "DATAOWNER" - } - ], - "lastModified": { - "time": 0, - "actor": "urn:li:corpuser:unknown" - } - } - }, { "com.linkedin.pegasus2avro.tag.TagProperties": { "name": "Dimension", @@ -583,20 +569,6 @@ "com.linkedin.pegasus2avro.metadata.snapshot.TagSnapshot": { "urn": "urn:li:tag:Temporal", "aspects": [ - { - "com.linkedin.pegasus2avro.common.Ownership": { - "owners": [ - { - "owner": "urn:li:corpuser:datahub", - "type": "DATAOWNER" - } - ], - "lastModified": { - "time": 0, - "actor": "urn:li:corpuser:unknown" - } - } - }, { "com.linkedin.pegasus2avro.tag.TagProperties": { "name": "Temporal", @@ -616,20 +588,6 @@ "com.linkedin.pegasus2avro.metadata.snapshot.TagSnapshot": { "urn": "urn:li:tag:Measure", "aspects": [ - { - "com.linkedin.pegasus2avro.common.Ownership": { - "owners": [ - { - "owner": "urn:li:corpuser:datahub", - "type": "DATAOWNER" - } - ], - "lastModified": { - "time": 0, - "actor": "urn:li:corpuser:unknown" - } - } - }, { "com.linkedin.pegasus2avro.tag.TagProperties": { "name": "Measure", diff --git a/metadata-ingestion/tests/integration/looker/golden_test_ingest.json b/metadata-ingestion/tests/integration/looker/golden_test_ingest.json index e93079119e4f4..dbacd52fe83de 100644 --- a/metadata-ingestion/tests/integration/looker/golden_test_ingest.json +++ b/metadata-ingestion/tests/integration/looker/golden_test_ingest.json @@ -327,20 +327,6 @@ "com.linkedin.pegasus2avro.metadata.snapshot.TagSnapshot": { "urn": "urn:li:tag:Dimension", "aspects": [ - { - "com.linkedin.pegasus2avro.common.Ownership": { - "owners": [ - { - "owner": "urn:li:corpuser:datahub", - "type": "DATAOWNER" - } - ], - "lastModified": { - "time": 0, - "actor": "urn:li:corpuser:unknown" - } - } - }, { "com.linkedin.pegasus2avro.tag.TagProperties": { "name": "Dimension", @@ -360,20 +346,6 @@ "com.linkedin.pegasus2avro.metadata.snapshot.TagSnapshot": { "urn": "urn:li:tag:Temporal", "aspects": [ - { - "com.linkedin.pegasus2avro.common.Ownership": { - "owners": [ - { - "owner": "urn:li:corpuser:datahub", - "type": "DATAOWNER" - } - ], - "lastModified": { - "time": 0, - "actor": "urn:li:corpuser:unknown" - } - } - }, { "com.linkedin.pegasus2avro.tag.TagProperties": { "name": "Temporal", @@ -393,20 +365,6 @@ "com.linkedin.pegasus2avro.metadata.snapshot.TagSnapshot": { "urn": "urn:li:tag:Measure", "aspects": [ - { - "com.linkedin.pegasus2avro.common.Ownership": { - "owners": [ - { - "owner": "urn:li:corpuser:datahub", - "type": "DATAOWNER" - } - ], - "lastModified": { - "time": 0, - "actor": "urn:li:corpuser:unknown" - } - } - }, { "com.linkedin.pegasus2avro.tag.TagProperties": { "name": "Measure", diff --git a/metadata-ingestion/tests/integration/looker/golden_test_ingest_joins.json b/metadata-ingestion/tests/integration/looker/golden_test_ingest_joins.json index a9c8efa7cdb98..aaa874d9ff348 100644 --- a/metadata-ingestion/tests/integration/looker/golden_test_ingest_joins.json +++ b/metadata-ingestion/tests/integration/looker/golden_test_ingest_joins.json @@ -351,20 +351,6 @@ "com.linkedin.pegasus2avro.metadata.snapshot.TagSnapshot": { "urn": "urn:li:tag:Dimension", "aspects": [ - { - "com.linkedin.pegasus2avro.common.Ownership": { - "owners": [ - { - "owner": "urn:li:corpuser:datahub", - "type": "DATAOWNER" - } - ], - "lastModified": { - "time": 0, - "actor": "urn:li:corpuser:unknown" - } - } - }, { "com.linkedin.pegasus2avro.tag.TagProperties": { "name": "Dimension", @@ -384,20 +370,6 @@ "com.linkedin.pegasus2avro.metadata.snapshot.TagSnapshot": { "urn": "urn:li:tag:Temporal", "aspects": [ - { - "com.linkedin.pegasus2avro.common.Ownership": { - "owners": [ - { - "owner": "urn:li:corpuser:datahub", - "type": "DATAOWNER" - } - ], - "lastModified": { - "time": 0, - "actor": "urn:li:corpuser:unknown" - } - } - }, { "com.linkedin.pegasus2avro.tag.TagProperties": { "name": "Temporal", @@ -417,20 +389,6 @@ "com.linkedin.pegasus2avro.metadata.snapshot.TagSnapshot": { "urn": "urn:li:tag:Measure", "aspects": [ - { - "com.linkedin.pegasus2avro.common.Ownership": { - "owners": [ - { - "owner": "urn:li:corpuser:datahub", - "type": "DATAOWNER" - } - ], - "lastModified": { - "time": 0, - "actor": "urn:li:corpuser:unknown" - } - } - }, { "com.linkedin.pegasus2avro.tag.TagProperties": { "name": "Measure", diff --git a/metadata-ingestion/tests/integration/looker/golden_test_ingest_unaliased_joins.json b/metadata-ingestion/tests/integration/looker/golden_test_ingest_unaliased_joins.json index edd15624a14cd..be8db0722aea3 100644 --- a/metadata-ingestion/tests/integration/looker/golden_test_ingest_unaliased_joins.json +++ b/metadata-ingestion/tests/integration/looker/golden_test_ingest_unaliased_joins.json @@ -343,20 +343,6 @@ "com.linkedin.pegasus2avro.metadata.snapshot.TagSnapshot": { "urn": "urn:li:tag:Dimension", "aspects": [ - { - "com.linkedin.pegasus2avro.common.Ownership": { - "owners": [ - { - "owner": "urn:li:corpuser:datahub", - "type": "DATAOWNER" - } - ], - "lastModified": { - "time": 0, - "actor": "urn:li:corpuser:unknown" - } - } - }, { "com.linkedin.pegasus2avro.tag.TagProperties": { "name": "Dimension", @@ -376,20 +362,6 @@ "com.linkedin.pegasus2avro.metadata.snapshot.TagSnapshot": { "urn": "urn:li:tag:Temporal", "aspects": [ - { - "com.linkedin.pegasus2avro.common.Ownership": { - "owners": [ - { - "owner": "urn:li:corpuser:datahub", - "type": "DATAOWNER" - } - ], - "lastModified": { - "time": 0, - "actor": "urn:li:corpuser:unknown" - } - } - }, { "com.linkedin.pegasus2avro.tag.TagProperties": { "name": "Temporal", @@ -409,20 +381,6 @@ "com.linkedin.pegasus2avro.metadata.snapshot.TagSnapshot": { "urn": "urn:li:tag:Measure", "aspects": [ - { - "com.linkedin.pegasus2avro.common.Ownership": { - "owners": [ - { - "owner": "urn:li:corpuser:datahub", - "type": "DATAOWNER" - } - ], - "lastModified": { - "time": 0, - "actor": "urn:li:corpuser:unknown" - } - } - }, { "com.linkedin.pegasus2avro.tag.TagProperties": { "name": "Measure", diff --git a/metadata-ingestion/tests/integration/looker/looker_mces_golden_deleted_stateful.json b/metadata-ingestion/tests/integration/looker/looker_mces_golden_deleted_stateful.json index aebc89b609a08..05b74f163ad45 100644 --- a/metadata-ingestion/tests/integration/looker/looker_mces_golden_deleted_stateful.json +++ b/metadata-ingestion/tests/integration/looker/looker_mces_golden_deleted_stateful.json @@ -327,20 +327,6 @@ "com.linkedin.pegasus2avro.metadata.snapshot.TagSnapshot": { "urn": "urn:li:tag:Dimension", "aspects": [ - { - "com.linkedin.pegasus2avro.common.Ownership": { - "owners": [ - { - "owner": "urn:li:corpuser:datahub", - "type": "DATAOWNER" - } - ], - "lastModified": { - "time": 0, - "actor": "urn:li:corpuser:unknown" - } - } - }, { "com.linkedin.pegasus2avro.tag.TagProperties": { "name": "Dimension", @@ -360,20 +346,6 @@ "com.linkedin.pegasus2avro.metadata.snapshot.TagSnapshot": { "urn": "urn:li:tag:Temporal", "aspects": [ - { - "com.linkedin.pegasus2avro.common.Ownership": { - "owners": [ - { - "owner": "urn:li:corpuser:datahub", - "type": "DATAOWNER" - } - ], - "lastModified": { - "time": 0, - "actor": "urn:li:corpuser:unknown" - } - } - }, { "com.linkedin.pegasus2avro.tag.TagProperties": { "name": "Temporal", @@ -393,20 +365,6 @@ "com.linkedin.pegasus2avro.metadata.snapshot.TagSnapshot": { "urn": "urn:li:tag:Measure", "aspects": [ - { - "com.linkedin.pegasus2avro.common.Ownership": { - "owners": [ - { - "owner": "urn:li:corpuser:datahub", - "type": "DATAOWNER" - } - ], - "lastModified": { - "time": 0, - "actor": "urn:li:corpuser:unknown" - } - } - }, { "com.linkedin.pegasus2avro.tag.TagProperties": { "name": "Measure", diff --git a/metadata-ingestion/tests/integration/looker/looker_mces_usage_history.json b/metadata-ingestion/tests/integration/looker/looker_mces_usage_history.json index 34bded3cf691e..0778aa0050b00 100644 --- a/metadata-ingestion/tests/integration/looker/looker_mces_usage_history.json +++ b/metadata-ingestion/tests/integration/looker/looker_mces_usage_history.json @@ -279,20 +279,6 @@ "com.linkedin.pegasus2avro.metadata.snapshot.TagSnapshot": { "urn": "urn:li:tag:Dimension", "aspects": [ - { - "com.linkedin.pegasus2avro.common.Ownership": { - "owners": [ - { - "owner": "urn:li:corpuser:datahub", - "type": "DATAOWNER" - } - ], - "lastModified": { - "time": 0, - "actor": "urn:li:corpuser:unknown" - } - } - }, { "com.linkedin.pegasus2avro.tag.TagProperties": { "name": "Dimension", @@ -312,20 +298,6 @@ "com.linkedin.pegasus2avro.metadata.snapshot.TagSnapshot": { "urn": "urn:li:tag:Temporal", "aspects": [ - { - "com.linkedin.pegasus2avro.common.Ownership": { - "owners": [ - { - "owner": "urn:li:corpuser:datahub", - "type": "DATAOWNER" - } - ], - "lastModified": { - "time": 0, - "actor": "urn:li:corpuser:unknown" - } - } - }, { "com.linkedin.pegasus2avro.tag.TagProperties": { "name": "Temporal", @@ -345,20 +317,6 @@ "com.linkedin.pegasus2avro.metadata.snapshot.TagSnapshot": { "urn": "urn:li:tag:Measure", "aspects": [ - { - "com.linkedin.pegasus2avro.common.Ownership": { - "owners": [ - { - "owner": "urn:li:corpuser:datahub", - "type": "DATAOWNER" - } - ], - "lastModified": { - "time": 0, - "actor": "urn:li:corpuser:unknown" - } - } - }, { "com.linkedin.pegasus2avro.tag.TagProperties": { "name": "Measure", diff --git a/metadata-ingestion/tests/integration/lookml/lookml_mces_api_bigquery.json b/metadata-ingestion/tests/integration/lookml/lookml_mces_api_bigquery.json index 238f4c2580cdf..5a0bd4e12fd3a 100644 --- a/metadata-ingestion/tests/integration/lookml/lookml_mces_api_bigquery.json +++ b/metadata-ingestion/tests/integration/lookml/lookml_mces_api_bigquery.json @@ -2121,20 +2121,6 @@ "com.linkedin.pegasus2avro.metadata.snapshot.TagSnapshot": { "urn": "urn:li:tag:Dimension", "aspects": [ - { - "com.linkedin.pegasus2avro.common.Ownership": { - "owners": [ - { - "owner": "urn:li:corpuser:datahub", - "type": "DATAOWNER" - } - ], - "lastModified": { - "time": 0, - "actor": "urn:li:corpuser:unknown" - } - } - }, { "com.linkedin.pegasus2avro.tag.TagProperties": { "name": "Dimension", @@ -2154,20 +2140,6 @@ "com.linkedin.pegasus2avro.metadata.snapshot.TagSnapshot": { "urn": "urn:li:tag:Temporal", "aspects": [ - { - "com.linkedin.pegasus2avro.common.Ownership": { - "owners": [ - { - "owner": "urn:li:corpuser:datahub", - "type": "DATAOWNER" - } - ], - "lastModified": { - "time": 0, - "actor": "urn:li:corpuser:unknown" - } - } - }, { "com.linkedin.pegasus2avro.tag.TagProperties": { "name": "Temporal", @@ -2187,20 +2159,6 @@ "com.linkedin.pegasus2avro.metadata.snapshot.TagSnapshot": { "urn": "urn:li:tag:Measure", "aspects": [ - { - "com.linkedin.pegasus2avro.common.Ownership": { - "owners": [ - { - "owner": "urn:li:corpuser:datahub", - "type": "DATAOWNER" - } - ], - "lastModified": { - "time": 0, - "actor": "urn:li:corpuser:unknown" - } - } - }, { "com.linkedin.pegasus2avro.tag.TagProperties": { "name": "Measure", diff --git a/metadata-ingestion/tests/integration/lookml/lookml_mces_api_hive2.json b/metadata-ingestion/tests/integration/lookml/lookml_mces_api_hive2.json index 45d5d839e9d21..1b0ee3216383c 100644 --- a/metadata-ingestion/tests/integration/lookml/lookml_mces_api_hive2.json +++ b/metadata-ingestion/tests/integration/lookml/lookml_mces_api_hive2.json @@ -2121,20 +2121,6 @@ "com.linkedin.pegasus2avro.metadata.snapshot.TagSnapshot": { "urn": "urn:li:tag:Dimension", "aspects": [ - { - "com.linkedin.pegasus2avro.common.Ownership": { - "owners": [ - { - "owner": "urn:li:corpuser:datahub", - "type": "DATAOWNER" - } - ], - "lastModified": { - "time": 0, - "actor": "urn:li:corpuser:unknown" - } - } - }, { "com.linkedin.pegasus2avro.tag.TagProperties": { "name": "Dimension", @@ -2154,20 +2140,6 @@ "com.linkedin.pegasus2avro.metadata.snapshot.TagSnapshot": { "urn": "urn:li:tag:Temporal", "aspects": [ - { - "com.linkedin.pegasus2avro.common.Ownership": { - "owners": [ - { - "owner": "urn:li:corpuser:datahub", - "type": "DATAOWNER" - } - ], - "lastModified": { - "time": 0, - "actor": "urn:li:corpuser:unknown" - } - } - }, { "com.linkedin.pegasus2avro.tag.TagProperties": { "name": "Temporal", @@ -2187,20 +2159,6 @@ "com.linkedin.pegasus2avro.metadata.snapshot.TagSnapshot": { "urn": "urn:li:tag:Measure", "aspects": [ - { - "com.linkedin.pegasus2avro.common.Ownership": { - "owners": [ - { - "owner": "urn:li:corpuser:datahub", - "type": "DATAOWNER" - } - ], - "lastModified": { - "time": 0, - "actor": "urn:li:corpuser:unknown" - } - } - }, { "com.linkedin.pegasus2avro.tag.TagProperties": { "name": "Measure", diff --git a/metadata-ingestion/tests/integration/lookml/lookml_mces_badsql_parser.json b/metadata-ingestion/tests/integration/lookml/lookml_mces_badsql_parser.json index 187cedaefb6b2..b960ba581e6b5 100644 --- a/metadata-ingestion/tests/integration/lookml/lookml_mces_badsql_parser.json +++ b/metadata-ingestion/tests/integration/lookml/lookml_mces_badsql_parser.json @@ -2004,20 +2004,6 @@ "com.linkedin.pegasus2avro.metadata.snapshot.TagSnapshot": { "urn": "urn:li:tag:Dimension", "aspects": [ - { - "com.linkedin.pegasus2avro.common.Ownership": { - "owners": [ - { - "owner": "urn:li:corpuser:datahub", - "type": "DATAOWNER" - } - ], - "lastModified": { - "time": 0, - "actor": "urn:li:corpuser:unknown" - } - } - }, { "com.linkedin.pegasus2avro.tag.TagProperties": { "name": "Dimension", @@ -2037,20 +2023,6 @@ "com.linkedin.pegasus2avro.metadata.snapshot.TagSnapshot": { "urn": "urn:li:tag:Temporal", "aspects": [ - { - "com.linkedin.pegasus2avro.common.Ownership": { - "owners": [ - { - "owner": "urn:li:corpuser:datahub", - "type": "DATAOWNER" - } - ], - "lastModified": { - "time": 0, - "actor": "urn:li:corpuser:unknown" - } - } - }, { "com.linkedin.pegasus2avro.tag.TagProperties": { "name": "Temporal", @@ -2070,20 +2042,6 @@ "com.linkedin.pegasus2avro.metadata.snapshot.TagSnapshot": { "urn": "urn:li:tag:Measure", "aspects": [ - { - "com.linkedin.pegasus2avro.common.Ownership": { - "owners": [ - { - "owner": "urn:li:corpuser:datahub", - "type": "DATAOWNER" - } - ], - "lastModified": { - "time": 0, - "actor": "urn:li:corpuser:unknown" - } - } - }, { "com.linkedin.pegasus2avro.tag.TagProperties": { "name": "Measure", diff --git a/metadata-ingestion/tests/integration/lookml/lookml_mces_offline.json b/metadata-ingestion/tests/integration/lookml/lookml_mces_offline.json index c2c879e38f37b..e29292a44c949 100644 --- a/metadata-ingestion/tests/integration/lookml/lookml_mces_offline.json +++ b/metadata-ingestion/tests/integration/lookml/lookml_mces_offline.json @@ -2121,20 +2121,6 @@ "com.linkedin.pegasus2avro.metadata.snapshot.TagSnapshot": { "urn": "urn:li:tag:Dimension", "aspects": [ - { - "com.linkedin.pegasus2avro.common.Ownership": { - "owners": [ - { - "owner": "urn:li:corpuser:datahub", - "type": "DATAOWNER" - } - ], - "lastModified": { - "time": 0, - "actor": "urn:li:corpuser:unknown" - } - } - }, { "com.linkedin.pegasus2avro.tag.TagProperties": { "name": "Dimension", @@ -2154,20 +2140,6 @@ "com.linkedin.pegasus2avro.metadata.snapshot.TagSnapshot": { "urn": "urn:li:tag:Temporal", "aspects": [ - { - "com.linkedin.pegasus2avro.common.Ownership": { - "owners": [ - { - "owner": "urn:li:corpuser:datahub", - "type": "DATAOWNER" - } - ], - "lastModified": { - "time": 0, - "actor": "urn:li:corpuser:unknown" - } - } - }, { "com.linkedin.pegasus2avro.tag.TagProperties": { "name": "Temporal", @@ -2187,20 +2159,6 @@ "com.linkedin.pegasus2avro.metadata.snapshot.TagSnapshot": { "urn": "urn:li:tag:Measure", "aspects": [ - { - "com.linkedin.pegasus2avro.common.Ownership": { - "owners": [ - { - "owner": "urn:li:corpuser:datahub", - "type": "DATAOWNER" - } - ], - "lastModified": { - "time": 0, - "actor": "urn:li:corpuser:unknown" - } - } - }, { "com.linkedin.pegasus2avro.tag.TagProperties": { "name": "Measure", diff --git a/metadata-ingestion/tests/integration/lookml/lookml_mces_offline_deny_pattern.json b/metadata-ingestion/tests/integration/lookml/lookml_mces_offline_deny_pattern.json index c1ac54b0fb588..04ecaecbd4afb 100644 --- a/metadata-ingestion/tests/integration/lookml/lookml_mces_offline_deny_pattern.json +++ b/metadata-ingestion/tests/integration/lookml/lookml_mces_offline_deny_pattern.json @@ -584,20 +584,6 @@ "com.linkedin.pegasus2avro.metadata.snapshot.TagSnapshot": { "urn": "urn:li:tag:Dimension", "aspects": [ - { - "com.linkedin.pegasus2avro.common.Ownership": { - "owners": [ - { - "owner": "urn:li:corpuser:datahub", - "type": "DATAOWNER" - } - ], - "lastModified": { - "time": 0, - "actor": "urn:li:corpuser:unknown" - } - } - }, { "com.linkedin.pegasus2avro.tag.TagProperties": { "name": "Dimension", @@ -617,20 +603,6 @@ "com.linkedin.pegasus2avro.metadata.snapshot.TagSnapshot": { "urn": "urn:li:tag:Temporal", "aspects": [ - { - "com.linkedin.pegasus2avro.common.Ownership": { - "owners": [ - { - "owner": "urn:li:corpuser:datahub", - "type": "DATAOWNER" - } - ], - "lastModified": { - "time": 0, - "actor": "urn:li:corpuser:unknown" - } - } - }, { "com.linkedin.pegasus2avro.tag.TagProperties": { "name": "Temporal", @@ -650,20 +622,6 @@ "com.linkedin.pegasus2avro.metadata.snapshot.TagSnapshot": { "urn": "urn:li:tag:Measure", "aspects": [ - { - "com.linkedin.pegasus2avro.common.Ownership": { - "owners": [ - { - "owner": "urn:li:corpuser:datahub", - "type": "DATAOWNER" - } - ], - "lastModified": { - "time": 0, - "actor": "urn:li:corpuser:unknown" - } - } - }, { "com.linkedin.pegasus2avro.tag.TagProperties": { "name": "Measure", diff --git a/metadata-ingestion/tests/integration/lookml/lookml_mces_offline_platform_instance.json b/metadata-ingestion/tests/integration/lookml/lookml_mces_offline_platform_instance.json index f602ca37b3160..080931ae637bc 100644 --- a/metadata-ingestion/tests/integration/lookml/lookml_mces_offline_platform_instance.json +++ b/metadata-ingestion/tests/integration/lookml/lookml_mces_offline_platform_instance.json @@ -2121,20 +2121,6 @@ "com.linkedin.pegasus2avro.metadata.snapshot.TagSnapshot": { "urn": "urn:li:tag:Dimension", "aspects": [ - { - "com.linkedin.pegasus2avro.common.Ownership": { - "owners": [ - { - "owner": "urn:li:corpuser:datahub", - "type": "DATAOWNER" - } - ], - "lastModified": { - "time": 0, - "actor": "urn:li:corpuser:unknown" - } - } - }, { "com.linkedin.pegasus2avro.tag.TagProperties": { "name": "Dimension", @@ -2154,20 +2140,6 @@ "com.linkedin.pegasus2avro.metadata.snapshot.TagSnapshot": { "urn": "urn:li:tag:Temporal", "aspects": [ - { - "com.linkedin.pegasus2avro.common.Ownership": { - "owners": [ - { - "owner": "urn:li:corpuser:datahub", - "type": "DATAOWNER" - } - ], - "lastModified": { - "time": 0, - "actor": "urn:li:corpuser:unknown" - } - } - }, { "com.linkedin.pegasus2avro.tag.TagProperties": { "name": "Temporal", @@ -2187,20 +2159,6 @@ "com.linkedin.pegasus2avro.metadata.snapshot.TagSnapshot": { "urn": "urn:li:tag:Measure", "aspects": [ - { - "com.linkedin.pegasus2avro.common.Ownership": { - "owners": [ - { - "owner": "urn:li:corpuser:datahub", - "type": "DATAOWNER" - } - ], - "lastModified": { - "time": 0, - "actor": "urn:li:corpuser:unknown" - } - } - }, { "com.linkedin.pegasus2avro.tag.TagProperties": { "name": "Measure", diff --git a/metadata-ingestion/tests/integration/lookml/lookml_mces_with_external_urls.json b/metadata-ingestion/tests/integration/lookml/lookml_mces_with_external_urls.json index 104bd365669e3..5826c4316b539 100644 --- a/metadata-ingestion/tests/integration/lookml/lookml_mces_with_external_urls.json +++ b/metadata-ingestion/tests/integration/lookml/lookml_mces_with_external_urls.json @@ -2134,20 +2134,6 @@ "com.linkedin.pegasus2avro.metadata.snapshot.TagSnapshot": { "urn": "urn:li:tag:Dimension", "aspects": [ - { - "com.linkedin.pegasus2avro.common.Ownership": { - "owners": [ - { - "owner": "urn:li:corpuser:datahub", - "type": "DATAOWNER" - } - ], - "lastModified": { - "time": 0, - "actor": "urn:li:corpuser:unknown" - } - } - }, { "com.linkedin.pegasus2avro.tag.TagProperties": { "name": "Dimension", @@ -2167,20 +2153,6 @@ "com.linkedin.pegasus2avro.metadata.snapshot.TagSnapshot": { "urn": "urn:li:tag:Temporal", "aspects": [ - { - "com.linkedin.pegasus2avro.common.Ownership": { - "owners": [ - { - "owner": "urn:li:corpuser:datahub", - "type": "DATAOWNER" - } - ], - "lastModified": { - "time": 0, - "actor": "urn:li:corpuser:unknown" - } - } - }, { "com.linkedin.pegasus2avro.tag.TagProperties": { "name": "Temporal", @@ -2200,20 +2172,6 @@ "com.linkedin.pegasus2avro.metadata.snapshot.TagSnapshot": { "urn": "urn:li:tag:Measure", "aspects": [ - { - "com.linkedin.pegasus2avro.common.Ownership": { - "owners": [ - { - "owner": "urn:li:corpuser:datahub", - "type": "DATAOWNER" - } - ], - "lastModified": { - "time": 0, - "actor": "urn:li:corpuser:unknown" - } - } - }, { "com.linkedin.pegasus2avro.tag.TagProperties": { "name": "Measure", diff --git a/metadata-ingestion/tests/integration/lookml/lookml_reachable_views.json b/metadata-ingestion/tests/integration/lookml/lookml_reachable_views.json index 37a6c94c6952e..53d1ec0229de1 100644 --- a/metadata-ingestion/tests/integration/lookml/lookml_reachable_views.json +++ b/metadata-ingestion/tests/integration/lookml/lookml_reachable_views.json @@ -681,20 +681,6 @@ "com.linkedin.pegasus2avro.metadata.snapshot.TagSnapshot": { "urn": "urn:li:tag:Dimension", "aspects": [ - { - "com.linkedin.pegasus2avro.common.Ownership": { - "owners": [ - { - "owner": "urn:li:corpuser:datahub", - "type": "DATAOWNER" - } - ], - "lastModified": { - "time": 0, - "actor": "urn:li:corpuser:unknown" - } - } - }, { "com.linkedin.pegasus2avro.tag.TagProperties": { "name": "Dimension", @@ -714,20 +700,6 @@ "com.linkedin.pegasus2avro.metadata.snapshot.TagSnapshot": { "urn": "urn:li:tag:Temporal", "aspects": [ - { - "com.linkedin.pegasus2avro.common.Ownership": { - "owners": [ - { - "owner": "urn:li:corpuser:datahub", - "type": "DATAOWNER" - } - ], - "lastModified": { - "time": 0, - "actor": "urn:li:corpuser:unknown" - } - } - }, { "com.linkedin.pegasus2avro.tag.TagProperties": { "name": "Temporal", @@ -747,20 +719,6 @@ "com.linkedin.pegasus2avro.metadata.snapshot.TagSnapshot": { "urn": "urn:li:tag:Measure", "aspects": [ - { - "com.linkedin.pegasus2avro.common.Ownership": { - "owners": [ - { - "owner": "urn:li:corpuser:datahub", - "type": "DATAOWNER" - } - ], - "lastModified": { - "time": 0, - "actor": "urn:li:corpuser:unknown" - } - } - }, { "com.linkedin.pegasus2avro.tag.TagProperties": { "name": "Measure", diff --git a/metadata-ingestion/tests/integration/powerbi/test_m_parser.py b/metadata-ingestion/tests/integration/powerbi/test_m_parser.py index e3cc6c8101650..b6cb578217a2c 100644 --- a/metadata-ingestion/tests/integration/powerbi/test_m_parser.py +++ b/metadata-ingestion/tests/integration/powerbi/test_m_parser.py @@ -17,7 +17,6 @@ ) from datahub.ingestion.source.powerbi.m_query import parser, resolver, tree_function from datahub.ingestion.source.powerbi.m_query.resolver import DataPlatformTable, Lineage -from datahub.utilities.sqlglot_lineage import ColumnLineageInfo, DownstreamColumnRef pytestmark = pytest.mark.integration_batch_2 @@ -742,75 +741,25 @@ def test_sqlglot_parser(): == "urn:li:dataset:(urn:li:dataPlatform:snowflake,sales_deployment.operations_analytics.transformed_prod.v_sme_unit_targets,PROD)" ) - assert lineage[0].column_lineage == [ - ColumnLineageInfo( - downstream=DownstreamColumnRef(table=None, column="client_director"), - upstreams=[], - logic=None, - ), - ColumnLineageInfo( - downstream=DownstreamColumnRef(table=None, column="tier"), - upstreams=[], - logic=None, - ), - ColumnLineageInfo( - downstream=DownstreamColumnRef(table=None, column='upper("manager")'), - upstreams=[], - logic=None, - ), - ColumnLineageInfo( - downstream=DownstreamColumnRef(table=None, column="team_type"), - upstreams=[], - logic=None, - ), - ColumnLineageInfo( - downstream=DownstreamColumnRef(table=None, column="date_target"), - upstreams=[], - logic=None, - ), - ColumnLineageInfo( - downstream=DownstreamColumnRef(table=None, column="monthid"), - upstreams=[], - logic=None, - ), - ColumnLineageInfo( - downstream=DownstreamColumnRef(table=None, column="target_team"), - upstreams=[], - logic=None, - ), - ColumnLineageInfo( - downstream=DownstreamColumnRef(table=None, column="seller_email"), - upstreams=[], - logic=None, - ), - ColumnLineageInfo( - downstream=DownstreamColumnRef(table=None, column="agent_key"), - upstreams=[], - logic=None, - ), - ColumnLineageInfo( - downstream=DownstreamColumnRef(table=None, column="sme_quota"), - upstreams=[], - logic=None, - ), - ColumnLineageInfo( - downstream=DownstreamColumnRef(table=None, column="revenue_quota"), - upstreams=[], - logic=None, - ), - ColumnLineageInfo( - downstream=DownstreamColumnRef(table=None, column="service_quota"), - upstreams=[], - logic=None, - ), - ColumnLineageInfo( - downstream=DownstreamColumnRef(table=None, column="bl_target"), - upstreams=[], - logic=None, - ), - ColumnLineageInfo( - downstream=DownstreamColumnRef(table=None, column="software_quota"), - upstreams=[], - logic=None, - ), + # TODO: None of these columns have upstreams? + # That doesn't seem right - we probably need to add fake schemas for the two tables above. + cols = [ + "client_director", + "tier", + 'upper("manager")', + "team_type", + "date_target", + "monthid", + "target_team", + "seller_email", + "agent_key", + "sme_quota", + "revenue_quota", + "service_quota", + "bl_target", + "software_quota", ] + for i, column in enumerate(cols): + assert lineage[0].column_lineage[i].downstream.table is None + assert lineage[0].column_lineage[i].downstream.column == column + assert lineage[0].column_lineage[i].upstreams == [] diff --git a/metadata-ingestion/tests/unit/sql_parsing/goldens/test_bigquery_create_view_with_cte.json b/metadata-ingestion/tests/unit/sql_parsing/goldens/test_bigquery_create_view_with_cte.json index e50d944ce72e3..f0175b4dc8892 100644 --- a/metadata-ingestion/tests/unit/sql_parsing/goldens/test_bigquery_create_view_with_cte.json +++ b/metadata-ingestion/tests/unit/sql_parsing/goldens/test_bigquery_create_view_with_cte.json @@ -12,7 +12,13 @@ { "downstream": { "table": "urn:li:dataset:(urn:li:dataPlatform:bigquery,my-proj-2.dataset.my_view,PROD)", - "column": "col5" + "column": "col5", + "column_type": { + "type": { + "com.linkedin.pegasus2avro.schema.StringType": {} + } + }, + "native_column_type": "TEXT" }, "upstreams": [ { @@ -24,7 +30,13 @@ { "downstream": { "table": "urn:li:dataset:(urn:li:dataPlatform:bigquery,my-proj-2.dataset.my_view,PROD)", - "column": "col1" + "column": "col1", + "column_type": { + "type": { + "com.linkedin.pegasus2avro.schema.StringType": {} + } + }, + "native_column_type": "TEXT" }, "upstreams": [ { @@ -36,7 +48,13 @@ { "downstream": { "table": "urn:li:dataset:(urn:li:dataPlatform:bigquery,my-proj-2.dataset.my_view,PROD)", - "column": "col2" + "column": "col2", + "column_type": { + "type": { + "com.linkedin.pegasus2avro.schema.StringType": {} + } + }, + "native_column_type": "TEXT" }, "upstreams": [ { @@ -48,7 +66,13 @@ { "downstream": { "table": "urn:li:dataset:(urn:li:dataPlatform:bigquery,my-proj-2.dataset.my_view,PROD)", - "column": "col3" + "column": "col3", + "column_type": { + "type": { + "com.linkedin.pegasus2avro.schema.StringType": {} + } + }, + "native_column_type": "TEXT" }, "upstreams": [ { diff --git a/metadata-ingestion/tests/unit/sql_parsing/goldens/test_bigquery_from_sharded_table_wildcard.json b/metadata-ingestion/tests/unit/sql_parsing/goldens/test_bigquery_from_sharded_table_wildcard.json index 78591286feb50..b7df5444987f2 100644 --- a/metadata-ingestion/tests/unit/sql_parsing/goldens/test_bigquery_from_sharded_table_wildcard.json +++ b/metadata-ingestion/tests/unit/sql_parsing/goldens/test_bigquery_from_sharded_table_wildcard.json @@ -8,7 +8,13 @@ { "downstream": { "table": null, - "column": "col1" + "column": "col1", + "column_type": { + "type": { + "com.linkedin.pegasus2avro.schema.StringType": {} + } + }, + "native_column_type": "TEXT" }, "upstreams": [ { @@ -20,7 +26,13 @@ { "downstream": { "table": null, - "column": "col2" + "column": "col2", + "column_type": { + "type": { + "com.linkedin.pegasus2avro.schema.StringType": {} + } + }, + "native_column_type": "TEXT" }, "upstreams": [ { diff --git a/metadata-ingestion/tests/unit/sql_parsing/goldens/test_bigquery_nested_subqueries.json b/metadata-ingestion/tests/unit/sql_parsing/goldens/test_bigquery_nested_subqueries.json index 0e93d31fbb6a6..67e306bebf545 100644 --- a/metadata-ingestion/tests/unit/sql_parsing/goldens/test_bigquery_nested_subqueries.json +++ b/metadata-ingestion/tests/unit/sql_parsing/goldens/test_bigquery_nested_subqueries.json @@ -8,7 +8,13 @@ { "downstream": { "table": null, - "column": "col1" + "column": "col1", + "column_type": { + "type": { + "com.linkedin.pegasus2avro.schema.StringType": {} + } + }, + "native_column_type": "TEXT" }, "upstreams": [ { @@ -20,7 +26,13 @@ { "downstream": { "table": null, - "column": "col2" + "column": "col2", + "column_type": { + "type": { + "com.linkedin.pegasus2avro.schema.StringType": {} + } + }, + "native_column_type": "TEXT" }, "upstreams": [ { diff --git a/metadata-ingestion/tests/unit/sql_parsing/goldens/test_bigquery_sharded_table_normalization.json b/metadata-ingestion/tests/unit/sql_parsing/goldens/test_bigquery_sharded_table_normalization.json index 78591286feb50..b7df5444987f2 100644 --- a/metadata-ingestion/tests/unit/sql_parsing/goldens/test_bigquery_sharded_table_normalization.json +++ b/metadata-ingestion/tests/unit/sql_parsing/goldens/test_bigquery_sharded_table_normalization.json @@ -8,7 +8,13 @@ { "downstream": { "table": null, - "column": "col1" + "column": "col1", + "column_type": { + "type": { + "com.linkedin.pegasus2avro.schema.StringType": {} + } + }, + "native_column_type": "TEXT" }, "upstreams": [ { @@ -20,7 +26,13 @@ { "downstream": { "table": null, - "column": "col2" + "column": "col2", + "column_type": { + "type": { + "com.linkedin.pegasus2avro.schema.StringType": {} + } + }, + "native_column_type": "TEXT" }, "upstreams": [ { diff --git a/metadata-ingestion/tests/unit/sql_parsing/goldens/test_bigquery_star_with_replace.json b/metadata-ingestion/tests/unit/sql_parsing/goldens/test_bigquery_star_with_replace.json index 17a801a63e3ff..b393b2445d6c4 100644 --- a/metadata-ingestion/tests/unit/sql_parsing/goldens/test_bigquery_star_with_replace.json +++ b/metadata-ingestion/tests/unit/sql_parsing/goldens/test_bigquery_star_with_replace.json @@ -10,7 +10,13 @@ { "downstream": { "table": "urn:li:dataset:(urn:li:dataPlatform:bigquery,my-project.my-dataset.test_table,PROD)", - "column": "col1" + "column": "col1", + "column_type": { + "type": { + "com.linkedin.pegasus2avro.schema.StringType": {} + } + }, + "native_column_type": "TEXT" }, "upstreams": [ { @@ -22,7 +28,13 @@ { "downstream": { "table": "urn:li:dataset:(urn:li:dataPlatform:bigquery,my-project.my-dataset.test_table,PROD)", - "column": "col2" + "column": "col2", + "column_type": { + "type": { + "com.linkedin.pegasus2avro.schema.StringType": {} + } + }, + "native_column_type": "TEXT" }, "upstreams": [ { @@ -34,7 +46,13 @@ { "downstream": { "table": "urn:li:dataset:(urn:li:dataPlatform:bigquery,my-project.my-dataset.test_table,PROD)", - "column": "something" + "column": "something", + "column_type": { + "type": { + "com.linkedin.pegasus2avro.schema.StringType": {} + } + }, + "native_column_type": "TEXT" }, "upstreams": [ { diff --git a/metadata-ingestion/tests/unit/sql_parsing/goldens/test_bigquery_view_from_union.json b/metadata-ingestion/tests/unit/sql_parsing/goldens/test_bigquery_view_from_union.json index fd8a586ac74ac..53fb94300e804 100644 --- a/metadata-ingestion/tests/unit/sql_parsing/goldens/test_bigquery_view_from_union.json +++ b/metadata-ingestion/tests/unit/sql_parsing/goldens/test_bigquery_view_from_union.json @@ -11,7 +11,13 @@ { "downstream": { "table": "urn:li:dataset:(urn:li:dataPlatform:bigquery,my_view,PROD)", - "column": "col1" + "column": "col1", + "column_type": { + "type": { + "com.linkedin.pegasus2avro.schema.StringType": {} + } + }, + "native_column_type": "TEXT" }, "upstreams": [ { @@ -27,7 +33,13 @@ { "downstream": { "table": "urn:li:dataset:(urn:li:dataPlatform:bigquery,my_view,PROD)", - "column": "col2" + "column": "col2", + "column_type": { + "type": { + "com.linkedin.pegasus2avro.schema.StringType": {} + } + }, + "native_column_type": "TEXT" }, "upstreams": [ { diff --git a/metadata-ingestion/tests/unit/sql_parsing/goldens/test_create_view_as_select.json b/metadata-ingestion/tests/unit/sql_parsing/goldens/test_create_view_as_select.json index 1ca56840531e4..ff452467aa5bd 100644 --- a/metadata-ingestion/tests/unit/sql_parsing/goldens/test_create_view_as_select.json +++ b/metadata-ingestion/tests/unit/sql_parsing/goldens/test_create_view_as_select.json @@ -10,7 +10,9 @@ { "downstream": { "table": "urn:li:dataset:(urn:li:dataPlatform:oracle,vsal,PROD)", - "column": "Department" + "column": "Department", + "column_type": null, + "native_column_type": null }, "upstreams": [ { @@ -22,14 +24,22 @@ { "downstream": { "table": "urn:li:dataset:(urn:li:dataPlatform:oracle,vsal,PROD)", - "column": "Employees" + "column": "Employees", + "column_type": { + "type": { + "com.linkedin.pegasus2avro.schema.NumberType": {} + } + }, + "native_column_type": "BIGINT" }, "upstreams": [] }, { "downstream": { "table": "urn:li:dataset:(urn:li:dataPlatform:oracle,vsal,PROD)", - "column": "Salary" + "column": "Salary", + "column_type": null, + "native_column_type": null }, "upstreams": [ { diff --git a/metadata-ingestion/tests/unit/sql_parsing/goldens/test_expand_select_star_basic.json b/metadata-ingestion/tests/unit/sql_parsing/goldens/test_expand_select_star_basic.json index e241bdd08e243..eecb2265eaec5 100644 --- a/metadata-ingestion/tests/unit/sql_parsing/goldens/test_expand_select_star_basic.json +++ b/metadata-ingestion/tests/unit/sql_parsing/goldens/test_expand_select_star_basic.json @@ -8,7 +8,13 @@ { "downstream": { "table": null, - "column": "total_agg" + "column": "total_agg", + "column_type": { + "type": { + "com.linkedin.pegasus2avro.schema.NumberType": {} + } + }, + "native_column_type": "DOUBLE" }, "upstreams": [ { @@ -20,7 +26,13 @@ { "downstream": { "table": null, - "column": "orderkey" + "column": "orderkey", + "column_type": { + "type": { + "com.linkedin.pegasus2avro.schema.NumberType": {} + } + }, + "native_column_type": "DECIMAL" }, "upstreams": [ { @@ -32,7 +44,13 @@ { "downstream": { "table": null, - "column": "custkey" + "column": "custkey", + "column_type": { + "type": { + "com.linkedin.pegasus2avro.schema.NumberType": {} + } + }, + "native_column_type": "DECIMAL" }, "upstreams": [ { @@ -44,7 +62,13 @@ { "downstream": { "table": null, - "column": "orderstatus" + "column": "orderstatus", + "column_type": { + "type": { + "com.linkedin.pegasus2avro.schema.StringType": {} + } + }, + "native_column_type": "TEXT" }, "upstreams": [ { @@ -56,7 +80,13 @@ { "downstream": { "table": null, - "column": "totalprice" + "column": "totalprice", + "column_type": { + "type": { + "com.linkedin.pegasus2avro.schema.NumberType": {} + } + }, + "native_column_type": "FLOAT" }, "upstreams": [ { @@ -68,7 +98,13 @@ { "downstream": { "table": null, - "column": "orderdate" + "column": "orderdate", + "column_type": { + "type": { + "com.linkedin.pegasus2avro.schema.DateType": {} + } + }, + "native_column_type": "DATE" }, "upstreams": [ { @@ -80,7 +116,13 @@ { "downstream": { "table": null, - "column": "orderpriority" + "column": "orderpriority", + "column_type": { + "type": { + "com.linkedin.pegasus2avro.schema.StringType": {} + } + }, + "native_column_type": "TEXT" }, "upstreams": [ { @@ -92,7 +134,13 @@ { "downstream": { "table": null, - "column": "clerk" + "column": "clerk", + "column_type": { + "type": { + "com.linkedin.pegasus2avro.schema.StringType": {} + } + }, + "native_column_type": "TEXT" }, "upstreams": [ { @@ -104,7 +152,13 @@ { "downstream": { "table": null, - "column": "shippriority" + "column": "shippriority", + "column_type": { + "type": { + "com.linkedin.pegasus2avro.schema.NumberType": {} + } + }, + "native_column_type": "DECIMAL" }, "upstreams": [ { @@ -116,7 +170,13 @@ { "downstream": { "table": null, - "column": "comment" + "column": "comment", + "column_type": { + "type": { + "com.linkedin.pegasus2avro.schema.StringType": {} + } + }, + "native_column_type": "TEXT" }, "upstreams": [ { diff --git a/metadata-ingestion/tests/unit/sql_parsing/goldens/test_insert_as_select.json b/metadata-ingestion/tests/unit/sql_parsing/goldens/test_insert_as_select.json index d7264fd2db6b2..326db47e7ab33 100644 --- a/metadata-ingestion/tests/unit/sql_parsing/goldens/test_insert_as_select.json +++ b/metadata-ingestion/tests/unit/sql_parsing/goldens/test_insert_as_select.json @@ -18,21 +18,27 @@ { "downstream": { "table": "urn:li:dataset:(urn:li:dataPlatform:hive,query72,PROD)", - "column": "i_item_desc" + "column": "i_item_desc", + "column_type": null, + "native_column_type": null }, "upstreams": [] }, { "downstream": { "table": "urn:li:dataset:(urn:li:dataPlatform:hive,query72,PROD)", - "column": "w_warehouse_name" + "column": "w_warehouse_name", + "column_type": null, + "native_column_type": null }, "upstreams": [] }, { "downstream": { "table": "urn:li:dataset:(urn:li:dataPlatform:hive,query72,PROD)", - "column": "d_week_seq" + "column": "d_week_seq", + "column_type": null, + "native_column_type": null }, "upstreams": [ { @@ -44,7 +50,13 @@ { "downstream": { "table": "urn:li:dataset:(urn:li:dataPlatform:hive,query72,PROD)", - "column": "no_promo" + "column": "no_promo", + "column_type": { + "type": { + "com.linkedin.pegasus2avro.schema.NumberType": {} + } + }, + "native_column_type": "BIGINT" }, "upstreams": [ { @@ -56,7 +68,13 @@ { "downstream": { "table": "urn:li:dataset:(urn:li:dataPlatform:hive,query72,PROD)", - "column": "promo" + "column": "promo", + "column_type": { + "type": { + "com.linkedin.pegasus2avro.schema.NumberType": {} + } + }, + "native_column_type": "BIGINT" }, "upstreams": [ { @@ -68,7 +86,13 @@ { "downstream": { "table": "urn:li:dataset:(urn:li:dataPlatform:hive,query72,PROD)", - "column": "total_cnt" + "column": "total_cnt", + "column_type": { + "type": { + "com.linkedin.pegasus2avro.schema.NumberType": {} + } + }, + "native_column_type": "BIGINT" }, "upstreams": [] } diff --git a/metadata-ingestion/tests/unit/sql_parsing/goldens/test_select_ambiguous_column_no_schema.json b/metadata-ingestion/tests/unit/sql_parsing/goldens/test_select_ambiguous_column_no_schema.json index 10f5ee20b0c1f..b5fd5eebeb1b1 100644 --- a/metadata-ingestion/tests/unit/sql_parsing/goldens/test_select_ambiguous_column_no_schema.json +++ b/metadata-ingestion/tests/unit/sql_parsing/goldens/test_select_ambiguous_column_no_schema.json @@ -9,21 +9,27 @@ { "downstream": { "table": null, - "column": "a" + "column": "a", + "column_type": null, + "native_column_type": null }, "upstreams": [] }, { "downstream": { "table": null, - "column": "b" + "column": "b", + "column_type": null, + "native_column_type": null }, "upstreams": [] }, { "downstream": { "table": null, - "column": "c" + "column": "c", + "column_type": null, + "native_column_type": null }, "upstreams": [] } diff --git a/metadata-ingestion/tests/unit/sql_parsing/goldens/test_select_count.json b/metadata-ingestion/tests/unit/sql_parsing/goldens/test_select_count.json index 9f6eeae46c294..a67c944822138 100644 --- a/metadata-ingestion/tests/unit/sql_parsing/goldens/test_select_count.json +++ b/metadata-ingestion/tests/unit/sql_parsing/goldens/test_select_count.json @@ -8,7 +8,13 @@ { "downstream": { "table": null, - "column": "COUNT(`fact_complaint_snapshot`.`etl_data_dt_id`)" + "column": "COUNT(`fact_complaint_snapshot`.`etl_data_dt_id`)", + "column_type": { + "type": { + "com.linkedin.pegasus2avro.schema.NumberType": {} + } + }, + "native_column_type": "BIGINT" }, "upstreams": [ { diff --git a/metadata-ingestion/tests/unit/sql_parsing/goldens/test_select_from_struct_subfields.json b/metadata-ingestion/tests/unit/sql_parsing/goldens/test_select_from_struct_subfields.json index 109de96180422..5ad847e252497 100644 --- a/metadata-ingestion/tests/unit/sql_parsing/goldens/test_select_from_struct_subfields.json +++ b/metadata-ingestion/tests/unit/sql_parsing/goldens/test_select_from_struct_subfields.json @@ -8,7 +8,13 @@ { "downstream": { "table": null, - "column": "post_id" + "column": "post_id", + "column_type": { + "type": { + "com.linkedin.pegasus2avro.schema.NumberType": {} + } + }, + "native_column_type": "DECIMAL" }, "upstreams": [ { @@ -20,7 +26,9 @@ { "downstream": { "table": null, - "column": "id" + "column": "id", + "column_type": null, + "native_column_type": null }, "upstreams": [ { @@ -32,7 +40,9 @@ { "downstream": { "table": null, - "column": "min_metric" + "column": "min_metric", + "column_type": null, + "native_column_type": null }, "upstreams": [ { diff --git a/metadata-ingestion/tests/unit/sql_parsing/goldens/test_select_from_union.json b/metadata-ingestion/tests/unit/sql_parsing/goldens/test_select_from_union.json index 2340b2e95b0d0..902aa010c8afc 100644 --- a/metadata-ingestion/tests/unit/sql_parsing/goldens/test_select_from_union.json +++ b/metadata-ingestion/tests/unit/sql_parsing/goldens/test_select_from_union.json @@ -9,14 +9,26 @@ { "downstream": { "table": null, - "column": "label" + "column": "label", + "column_type": { + "type": { + "com.linkedin.pegasus2avro.schema.StringType": {} + } + }, + "native_column_type": "VARCHAR" }, "upstreams": [] }, { "downstream": { "table": null, - "column": "total_agg" + "column": "total_agg", + "column_type": { + "type": { + "com.linkedin.pegasus2avro.schema.NumberType": {} + } + }, + "native_column_type": "DOUBLE" }, "upstreams": [ { diff --git a/metadata-ingestion/tests/unit/sql_parsing/goldens/test_select_max.json b/metadata-ingestion/tests/unit/sql_parsing/goldens/test_select_max.json index 326c07d332c26..6ea88f45847ce 100644 --- a/metadata-ingestion/tests/unit/sql_parsing/goldens/test_select_max.json +++ b/metadata-ingestion/tests/unit/sql_parsing/goldens/test_select_max.json @@ -8,7 +8,9 @@ { "downstream": { "table": null, - "column": "max_col" + "column": "max_col", + "column_type": null, + "native_column_type": null }, "upstreams": [ { diff --git a/metadata-ingestion/tests/unit/sql_parsing/goldens/test_select_with_ctes.json b/metadata-ingestion/tests/unit/sql_parsing/goldens/test_select_with_ctes.json index 3e02314d6e8c3..67e9fd2d21a0e 100644 --- a/metadata-ingestion/tests/unit/sql_parsing/goldens/test_select_with_ctes.json +++ b/metadata-ingestion/tests/unit/sql_parsing/goldens/test_select_with_ctes.json @@ -9,7 +9,9 @@ { "downstream": { "table": null, - "column": "COL1" + "column": "COL1", + "column_type": null, + "native_column_type": null }, "upstreams": [ { @@ -21,7 +23,9 @@ { "downstream": { "table": null, - "column": "COL3" + "column": "COL3", + "column_type": null, + "native_column_type": null }, "upstreams": [ { diff --git a/metadata-ingestion/tests/unit/sql_parsing/goldens/test_select_with_full_col_name.json b/metadata-ingestion/tests/unit/sql_parsing/goldens/test_select_with_full_col_name.json index c12ad23b2f03b..6ee3d2e61c39b 100644 --- a/metadata-ingestion/tests/unit/sql_parsing/goldens/test_select_with_full_col_name.json +++ b/metadata-ingestion/tests/unit/sql_parsing/goldens/test_select_with_full_col_name.json @@ -8,7 +8,13 @@ { "downstream": { "table": null, - "column": "post_id" + "column": "post_id", + "column_type": { + "type": { + "com.linkedin.pegasus2avro.schema.NumberType": {} + } + }, + "native_column_type": "DECIMAL" }, "upstreams": [ { @@ -20,7 +26,9 @@ { "downstream": { "table": null, - "column": "id" + "column": "id", + "column_type": null, + "native_column_type": null }, "upstreams": [ { diff --git a/metadata-ingestion/tests/unit/sql_parsing/goldens/test_snowflake_case_statement.json b/metadata-ingestion/tests/unit/sql_parsing/goldens/test_snowflake_case_statement.json index 64cd80e9a2d69..a876824127ec1 100644 --- a/metadata-ingestion/tests/unit/sql_parsing/goldens/test_snowflake_case_statement.json +++ b/metadata-ingestion/tests/unit/sql_parsing/goldens/test_snowflake_case_statement.json @@ -8,7 +8,13 @@ { "downstream": { "table": null, - "column": "total_price_category" + "column": "total_price_category", + "column_type": { + "type": { + "com.linkedin.pegasus2avro.schema.StringType": {} + } + }, + "native_column_type": "VARCHAR" }, "upstreams": [ { @@ -20,7 +26,13 @@ { "downstream": { "table": null, - "column": "total_price_success" + "column": "total_price_success", + "column_type": { + "type": { + "com.linkedin.pegasus2avro.schema.NumberType": {} + } + }, + "native_column_type": "FLOAT" }, "upstreams": [ { diff --git a/metadata-ingestion/tests/unit/sql_parsing/goldens/test_snowflake_column_cast.json b/metadata-ingestion/tests/unit/sql_parsing/goldens/test_snowflake_column_cast.json new file mode 100644 index 0000000000000..7545e2b3269dc --- /dev/null +++ b/metadata-ingestion/tests/unit/sql_parsing/goldens/test_snowflake_column_cast.json @@ -0,0 +1,63 @@ +{ + "query_type": "SELECT", + "in_tables": [ + "urn:li:dataset:(urn:li:dataPlatform:snowflake,snowflake_sample_data.tpch_sf1.orders,PROD)" + ], + "out_tables": [], + "column_lineage": [ + { + "downstream": { + "table": null, + "column": "orderkey", + "column_type": { + "type": { + "com.linkedin.pegasus2avro.schema.NumberType": {} + } + }, + "native_column_type": "DECIMAL(20, 0)" + }, + "upstreams": [ + { + "table": "urn:li:dataset:(urn:li:dataPlatform:snowflake,snowflake_sample_data.tpch_sf1.orders,PROD)", + "column": "o_orderkey" + } + ] + }, + { + "downstream": { + "table": null, + "column": "total_cast_int", + "column_type": { + "type": { + "com.linkedin.pegasus2avro.schema.NumberType": {} + } + }, + "native_column_type": "INT" + }, + "upstreams": [ + { + "table": "urn:li:dataset:(urn:li:dataPlatform:snowflake,snowflake_sample_data.tpch_sf1.orders,PROD)", + "column": "o_totalprice" + } + ] + }, + { + "downstream": { + "table": null, + "column": "total_cast_float", + "column_type": { + "type": { + "com.linkedin.pegasus2avro.schema.NumberType": {} + } + }, + "native_column_type": "DECIMAL(16, 4)" + }, + "upstreams": [ + { + "table": "urn:li:dataset:(urn:li:dataPlatform:snowflake,snowflake_sample_data.tpch_sf1.orders,PROD)", + "column": "o_totalprice" + } + ] + } + ] +} \ No newline at end of file diff --git a/metadata-ingestion/tests/unit/sql_parsing/goldens/test_snowflake_column_normalization.json b/metadata-ingestion/tests/unit/sql_parsing/goldens/test_snowflake_column_normalization.json index 7b22a46757e39..84e6b053000f1 100644 --- a/metadata-ingestion/tests/unit/sql_parsing/goldens/test_snowflake_column_normalization.json +++ b/metadata-ingestion/tests/unit/sql_parsing/goldens/test_snowflake_column_normalization.json @@ -8,7 +8,13 @@ { "downstream": { "table": null, - "column": "total_agg" + "column": "total_agg", + "column_type": { + "type": { + "com.linkedin.pegasus2avro.schema.NumberType": {} + } + }, + "native_column_type": "DOUBLE" }, "upstreams": [ { @@ -20,7 +26,13 @@ { "downstream": { "table": null, - "column": "total_avg" + "column": "total_avg", + "column_type": { + "type": { + "com.linkedin.pegasus2avro.schema.NumberType": {} + } + }, + "native_column_type": "DOUBLE" }, "upstreams": [ { @@ -32,7 +44,13 @@ { "downstream": { "table": null, - "column": "total_min" + "column": "total_min", + "column_type": { + "type": { + "com.linkedin.pegasus2avro.schema.NumberType": {} + } + }, + "native_column_type": "FLOAT" }, "upstreams": [ { @@ -44,7 +62,13 @@ { "downstream": { "table": null, - "column": "total_max" + "column": "total_max", + "column_type": { + "type": { + "com.linkedin.pegasus2avro.schema.NumberType": {} + } + }, + "native_column_type": "FLOAT" }, "upstreams": [ { diff --git a/metadata-ingestion/tests/unit/sql_parsing/goldens/test_snowflake_ctas_column_normalization.json b/metadata-ingestion/tests/unit/sql_parsing/goldens/test_snowflake_ctas_column_normalization.json index c912d99a3a8a3..39c94cf83c561 100644 --- a/metadata-ingestion/tests/unit/sql_parsing/goldens/test_snowflake_ctas_column_normalization.json +++ b/metadata-ingestion/tests/unit/sql_parsing/goldens/test_snowflake_ctas_column_normalization.json @@ -10,7 +10,13 @@ { "downstream": { "table": "urn:li:dataset:(urn:li:dataPlatform:snowflake,snowflake_sample_data.tpch_sf1.orders_normalized,PROD)", - "column": "Total_Agg" + "column": "Total_Agg", + "column_type": { + "type": { + "com.linkedin.pegasus2avro.schema.NumberType": {} + } + }, + "native_column_type": "DOUBLE" }, "upstreams": [ { @@ -22,7 +28,13 @@ { "downstream": { "table": "urn:li:dataset:(urn:li:dataPlatform:snowflake,snowflake_sample_data.tpch_sf1.orders_normalized,PROD)", - "column": "total_avg" + "column": "total_avg", + "column_type": { + "type": { + "com.linkedin.pegasus2avro.schema.NumberType": {} + } + }, + "native_column_type": "DOUBLE" }, "upstreams": [ { @@ -34,7 +46,13 @@ { "downstream": { "table": "urn:li:dataset:(urn:li:dataPlatform:snowflake,snowflake_sample_data.tpch_sf1.orders_normalized,PROD)", - "column": "TOTAL_MIN" + "column": "TOTAL_MIN", + "column_type": { + "type": { + "com.linkedin.pegasus2avro.schema.NumberType": {} + } + }, + "native_column_type": "FLOAT" }, "upstreams": [ { @@ -46,7 +64,13 @@ { "downstream": { "table": "urn:li:dataset:(urn:li:dataPlatform:snowflake,snowflake_sample_data.tpch_sf1.orders_normalized,PROD)", - "column": "total_max" + "column": "total_max", + "column_type": { + "type": { + "com.linkedin.pegasus2avro.schema.NumberType": {} + } + }, + "native_column_type": "FLOAT" }, "upstreams": [ { diff --git a/metadata-ingestion/tests/unit/sql_parsing/goldens/test_snowflake_default_normalization.json b/metadata-ingestion/tests/unit/sql_parsing/goldens/test_snowflake_default_normalization.json index 2af308ec60623..dbf5b1b9a4453 100644 --- a/metadata-ingestion/tests/unit/sql_parsing/goldens/test_snowflake_default_normalization.json +++ b/metadata-ingestion/tests/unit/sql_parsing/goldens/test_snowflake_default_normalization.json @@ -11,7 +11,13 @@ { "downstream": { "table": "urn:li:dataset:(urn:li:dataPlatform:snowflake,long_tail_companions.analytics.active_customer_ltv,PROD)", - "column": "user_fk" + "column": "user_fk", + "column_type": { + "type": { + "com.linkedin.pegasus2avro.schema.NumberType": {} + } + }, + "native_column_type": "DECIMAL(38, 0)" }, "upstreams": [ { @@ -23,7 +29,13 @@ { "downstream": { "table": "urn:li:dataset:(urn:li:dataPlatform:snowflake,long_tail_companions.analytics.active_customer_ltv,PROD)", - "column": "email" + "column": "email", + "column_type": { + "type": { + "com.linkedin.pegasus2avro.schema.StringType": {} + } + }, + "native_column_type": "VARCHAR(16777216)" }, "upstreams": [ { @@ -35,7 +47,13 @@ { "downstream": { "table": "urn:li:dataset:(urn:li:dataPlatform:snowflake,long_tail_companions.analytics.active_customer_ltv,PROD)", - "column": "last_purchase_date" + "column": "last_purchase_date", + "column_type": { + "type": { + "com.linkedin.pegasus2avro.schema.DateType": {} + } + }, + "native_column_type": "DATE" }, "upstreams": [ { @@ -47,7 +65,13 @@ { "downstream": { "table": "urn:li:dataset:(urn:li:dataPlatform:snowflake,long_tail_companions.analytics.active_customer_ltv,PROD)", - "column": "lifetime_purchase_amount" + "column": "lifetime_purchase_amount", + "column_type": { + "type": { + "com.linkedin.pegasus2avro.schema.NumberType": {} + } + }, + "native_column_type": "DECIMAL" }, "upstreams": [ { @@ -59,7 +83,13 @@ { "downstream": { "table": "urn:li:dataset:(urn:li:dataPlatform:snowflake,long_tail_companions.analytics.active_customer_ltv,PROD)", - "column": "lifetime_purchase_count" + "column": "lifetime_purchase_count", + "column_type": { + "type": { + "com.linkedin.pegasus2avro.schema.NumberType": {} + } + }, + "native_column_type": "BIGINT" }, "upstreams": [ { @@ -71,7 +101,13 @@ { "downstream": { "table": "urn:li:dataset:(urn:li:dataPlatform:snowflake,long_tail_companions.analytics.active_customer_ltv,PROD)", - "column": "average_purchase_amount" + "column": "average_purchase_amount", + "column_type": { + "type": { + "com.linkedin.pegasus2avro.schema.NumberType": {} + } + }, + "native_column_type": "DECIMAL" }, "upstreams": [ { diff --git a/metadata-ingestion/tests/unit/sql_parsing/test_sqlglot_lineage.py b/metadata-ingestion/tests/unit/sql_parsing/test_sqlglot_lineage.py index 2a965a9bb1e61..bb6e5f1581754 100644 --- a/metadata-ingestion/tests/unit/sql_parsing/test_sqlglot_lineage.py +++ b/metadata-ingestion/tests/unit/sql_parsing/test_sqlglot_lineage.py @@ -608,4 +608,25 @@ def test_snowflake_default_normalization(): ) +def test_snowflake_column_cast(): + assert_sql_result( + """ +SELECT + o.o_orderkey::NUMBER(20,0) as orderkey, + CAST(o.o_totalprice AS INT) as total_cast_int, + CAST(o.o_totalprice AS NUMBER(16,4)) as total_cast_float +FROM snowflake_sample_data.tpch_sf1.orders o +LIMIT 10 +""", + dialect="snowflake", + schemas={ + "urn:li:dataset:(urn:li:dataPlatform:snowflake,snowflake_sample_data.tpch_sf1.orders,PROD)": { + "orderkey": "NUMBER(38,0)", + "totalprice": "NUMBER(12,2)", + }, + }, + expected_file=RESOURCE_DIR / "test_snowflake_column_cast.json", + ) + + # TODO: Add a test for setting platform_instance or env