mirror of
https://github.com/open-metadata/OpenMetadata.git
synced 2026-01-06 12:36:56 +00:00
98850ab5cc
* 🎉 Init OpenLineage connector Co-authored-by: dechoma <dominik.choma@gmail.com> * MLH - make linter happy * review fixes * 🐛 Fix path for ol event in tests * 🐛 Fix path for ol event in tests * Update ingestion/setup.py Co-authored-by: Mayur Singal <39544459+ulixius9@users.noreply.github.com> * Update ingestion/src/metadata/ingestion/source/pipeline/openlineage/metadata.py Co-authored-by: Mayur Singal <39544459+ulixius9@users.noreply.github.com> * Update ingestion/src/metadata/ingestion/source/pipeline/openlineage/models.py Co-authored-by: Mayur Singal <39544459+ulixius9@users.noreply.github.com> * review fixes 2 * linter * review * review * make linter happy * fix test_yield_pipeline_lineage_details test * make linter happy * fix tests * fix tests 2 --------- Co-authored-by: dechoma <dominik.choma@gmail.com> Co-authored-by: Mayur Singal <39544459+ulixius9@users.noreply.github.com>
330 lines
13 KiB
JSON
330 lines
13 KiB
JSON
{
|
|
"eventTime": "2023-12-16T14:22:11.949Z",
|
|
"producer": "https://github.com/OpenLineage/OpenLineage/tree/1.5.0/integration/spark",
|
|
"schemaURL": "https://openlineage.io/spec/2-0-2/OpenLineage.json#/$defs/RunEvent",
|
|
"eventType": "COMPLETE",
|
|
"run": {
|
|
"runId": "59fc8906-4a4a-45ab-9a54-9cc2d399e10e",
|
|
"facets": {
|
|
"parent": {
|
|
"_producer": "https://github.com/OpenLineage/OpenLineage/tree/1.5.0/integration/spark",
|
|
"_schemaURL": "https://openlineage.io/spec/facets/1-0-0/ParentRunFacet.json#/$defs/ParentRunFacet",
|
|
"run": {
|
|
"runId": "daf8bcc1-cc3c-41bb-9251-334cacf698fa"
|
|
},
|
|
"job": {
|
|
"namespace": "TESTSchedulerID",
|
|
"name": "TESTParentJobName4"
|
|
}
|
|
},
|
|
"spark.logicalPlan": {
|
|
"_producer": "https://github.com/OpenLineage/OpenLineage/tree/1.5.0/integration/spark",
|
|
"_schemaURL": "https://openlineage.io/spec/2-0-2/OpenLineage.json#/$defs/RunFacet",
|
|
"plan": [
|
|
{
|
|
"class": "org.apache.spark.sql.execution.command.CreateDataSourceTableAsSelectCommand",
|
|
"num-children": 1,
|
|
"table": {
|
|
"product-class": "org.apache.spark.sql.catalyst.catalog.CatalogTable",
|
|
"identifier": {
|
|
"product-class": "org.apache.spark.sql.catalyst.TableIdentifier",
|
|
"table": "dst_table_test_from_src_table_df",
|
|
"database": "test_db"
|
|
},
|
|
"tableType": {
|
|
"product-class": "org.apache.spark.sql.catalyst.catalog.CatalogTableType",
|
|
"name": "MANAGED"
|
|
},
|
|
"storage": {
|
|
"product-class": "org.apache.spark.sql.catalyst.catalog.CatalogStorageFormat",
|
|
"compressed": false,
|
|
"properties": null
|
|
},
|
|
"schema": {
|
|
"type": "struct",
|
|
"fields": []
|
|
},
|
|
"provider": "parquet",
|
|
"partitionColumnNames": [],
|
|
"owner": "",
|
|
"createTime": 1702736481797,
|
|
"lastAccessTime": -1,
|
|
"createVersion": "",
|
|
"properties": null,
|
|
"unsupportedFeatures": [],
|
|
"tracksPartitionsInCatalog": false,
|
|
"schemaPreservesCase": true,
|
|
"ignoredProperties": null
|
|
},
|
|
"mode": null,
|
|
"query": 0,
|
|
"outputColumnNames": "[id, randomid, zip]"
|
|
},
|
|
{
|
|
"class": "org.apache.spark.sql.execution.datasources.LogicalRelation",
|
|
"num-children": 0,
|
|
"relation": null,
|
|
"output": [
|
|
[
|
|
{
|
|
"class": "org.apache.spark.sql.catalyst.expressions.AttributeReference",
|
|
"num-children": 0,
|
|
"name": "id",
|
|
"dataType": "long",
|
|
"nullable": true,
|
|
"metadata": {},
|
|
"exprId": {
|
|
"product-class": "org.apache.spark.sql.catalyst.expressions.ExprId",
|
|
"id": 9,
|
|
"jvmId": "78343417-b80d-45a2-b489-e7d8920e61dd"
|
|
},
|
|
"qualifier": []
|
|
}
|
|
],
|
|
[
|
|
{
|
|
"class": "org.apache.spark.sql.catalyst.expressions.AttributeReference",
|
|
"num-children": 0,
|
|
"name": "randomid",
|
|
"dataType": "string",
|
|
"nullable": true,
|
|
"metadata": {},
|
|
"exprId": {
|
|
"product-class": "org.apache.spark.sql.catalyst.expressions.ExprId",
|
|
"id": 10,
|
|
"jvmId": "78343417-b80d-45a2-b489-e7d8920e61dd"
|
|
},
|
|
"qualifier": []
|
|
}
|
|
],
|
|
[
|
|
{
|
|
"class": "org.apache.spark.sql.catalyst.expressions.AttributeReference",
|
|
"num-children": 0,
|
|
"name": "zip",
|
|
"dataType": "string",
|
|
"nullable": true,
|
|
"metadata": {},
|
|
"exprId": {
|
|
"product-class": "org.apache.spark.sql.catalyst.expressions.ExprId",
|
|
"id": 11,
|
|
"jvmId": "78343417-b80d-45a2-b489-e7d8920e61dd"
|
|
},
|
|
"qualifier": []
|
|
}
|
|
]
|
|
],
|
|
"catalogTable": {
|
|
"product-class": "org.apache.spark.sql.catalyst.catalog.CatalogTable",
|
|
"identifier": {
|
|
"product-class": "org.apache.spark.sql.catalyst.TableIdentifier",
|
|
"table": "src_table_test",
|
|
"database": "test_db"
|
|
},
|
|
"tableType": {
|
|
"product-class": "org.apache.spark.sql.catalyst.catalog.CatalogTableType",
|
|
"name": "MANAGED"
|
|
},
|
|
"storage": {
|
|
"product-class": "org.apache.spark.sql.catalyst.catalog.CatalogStorageFormat",
|
|
"locationUri": null,
|
|
"inputFormat": "org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat",
|
|
"outputFormat": "org.apache.hadoop.hive.ql.io.parquet.MapredParquetOutputFormat",
|
|
"serde": "org.apache.hadoop.hive.ql.io.parquet.serde.ParquetHiveSerDe",
|
|
"compressed": false,
|
|
"properties": null
|
|
},
|
|
"schema": {
|
|
"type": "struct",
|
|
"fields": [
|
|
{
|
|
"name": "id",
|
|
"type": "long",
|
|
"nullable": true,
|
|
"metadata": {}
|
|
},
|
|
{
|
|
"name": "randomid",
|
|
"type": "string",
|
|
"nullable": true,
|
|
"metadata": {}
|
|
},
|
|
{
|
|
"name": "zip",
|
|
"type": "string",
|
|
"nullable": true,
|
|
"metadata": {
|
|
"__CHAR_VARCHAR_TYPE_STRING": "varchar(10)"
|
|
}
|
|
}
|
|
]
|
|
},
|
|
"provider": "parquet",
|
|
"partitionColumnNames": [],
|
|
"owner": "test_user@ad.test.net",
|
|
"createTime": 1682523315000,
|
|
"lastAccessTime": 0,
|
|
"createVersion": "3.3.1",
|
|
"properties": null,
|
|
"stats": null,
|
|
"unsupportedFeatures": [],
|
|
"tracksPartitionsInCatalog": false,
|
|
"schemaPreservesCase": true,
|
|
"ignoredProperties": null
|
|
},
|
|
"isStreaming": false
|
|
}
|
|
]
|
|
},
|
|
"spark_version": {
|
|
"_producer": "https://github.com/OpenLineage/OpenLineage/tree/1.5.0/integration/spark",
|
|
"_schemaURL": "https://openlineage.io/spec/2-0-2/OpenLineage.json#/$defs/RunFacet",
|
|
"spark-version": "3.3.1",
|
|
"openlineage-spark-version": "1.5.0"
|
|
},
|
|
"processing_engine": {
|
|
"_producer": "https://github.com/OpenLineage/OpenLineage/tree/1.5.0/integration/spark",
|
|
"_schemaURL": "https://openlineage.io/spec/facets/1-1-0/ProcessingEngineRunFacet.json#/$defs/ProcessingEngineRunFacet",
|
|
"version": "3.3.1",
|
|
"name": "spark",
|
|
"openlineageAdapterVersion": "1.5.0"
|
|
},
|
|
"environment-properties": {
|
|
"_producer": "https://github.com/OpenLineage/OpenLineage/tree/1.5.0/integration/spark",
|
|
"_schemaURL": "https://openlineage.io/spec/2-0-2/OpenLineage.json#/$defs/RunFacet",
|
|
"environment-properties": {}
|
|
}
|
|
}
|
|
},
|
|
"job": {
|
|
"namespace": "TESTSchedulerID",
|
|
"name": "test_user_spark.execute_create_data_source_table_as_select_command.dst_table_test_from_src_table_df",
|
|
"facets": {}
|
|
},
|
|
"inputs": [
|
|
{
|
|
"namespace": "s3a://test_db-db",
|
|
"name": "src_table_test",
|
|
"facets": {
|
|
"dataSource": {
|
|
"_producer": "https://github.com/OpenLineage/OpenLineage/tree/1.5.0/integration/spark",
|
|
"_schemaURL": "https://openlineage.io/spec/facets/1-0-0/DatasourceDatasetFacet.json#/$defs/DatasourceDatasetFacet",
|
|
"name": "s3a://test_db-db",
|
|
"uri": "s3a://test_db-db"
|
|
},
|
|
"schema": {
|
|
"_producer": "https://github.com/OpenLineage/OpenLineage/tree/1.5.0/integration/spark",
|
|
"_schemaURL": "https://openlineage.io/spec/facets/1-0-0/SchemaDatasetFacet.json#/$defs/SchemaDatasetFacet",
|
|
"fields": [
|
|
{
|
|
"name": "id",
|
|
"type": "long"
|
|
},
|
|
{
|
|
"name": "randomid",
|
|
"type": "string"
|
|
},
|
|
{
|
|
"name": "zip",
|
|
"type": "string"
|
|
}
|
|
]
|
|
},
|
|
"symlinks": {
|
|
"_producer": "https://github.com/OpenLineage/OpenLineage/tree/1.5.0/integration/spark",
|
|
"_schemaURL": "https://openlineage.io/spec/facets/1-0-0/SymlinksDatasetFacet.json#/$defs/SymlinksDatasetFacet",
|
|
"identifiers": [
|
|
{
|
|
"namespace": "hive://hive-metastore.hive.svc.cluster.local:9083",
|
|
"name": "shopify.raw_product_catalog",
|
|
"type": "TABLE"
|
|
}
|
|
]
|
|
}
|
|
},
|
|
"inputFacets": {}
|
|
}
|
|
],
|
|
"outputs": [
|
|
{
|
|
"namespace": "s3a://test_db-db",
|
|
"name": "dst_table_test_from_src_table_df",
|
|
"facets": {
|
|
"dataSource": {
|
|
"_producer": "https://github.com/OpenLineage/OpenLineage/tree/1.5.0/integration/spark",
|
|
"_schemaURL": "https://openlineage.io/spec/facets/1-0-0/DatasourceDatasetFacet.json#/$defs/DatasourceDatasetFacet",
|
|
"name": "s3a://test_db-db",
|
|
"uri": "s3a://test_db-db"
|
|
},
|
|
"schema": {
|
|
"_producer": "https://github.com/OpenLineage/OpenLineage/tree/1.5.0/integration/spark",
|
|
"_schemaURL": "https://openlineage.io/spec/facets/1-0-0/SchemaDatasetFacet.json#/$defs/SchemaDatasetFacet",
|
|
"fields": [
|
|
{
|
|
"name": "id",
|
|
"type": "long"
|
|
},
|
|
{
|
|
"name": "randomid",
|
|
"type": "string"
|
|
},
|
|
{
|
|
"name": "zip",
|
|
"type": "string"
|
|
}
|
|
]
|
|
},
|
|
"columnLineage": {
|
|
"_producer": "https://github.com/OpenLineage/OpenLineage/tree/1.5.0/integration/spark",
|
|
"_schemaURL": "https://openlineage.io/spec/facets/1-0-1/ColumnLineageDatasetFacet.json#/$defs/ColumnLineageDatasetFacet",
|
|
"fields": {
|
|
"id": {
|
|
"inputFields": [
|
|
{
|
|
"namespace": "s3a://test_db-db",
|
|
"name": "/src_table_test",
|
|
"field": "comments"
|
|
}
|
|
]
|
|
},
|
|
"randomid": {
|
|
"inputFields": [
|
|
{
|
|
"namespace": "s3a://test_db-db",
|
|
"name": "/src_table_test",
|
|
"field": "products"
|
|
}
|
|
]
|
|
},
|
|
"zip": {
|
|
"inputFields": [
|
|
{
|
|
"namespace": "s3a://test_db-db",
|
|
"name": "/src_table_test",
|
|
"field": "platform"
|
|
}
|
|
]
|
|
}
|
|
}
|
|
},
|
|
"symlinks": {
|
|
"_producer": "https://github.com/OpenLineage/OpenLineage/tree/1.5.0/integration/spark",
|
|
"_schemaURL": "https://openlineage.io/spec/facets/1-0-0/SymlinksDatasetFacet.json#/$defs/SymlinksDatasetFacet",
|
|
"identifiers": [
|
|
{
|
|
"namespace": "hive://hive-metastore.hive.svc.cluster.local:9083",
|
|
"name": "shopify.fact_order_new5",
|
|
"type": "TABLE"
|
|
}
|
|
]
|
|
},
|
|
"lifecycleStateChange": {
|
|
"_producer": "https://github.com/OpenLineage/OpenLineage/tree/1.5.0/integration/spark",
|
|
"_schemaURL": "https://openlineage.io/spec/facets/1-0-0/LifecycleStateChangeDatasetFacet.json#/$defs/LifecycleStateChangeDatasetFacet",
|
|
"lifecycleStateChange": "CREATE"
|
|
}
|
|
},
|
|
"outputFacets": {}
|
|
}
|
|
]
|
|
} |