acryl-datahub 1.0.0rc18__py3-none-any.whl → 1.3.0.1rc9__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 (503) hide show
  1. {acryl_datahub-1.0.0rc18.dist-info → acryl_datahub-1.3.0.1rc9.dist-info}/METADATA +2686 -2563
  2. {acryl_datahub-1.0.0rc18.dist-info → acryl_datahub-1.3.0.1rc9.dist-info}/RECORD +499 -392
  3. {acryl_datahub-1.0.0rc18.dist-info → acryl_datahub-1.3.0.1rc9.dist-info}/WHEEL +1 -1
  4. {acryl_datahub-1.0.0rc18.dist-info → acryl_datahub-1.3.0.1rc9.dist-info}/entry_points.txt +7 -1
  5. datahub/_version.py +1 -1
  6. datahub/api/circuit_breaker/operation_circuit_breaker.py +2 -2
  7. datahub/api/entities/assertion/assertion.py +1 -1
  8. datahub/api/entities/common/serialized_value.py +1 -1
  9. datahub/api/entities/corpgroup/corpgroup.py +1 -1
  10. datahub/api/entities/datacontract/datacontract.py +35 -3
  11. datahub/api/entities/datajob/dataflow.py +18 -3
  12. datahub/api/entities/datajob/datajob.py +24 -4
  13. datahub/api/entities/dataprocess/dataprocess_instance.py +4 -0
  14. datahub/api/entities/dataproduct/dataproduct.py +32 -3
  15. datahub/api/entities/dataset/dataset.py +47 -72
  16. datahub/api/entities/external/__init__.py +0 -0
  17. datahub/api/entities/external/external_entities.py +724 -0
  18. datahub/api/entities/external/external_tag.py +147 -0
  19. datahub/api/entities/external/lake_formation_external_entites.py +162 -0
  20. datahub/api/entities/external/restricted_text.py +172 -0
  21. datahub/api/entities/external/unity_catalog_external_entites.py +172 -0
  22. datahub/api/entities/forms/forms.py +37 -37
  23. datahub/api/entities/structuredproperties/structuredproperties.py +6 -6
  24. datahub/api/graphql/assertion.py +1 -1
  25. datahub/api/graphql/base.py +8 -6
  26. datahub/api/graphql/operation.py +14 -10
  27. datahub/cli/check_cli.py +91 -9
  28. datahub/cli/cli_utils.py +63 -0
  29. datahub/cli/config_utils.py +20 -12
  30. datahub/cli/container_cli.py +5 -0
  31. datahub/cli/delete_cli.py +133 -34
  32. datahub/cli/docker_check.py +110 -14
  33. datahub/cli/docker_cli.py +155 -231
  34. datahub/cli/exists_cli.py +2 -3
  35. datahub/cli/get_cli.py +2 -3
  36. datahub/cli/graphql_cli.py +1422 -0
  37. datahub/cli/iceberg_cli.py +11 -5
  38. datahub/cli/ingest_cli.py +25 -26
  39. datahub/cli/migrate.py +12 -9
  40. datahub/cli/migration_utils.py +4 -3
  41. datahub/cli/put_cli.py +4 -6
  42. datahub/cli/quickstart_versioning.py +53 -10
  43. datahub/cli/specific/assertions_cli.py +39 -7
  44. datahub/cli/specific/datacontract_cli.py +57 -9
  45. datahub/cli/specific/dataproduct_cli.py +12 -24
  46. datahub/cli/specific/dataset_cli.py +31 -21
  47. datahub/cli/specific/forms_cli.py +2 -5
  48. datahub/cli/specific/group_cli.py +2 -3
  49. datahub/cli/specific/structuredproperties_cli.py +5 -7
  50. datahub/cli/specific/user_cli.py +174 -4
  51. datahub/cli/state_cli.py +2 -3
  52. datahub/cli/timeline_cli.py +2 -3
  53. datahub/configuration/common.py +46 -2
  54. datahub/configuration/connection_resolver.py +5 -2
  55. datahub/configuration/env_vars.py +331 -0
  56. datahub/configuration/import_resolver.py +7 -4
  57. datahub/configuration/kafka.py +21 -1
  58. datahub/configuration/pydantic_migration_helpers.py +6 -13
  59. datahub/configuration/source_common.py +4 -3
  60. datahub/configuration/validate_field_deprecation.py +5 -2
  61. datahub/configuration/validate_field_removal.py +8 -2
  62. datahub/configuration/validate_field_rename.py +6 -5
  63. datahub/configuration/validate_multiline_string.py +5 -2
  64. datahub/emitter/mce_builder.py +12 -8
  65. datahub/emitter/mcp.py +20 -5
  66. datahub/emitter/mcp_builder.py +12 -0
  67. datahub/emitter/request_helper.py +138 -15
  68. datahub/emitter/response_helper.py +111 -19
  69. datahub/emitter/rest_emitter.py +399 -163
  70. datahub/entrypoints.py +10 -5
  71. datahub/errors.py +12 -0
  72. datahub/ingestion/api/auto_work_units/auto_ensure_aspect_size.py +299 -2
  73. datahub/ingestion/api/auto_work_units/auto_validate_input_fields.py +87 -0
  74. datahub/ingestion/api/common.py +9 -0
  75. datahub/ingestion/api/decorators.py +15 -3
  76. datahub/ingestion/api/report.py +381 -3
  77. datahub/ingestion/api/sink.py +27 -2
  78. datahub/ingestion/api/source.py +174 -62
  79. datahub/ingestion/api/source_helpers.py +41 -3
  80. datahub/ingestion/api/source_protocols.py +23 -0
  81. datahub/ingestion/autogenerated/__init__.py +0 -0
  82. datahub/ingestion/autogenerated/capability_summary.json +3652 -0
  83. datahub/ingestion/autogenerated/lineage.json +402 -0
  84. datahub/ingestion/autogenerated/lineage_helper.py +177 -0
  85. datahub/ingestion/extractor/schema_util.py +31 -5
  86. datahub/ingestion/glossary/classification_mixin.py +9 -2
  87. datahub/ingestion/graph/client.py +492 -55
  88. datahub/ingestion/graph/config.py +18 -2
  89. datahub/ingestion/graph/filters.py +96 -32
  90. datahub/ingestion/graph/links.py +55 -0
  91. datahub/ingestion/reporting/datahub_ingestion_run_summary_provider.py +21 -11
  92. datahub/ingestion/run/pipeline.py +90 -23
  93. datahub/ingestion/run/pipeline_config.py +3 -3
  94. datahub/ingestion/sink/datahub_kafka.py +1 -0
  95. datahub/ingestion/sink/datahub_rest.py +31 -23
  96. datahub/ingestion/sink/file.py +1 -0
  97. datahub/ingestion/source/abs/config.py +1 -1
  98. datahub/ingestion/source/abs/datalake_profiler_config.py +1 -1
  99. datahub/ingestion/source/abs/source.py +15 -30
  100. datahub/ingestion/source/apply/datahub_apply.py +6 -5
  101. datahub/ingestion/source/aws/aws_common.py +185 -13
  102. datahub/ingestion/source/aws/glue.py +517 -244
  103. datahub/ingestion/source/aws/platform_resource_repository.py +30 -0
  104. datahub/ingestion/source/aws/s3_boto_utils.py +100 -5
  105. datahub/ingestion/source/aws/sagemaker_processors/feature_groups.py +1 -1
  106. datahub/ingestion/source/aws/sagemaker_processors/models.py +4 -4
  107. datahub/ingestion/source/aws/tag_entities.py +270 -0
  108. datahub/ingestion/source/azure/azure_common.py +3 -3
  109. datahub/ingestion/source/bigquery_v2/bigquery.py +51 -7
  110. datahub/ingestion/source/bigquery_v2/bigquery_config.py +51 -81
  111. datahub/ingestion/source/bigquery_v2/bigquery_connection.py +81 -0
  112. datahub/ingestion/source/bigquery_v2/bigquery_queries.py +6 -1
  113. datahub/ingestion/source/bigquery_v2/bigquery_report.py +0 -2
  114. datahub/ingestion/source/bigquery_v2/bigquery_schema.py +23 -16
  115. datahub/ingestion/source/bigquery_v2/bigquery_schema_gen.py +20 -5
  116. datahub/ingestion/source/bigquery_v2/common.py +1 -1
  117. datahub/ingestion/source/bigquery_v2/lineage.py +1 -1
  118. datahub/ingestion/source/bigquery_v2/profiler.py +4 -2
  119. datahub/ingestion/source/bigquery_v2/queries.py +3 -3
  120. datahub/ingestion/source/bigquery_v2/queries_extractor.py +45 -9
  121. datahub/ingestion/source/cassandra/cassandra.py +7 -18
  122. datahub/ingestion/source/cassandra/cassandra_api.py +36 -0
  123. datahub/ingestion/source/cassandra/cassandra_config.py +20 -0
  124. datahub/ingestion/source/cassandra/cassandra_profiling.py +26 -24
  125. datahub/ingestion/source/cassandra/cassandra_utils.py +1 -2
  126. datahub/ingestion/source/common/data_platforms.py +23 -0
  127. datahub/ingestion/source/common/gcp_credentials_config.py +9 -1
  128. datahub/ingestion/source/common/subtypes.py +73 -1
  129. datahub/ingestion/source/data_lake_common/data_lake_utils.py +59 -10
  130. datahub/ingestion/source/data_lake_common/object_store.py +732 -0
  131. datahub/ingestion/source/data_lake_common/path_spec.py +87 -38
  132. datahub/ingestion/source/datahub/config.py +19 -5
  133. datahub/ingestion/source/datahub/datahub_database_reader.py +205 -36
  134. datahub/ingestion/source/datahub/datahub_source.py +11 -1
  135. datahub/ingestion/source/dbt/dbt_cloud.py +17 -10
  136. datahub/ingestion/source/dbt/dbt_common.py +270 -26
  137. datahub/ingestion/source/dbt/dbt_core.py +88 -47
  138. datahub/ingestion/source/dbt/dbt_tests.py +8 -6
  139. datahub/ingestion/source/debug/__init__.py +0 -0
  140. datahub/ingestion/source/debug/datahub_debug.py +300 -0
  141. datahub/ingestion/source/delta_lake/config.py +9 -5
  142. datahub/ingestion/source/delta_lake/source.py +8 -0
  143. datahub/ingestion/source/dremio/dremio_api.py +114 -73
  144. datahub/ingestion/source/dremio/dremio_aspects.py +3 -2
  145. datahub/ingestion/source/dremio/dremio_config.py +5 -4
  146. datahub/ingestion/source/dremio/dremio_datahub_source_mapping.py +1 -1
  147. datahub/ingestion/source/dremio/dremio_entities.py +6 -5
  148. datahub/ingestion/source/dremio/dremio_reporting.py +22 -3
  149. datahub/ingestion/source/dremio/dremio_source.py +228 -215
  150. datahub/ingestion/source/dremio/dremio_sql_queries.py +82 -21
  151. datahub/ingestion/source/dynamodb/dynamodb.py +19 -13
  152. datahub/ingestion/source/excel/__init__.py +0 -0
  153. datahub/ingestion/source/excel/config.py +92 -0
  154. datahub/ingestion/source/excel/excel_file.py +539 -0
  155. datahub/ingestion/source/excel/profiling.py +308 -0
  156. datahub/ingestion/source/excel/report.py +49 -0
  157. datahub/ingestion/source/excel/source.py +662 -0
  158. datahub/ingestion/source/excel/util.py +18 -0
  159. datahub/ingestion/source/feast.py +12 -14
  160. datahub/ingestion/source/file.py +3 -0
  161. datahub/ingestion/source/fivetran/config.py +67 -8
  162. datahub/ingestion/source/fivetran/fivetran.py +228 -43
  163. datahub/ingestion/source/fivetran/fivetran_log_api.py +42 -9
  164. datahub/ingestion/source/fivetran/fivetran_query.py +58 -36
  165. datahub/ingestion/source/fivetran/fivetran_rest_api.py +65 -0
  166. datahub/ingestion/source/fivetran/response_models.py +97 -0
  167. datahub/ingestion/source/gc/datahub_gc.py +0 -2
  168. datahub/ingestion/source/gc/soft_deleted_entity_cleanup.py +101 -104
  169. datahub/ingestion/source/gcs/gcs_source.py +53 -10
  170. datahub/ingestion/source/gcs/gcs_utils.py +36 -9
  171. datahub/ingestion/source/ge_data_profiler.py +146 -33
  172. datahub/ingestion/source/ge_profiling_config.py +26 -11
  173. datahub/ingestion/source/grafana/entity_mcp_builder.py +272 -0
  174. datahub/ingestion/source/grafana/field_utils.py +307 -0
  175. datahub/ingestion/source/grafana/grafana_api.py +142 -0
  176. datahub/ingestion/source/grafana/grafana_config.py +104 -0
  177. datahub/ingestion/source/grafana/grafana_source.py +522 -84
  178. datahub/ingestion/source/grafana/lineage.py +202 -0
  179. datahub/ingestion/source/grafana/models.py +137 -0
  180. datahub/ingestion/source/grafana/report.py +90 -0
  181. datahub/ingestion/source/grafana/types.py +16 -0
  182. datahub/ingestion/source/hex/__init__.py +0 -0
  183. datahub/ingestion/source/hex/api.py +402 -0
  184. datahub/ingestion/source/hex/constants.py +8 -0
  185. datahub/ingestion/source/hex/hex.py +311 -0
  186. datahub/ingestion/source/hex/mapper.py +412 -0
  187. datahub/ingestion/source/hex/model.py +78 -0
  188. datahub/ingestion/source/hex/query_fetcher.py +307 -0
  189. datahub/ingestion/source/iceberg/iceberg.py +385 -164
  190. datahub/ingestion/source/iceberg/iceberg_common.py +2 -2
  191. datahub/ingestion/source/iceberg/iceberg_profiler.py +25 -20
  192. datahub/ingestion/source/identity/azure_ad.py +1 -1
  193. datahub/ingestion/source/identity/okta.py +1 -14
  194. datahub/ingestion/source/kafka/kafka.py +28 -71
  195. datahub/ingestion/source/kafka/kafka_config.py +78 -0
  196. datahub/ingestion/source/kafka_connect/common.py +2 -2
  197. datahub/ingestion/source/kafka_connect/sink_connectors.py +157 -48
  198. datahub/ingestion/source/kafka_connect/source_connectors.py +63 -5
  199. datahub/ingestion/source/ldap.py +1 -1
  200. datahub/ingestion/source/looker/looker_common.py +216 -86
  201. datahub/ingestion/source/looker/looker_config.py +15 -4
  202. datahub/ingestion/source/looker/looker_constant.py +4 -0
  203. datahub/ingestion/source/looker/looker_lib_wrapper.py +37 -4
  204. datahub/ingestion/source/looker/looker_liquid_tag.py +56 -5
  205. datahub/ingestion/source/looker/looker_source.py +539 -555
  206. datahub/ingestion/source/looker/looker_view_id_cache.py +1 -1
  207. datahub/ingestion/source/looker/lookml_concept_context.py +1 -1
  208. datahub/ingestion/source/looker/lookml_config.py +31 -3
  209. datahub/ingestion/source/looker/lookml_refinement.py +1 -1
  210. datahub/ingestion/source/looker/lookml_source.py +103 -118
  211. datahub/ingestion/source/looker/view_upstream.py +494 -1
  212. datahub/ingestion/source/metabase.py +32 -6
  213. datahub/ingestion/source/metadata/business_glossary.py +7 -7
  214. datahub/ingestion/source/metadata/lineage.py +11 -10
  215. datahub/ingestion/source/mlflow.py +254 -23
  216. datahub/ingestion/source/mock_data/__init__.py +0 -0
  217. datahub/ingestion/source/mock_data/datahub_mock_data.py +533 -0
  218. datahub/ingestion/source/mock_data/datahub_mock_data_report.py +12 -0
  219. datahub/ingestion/source/mock_data/table_naming_helper.py +97 -0
  220. datahub/ingestion/source/mode.py +359 -181
  221. datahub/ingestion/source/mongodb.py +11 -1
  222. datahub/ingestion/source/neo4j/neo4j_source.py +122 -153
  223. datahub/ingestion/source/nifi.py +5 -5
  224. datahub/ingestion/source/openapi.py +85 -38
  225. datahub/ingestion/source/openapi_parser.py +59 -40
  226. datahub/ingestion/source/powerbi/config.py +92 -27
  227. datahub/ingestion/source/powerbi/m_query/data_classes.py +3 -0
  228. datahub/ingestion/source/powerbi/m_query/odbc.py +185 -0
  229. datahub/ingestion/source/powerbi/m_query/parser.py +2 -2
  230. datahub/ingestion/source/powerbi/m_query/pattern_handler.py +358 -14
  231. datahub/ingestion/source/powerbi/m_query/resolver.py +10 -0
  232. datahub/ingestion/source/powerbi/powerbi.py +66 -32
  233. datahub/ingestion/source/powerbi/rest_api_wrapper/data_resolver.py +2 -2
  234. datahub/ingestion/source/powerbi/rest_api_wrapper/powerbi_api.py +11 -12
  235. datahub/ingestion/source/powerbi_report_server/report_server.py +0 -23
  236. datahub/ingestion/source/powerbi_report_server/report_server_domain.py +2 -4
  237. datahub/ingestion/source/preset.py +3 -3
  238. datahub/ingestion/source/qlik_sense/data_classes.py +28 -8
  239. datahub/ingestion/source/qlik_sense/qlik_sense.py +2 -1
  240. datahub/ingestion/source/redash.py +1 -1
  241. datahub/ingestion/source/redshift/config.py +15 -9
  242. datahub/ingestion/source/redshift/datashares.py +1 -1
  243. datahub/ingestion/source/redshift/lineage.py +386 -687
  244. datahub/ingestion/source/redshift/profile.py +2 -2
  245. datahub/ingestion/source/redshift/query.py +24 -20
  246. datahub/ingestion/source/redshift/redshift.py +52 -111
  247. datahub/ingestion/source/redshift/redshift_schema.py +17 -12
  248. datahub/ingestion/source/redshift/report.py +0 -2
  249. datahub/ingestion/source/redshift/usage.py +13 -11
  250. datahub/ingestion/source/s3/report.py +4 -2
  251. datahub/ingestion/source/s3/source.py +515 -244
  252. datahub/ingestion/source/sac/sac.py +3 -1
  253. datahub/ingestion/source/salesforce.py +28 -13
  254. datahub/ingestion/source/schema/json_schema.py +14 -14
  255. datahub/ingestion/source/schema_inference/object.py +22 -6
  256. datahub/ingestion/source/sigma/config.py +75 -8
  257. datahub/ingestion/source/sigma/data_classes.py +3 -0
  258. datahub/ingestion/source/sigma/sigma.py +36 -7
  259. datahub/ingestion/source/sigma/sigma_api.py +99 -58
  260. datahub/ingestion/source/slack/slack.py +403 -140
  261. datahub/ingestion/source/snaplogic/__init__.py +0 -0
  262. datahub/ingestion/source/snaplogic/snaplogic.py +355 -0
  263. datahub/ingestion/source/snaplogic/snaplogic_config.py +37 -0
  264. datahub/ingestion/source/snaplogic/snaplogic_lineage_extractor.py +107 -0
  265. datahub/ingestion/source/snaplogic/snaplogic_parser.py +168 -0
  266. datahub/ingestion/source/snaplogic/snaplogic_utils.py +31 -0
  267. datahub/ingestion/source/snowflake/constants.py +4 -0
  268. datahub/ingestion/source/snowflake/snowflake_config.py +103 -34
  269. datahub/ingestion/source/snowflake/snowflake_connection.py +47 -25
  270. datahub/ingestion/source/snowflake/snowflake_lineage_v2.py +25 -6
  271. datahub/ingestion/source/snowflake/snowflake_profiler.py +1 -6
  272. datahub/ingestion/source/snowflake/snowflake_queries.py +511 -107
  273. datahub/ingestion/source/snowflake/snowflake_query.py +100 -72
  274. datahub/ingestion/source/snowflake/snowflake_report.py +4 -2
  275. datahub/ingestion/source/snowflake/snowflake_schema.py +381 -16
  276. datahub/ingestion/source/snowflake/snowflake_schema_gen.py +163 -52
  277. datahub/ingestion/source/snowflake/snowflake_summary.py +7 -1
  278. datahub/ingestion/source/snowflake/snowflake_tag.py +4 -1
  279. datahub/ingestion/source/snowflake/snowflake_usage_v2.py +8 -2
  280. datahub/ingestion/source/snowflake/snowflake_utils.py +62 -17
  281. datahub/ingestion/source/snowflake/snowflake_v2.py +56 -10
  282. datahub/ingestion/source/snowflake/stored_proc_lineage.py +143 -0
  283. datahub/ingestion/source/sql/athena.py +219 -26
  284. datahub/ingestion/source/sql/athena_properties_extractor.py +795 -0
  285. datahub/ingestion/source/sql/clickhouse.py +29 -9
  286. datahub/ingestion/source/sql/cockroachdb.py +5 -4
  287. datahub/ingestion/source/sql/druid.py +9 -4
  288. datahub/ingestion/source/sql/hana.py +3 -1
  289. datahub/ingestion/source/sql/hive.py +28 -8
  290. datahub/ingestion/source/sql/hive_metastore.py +24 -25
  291. datahub/ingestion/source/sql/mariadb.py +0 -1
  292. datahub/ingestion/source/sql/mssql/job_models.py +18 -2
  293. datahub/ingestion/source/sql/mssql/source.py +376 -62
  294. datahub/ingestion/source/sql/mysql.py +154 -4
  295. datahub/ingestion/source/sql/oracle.py +62 -11
  296. datahub/ingestion/source/sql/postgres.py +142 -6
  297. datahub/ingestion/source/sql/presto.py +20 -2
  298. datahub/ingestion/source/sql/sql_common.py +281 -49
  299. datahub/ingestion/source/sql/sql_config.py +1 -34
  300. datahub/ingestion/source/sql/sql_generic_profiler.py +2 -1
  301. datahub/ingestion/source/sql/sql_types.py +27 -2
  302. datahub/ingestion/source/sql/sqlalchemy_uri.py +68 -0
  303. datahub/ingestion/source/sql/stored_procedures/__init__.py +0 -0
  304. datahub/ingestion/source/sql/stored_procedures/base.py +253 -0
  305. datahub/ingestion/source/sql/{mssql/stored_procedure_lineage.py → stored_procedures/lineage.py} +2 -29
  306. datahub/ingestion/source/sql/teradata.py +1028 -245
  307. datahub/ingestion/source/sql/trino.py +43 -10
  308. datahub/ingestion/source/sql/two_tier_sql_source.py +3 -4
  309. datahub/ingestion/source/sql/vertica.py +14 -7
  310. datahub/ingestion/source/sql_queries.py +219 -121
  311. datahub/ingestion/source/state/checkpoint.py +8 -29
  312. datahub/ingestion/source/state/entity_removal_state.py +5 -2
  313. datahub/ingestion/source/state/redundant_run_skip_handler.py +21 -0
  314. datahub/ingestion/source/state/stale_entity_removal_handler.py +0 -1
  315. datahub/ingestion/source/state/stateful_ingestion_base.py +36 -11
  316. datahub/ingestion/source/state_provider/datahub_ingestion_checkpointing_provider.py +2 -1
  317. datahub/ingestion/source/superset.py +810 -126
  318. datahub/ingestion/source/tableau/tableau.py +172 -69
  319. datahub/ingestion/source/tableau/tableau_common.py +11 -4
  320. datahub/ingestion/source/tableau/tableau_constant.py +1 -4
  321. datahub/ingestion/source/tableau/tableau_server_wrapper.py +3 -0
  322. datahub/ingestion/source/tableau/tableau_validation.py +1 -1
  323. datahub/ingestion/source/unity/config.py +161 -40
  324. datahub/ingestion/source/unity/connection.py +61 -0
  325. datahub/ingestion/source/unity/connection_test.py +1 -0
  326. datahub/ingestion/source/unity/platform_resource_repository.py +19 -0
  327. datahub/ingestion/source/unity/proxy.py +794 -51
  328. datahub/ingestion/source/unity/proxy_patch.py +321 -0
  329. datahub/ingestion/source/unity/proxy_types.py +36 -2
  330. datahub/ingestion/source/unity/report.py +15 -3
  331. datahub/ingestion/source/unity/source.py +465 -131
  332. datahub/ingestion/source/unity/tag_entities.py +197 -0
  333. datahub/ingestion/source/unity/usage.py +46 -4
  334. datahub/ingestion/source/usage/clickhouse_usage.py +11 -4
  335. datahub/ingestion/source/usage/starburst_trino_usage.py +10 -5
  336. datahub/ingestion/source/usage/usage_common.py +4 -68
  337. datahub/ingestion/source/vertexai/__init__.py +0 -0
  338. datahub/ingestion/source/vertexai/vertexai.py +1367 -0
  339. datahub/ingestion/source/vertexai/vertexai_config.py +29 -0
  340. datahub/ingestion/source/vertexai/vertexai_result_type_utils.py +89 -0
  341. datahub/ingestion/source_config/pulsar.py +3 -1
  342. datahub/ingestion/source_report/ingestion_stage.py +50 -11
  343. datahub/ingestion/transformer/add_dataset_dataproduct.py +1 -1
  344. datahub/ingestion/transformer/add_dataset_ownership.py +19 -3
  345. datahub/ingestion/transformer/base_transformer.py +8 -5
  346. datahub/ingestion/transformer/dataset_domain.py +1 -1
  347. datahub/ingestion/transformer/set_browse_path.py +112 -0
  348. datahub/integrations/assertion/common.py +3 -2
  349. datahub/integrations/assertion/snowflake/compiler.py +4 -3
  350. datahub/lite/lite_util.py +2 -2
  351. datahub/metadata/{_schema_classes.py → _internal_schema_classes.py} +3095 -631
  352. datahub/metadata/_urns/urn_defs.py +1866 -1582
  353. datahub/metadata/com/linkedin/pegasus2avro/application/__init__.py +19 -0
  354. datahub/metadata/com/linkedin/pegasus2avro/common/__init__.py +2 -0
  355. datahub/metadata/com/linkedin/pegasus2avro/dataplatform/slack/__init__.py +15 -0
  356. datahub/metadata/com/linkedin/pegasus2avro/event/__init__.py +11 -0
  357. datahub/metadata/com/linkedin/pegasus2avro/event/notification/__init__.py +15 -0
  358. datahub/metadata/com/linkedin/pegasus2avro/event/notification/settings/__init__.py +19 -0
  359. datahub/metadata/com/linkedin/pegasus2avro/file/__init__.py +19 -0
  360. datahub/metadata/com/linkedin/pegasus2avro/identity/__init__.py +2 -0
  361. datahub/metadata/com/linkedin/pegasus2avro/logical/__init__.py +15 -0
  362. datahub/metadata/com/linkedin/pegasus2avro/metadata/key/__init__.py +8 -0
  363. datahub/metadata/com/linkedin/pegasus2avro/module/__init__.py +31 -0
  364. datahub/metadata/com/linkedin/pegasus2avro/platform/event/v1/__init__.py +4 -0
  365. datahub/metadata/com/linkedin/pegasus2avro/role/__init__.py +2 -0
  366. datahub/metadata/com/linkedin/pegasus2avro/settings/asset/__init__.py +19 -0
  367. datahub/metadata/com/linkedin/pegasus2avro/settings/global/__init__.py +8 -0
  368. datahub/metadata/com/linkedin/pegasus2avro/template/__init__.py +31 -0
  369. datahub/metadata/schema.avsc +18404 -16617
  370. datahub/metadata/schema_classes.py +3 -3
  371. datahub/metadata/schemas/Actors.avsc +38 -1
  372. datahub/metadata/schemas/ApplicationKey.avsc +31 -0
  373. datahub/metadata/schemas/ApplicationProperties.avsc +72 -0
  374. datahub/metadata/schemas/Applications.avsc +38 -0
  375. datahub/metadata/schemas/AssetSettings.avsc +63 -0
  376. datahub/metadata/schemas/ChartInfo.avsc +2 -1
  377. datahub/metadata/schemas/ChartKey.avsc +1 -0
  378. datahub/metadata/schemas/ContainerKey.avsc +1 -0
  379. datahub/metadata/schemas/ContainerProperties.avsc +8 -0
  380. datahub/metadata/schemas/CorpUserEditableInfo.avsc +15 -1
  381. datahub/metadata/schemas/CorpUserKey.avsc +2 -1
  382. datahub/metadata/schemas/CorpUserSettings.avsc +145 -0
  383. datahub/metadata/schemas/DashboardKey.avsc +1 -0
  384. datahub/metadata/schemas/DataContractKey.avsc +2 -1
  385. datahub/metadata/schemas/DataFlowInfo.avsc +8 -0
  386. datahub/metadata/schemas/DataFlowKey.avsc +1 -0
  387. datahub/metadata/schemas/DataHubFileInfo.avsc +230 -0
  388. datahub/metadata/schemas/DataHubFileKey.avsc +21 -0
  389. datahub/metadata/schemas/DataHubIngestionSourceKey.avsc +2 -1
  390. datahub/metadata/schemas/DataHubOpenAPISchemaKey.avsc +22 -0
  391. datahub/metadata/schemas/DataHubPageModuleKey.avsc +21 -0
  392. datahub/metadata/schemas/DataHubPageModuleProperties.avsc +298 -0
  393. datahub/metadata/schemas/DataHubPageTemplateKey.avsc +21 -0
  394. datahub/metadata/schemas/DataHubPageTemplateProperties.avsc +251 -0
  395. datahub/metadata/schemas/DataHubPolicyInfo.avsc +12 -1
  396. datahub/metadata/schemas/DataJobInfo.avsc +8 -0
  397. datahub/metadata/schemas/DataJobInputOutput.avsc +8 -0
  398. datahub/metadata/schemas/DataJobKey.avsc +1 -0
  399. datahub/metadata/schemas/DataProcessInstanceInput.avsc +2 -1
  400. datahub/metadata/schemas/DataProcessInstanceOutput.avsc +2 -1
  401. datahub/metadata/schemas/DataProcessKey.avsc +8 -0
  402. datahub/metadata/schemas/DataProductKey.avsc +3 -1
  403. datahub/metadata/schemas/DataProductProperties.avsc +1 -1
  404. datahub/metadata/schemas/DataTransformLogic.avsc +4 -2
  405. datahub/metadata/schemas/DatasetKey.avsc +11 -1
  406. datahub/metadata/schemas/DatasetUsageStatistics.avsc +8 -0
  407. datahub/metadata/schemas/Deprecation.avsc +2 -0
  408. datahub/metadata/schemas/DomainKey.avsc +2 -1
  409. datahub/metadata/schemas/ExecutionRequestInput.avsc +5 -0
  410. datahub/metadata/schemas/FormInfo.avsc +5 -0
  411. datahub/metadata/schemas/GlobalSettingsInfo.avsc +134 -0
  412. datahub/metadata/schemas/GlossaryNodeKey.avsc +2 -1
  413. datahub/metadata/schemas/GlossaryTermKey.avsc +3 -1
  414. datahub/metadata/schemas/IcebergWarehouseInfo.avsc +8 -0
  415. datahub/metadata/schemas/IncidentInfo.avsc +3 -3
  416. datahub/metadata/schemas/InstitutionalMemory.avsc +31 -0
  417. datahub/metadata/schemas/LogicalParent.avsc +145 -0
  418. datahub/metadata/schemas/MLFeatureKey.avsc +1 -0
  419. datahub/metadata/schemas/MLFeatureTableKey.avsc +1 -0
  420. datahub/metadata/schemas/MLModelDeploymentKey.avsc +8 -0
  421. datahub/metadata/schemas/MLModelDeploymentProperties.avsc +3 -0
  422. datahub/metadata/schemas/MLModelGroupKey.avsc +11 -1
  423. datahub/metadata/schemas/MLModelGroupProperties.avsc +16 -0
  424. datahub/metadata/schemas/MLModelKey.avsc +9 -0
  425. datahub/metadata/schemas/MLPrimaryKeyKey.avsc +1 -0
  426. datahub/metadata/schemas/MetadataChangeEvent.avsc +189 -47
  427. datahub/metadata/schemas/MetadataChangeLog.avsc +65 -44
  428. datahub/metadata/schemas/MetadataChangeProposal.avsc +64 -0
  429. datahub/metadata/schemas/NotebookKey.avsc +1 -0
  430. datahub/metadata/schemas/Operation.avsc +21 -2
  431. datahub/metadata/schemas/Ownership.avsc +69 -0
  432. datahub/metadata/schemas/QueryProperties.avsc +24 -2
  433. datahub/metadata/schemas/QuerySubjects.avsc +1 -12
  434. datahub/metadata/schemas/RelationshipChangeEvent.avsc +215 -0
  435. datahub/metadata/schemas/SchemaFieldKey.avsc +4 -1
  436. datahub/metadata/schemas/Siblings.avsc +2 -0
  437. datahub/metadata/schemas/SlackUserInfo.avsc +160 -0
  438. datahub/metadata/schemas/StructuredProperties.avsc +69 -0
  439. datahub/metadata/schemas/StructuredPropertySettings.avsc +9 -0
  440. datahub/metadata/schemas/SystemMetadata.avsc +147 -0
  441. datahub/metadata/schemas/UpstreamLineage.avsc +9 -0
  442. datahub/metadata/schemas/__init__.py +3 -3
  443. datahub/sdk/__init__.py +7 -0
  444. datahub/sdk/_all_entities.py +15 -0
  445. datahub/sdk/_shared.py +393 -10
  446. datahub/sdk/_utils.py +4 -0
  447. datahub/sdk/chart.py +386 -0
  448. datahub/sdk/container.py +7 -0
  449. datahub/sdk/dashboard.py +453 -0
  450. datahub/sdk/dataflow.py +309 -0
  451. datahub/sdk/datajob.py +367 -0
  452. datahub/sdk/dataset.py +180 -4
  453. datahub/sdk/entity.py +99 -3
  454. datahub/sdk/entity_client.py +154 -12
  455. datahub/sdk/lineage_client.py +943 -0
  456. datahub/sdk/main_client.py +83 -8
  457. datahub/sdk/mlmodel.py +383 -0
  458. datahub/sdk/mlmodelgroup.py +240 -0
  459. datahub/sdk/search_client.py +85 -8
  460. datahub/sdk/search_filters.py +393 -68
  461. datahub/secret/datahub_secret_store.py +5 -1
  462. datahub/secret/environment_secret_store.py +29 -0
  463. datahub/secret/file_secret_store.py +49 -0
  464. datahub/specific/aspect_helpers/fine_grained_lineage.py +76 -0
  465. datahub/specific/aspect_helpers/siblings.py +73 -0
  466. datahub/specific/aspect_helpers/structured_properties.py +27 -0
  467. datahub/specific/chart.py +1 -1
  468. datahub/specific/datajob.py +15 -1
  469. datahub/specific/dataproduct.py +4 -0
  470. datahub/specific/dataset.py +51 -59
  471. datahub/sql_parsing/_sqlglot_patch.py +1 -2
  472. datahub/sql_parsing/fingerprint_utils.py +6 -0
  473. datahub/sql_parsing/split_statements.py +30 -3
  474. datahub/sql_parsing/sql_parsing_aggregator.py +144 -63
  475. datahub/sql_parsing/sqlglot_lineage.py +517 -44
  476. datahub/sql_parsing/sqlglot_utils.py +30 -18
  477. datahub/sql_parsing/tool_meta_extractor.py +25 -2
  478. datahub/telemetry/telemetry.py +30 -16
  479. datahub/testing/check_imports.py +1 -1
  480. datahub/testing/docker_utils.py +8 -2
  481. datahub/testing/mce_helpers.py +421 -0
  482. datahub/testing/mcp_diff.py +17 -21
  483. datahub/testing/sdk_v2_helpers.py +18 -0
  484. datahub/upgrade/upgrade.py +86 -30
  485. datahub/utilities/file_backed_collections.py +14 -15
  486. datahub/utilities/hive_schema_to_avro.py +2 -2
  487. datahub/utilities/ingest_utils.py +2 -2
  488. datahub/utilities/is_pytest.py +3 -2
  489. datahub/utilities/logging_manager.py +30 -7
  490. datahub/utilities/mapping.py +29 -2
  491. datahub/utilities/sample_data.py +5 -4
  492. datahub/utilities/server_config_util.py +298 -10
  493. datahub/utilities/sqlalchemy_query_combiner.py +6 -4
  494. datahub/utilities/stats_collections.py +4 -0
  495. datahub/utilities/threaded_iterator_executor.py +16 -3
  496. datahub/utilities/urn_encoder.py +1 -1
  497. datahub/utilities/urns/urn.py +41 -2
  498. datahub/emitter/sql_parsing_builder.py +0 -306
  499. datahub/ingestion/source/redshift/lineage_v2.py +0 -458
  500. datahub/ingestion/source/vertexai.py +0 -697
  501. datahub/ingestion/transformer/system_metadata_transformer.py +0 -45
  502. {acryl_datahub-1.0.0rc18.dist-info → acryl_datahub-1.3.0.1rc9.dist-info/licenses}/LICENSE +0 -0
  503. {acryl_datahub-1.0.0rc18.dist-info → acryl_datahub-1.3.0.1rc9.dist-info}/top_level.txt +0 -0
@@ -332,7 +332,8 @@
332
332
  "createdActor": "inputEdges/*/created/actor",
333
333
  "createdOn": "inputEdges/*/created/time",
334
334
  "entityTypes": [
335
- "dataset"
335
+ "dataset",
336
+ "chart"
336
337
  ],
337
338
  "isLineage": true,
338
339
  "name": "Consumes",
@@ -747,6 +748,75 @@
747
748
  "name": "source",
748
749
  "default": null,
749
750
  "doc": "Source information for the ownership"
751
+ },
752
+ {
753
+ "Searchable": {
754
+ "/actor": {
755
+ "fieldName": "ownerAttributionActors",
756
+ "fieldType": "URN",
757
+ "queryByDefault": false
758
+ },
759
+ "/source": {
760
+ "fieldName": "ownerAttributionSources",
761
+ "fieldType": "URN",
762
+ "queryByDefault": false
763
+ },
764
+ "/time": {
765
+ "fieldName": "ownerAttributionDates",
766
+ "fieldType": "DATETIME",
767
+ "queryByDefault": false
768
+ }
769
+ },
770
+ "type": [
771
+ "null",
772
+ {
773
+ "type": "record",
774
+ "name": "MetadataAttribution",
775
+ "namespace": "com.linkedin.pegasus2avro.common",
776
+ "fields": [
777
+ {
778
+ "type": "long",
779
+ "name": "time",
780
+ "doc": "When this metadata was updated."
781
+ },
782
+ {
783
+ "java": {
784
+ "class": "com.linkedin.pegasus2avro.common.urn.Urn"
785
+ },
786
+ "type": "string",
787
+ "name": "actor",
788
+ "doc": "The entity (e.g. a member URN) responsible for applying the assocated metadata. This can\neither be a user (in case of UI edits) or the datahub system for automation.",
789
+ "Urn": "Urn"
790
+ },
791
+ {
792
+ "java": {
793
+ "class": "com.linkedin.pegasus2avro.common.urn.Urn"
794
+ },
795
+ "type": [
796
+ "null",
797
+ "string"
798
+ ],
799
+ "name": "source",
800
+ "default": null,
801
+ "doc": "The DataHub source responsible for applying the associated metadata. This will only be filled out\nwhen a DataHub source is responsible. This includes the specific metadata test urn, the automation urn.",
802
+ "Urn": "Urn"
803
+ },
804
+ {
805
+ "type": {
806
+ "type": "map",
807
+ "values": "string"
808
+ },
809
+ "name": "sourceDetail",
810
+ "default": {},
811
+ "doc": "The details associated with why this metadata was applied. For example, this could include\nthe actual regex rule, sql statement, ingestion pipeline ID, etc."
812
+ }
813
+ ],
814
+ "doc": "Information about who, why, and how this metadata was applied"
815
+ }
816
+ ],
817
+ "name": "attribution",
818
+ "default": null,
819
+ "doc": "Information about who, why, and how this metadata was applied"
750
820
  }
751
821
  ],
752
822
  "doc": "Ownership information"
@@ -883,50 +953,7 @@
883
953
  },
884
954
  "type": [
885
955
  "null",
886
- {
887
- "type": "record",
888
- "name": "MetadataAttribution",
889
- "namespace": "com.linkedin.pegasus2avro.common",
890
- "fields": [
891
- {
892
- "type": "long",
893
- "name": "time",
894
- "doc": "When this metadata was updated."
895
- },
896
- {
897
- "java": {
898
- "class": "com.linkedin.pegasus2avro.common.urn.Urn"
899
- },
900
- "type": "string",
901
- "name": "actor",
902
- "doc": "The entity (e.g. a member URN) responsible for applying the assocated metadata. This can\neither be a user (in case of UI edits) or the datahub system for automation.",
903
- "Urn": "Urn"
904
- },
905
- {
906
- "java": {
907
- "class": "com.linkedin.pegasus2avro.common.urn.Urn"
908
- },
909
- "type": [
910
- "null",
911
- "string"
912
- ],
913
- "name": "source",
914
- "default": null,
915
- "doc": "The DataHub source responsible for applying the associated metadata. This will only be filled out\nwhen a DataHub source is responsible. This includes the specific metadata test urn, the automation urn.",
916
- "Urn": "Urn"
917
- },
918
- {
919
- "type": {
920
- "type": "map",
921
- "values": "string"
922
- },
923
- "name": "sourceDetail",
924
- "default": {},
925
- "doc": "The details associated with why this metadata was applied. For example, this could include\nthe actual regex rule, sql statement, ingestion pipeline ID, etc."
926
- }
927
- ],
928
- "doc": "Information about who, why, and how this metadata was applied"
929
- }
956
+ "com.linkedin.pegasus2avro.common.MetadataAttribution"
930
957
  ],
931
958
  "name": "attribution",
932
959
  "default": null,
@@ -1107,6 +1134,37 @@
1107
1134
  "type": "com.linkedin.pegasus2avro.common.AuditStamp",
1108
1135
  "name": "createStamp",
1109
1136
  "doc": "Audit stamp associated with creation of this record"
1137
+ },
1138
+ {
1139
+ "type": [
1140
+ "null",
1141
+ "com.linkedin.pegasus2avro.common.AuditStamp"
1142
+ ],
1143
+ "name": "updateStamp",
1144
+ "default": null,
1145
+ "doc": "Audit stamp associated with updation of this record"
1146
+ },
1147
+ {
1148
+ "type": [
1149
+ "null",
1150
+ {
1151
+ "type": "record",
1152
+ "name": "InstitutionalMemoryMetadataSettings",
1153
+ "namespace": "com.linkedin.pegasus2avro.common",
1154
+ "fields": [
1155
+ {
1156
+ "type": "boolean",
1157
+ "name": "showInAssetPreview",
1158
+ "default": false,
1159
+ "doc": "Show record in asset preview like on entity header and search previews"
1160
+ }
1161
+ ],
1162
+ "doc": "Settings related to a record of InstitutionalMemoryMetadata"
1163
+ }
1164
+ ],
1165
+ "name": "settings",
1166
+ "default": null,
1167
+ "doc": "Settings for this record"
1110
1168
  }
1111
1169
  ],
1112
1170
  "doc": "Metadata corresponding to a record of institutional memory."
@@ -1691,7 +1749,7 @@
1691
1749
  },
1692
1750
  "type": "string",
1693
1751
  "name": "pictureLink",
1694
- "default": "https://raw.githubusercontent.com/datahub-project/datahub/master/datahub-web-react/src/images/default_avatar.png",
1752
+ "default": "assets/platforms/default_avatar.png",
1695
1753
  "doc": "A URL which points to a picture which user wants to set as a profile photo"
1696
1754
  },
1697
1755
  {
@@ -1787,6 +1845,20 @@
1787
1845
  "name": "email",
1788
1846
  "default": null,
1789
1847
  "doc": "Email address to contact the user"
1848
+ },
1849
+ {
1850
+ "type": [
1851
+ "null",
1852
+ {
1853
+ "type": "array",
1854
+ "items": "string"
1855
+ }
1856
+ ],
1857
+ "name": "informationSources",
1858
+ "default": null,
1859
+ "doc": "Information sources that have been used to populate this CorpUserEditableInfo.\nThese include platform resources, such as Slack members or Looker users.\nThey can also refer to other semantic urns in the future.",
1860
+ "Urn": "Urn",
1861
+ "urn_is_array": true
1790
1862
  }
1791
1863
  ],
1792
1864
  "doc": "Linkedin corp user information that can be edited from UI"
@@ -2410,13 +2482,17 @@
2410
2482
  "DEV": "Designates development fabrics",
2411
2483
  "EI": "Designates early-integration fabrics",
2412
2484
  "NON_PROD": "Designates non-production fabrics",
2485
+ "PRD": "Alternative Prod spelling",
2413
2486
  "PRE": "Designates pre-production fabrics",
2414
2487
  "PROD": "Designates production fabrics",
2415
2488
  "QA": "Designates quality assurance fabrics",
2416
2489
  "RVW": "Designates review fabrics",
2417
2490
  "SANDBOX": "Designates sandbox fabrics",
2491
+ "SBX": "Alternative spelling for sandbox",
2492
+ "SIT": "System Integration Testing",
2418
2493
  "STG": "Designates staging fabrics",
2419
2494
  "TEST": "Designates testing fabrics",
2495
+ "TST": "Alternative Test spelling",
2420
2496
  "UAT": "Designates user acceptance testing fabrics"
2421
2497
  },
2422
2498
  "name": "FabricType",
@@ -2433,6 +2509,10 @@
2433
2509
  "PROD",
2434
2510
  "CORP",
2435
2511
  "RVW",
2512
+ "PRD",
2513
+ "TST",
2514
+ "SIT",
2515
+ "SBX",
2436
2516
  "SANDBOX"
2437
2517
  ],
2438
2518
  "doc": "Fabric group type"
@@ -3048,6 +3128,14 @@
3048
3128
  "doc": "The type of upstream entity"
3049
3129
  },
3050
3130
  {
3131
+ "Searchable": {
3132
+ "/*": {
3133
+ "fieldName": "fineGrainedUpstreams",
3134
+ "fieldType": "URN",
3135
+ "hasValuesFieldName": "hasFineGrainedUpstreams",
3136
+ "queryByDefault": false
3137
+ }
3138
+ },
3051
3139
  "type": [
3052
3140
  "null",
3053
3141
  {
@@ -3669,6 +3757,7 @@
3669
3757
  "Searchable": {
3670
3758
  "fieldName": "upstreams",
3671
3759
  "fieldType": "URN",
3760
+ "hasValuesFieldName": "hasUpstreams",
3672
3761
  "queryByDefault": false
3673
3762
  },
3674
3763
  "java": {
@@ -6038,7 +6127,9 @@
6038
6127
  "fields": [
6039
6128
  {
6040
6129
  "Searchable": {
6130
+ "addToFilters": true,
6041
6131
  "fieldType": "BOOLEAN",
6132
+ "filterNameOverride": "Deprecated",
6042
6133
  "weightsPerFieldValue": {
6043
6134
  "true": 0.5
6044
6135
  }
@@ -6739,6 +6830,9 @@
6739
6830
  "doc": "Version of the MLModelDeployment"
6740
6831
  },
6741
6832
  {
6833
+ "Searchable": {
6834
+ "fieldName": "deploymentStatus"
6835
+ },
6742
6836
  "type": [
6743
6837
  "null",
6744
6838
  {
@@ -6919,6 +7013,22 @@
6919
7013
  "default": null,
6920
7014
  "doc": "List of jobs or process instances (if any) that use the model or group."
6921
7015
  },
7016
+ {
7017
+ "Searchable": {
7018
+ "fieldType": "KEYWORD"
7019
+ },
7020
+ "java": {
7021
+ "class": "com.linkedin.pegasus2avro.common.url.Url",
7022
+ "coercerClass": "com.linkedin.pegasus2avro.common.url.UrlCoercer"
7023
+ },
7024
+ "type": [
7025
+ "null",
7026
+ "string"
7027
+ ],
7028
+ "name": "externalUrl",
7029
+ "default": null,
7030
+ "doc": "URL where the reference exist"
7031
+ },
6922
7032
  {
6923
7033
  "Searchable": {
6924
7034
  "boostScore": 10.0,
@@ -7698,13 +7808,15 @@
7698
7808
  "type": "enum",
7699
7809
  "symbolDocs": {
7700
7810
  "EQUALS": "Whether the field matches the value",
7811
+ "NOT_EQUALS": "Whether the field does not match the value",
7701
7812
  "STARTS_WITH": "Whether the field value starts with the value"
7702
7813
  },
7703
7814
  "name": "PolicyMatchCondition",
7704
7815
  "namespace": "com.linkedin.pegasus2avro.policy",
7705
7816
  "symbols": [
7706
7817
  "EQUALS",
7707
- "STARTS_WITH"
7818
+ "STARTS_WITH",
7819
+ "NOT_EQUALS"
7708
7820
  ],
7709
7821
  "doc": "The matching condition in a filter criterion"
7710
7822
  },
@@ -7726,6 +7838,15 @@
7726
7838
  "name": "filter",
7727
7839
  "default": null,
7728
7840
  "doc": "Filter to apply privileges to"
7841
+ },
7842
+ {
7843
+ "type": [
7844
+ "null",
7845
+ "com.linkedin.pegasus2avro.policy.PolicyMatchFilter"
7846
+ ],
7847
+ "name": "privilegeConstraints",
7848
+ "default": null,
7849
+ "doc": "Constraints around what sub-resources operations are allowed to modify, i.e. NOT_EQUALS - cannot modify a particular defined tag, EQUALS - can only modify a particular defined tag, STARTS_WITH - can only modify a tag starting with xyz"
7729
7850
  }
7730
7851
  ],
7731
7852
  "doc": "Information used to filter DataHub resource."
@@ -8084,6 +8205,9 @@
8084
8205
  "null",
8085
8206
  {
8086
8207
  "type": "record",
8208
+ "Aspect": {
8209
+ "name": "systemMetadata"
8210
+ },
8087
8211
  "name": "SystemMetadata",
8088
8212
  "namespace": "com.linkedin.pegasus2avro.mxe",
8089
8213
  "fields": [
@@ -8161,6 +8285,24 @@
8161
8285
  "name": "version",
8162
8286
  "default": null,
8163
8287
  "doc": "Aspect version\n Initial implementation will use the aspect version's number, however stored as\n a string in the case where a different aspect versioning scheme is later adopted."
8288
+ },
8289
+ {
8290
+ "type": [
8291
+ "null",
8292
+ "com.linkedin.pegasus2avro.common.AuditStamp"
8293
+ ],
8294
+ "name": "aspectCreated",
8295
+ "default": null,
8296
+ "doc": "When the aspect was initially created and who created it, detected by version 0 -> 1 change"
8297
+ },
8298
+ {
8299
+ "type": [
8300
+ "null",
8301
+ "com.linkedin.pegasus2avro.common.AuditStamp"
8302
+ ],
8303
+ "name": "aspectModified",
8304
+ "default": null,
8305
+ "doc": "When the aspect was last modified and the actor that performed the modification"
8164
8306
  }
8165
8307
  ],
8166
8308
  "doc": "Metadata associated with each metadata change that is processed by the system"
@@ -187,6 +187,9 @@
187
187
  "null",
188
188
  {
189
189
  "type": "record",
190
+ "Aspect": {
191
+ "name": "systemMetadata"
192
+ },
190
193
  "name": "SystemMetadata",
191
194
  "namespace": "com.linkedin.pegasus2avro.mxe",
192
195
  "fields": [
@@ -264,6 +267,67 @@
264
267
  "name": "version",
265
268
  "default": null,
266
269
  "doc": "Aspect version\n Initial implementation will use the aspect version's number, however stored as\n a string in the case where a different aspect versioning scheme is later adopted."
270
+ },
271
+ {
272
+ "type": [
273
+ "null",
274
+ {
275
+ "type": "record",
276
+ "name": "AuditStamp",
277
+ "namespace": "com.linkedin.pegasus2avro.common",
278
+ "fields": [
279
+ {
280
+ "type": "long",
281
+ "name": "time",
282
+ "doc": "When did the resource/association/sub-resource move into the specific lifecycle stage represented by this AuditEvent."
283
+ },
284
+ {
285
+ "java": {
286
+ "class": "com.linkedin.pegasus2avro.common.urn.Urn"
287
+ },
288
+ "type": "string",
289
+ "name": "actor",
290
+ "doc": "The entity (e.g. a member URN) which will be credited for moving the resource/association/sub-resource into the specific lifecycle stage. It is also the one used to authorize the change.",
291
+ "Urn": "Urn"
292
+ },
293
+ {
294
+ "java": {
295
+ "class": "com.linkedin.pegasus2avro.common.urn.Urn"
296
+ },
297
+ "type": [
298
+ "null",
299
+ "string"
300
+ ],
301
+ "name": "impersonator",
302
+ "default": null,
303
+ "doc": "The entity (e.g. a service URN) which performs the change on behalf of the Actor and must be authorized to act as the Actor.",
304
+ "Urn": "Urn"
305
+ },
306
+ {
307
+ "type": [
308
+ "null",
309
+ "string"
310
+ ],
311
+ "name": "message",
312
+ "default": null,
313
+ "doc": "Additional context around how DataHub was informed of the particular change. For example: was the change created by an automated process, or manually."
314
+ }
315
+ ],
316
+ "doc": "Data captured on a resource/association/sub-resource level giving insight into when that resource/association/sub-resource moved into a particular lifecycle stage, and who acted to move it into that specific lifecycle stage."
317
+ }
318
+ ],
319
+ "name": "aspectCreated",
320
+ "default": null,
321
+ "doc": "When the aspect was initially created and who created it, detected by version 0 -> 1 change"
322
+ },
323
+ {
324
+ "type": [
325
+ "null",
326
+ "com.linkedin.pegasus2avro.common.AuditStamp"
327
+ ],
328
+ "name": "aspectModified",
329
+ "default": null,
330
+ "doc": "When the aspect was last modified and the actor that performed the modification"
267
331
  }
268
332
  ],
269
333
  "doc": "Metadata associated with each metadata change that is processed by the system"
@@ -306,50 +370,7 @@
306
370
  {
307
371
  "type": [
308
372
  "null",
309
- {
310
- "type": "record",
311
- "name": "AuditStamp",
312
- "namespace": "com.linkedin.pegasus2avro.common",
313
- "fields": [
314
- {
315
- "type": "long",
316
- "name": "time",
317
- "doc": "When did the resource/association/sub-resource move into the specific lifecycle stage represented by this AuditEvent."
318
- },
319
- {
320
- "java": {
321
- "class": "com.linkedin.pegasus2avro.common.urn.Urn"
322
- },
323
- "type": "string",
324
- "name": "actor",
325
- "doc": "The entity (e.g. a member URN) which will be credited for moving the resource/association/sub-resource into the specific lifecycle stage. It is also the one used to authorize the change.",
326
- "Urn": "Urn"
327
- },
328
- {
329
- "java": {
330
- "class": "com.linkedin.pegasus2avro.common.urn.Urn"
331
- },
332
- "type": [
333
- "null",
334
- "string"
335
- ],
336
- "name": "impersonator",
337
- "default": null,
338
- "doc": "The entity (e.g. a service URN) which performs the change on behalf of the Actor and must be authorized to act as the Actor.",
339
- "Urn": "Urn"
340
- },
341
- {
342
- "type": [
343
- "null",
344
- "string"
345
- ],
346
- "name": "message",
347
- "default": null,
348
- "doc": "Additional context around how DataHub was informed of the particular change. For example: was the change created by an automated process, or manually."
349
- }
350
- ],
351
- "doc": "Data captured on a resource/association/sub-resource level giving insight into when that resource/association/sub-resource moved into a particular lifecycle stage, and who acted to move it into that specific lifecycle stage."
352
- }
373
+ "com.linkedin.pegasus2avro.common.AuditStamp"
353
374
  ],
354
375
  "name": "created",
355
376
  "default": null,
@@ -187,6 +187,9 @@
187
187
  "null",
188
188
  {
189
189
  "type": "record",
190
+ "Aspect": {
191
+ "name": "systemMetadata"
192
+ },
190
193
  "name": "SystemMetadata",
191
194
  "namespace": "com.linkedin.pegasus2avro.mxe",
192
195
  "fields": [
@@ -264,6 +267,67 @@
264
267
  "name": "version",
265
268
  "default": null,
266
269
  "doc": "Aspect version\n Initial implementation will use the aspect version's number, however stored as\n a string in the case where a different aspect versioning scheme is later adopted."
270
+ },
271
+ {
272
+ "type": [
273
+ "null",
274
+ {
275
+ "type": "record",
276
+ "name": "AuditStamp",
277
+ "namespace": "com.linkedin.pegasus2avro.common",
278
+ "fields": [
279
+ {
280
+ "type": "long",
281
+ "name": "time",
282
+ "doc": "When did the resource/association/sub-resource move into the specific lifecycle stage represented by this AuditEvent."
283
+ },
284
+ {
285
+ "java": {
286
+ "class": "com.linkedin.pegasus2avro.common.urn.Urn"
287
+ },
288
+ "type": "string",
289
+ "name": "actor",
290
+ "doc": "The entity (e.g. a member URN) which will be credited for moving the resource/association/sub-resource into the specific lifecycle stage. It is also the one used to authorize the change.",
291
+ "Urn": "Urn"
292
+ },
293
+ {
294
+ "java": {
295
+ "class": "com.linkedin.pegasus2avro.common.urn.Urn"
296
+ },
297
+ "type": [
298
+ "null",
299
+ "string"
300
+ ],
301
+ "name": "impersonator",
302
+ "default": null,
303
+ "doc": "The entity (e.g. a service URN) which performs the change on behalf of the Actor and must be authorized to act as the Actor.",
304
+ "Urn": "Urn"
305
+ },
306
+ {
307
+ "type": [
308
+ "null",
309
+ "string"
310
+ ],
311
+ "name": "message",
312
+ "default": null,
313
+ "doc": "Additional context around how DataHub was informed of the particular change. For example: was the change created by an automated process, or manually."
314
+ }
315
+ ],
316
+ "doc": "Data captured on a resource/association/sub-resource level giving insight into when that resource/association/sub-resource moved into a particular lifecycle stage, and who acted to move it into that specific lifecycle stage."
317
+ }
318
+ ],
319
+ "name": "aspectCreated",
320
+ "default": null,
321
+ "doc": "When the aspect was initially created and who created it, detected by version 0 -> 1 change"
322
+ },
323
+ {
324
+ "type": [
325
+ "null",
326
+ "com.linkedin.pegasus2avro.common.AuditStamp"
327
+ ],
328
+ "name": "aspectModified",
329
+ "default": null,
330
+ "doc": "When the aspect was last modified and the actor that performed the modification"
267
331
  }
268
332
  ],
269
333
  "doc": "Metadata associated with each metadata change that is processed by the system"
@@ -15,6 +15,7 @@
15
15
  "browsePaths",
16
16
  "institutionalMemory",
17
17
  "domains",
18
+ "applications",
18
19
  "subTypes",
19
20
  "dataPlatformInstance",
20
21
  "browsePathsV2",
@@ -150,7 +150,7 @@
150
150
  "symbolDocs": {
151
151
  "ALTER": "Asset was altered",
152
152
  "CREATE": "Asset was created",
153
- "CUSTOM": "Custom asset operation",
153
+ "CUSTOM": "Custom asset operation. If this is set, ensure customOperationType is filled out.",
154
154
  "DELETE": "Rows were deleted",
155
155
  "DROP": "Asset was dropped",
156
156
  "INSERT": "Rows were inserted",
@@ -250,10 +250,29 @@
250
250
  "fieldName": "lastOperationTime",
251
251
  "fieldType": "DATETIME"
252
252
  },
253
- "TimeseriesField": {},
253
+ "TimeseriesField": {
254
+ "fieldType": "DATETIME"
255
+ },
254
256
  "type": "long",
255
257
  "name": "lastUpdatedTimestamp",
256
258
  "doc": "The time at which the operation occurred. Would be better named 'operationTime'"
259
+ },
260
+ {
261
+ "TimeseriesFieldCollection": {
262
+ "key": "query"
263
+ },
264
+ "type": [
265
+ "null",
266
+ {
267
+ "type": "array",
268
+ "items": "string"
269
+ }
270
+ ],
271
+ "name": "queries",
272
+ "default": null,
273
+ "doc": "Which queries were used in this operation.",
274
+ "Urn": "Urn",
275
+ "urn_is_array": true
257
276
  }
258
277
  ],
259
278
  "doc": "Operational info for an entity."