acryl-datahub 1.1.1rc4__py3-none-any.whl → 1.2.0.1rc1__py3-none-any.whl

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Potentially problematic release.


This version of acryl-datahub might be problematic. Click here for more details.

Files changed (223) hide show
  1. {acryl_datahub-1.1.1rc4.dist-info → acryl_datahub-1.2.0.1rc1.dist-info}/METADATA +2617 -2590
  2. {acryl_datahub-1.1.1rc4.dist-info → acryl_datahub-1.2.0.1rc1.dist-info}/RECORD +223 -189
  3. {acryl_datahub-1.1.1rc4.dist-info → acryl_datahub-1.2.0.1rc1.dist-info}/entry_points.txt +2 -0
  4. datahub/_version.py +1 -1
  5. datahub/api/entities/dataset/dataset.py +1 -1
  6. datahub/api/entities/external/__init__.py +0 -0
  7. datahub/api/entities/external/external_entities.py +239 -0
  8. datahub/api/entities/external/external_tag.py +145 -0
  9. datahub/api/entities/external/lake_formation_external_entites.py +161 -0
  10. datahub/api/entities/external/restricted_text.py +247 -0
  11. datahub/api/entities/external/unity_catalog_external_entites.py +173 -0
  12. datahub/cli/check_cli.py +88 -7
  13. datahub/cli/cli_utils.py +63 -0
  14. datahub/cli/container_cli.py +5 -0
  15. datahub/cli/delete_cli.py +124 -27
  16. datahub/cli/docker_check.py +107 -12
  17. datahub/cli/docker_cli.py +149 -227
  18. datahub/cli/exists_cli.py +0 -2
  19. datahub/cli/get_cli.py +0 -2
  20. datahub/cli/iceberg_cli.py +5 -0
  21. datahub/cli/ingest_cli.py +3 -15
  22. datahub/cli/migrate.py +2 -0
  23. datahub/cli/put_cli.py +1 -4
  24. datahub/cli/quickstart_versioning.py +50 -7
  25. datahub/cli/specific/assertions_cli.py +0 -4
  26. datahub/cli/specific/datacontract_cli.py +0 -3
  27. datahub/cli/specific/dataproduct_cli.py +0 -11
  28. datahub/cli/specific/dataset_cli.py +1 -8
  29. datahub/cli/specific/forms_cli.py +0 -4
  30. datahub/cli/specific/group_cli.py +0 -2
  31. datahub/cli/specific/structuredproperties_cli.py +1 -4
  32. datahub/cli/specific/user_cli.py +0 -2
  33. datahub/cli/state_cli.py +0 -2
  34. datahub/cli/timeline_cli.py +0 -2
  35. datahub/configuration/pydantic_migration_helpers.py +7 -5
  36. datahub/emitter/rest_emitter.py +70 -12
  37. datahub/entrypoints.py +4 -3
  38. datahub/ingestion/api/decorators.py +15 -3
  39. datahub/ingestion/api/report.py +332 -3
  40. datahub/ingestion/api/sink.py +3 -0
  41. datahub/ingestion/api/source.py +48 -44
  42. datahub/ingestion/autogenerated/__init__.py +0 -0
  43. datahub/ingestion/autogenerated/capability_summary.json +3449 -0
  44. datahub/ingestion/autogenerated/lineage.json +401 -0
  45. datahub/ingestion/autogenerated/lineage_helper.py +177 -0
  46. datahub/ingestion/extractor/schema_util.py +13 -4
  47. datahub/ingestion/glossary/classification_mixin.py +5 -0
  48. datahub/ingestion/graph/client.py +100 -15
  49. datahub/ingestion/graph/config.py +1 -0
  50. datahub/ingestion/reporting/datahub_ingestion_run_summary_provider.py +20 -10
  51. datahub/ingestion/run/pipeline.py +54 -2
  52. datahub/ingestion/sink/datahub_rest.py +13 -0
  53. datahub/ingestion/source/abs/source.py +1 -1
  54. datahub/ingestion/source/aws/aws_common.py +4 -0
  55. datahub/ingestion/source/aws/glue.py +489 -244
  56. datahub/ingestion/source/aws/tag_entities.py +292 -0
  57. datahub/ingestion/source/azure/azure_common.py +2 -2
  58. datahub/ingestion/source/bigquery_v2/bigquery.py +50 -23
  59. datahub/ingestion/source/bigquery_v2/bigquery_config.py +1 -1
  60. datahub/ingestion/source/bigquery_v2/bigquery_queries.py +1 -0
  61. datahub/ingestion/source/bigquery_v2/bigquery_schema_gen.py +2 -0
  62. datahub/ingestion/source/bigquery_v2/common.py +1 -1
  63. datahub/ingestion/source/bigquery_v2/profiler.py +4 -2
  64. datahub/ingestion/source/bigquery_v2/queries.py +3 -3
  65. datahub/ingestion/source/cassandra/cassandra.py +1 -1
  66. datahub/ingestion/source/cassandra/cassandra_profiling.py +6 -5
  67. datahub/ingestion/source/common/subtypes.py +45 -0
  68. datahub/ingestion/source/data_lake_common/object_store.py +115 -27
  69. datahub/ingestion/source/data_lake_common/path_spec.py +10 -21
  70. datahub/ingestion/source/datahub/datahub_database_reader.py +1 -2
  71. datahub/ingestion/source/dbt/dbt_cloud.py +10 -2
  72. datahub/ingestion/source/dbt/dbt_common.py +6 -2
  73. datahub/ingestion/source/dbt/dbt_core.py +3 -0
  74. datahub/ingestion/source/debug/__init__.py +0 -0
  75. datahub/ingestion/source/debug/datahub_debug.py +300 -0
  76. datahub/ingestion/source/dremio/dremio_api.py +114 -73
  77. datahub/ingestion/source/dremio/dremio_config.py +2 -0
  78. datahub/ingestion/source/dremio/dremio_reporting.py +23 -2
  79. datahub/ingestion/source/dremio/dremio_source.py +94 -81
  80. datahub/ingestion/source/dremio/dremio_sql_queries.py +82 -21
  81. datahub/ingestion/source/file.py +3 -0
  82. datahub/ingestion/source/fivetran/fivetran.py +34 -26
  83. datahub/ingestion/source/gcs/gcs_source.py +13 -2
  84. datahub/ingestion/source/ge_data_profiler.py +76 -28
  85. datahub/ingestion/source/ge_profiling_config.py +11 -0
  86. datahub/ingestion/source/hex/api.py +26 -1
  87. datahub/ingestion/source/iceberg/iceberg.py +3 -1
  88. datahub/ingestion/source/identity/azure_ad.py +1 -1
  89. datahub/ingestion/source/identity/okta.py +1 -14
  90. datahub/ingestion/source/kafka/kafka.py +16 -0
  91. datahub/ingestion/source/kafka_connect/sink_connectors.py +156 -47
  92. datahub/ingestion/source/kafka_connect/source_connectors.py +59 -4
  93. datahub/ingestion/source/looker/looker_source.py +1 -0
  94. datahub/ingestion/source/mlflow.py +11 -1
  95. datahub/ingestion/source/mock_data/__init__.py +0 -0
  96. datahub/ingestion/source/mock_data/datahub_mock_data.py +507 -0
  97. datahub/ingestion/source/mock_data/datahub_mock_data_report.py +12 -0
  98. datahub/ingestion/source/mock_data/table_naming_helper.py +97 -0
  99. datahub/ingestion/source/nifi.py +1 -1
  100. datahub/ingestion/source/powerbi/powerbi.py +1 -5
  101. datahub/ingestion/source/powerbi/rest_api_wrapper/powerbi_api.py +0 -1
  102. datahub/ingestion/source/powerbi_report_server/report_server.py +0 -23
  103. datahub/ingestion/source/preset.py +2 -2
  104. datahub/ingestion/source/qlik_sense/qlik_sense.py +1 -0
  105. datahub/ingestion/source/redshift/redshift.py +21 -1
  106. datahub/ingestion/source/redshift/usage.py +4 -3
  107. datahub/ingestion/source/s3/report.py +4 -2
  108. datahub/ingestion/source/s3/source.py +367 -115
  109. datahub/ingestion/source/sac/sac.py +3 -1
  110. datahub/ingestion/source/salesforce.py +6 -3
  111. datahub/ingestion/source/sigma/sigma.py +7 -1
  112. datahub/ingestion/source/slack/slack.py +2 -1
  113. datahub/ingestion/source/snowflake/snowflake_config.py +30 -7
  114. datahub/ingestion/source/snowflake/snowflake_queries.py +348 -82
  115. datahub/ingestion/source/snowflake/snowflake_summary.py +5 -0
  116. datahub/ingestion/source/snowflake/snowflake_usage_v2.py +8 -2
  117. datahub/ingestion/source/snowflake/snowflake_utils.py +2 -7
  118. datahub/ingestion/source/snowflake/snowflake_v2.py +16 -2
  119. datahub/ingestion/source/snowflake/stored_proc_lineage.py +143 -0
  120. datahub/ingestion/source/sql/athena.py +119 -11
  121. datahub/ingestion/source/sql/athena_properties_extractor.py +777 -0
  122. datahub/ingestion/source/sql/clickhouse.py +3 -1
  123. datahub/ingestion/source/sql/cockroachdb.py +0 -1
  124. datahub/ingestion/source/sql/hana.py +3 -1
  125. datahub/ingestion/source/sql/hive_metastore.py +3 -11
  126. datahub/ingestion/source/sql/mariadb.py +0 -1
  127. datahub/ingestion/source/sql/mssql/source.py +239 -34
  128. datahub/ingestion/source/sql/mysql.py +0 -1
  129. datahub/ingestion/source/sql/oracle.py +1 -1
  130. datahub/ingestion/source/sql/postgres.py +0 -1
  131. datahub/ingestion/source/sql/sql_common.py +121 -34
  132. datahub/ingestion/source/sql/sql_generic_profiler.py +2 -1
  133. datahub/ingestion/source/sql/teradata.py +997 -235
  134. datahub/ingestion/source/sql/vertica.py +10 -6
  135. datahub/ingestion/source/sql_queries.py +2 -2
  136. datahub/ingestion/source/state/stateful_ingestion_base.py +1 -1
  137. datahub/ingestion/source/superset.py +58 -3
  138. datahub/ingestion/source/tableau/tableau.py +58 -37
  139. datahub/ingestion/source/tableau/tableau_common.py +4 -2
  140. datahub/ingestion/source/tableau/tableau_constant.py +0 -4
  141. datahub/ingestion/source/unity/config.py +5 -0
  142. datahub/ingestion/source/unity/proxy.py +118 -0
  143. datahub/ingestion/source/unity/source.py +195 -17
  144. datahub/ingestion/source/unity/tag_entities.py +295 -0
  145. datahub/ingestion/source/usage/clickhouse_usage.py +4 -1
  146. datahub/ingestion/source/usage/starburst_trino_usage.py +3 -0
  147. datahub/ingestion/transformer/add_dataset_ownership.py +18 -2
  148. datahub/integrations/assertion/snowflake/compiler.py +4 -3
  149. datahub/metadata/_internal_schema_classes.py +1522 -569
  150. datahub/metadata/_urns/urn_defs.py +1826 -1658
  151. datahub/metadata/com/linkedin/pegasus2avro/application/__init__.py +19 -0
  152. datahub/metadata/com/linkedin/pegasus2avro/identity/__init__.py +2 -0
  153. datahub/metadata/com/linkedin/pegasus2avro/logical/__init__.py +15 -0
  154. datahub/metadata/com/linkedin/pegasus2avro/metadata/key/__init__.py +4 -0
  155. datahub/metadata/com/linkedin/pegasus2avro/module/__init__.py +29 -0
  156. datahub/metadata/com/linkedin/pegasus2avro/settings/global/__init__.py +4 -0
  157. datahub/metadata/com/linkedin/pegasus2avro/template/__init__.py +25 -0
  158. datahub/metadata/schema.avsc +17758 -17097
  159. datahub/metadata/schemas/ApplicationKey.avsc +31 -0
  160. datahub/metadata/schemas/ApplicationProperties.avsc +72 -0
  161. datahub/metadata/schemas/Applications.avsc +38 -0
  162. datahub/metadata/schemas/ChartKey.avsc +1 -0
  163. datahub/metadata/schemas/ContainerKey.avsc +1 -0
  164. datahub/metadata/schemas/ContainerProperties.avsc +8 -0
  165. datahub/metadata/schemas/CorpUserSettings.avsc +41 -0
  166. datahub/metadata/schemas/DashboardKey.avsc +1 -0
  167. datahub/metadata/schemas/DataFlowInfo.avsc +8 -0
  168. datahub/metadata/schemas/DataFlowKey.avsc +1 -0
  169. datahub/metadata/schemas/DataHubPageModuleKey.avsc +21 -0
  170. datahub/metadata/schemas/DataHubPageModuleProperties.avsc +237 -0
  171. datahub/metadata/schemas/DataHubPageTemplateKey.avsc +21 -0
  172. datahub/metadata/schemas/DataHubPageTemplateProperties.avsc +175 -0
  173. datahub/metadata/schemas/DataHubPolicyInfo.avsc +12 -1
  174. datahub/metadata/schemas/DataJobInfo.avsc +8 -0
  175. datahub/metadata/schemas/DataJobKey.avsc +1 -0
  176. datahub/metadata/schemas/DataProcessKey.avsc +8 -0
  177. datahub/metadata/schemas/DataProductKey.avsc +1 -0
  178. datahub/metadata/schemas/DataProductProperties.avsc +1 -1
  179. datahub/metadata/schemas/DatasetKey.avsc +11 -1
  180. datahub/metadata/schemas/GlobalSettingsInfo.avsc +62 -0
  181. datahub/metadata/schemas/GlossaryTermKey.avsc +1 -0
  182. datahub/metadata/schemas/IcebergWarehouseInfo.avsc +8 -0
  183. datahub/metadata/schemas/LogicalParent.avsc +140 -0
  184. datahub/metadata/schemas/MLFeatureKey.avsc +1 -0
  185. datahub/metadata/schemas/MLFeatureTableKey.avsc +1 -0
  186. datahub/metadata/schemas/MLModelDeploymentKey.avsc +8 -0
  187. datahub/metadata/schemas/MLModelGroupKey.avsc +9 -0
  188. datahub/metadata/schemas/MLModelKey.avsc +9 -0
  189. datahub/metadata/schemas/MLPrimaryKeyKey.avsc +1 -0
  190. datahub/metadata/schemas/MetadataChangeEvent.avsc +20 -1
  191. datahub/metadata/schemas/NotebookKey.avsc +1 -0
  192. datahub/metadata/schemas/QuerySubjects.avsc +1 -12
  193. datahub/metadata/schemas/SchemaFieldKey.avsc +2 -1
  194. datahub/metadata/schemas/__init__.py +3 -3
  195. datahub/sdk/__init__.py +2 -0
  196. datahub/sdk/_all_entities.py +7 -0
  197. datahub/sdk/_shared.py +116 -0
  198. datahub/sdk/chart.py +315 -0
  199. datahub/sdk/container.py +7 -0
  200. datahub/sdk/dashboard.py +432 -0
  201. datahub/sdk/dataflow.py +7 -0
  202. datahub/sdk/datajob.py +45 -13
  203. datahub/sdk/dataset.py +8 -2
  204. datahub/sdk/entity_client.py +82 -2
  205. datahub/sdk/lineage_client.py +683 -82
  206. datahub/sdk/main_client.py +46 -16
  207. datahub/sdk/mlmodel.py +101 -38
  208. datahub/sdk/mlmodelgroup.py +7 -0
  209. datahub/sdk/search_client.py +4 -3
  210. datahub/sdk/search_filters.py +95 -27
  211. datahub/specific/chart.py +1 -1
  212. datahub/specific/dataproduct.py +4 -0
  213. datahub/sql_parsing/sql_parsing_aggregator.py +29 -17
  214. datahub/sql_parsing/sqlglot_lineage.py +62 -13
  215. datahub/telemetry/telemetry.py +17 -11
  216. datahub/testing/sdk_v2_helpers.py +7 -1
  217. datahub/upgrade/upgrade.py +56 -14
  218. datahub/utilities/server_config_util.py +8 -0
  219. datahub/utilities/sqlalchemy_query_combiner.py +5 -2
  220. datahub/utilities/stats_collections.py +4 -0
  221. {acryl_datahub-1.1.1rc4.dist-info → acryl_datahub-1.2.0.1rc1.dist-info}/WHEEL +0 -0
  222. {acryl_datahub-1.1.1rc4.dist-info → acryl_datahub-1.2.0.1rc1.dist-info}/licenses/LICENSE +0 -0
  223. {acryl_datahub-1.1.1rc4.dist-info → acryl_datahub-1.2.0.1rc1.dist-info}/top_level.txt +0 -0
@@ -71,8 +71,24 @@ class AddDatasetOwnership(OwnershipTransformer):
71
71
 
72
72
  server_ownership = graph.get_ownership(entity_urn=urn)
73
73
  if server_ownership:
74
- owners = {owner.owner: owner for owner in server_ownership.owners}
75
- owners.update({owner.owner: owner for owner in mce_ownership.owners})
74
+ owners = {
75
+ (
76
+ owner.owner,
77
+ owner.type,
78
+ owner.typeUrn,
79
+ ): owner
80
+ for owner in server_ownership.owners
81
+ }
82
+ owners.update(
83
+ {
84
+ (
85
+ owner.owner,
86
+ owner.type,
87
+ owner.typeUrn,
88
+ ): owner
89
+ for owner in mce_ownership.owners
90
+ }
91
+ )
76
92
  mce_ownership.owners = list(owners.values())
77
93
 
78
94
  return mce_ownership
@@ -84,9 +84,10 @@ class SnowflakeAssertionCompiler(AssertionCompiler):
84
84
 
85
85
  dmf_definitions_path = self.output_dir / DMF_DEFINITIONS_FILE_NAME
86
86
  dmf_associations_path = self.output_dir / DMF_ASSOCIATIONS_FILE_NAME
87
- with (dmf_definitions_path).open("w") as definitions, (
88
- dmf_associations_path
89
- ).open("w") as associations:
87
+ with (
88
+ (dmf_definitions_path).open("w") as definitions,
89
+ (dmf_associations_path).open("w") as associations,
90
+ ):
90
91
  for assertion_spec in assertion_config_spec.assertions:
91
92
  result.report.num_processed += 1
92
93
  try: