acryl-datahub 0.15.0rc24__py3-none-any.whl → 0.15.0.1rc1__py3-none-any.whl

{acryl_datahub-0.15.0rc24.dist-info → acryl_datahub-0.15.0.1rc1.dist-info}/RECORD

@@ -1,4 +1,4 @@
-datahub/__init__.py,sha256=I7rWvDl7l3VZ5DC3mtaoQKDToqQCmmprWfOtkh9E_mM,575
+datahub/__init__.py,sha256=gK5aLEGMHMZfg-QUDI5T7mr1ej_5OFVKhCrqqoj_QGk,576
 datahub/__main__.py,sha256=pegIvQ9hzK7IhqVeUi1MeADSZ2QlP-D3K0OQdEg55RU,106
 datahub/entrypoints.py,sha256=3-qSfXAx3Z0FEkBV5tlO8fQr4xk4ySeDRMVTpS5Xd6A,7793
 datahub/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -52,7 +52,7 @@ datahub/api/entities/forms/forms_graphql_constants.py,sha256=DKpnKlMKTjmnyrCTvp6
 datahub/api/entities/platformresource/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 datahub/api/entities/platformresource/platform_resource.py,sha256=pVAjv6NoH746Mfvdak7ji0eqlEcEeV-Ji7M5gyNXmds,10603
 datahub/api/entities/structuredproperties/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-datahub/api/entities/structuredproperties/structuredproperties.py,sha256=tYEVp2oqJa9FhlrnbAf2Zw82WqicJI9lF0P5U9soY9E,7502
+datahub/api/entities/structuredproperties/structuredproperties.py,sha256=wtIt-zqW8_PamvSPpRR28tKkiOAZ7ME3lufoaTeGnlU,8116
 datahub/api/graphql/__init__.py,sha256=5yl0dJxO-2d_QuykdJrDIbWq4ja9bo0t2dAEh89JOog,142
 datahub/api/graphql/assertion.py,sha256=ponITypRQ8vE8kiqRNpvdoniNJzi4aeBK97UvkF0VhA,2818
 datahub/api/graphql/base.py,sha256=9q637r6v-RGOd8Mk8HW2g0vt9zpqFexsQ5R6TPEHVbs,1614
@@ -100,7 +100,7 @@ datahub/configuration/kafka.py,sha256=MlIwpd5FFyOyjdDXW_X9JTLNk7f988sPMgevkcZYVg
 datahub/configuration/kafka_consumer_config.py,sha256=LivsObTt9yC3WoGnslJbF_x4ojfNdxMIMEhb8vvJfcA,2133
 datahub/configuration/pattern_utils.py,sha256=Q5IB9RfWOOo5FvRVBU7XkhiwHCxSQ1NTMfUlWtWI9qc,699
 datahub/configuration/pydantic_migration_helpers.py,sha256=4C_COAVZ5iJ8yxcWNgXZNWsY7ULogICNZ368oNF7zWg,1462
-datahub/configuration/source_common.py,sha256=68LZOuB23zSEcfgQJE1wZQnyYQHVVnEZK3Sniv_nEQs,2107
+datahub/configuration/source_common.py,sha256=CXs5xJzeFpnrKojVZbHZOvoBDnrkEogN-e8hqMERzfo,2606
 datahub/configuration/time_window_config.py,sha256=xuwoftrHWC069qfumErCV3BCuE-RWVsDLAefNWn_RFc,5347
 datahub/configuration/toml.py,sha256=Ohc5sAWLPoAinPYL8njyheZ3ak81fC2Sp8IbBbESPGg,380
 datahub/configuration/validate_field_deprecation.py,sha256=byBKOlGhPkRO_aCXlJ9BQk7-v3RqCnwI5_sho72ZDMQ,1268
@@ -195,7 +195,7 @@ datahub/ingestion/source/ge_profiling_config.py,sha256=P-9pd20koFvpxeEL_pqFvKWWz
 datahub/ingestion/source/glue_profiling_config.py,sha256=vpMJH4Lf_qgR32BZy58suabri1yV5geaAPjzg2eORDc,2559
 datahub/ingestion/source/ldap.py,sha256=Vnzg8tpwBYeyM-KBVVsUJvGZGBMJiCJ_i_FhxaFRQ9A,18627
 datahub/ingestion/source/metabase.py,sha256=oemiMdzjfr82Hx6rdwTNBzFM8962LDkosYh7SD_I5cY,31717
-datahub/ingestion/source/mlflow.py,sha256=SxCt4jtxQcpPWEI2rRNagCiE_6TWr2RroqmxRd_td1Y,11565
+datahub/ingestion/source/mlflow.py,sha256=-yWUuAEVBiNN-elz8Pgn0UeGsC3fVB20z1zKNIr4LXI,12309
 datahub/ingestion/source/mode.py,sha256=n_5em3jADCr5gWTLDOP4O4bRS0Zt_TCZtW8uFPxn-DI,63043
 datahub/ingestion/source/mongodb.py,sha256=vZue4Nz0xaBoCUsQr3_0OIRkWRxeE_IH_Y_QKZ1s7S0,21077
 datahub/ingestion/source/nifi.py,sha256=ttsjZ9aRUvINmewvKFIQD8Rwa4jcl35WFG-F-jPGPWQ,56146
@@ -313,28 +313,32 @@ datahub/ingestion/source/git/git_import.py,sha256=5CT6vMDb0MDctCtShnxb3JVihULtvk
 datahub/ingestion/source/grafana/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 datahub/ingestion/source/grafana/grafana_source.py,sha256=3pU3xodPgS5lmnjuQ_u7F0XPzD_Y8MnPlMxRJ86qz4g,4960
 datahub/ingestion/source/iceberg/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-datahub/ingestion/source/iceberg/iceberg.py,sha256=fjqp3VBW5W5-54X_-ubkRZiAmdHvuMbxRbC4UYzEr4U,25900
-datahub/ingestion/source/iceberg/iceberg_common.py,sha256=TS3_ZYZ47Fe02CmzEo1z0pvy7yjXuG1VlwqNxa0U6pc,8506
+datahub/ingestion/source/iceberg/iceberg.py,sha256=Pi2QD8v0HOpqr8M9la78Nlm3Be9iy3G4pCZqu2NitZM,27253
+datahub/ingestion/source/iceberg/iceberg_common.py,sha256=4efWbnj8iWWNcO6_lFXFZRIzaKVPWhd1MmmxdJafemw,8684
 datahub/ingestion/source/iceberg/iceberg_profiler.py,sha256=hLT1Le_TEUoFXvsJSlrRB1qbTiTe-YVGCof5TFHMyd8,9908
 datahub/ingestion/source/identity/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 datahub/ingestion/source/identity/azure_ad.py,sha256=GdmJFD4UMsb5353Z7phXRf-YsXR2woGLRJwBXUkgXq0,28809
 datahub/ingestion/source/identity/okta.py,sha256=PnRokWLG8wSoNZlXJiRZiW6APTEHO09q4n2j_l6m3V0,30756
 datahub/ingestion/source/kafka/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 datahub/ingestion/source/kafka/kafka.py,sha256=9SR7bqp9J0rPYde5IClhnAuVNy9ItsB8-ZeXtTc_mEY,26442
-datahub/ingestion/source/kafka/kafka_connect.py,sha256=Jm1MYky_OPIwvVHuEjgOjK0e6-jA-dYnsLZ7r-Y_9mA,56208
 datahub/ingestion/source/kafka/kafka_schema_registry_base.py,sha256=13XjSwqyVhH1CJUFHAbWdmmv_Rw0Ju_9HQdBmIzPNNA,566
+datahub/ingestion/source/kafka_connect/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+datahub/ingestion/source/kafka_connect/common.py,sha256=Ekb1K_J1eTgiH7LSP1AbEIf7NQh_2Vyu1lYX_Ggcqk4,7049
+datahub/ingestion/source/kafka_connect/kafka_connect.py,sha256=8bjVFDkwjgs3gP7Y3itzABGfBcY_WbMQ5PWjrm-g93A,14249
+datahub/ingestion/source/kafka_connect/sink_connectors.py,sha256=ESuJE5SFLLvss9OwDEIB8SAko4rhzaWZ-4dKY0Dh0N8,12900
+datahub/ingestion/source/kafka_connect/source_connectors.py,sha256=_765fSMDAWAe0Cf_F4VNHfOWKNhtqBA1Ep2jL3rf-qc,21263
 datahub/ingestion/source/looker/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 datahub/ingestion/source/looker/lkml_patched.py,sha256=XShEU7Wbz0DubDhYMjKf9wjKZrBJa2XPg9MIjp8rPhk,733
-datahub/ingestion/source/looker/looker_common.py,sha256=cIrsc0nDEsODxx9tjvSm2A3-OlCkPKCu4W2L8PxzLWs,59926
+datahub/ingestion/source/looker/looker_common.py,sha256=0-5xhq7vE9YFj8tzbvRI7RnP1cD_oxnN4NpSXjKzxjE,61726
 datahub/ingestion/source/looker/looker_config.py,sha256=87WAgdJ_QWdTq25RBwgIqfc2kq7dubSpzbEtXb2ihMw,13182
 datahub/ingestion/source/looker/looker_connection.py,sha256=yDmC6lDsHmL2e_Pw8ULylwOIHPWPp_6gT1iyLvD0fTw,2075
 datahub/ingestion/source/looker/looker_constant.py,sha256=GMKYtNXlpojPxa9azridKfcGLSJwKdUCTesp7U8dIrQ,402
 datahub/ingestion/source/looker/looker_dataclasses.py,sha256=ULWLFWsV2cKmTuOFavD8QjEBmnXmvjyr8RbUB62DwJQ,12178
 datahub/ingestion/source/looker/looker_file_loader.py,sha256=c1ewDrIb9VJg1o-asbwX9gL83kgL01vIETzzbmZIhmw,4267
-datahub/ingestion/source/looker/looker_lib_wrapper.py,sha256=QTTCW-rPNUoazQG_sTJbCARXJzQ7NKS-XKURp2AAWls,11106
+datahub/ingestion/source/looker/looker_lib_wrapper.py,sha256=0gaYjBv4wkbbLWVgvaAV6JyWAFb0utTG6TCve2d9xss,11511
 datahub/ingestion/source/looker/looker_liquid_tag.py,sha256=mO4G4MNA4YZFvZaDBpdiJ2vP3irC82kY34RdaK4Pbfs,3100
 datahub/ingestion/source/looker/looker_query_model.py,sha256=N0jBbFruiCIIGT6sJn6tNeppeQ78KGTkOwTLirhxFNc,2144
-datahub/ingestion/source/looker/looker_source.py,sha256=AByQxWVfOBqOtZPaR_cw9SB-tFZtfppiKRkFSbcK1GA,65346
+datahub/ingestion/source/looker/looker_source.py,sha256=IUI2FpYG2_bhVnP_LZeQymjc5D0F7lqYTADktzV3yr8,65735
 datahub/ingestion/source/looker/looker_template_language.py,sha256=EG4ZfVZ0x53lgaYh2ohzL4ZCy9KsX0TA51XqCmsCd2Q,14328
 datahub/ingestion/source/looker/looker_usage.py,sha256=qegMr-Rnqz3xNGSBfsuD3S_BPXf7UEMhwFN7DPQeLNo,22914
 datahub/ingestion/source/looker/looker_view_id_cache.py,sha256=92gDy6NONhJYBp92z_IBzDVZvezmUIkaBCZY1bdk6mE,4392
@@ -351,15 +355,15 @@ datahub/ingestion/source/metadata/lineage.py,sha256=XiZGuY6k3O9qBmgo7AzosIndJHwr
 datahub/ingestion/source/neo4j/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 datahub/ingestion/source/neo4j/neo4j_source.py,sha256=L9WiZ5yZrIDMrgj3gYU9j6zz3TRMXYpcWxeTegD7sFg,12409
 datahub/ingestion/source/powerbi/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-datahub/ingestion/source/powerbi/config.py,sha256=LV8BOm2zzF9t0RMwQVVUNB0bStzBPo8A6JkaW0xlgsQ,23241
-datahub/ingestion/source/powerbi/dataplatform_instance_resolver.py,sha256=AIU89lVPoCWlzc_RfUjDJwRQ11akPtnGpBTluBMCKio,2242
+datahub/ingestion/source/powerbi/config.py,sha256=9cgMrwp3DQqv14iTqulAONkbVe5nhycJ1ElkA_275go,22732
+datahub/ingestion/source/powerbi/dataplatform_instance_resolver.py,sha256=-njW1kJOy-LY5JFwJLhVQ0bMBj9NQz5TZhQqsSi_KsM,2285
 datahub/ingestion/source/powerbi/powerbi-lexical-grammar.rule,sha256=PRWzuZMMhKdOVoAaE8csHvUFbZHxYe5meJHgrqlgiuw,19795
 datahub/ingestion/source/powerbi/powerbi.py,sha256=7UsAEqaFlkWONcXJdQ2hotUYYn46ks6Fe71KXEMh7lI,54495
 datahub/ingestion/source/powerbi/m_query/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 datahub/ingestion/source/powerbi/m_query/data_classes.py,sha256=EbaEasEOGZ73jz0cQofH9ez65wSvRBof0R6GQaIVLnM,2009
 datahub/ingestion/source/powerbi/m_query/native_sql_parser.py,sha256=zzKVDGeUM3Yv3-zNah4D6mSnr6jXsstNuLmzczcPQEE,3683
 datahub/ingestion/source/powerbi/m_query/parser.py,sha256=pB1LGdb02Ryf8Pr8JPSgiOmLE6mEAgDbKodtKOOY6LU,5782
-datahub/ingestion/source/powerbi/m_query/pattern_handler.py,sha256=h1gBh9Gz1zF3m-hA0WMQaBdEtcZUW9vScNKEvqIWCfk,32442
+datahub/ingestion/source/powerbi/m_query/pattern_handler.py,sha256=yDNdzPREzegarux_I9F_PsLe1hlSFa-uwoORrEgbO-c,32485
 datahub/ingestion/source/powerbi/m_query/resolver.py,sha256=TMt84_JaCazpP7vcneW0O3cUjtbIuh8Yid78JWfDxsI,16953
 datahub/ingestion/source/powerbi/m_query/tree_function.py,sha256=h77DunhlgOP0fAg8UXDXxxInOi7Pay85_d1Ca4YqyKs,6134
 datahub/ingestion/source/powerbi/m_query/validator.py,sha256=crG-VZy2XPieiDliP9yVMgiFcc8b2xbZyDFEATXqEAQ,1155
@@ -439,7 +443,7 @@ datahub/ingestion/source/snowflake/snowflake_summary.py,sha256=kTmuCtRnvHqM8WBYh
 datahub/ingestion/source/snowflake/snowflake_tag.py,sha256=fyfWmFVz2WZrpTJWNIe9m0WpDHgeFrGPf8diORJZUwo,6212
 datahub/ingestion/source/snowflake/snowflake_usage_v2.py,sha256=PEmYNMXJRUvLQmVd8juVqjokfuSPuH9ppcM0ruXamxA,24807
 datahub/ingestion/source/snowflake/snowflake_utils.py,sha256=YczNEupY89jeegjR2_1pT4bPi9wQ69EIhGpzyCe9Jdg,12600
-datahub/ingestion/source/snowflake/snowflake_v2.py,sha256=lo_3asTuIZbF-LuEUcYL-9NIZ720n7oB9mYA6WVTWA4,31960
+datahub/ingestion/source/snowflake/snowflake_v2.py,sha256=TlS5d1lpEN74ZP0c8UzUhJZIeBMO3ZIUxRler1p7lnA,31998
 datahub/ingestion/source/sql/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 datahub/ingestion/source/sql/athena.py,sha256=G3cIY8H_76lIUAzQWW2kLnZOEsfbakmojxbiHb3dYZ8,24059
 datahub/ingestion/source/sql/clickhouse.py,sha256=jzvaXP5Wr0SMhj2rtuvVE821xnfpKiXhO3cm0xblgHs,27299
@@ -467,8 +471,8 @@ datahub/ingestion/source/sql/trino.py,sha256=FEn_BQ3pm23hKx94ek5kk5IXGNYcBqZEhll
 datahub/ingestion/source/sql/two_tier_sql_source.py,sha256=YDrGBb5WKVls6qv17QU5foKrf71SydzEltc3WsVAhQc,5732
 datahub/ingestion/source/sql/vertica.py,sha256=_9OgSgIgqBml0av063rb8nACiT3SAmzpw0ouyF91wv8,33382
 datahub/ingestion/source/sql/mssql/__init__.py,sha256=1agpl8S_uDW40olkhCX_W19dbr5GO9qgjS3R7pLRZSk,87
-datahub/ingestion/source/sql/mssql/job_models.py,sha256=eMyR0Efl5kvi7QNgNXzd5_6PdDKYly_552Y8OGSj9PY,6012
-datahub/ingestion/source/sql/mssql/source.py,sha256=-B0bnFKEReciYzQ4p_2xJJzdn-H8vYz2MQ_h-1B0ibs,30329
+datahub/ingestion/source/sql/mssql/job_models.py,sha256=ztXDrD4anhzwWvACIm9fucE2WhMDMKkJ4alMYOQOqWA,7083
+datahub/ingestion/source/sql/mssql/source.py,sha256=ODdsOIbDA3X0E7En6GT15mD49W6RW9sXLwRoUgw2a8I,30925
 datahub/ingestion/source/sql/mssql/stored_procedure_lineage.py,sha256=RpnvKPalAAaOD_eUg8bZ4VkGTSeLFWuy0mefwc4s3x8,2837
 datahub/ingestion/source/state/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 datahub/ingestion/source/state/checkpoint.py,sha256=x9Xww-MIFXSKjeg1tOZXE72LehCm5OfKy3HfucgIRWM,8833
@@ -486,11 +490,11 @@ datahub/ingestion/source/state_provider/datahub_ingestion_checkpointing_provider
 datahub/ingestion/source/state_provider/file_ingestion_checkpointing_provider.py,sha256=xsH7Ao_05VTjqpkzLkhdf5B1ULMzFoD8vkJJIJU9w-U,4077
 datahub/ingestion/source/state_provider/state_provider_registry.py,sha256=SVq4mIyGNmLXE9OZx1taOiNPqDoQp03-Ot9rYnB5F3k,401
 datahub/ingestion/source/tableau/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-datahub/ingestion/source/tableau/tableau.py,sha256=P_DUuUvXk5u2ihA0JghtRkYc_KI_yQR2ZiQVe9IUvsU,138197
+datahub/ingestion/source/tableau/tableau.py,sha256=80m5a8g2q5jnm5pFtL4s_SmSeGPQIuZGqGe9RGn6OSI,138248
 datahub/ingestion/source/tableau/tableau_common.py,sha256=9gQLq_3BlAsKll83uVlnWJRWaIDtFtREUyuimXF13Z0,26219
-datahub/ingestion/source/tableau/tableau_constant.py,sha256=jVQMgLXND5aPL6XLETKp81BehRkvyLTU_Vhhe_1NOkI,2576
-datahub/ingestion/source/tableau/tableau_server_wrapper.py,sha256=PEGfcoUcBdsnOa5EzCqy1IiuQ3OZ9fZVEMzDqhhHOto,922
-datahub/ingestion/source/tableau/tableau_validation.py,sha256=l0DuXUuxJwEXMzo61xLx-KLc5u6tiz2n0e9EepJdWEM,1808
+datahub/ingestion/source/tableau/tableau_constant.py,sha256=ZcAeHsQUXVVL26ORly0ByZk_GJAFbxaKuJAlX_sYMac,2686
+datahub/ingestion/source/tableau/tableau_server_wrapper.py,sha256=nSyx9RzC6TCQDm-cTVJ657qT8iDwzk_8JMKpohhmOc4,1046
+datahub/ingestion/source/tableau/tableau_validation.py,sha256=pd--LcTLTfrFsouhCOvGC_2IjeMfKbJV81EEo3ibMwE,1820
 datahub/ingestion/source/unity/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 datahub/ingestion/source/unity/analyze_profiler.py,sha256=2pqkFY30CfN4aHgFZZntjeG0hNhBytZJvXC13VfTc1I,4689
 datahub/ingestion/source/unity/config.py,sha256=m4-n7mYz4Ct4L1QdfJFklwHyj8boKCbV7Sb3Ou6AT3Q,14756
@@ -871,12 +875,12 @@ datahub/sql_parsing/datajob.py,sha256=1X8KpEk-y3_8xJuA_Po27EHZgOcxK9QADI6Om9gSGn
 datahub/sql_parsing/query_types.py,sha256=FKjDzszZzsrCfYfm7dgD6T_8865qxWl767fdGyHWBh4,2720
 datahub/sql_parsing/schema_resolver.py,sha256=9INZWdxA2dMSLK6RXaVqjbjyLY_VKMhCkQv_Xd6Ln3I,10848
 datahub/sql_parsing/split_statements.py,sha256=uZhAXLaRxDfmK0lPBW2oM_YVdJfSMhdgndnfd9iIXuA,5001
-datahub/sql_parsing/sql_parsing_aggregator.py,sha256=F-aj7yqOwbo7FpxduFO5a7cLWkojL_Npv3_dlfHPNGY,69877
+datahub/sql_parsing/sql_parsing_aggregator.py,sha256=LBs1RjRqh3natrx4WfgRQGNpI56o12jtbABO5ipEBWA,69889
 datahub/sql_parsing/sql_parsing_common.py,sha256=h_V_m54hJ9EUh5kczq7cYOIeNeo4bgf0Px0H-Nq-UIg,2602
 datahub/sql_parsing/sql_parsing_result_utils.py,sha256=prwWTj1EB2fRPv1eMB4EkpFNafIYAt-X8TIK0NWqank,796
 datahub/sql_parsing/sqlglot_lineage.py,sha256=CLDOc0HNqL_539eahOP3QOoldIYC6CF29id4Xe3TlEM,47018
 datahub/sql_parsing/sqlglot_utils.py,sha256=n6yufzEGwSlFeCSU540hEldIuab0q8KGqm9x0vSawkc,14699
-datahub/sql_parsing/tool_meta_extractor.py,sha256=pE-pkRKBfNTXEJkaQM9NlG807mc-X6OtetgskJySCs8,2908
+datahub/sql_parsing/tool_meta_extractor.py,sha256=7tY4FAClhFcqwc23lGVlnT6Dequ_5Xcpbt0hDvnlLzM,6670
 datahub/telemetry/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 datahub/telemetry/stats.py,sha256=YltbtC3fe6rl1kcxn1A-mSnVpECTPm5k-brrUt7QxTI,967
 datahub/telemetry/telemetry.py,sha256=gzla-QGNsynGg2FqFxiDDFQ0emG53MJ9lhOA2-UUg-Y,15047
@@ -976,8 +980,8 @@ datahub_provider/operators/datahub_assertion_operator.py,sha256=uvTQ-jk2F0sbqqxp
 datahub_provider/operators/datahub_assertion_sensor.py,sha256=lCBj_3x1cf5GMNpHdfkpHuyHfVxsm6ff5x2Z5iizcAo,140
 datahub_provider/operators/datahub_operation_operator.py,sha256=aevDp2FzX7FxGlXrR0khoHNbxbhKR2qPEX5e8O2Jyzw,174
 datahub_provider/operators/datahub_operation_sensor.py,sha256=8fcdVBCEPgqy1etTXgLoiHoJrRt_nzFZQMdSzHqSG7M,168
-acryl_datahub-0.15.0rc24.dist-info/METADATA,sha256=z1GOrJZhoUNozAZuAKJuhaUEOtkFO6qXVGtHd5xC3mo,173559
-acryl_datahub-0.15.0rc24.dist-info/WHEEL,sha256=PZUExdf71Ui_so67QXpySuHtCi3-J3wvF4ORK6k_S8U,91
-acryl_datahub-0.15.0rc24.dist-info/entry_points.txt,sha256=Yj0PWB0LQOq4Rj2fyR6ETx4BUGw4TOcNL0ZNoAZ9kQg,9504
-acryl_datahub-0.15.0rc24.dist-info/top_level.txt,sha256=iLjSrLK5ox1YVYcglRUkcvfZPvKlobBWx7CTUXx8_GI,25
-acryl_datahub-0.15.0rc24.dist-info/RECORD,,
+acryl_datahub-0.15.0.1rc1.dist-info/METADATA,sha256=Ll6D3fw03bz2dVmCp9Mcez5IbFKIfXzUnMeSe6Ej4eM,173642
+acryl_datahub-0.15.0.1rc1.dist-info/WHEEL,sha256=PZUExdf71Ui_so67QXpySuHtCi3-J3wvF4ORK6k_S8U,91
+acryl_datahub-0.15.0.1rc1.dist-info/entry_points.txt,sha256=xnPSPLK3bJGADxe4TDS4wL4u0FT_PGlahDa-ENYdYCQ,9512
+acryl_datahub-0.15.0.1rc1.dist-info/top_level.txt,sha256=iLjSrLK5ox1YVYcglRUkcvfZPvKlobBWx7CTUXx8_GI,25
+acryl_datahub-0.15.0.1rc1.dist-info/RECORD,,

{acryl_datahub-0.15.0rc24.dist-info → acryl_datahub-0.15.0.1rc1.dist-info}/entry_points.txt

@@ -57,7 +57,7 @@ hive-metastore = datahub.ingestion.source.sql.hive_metastore:HiveMetastoreSource
 iceberg = datahub.ingestion.source.iceberg.iceberg:IcebergSource
 json-schema = datahub.ingestion.source.schema.json_schema:JsonSchemaSource
 kafka = datahub.ingestion.source.kafka.kafka:KafkaSource
-kafka-connect = datahub.ingestion.source.kafka.kafka_connect:KafkaConnectSource
+kafka-connect = datahub.ingestion.source.kafka_connect.kafka_connect:KafkaConnectSource
 ldap = datahub.ingestion.source.ldap:LDAPSource
 looker = datahub.ingestion.source.looker.looker_source:LookerDashboardSource
 lookml = datahub.ingestion.source.looker.lookml_source:LookMLSource

datahub/__init__.py

@@ -3,7 +3,7 @@ import warnings
 
 # Published at https://pypi.org/project/acryl-datahub/.
 __package_name__ = "acryl-datahub"
-__version__ = "0.15.0rc24"
+__version__ = "0.15.0.1rc1"
 
 
 def is_dev_mode() -> bool:

datahub/api/entities/structuredproperties/structuredproperties.py

@@ -14,7 +14,7 @@ from datahub.metadata.schema_classes import (
     PropertyValueClass,
     StructuredPropertyDefinitionClass,
 )
-from datahub.metadata.urns import StructuredPropertyUrn, Urn
+from datahub.metadata.urns import DataTypeUrn, StructuredPropertyUrn, Urn
 from datahub.utilities.urns._urn_base import URN_TYPES
 
 logging.basicConfig(level=logging.INFO)
@@ -86,19 +86,31 @@ class StructuredProperties(ConfigModel):
 
     @validator("type")
     def validate_type(cls, v: str) -> str:
-        # Convert to lowercase if needed
-        if not v.islower():
+        # This logic is somewhat hacky, since we need to deal with
+        # 1. fully qualified urns
+        # 2. raw data types, that need to get the datahub namespace prefix
+        # While keeping the user-facing interface and error messages clean.
+
+        if not v.startswith("urn:li:") and not v.islower():
+            # Convert to lowercase if needed
+            v = v.lower()
             logger.warning(
-                f"Structured property type should be lowercase. Updated to {v.lower()}"
+                f"Structured property type should be lowercase. Updated to {v}"
             )
-            v = v.lower()
+
+        urn = Urn.make_data_type_urn(v)
 
         # Check if type is allowed
-        if not AllowedTypes.check_allowed_type(v):
+        data_type_urn = DataTypeUrn.from_string(urn)
+        unqualified_data_type = data_type_urn.id
+        if unqualified_data_type.startswith("datahub."):
+            unqualified_data_type = unqualified_data_type[len("datahub.") :]
+        if not AllowedTypes.check_allowed_type(unqualified_data_type):
             raise ValueError(
-                f"Type {v} is not allowed. Allowed types are {AllowedTypes.values()}"
+                f"Type {unqualified_data_type} is not allowed. Allowed types are {AllowedTypes.values()}"
             )
-        return v
+
+        return urn
 
     @property
     def fqn(self) -> str:

datahub/configuration/source_common.py

@@ -63,3 +63,16 @@ class DatasetLineageProviderConfigBase(EnvConfigMixin):
         default=None,
         description="A holder for platform -> platform_instance mappings to generate correct dataset urns",
     )
+
+
+class PlatformDetail(ConfigModel):
+    platform_instance: Optional[str] = Field(
+        default=None,
+        description="DataHub platform instance name. To generate correct urn for upstream dataset, this should match "
+        "with platform instance name used in ingestion "
+        "recipe of other datahub sources.",
+    )
+    env: str = Field(
+        default=DEFAULT_ENV,
+        description="The environment that all assets produced by DataHub platform ingestion source belong to",
+    )

datahub/ingestion/source/iceberg/iceberg.py

@@ -10,6 +10,7 @@ from pyiceberg.exceptions import (
     NoSuchNamespaceError,
     NoSuchPropertyException,
     NoSuchTableError,
+    ServerError,
 )
 from pyiceberg.schema import Schema, SchemaVisitorPerPrimitiveType, visit
 from pyiceberg.table import Table
@@ -145,6 +146,13 @@ class IcebergSource(StatefulIngestionSourceBase):
         self.report.report_no_listed_namespaces(len(namespaces))
         tables_count = 0
         for namespace in namespaces:
+            namespace_repr = ".".join(namespace)
+            if not self.config.namespace_pattern.allowed(namespace_repr):
+                LOGGER.info(
+                    f"Namespace {namespace_repr} is not allowed by config pattern, skipping"
+                )
+                self.report.report_dropped(f"{namespace_repr}.*")
+                continue
             try:
                 tables = catalog.list_tables(namespace)
                 tables_count += len(tables)
@@ -181,6 +189,9 @@ class IcebergSource(StatefulIngestionSourceBase):
             if not self.config.table_pattern.allowed(dataset_name):
                 # Dataset name is rejected by pattern, report as dropped.
                 self.report.report_dropped(dataset_name)
+                LOGGER.debug(
+                    f"Skipping table {dataset_name} due to not being allowed by the config pattern"
+                )
                 return
             try:
                 if not hasattr(thread_local, "local_catalog"):
@@ -219,6 +230,22 @@ class IcebergSource(StatefulIngestionSourceBase):
                 LOGGER.warning(
                     f"NoSuchTableError while processing table {dataset_path}, skipping it.",
                 )
+            except FileNotFoundError as e:
+                self.report.report_warning(
+                    "file-not-found",
+                    f"Encountered FileNotFoundError when trying to read manifest file for {dataset_name}. {e}",
+                )
+                LOGGER.warning(
+                    f"FileNotFoundError while processing table {dataset_path}, skipping it."
+                )
+            except ServerError as e:
+                self.report.report_warning(
+                    "iceberg-rest-server-error",
+                    f"Iceberg Rest Catalog returned 500 status due to an unhandled exception for {dataset_name}. Exception: {e}",
+                )
+                LOGGER.warning(
+                    f"Iceberg Rest Catalog server error (500 status) encountered when processing table {dataset_path}, skipping it."
+                )
             except Exception as e:
                 self.report.report_failure("general", f"Failed to create workunit: {e}")
                 LOGGER.exception(
@@ -269,7 +296,6 @@ class IcebergSource(StatefulIngestionSourceBase):
                 ] = table.current_snapshot().manifest_list
             dataset_properties = DatasetPropertiesClass(
                 name=table.name()[-1],
-                tags=[],
                 description=table.metadata.properties.get("comment", None),
                 customProperties=custom_properties,
             )

datahub/ingestion/source/iceberg/iceberg_common.py

@@ -68,6 +68,10 @@ class IcebergSourceConfig(StatefulIngestionConfigBase, DatasetSourceConfigMixin)
         default=AllowDenyPattern.allow_all(),
         description="Regex patterns for tables to filter in ingestion.",
     )
+    namespace_pattern: AllowDenyPattern = Field(
+        default=AllowDenyPattern.allow_all(),
+        description="Regex patterns for namespaces to filter in ingestion.",
+    )
     user_ownership_property: Optional[str] = Field(
         default="owner",
         description="Iceberg table property to look for a `CorpUser` owner.  Can only hold a single user value.  If property has no value, no owner information will be emitted.",

datahub/ingestion/source/kafka_connect/common.py

@@ -0,0 +1,202 @@
+import logging
+from dataclasses import dataclass, field
+from typing import Dict, Iterable, List, Optional
+
+from pydantic.fields import Field
+
+from datahub.configuration.common import AllowDenyPattern, ConfigModel
+from datahub.configuration.source_common import (
+    DatasetLineageProviderConfigBase,
+    PlatformInstanceConfigMixin,
+)
+from datahub.ingestion.source.state.stale_entity_removal_handler import (
+    StaleEntityRemovalSourceReport,
+    StatefulStaleMetadataRemovalConfig,
+)
+from datahub.ingestion.source.state.stateful_ingestion_base import (
+    StatefulIngestionConfigBase,
+)
+
+logger = logging.getLogger(__name__)
+
+KAFKA = "kafka"
+SOURCE = "source"
+SINK = "sink"
+CONNECTOR_CLASS = "connector.class"
+
+
+class ProvidedConfig(ConfigModel):
+    provider: str
+    path_key: str
+    value: str
+
+
+class GenericConnectorConfig(ConfigModel):
+    connector_name: str
+    source_dataset: str
+    source_platform: str
+
+
+class KafkaConnectSourceConfig(
+    PlatformInstanceConfigMixin,
+    DatasetLineageProviderConfigBase,
+    StatefulIngestionConfigBase,
+):
+    # See the Connect REST Interface for details
+    # https://docs.confluent.io/platform/current/connect/references/restapi.html#
+    connect_uri: str = Field(
+        default="http://localhost:8083/", description="URI to connect to."
+    )
+    username: Optional[str] = Field(default=None, description="Kafka Connect username.")
+    password: Optional[str] = Field(default=None, description="Kafka Connect password.")
+    cluster_name: Optional[str] = Field(
+        default="connect-cluster", description="Cluster to ingest from."
+    )
+    # convert lineage dataset's urns to lowercase
+    convert_lineage_urns_to_lowercase: bool = Field(
+        default=False,
+        description="Whether to convert the urns of ingested lineage dataset to lowercase",
+    )
+    connector_patterns: AllowDenyPattern = Field(
+        default=AllowDenyPattern.allow_all(),
+        description="regex patterns for connectors to filter for ingestion.",
+    )
+    provided_configs: Optional[List[ProvidedConfig]] = Field(
+        default=None, description="Provided Configurations"
+    )
+    connect_to_platform_map: Optional[Dict[str, Dict[str, str]]] = Field(
+        default=None,
+        description='Platform instance mapping when multiple instances for a platform is available. Entry for a platform should be in either `platform_instance_map` or `connect_to_platform_map`. e.g.`connect_to_platform_map: { "postgres-connector-finance-db": "postgres": "core_finance_instance" }`',
+    )
+    platform_instance_map: Optional[Dict[str, str]] = Field(
+        default=None,
+        description='Platform instance mapping to use when constructing URNs. e.g.`platform_instance_map: { "hive": "warehouse" }`',
+    )
+    generic_connectors: List[GenericConnectorConfig] = Field(
+        default=[],
+        description="Provide lineage graph for sources connectors other than Confluent JDBC Source Connector, Debezium Source Connector, and Mongo Source Connector",
+    )
+
+    stateful_ingestion: Optional[StatefulStaleMetadataRemovalConfig] = None
+
+
+@dataclass
+class KafkaConnectSourceReport(StaleEntityRemovalSourceReport):
+    connectors_scanned: int = 0
+    filtered: List[str] = field(default_factory=list)
+
+    def report_connector_scanned(self, connector: str) -> None:
+        self.connectors_scanned += 1
+
+    def report_dropped(self, connector: str) -> None:
+        self.filtered.append(connector)
+
+
+@dataclass
+class KafkaConnectLineage:
+    """Class to store Kafka Connect lineage mapping, Each instance is potential DataJob"""
+
+    source_platform: str
+    target_dataset: str
+    target_platform: str
+    job_property_bag: Optional[Dict[str, str]] = None
+    source_dataset: Optional[str] = None
+
+
+@dataclass
+class ConnectorManifest:
+    """Each instance is potential DataFlow"""
+
+    name: str
+    type: str
+    config: Dict
+    tasks: Dict
+    url: Optional[str] = None
+    flow_property_bag: Optional[Dict[str, str]] = None
+    lineages: List[KafkaConnectLineage] = field(default_factory=list)
+    topic_names: Iterable[str] = field(default_factory=list)
+
+
+def remove_prefix(text: str, prefix: str) -> str:
+    if text.startswith(prefix):
+        index = len(prefix)
+        return text[index:]
+    return text
+
+
+def unquote(
+    string: str, leading_quote: str = '"', trailing_quote: Optional[str] = None
+) -> str:
+    """
+    If string starts and ends with a quote, unquote it
+    """
+    trailing_quote = trailing_quote if trailing_quote else leading_quote
+    if string.startswith(leading_quote) and string.endswith(trailing_quote):
+        string = string[1:-1]
+    return string
+
+
+def get_dataset_name(
+    database_name: Optional[str],
+    source_table: str,
+) -> str:
+    if database_name:
+        dataset_name = database_name + "." + source_table
+    else:
+        dataset_name = source_table
+
+    return dataset_name
+
+
+def get_platform_instance(
+    config: KafkaConnectSourceConfig, connector_name: str, platform: str
+) -> Optional[str]:
+    instance_name = None
+    if (
+        config.connect_to_platform_map
+        and config.connect_to_platform_map.get(connector_name)
+        and config.connect_to_platform_map[connector_name].get(platform)
+    ):
+        instance_name = config.connect_to_platform_map[connector_name][platform]
+        if config.platform_instance_map and config.platform_instance_map.get(platform):
+            logger.warning(
+                f"Same source platform {platform} configured in both platform_instance_map and connect_to_platform_map."
+                "Will prefer connector specific platform instance from connect_to_platform_map."
+            )
+    elif config.platform_instance_map and config.platform_instance_map.get(platform):
+        instance_name = config.platform_instance_map[platform]
+    logger.info(
+        f"Instance name assigned is: {instance_name} for Connector Name {connector_name} and platform {platform}"
+    )
+    return instance_name
+
+
+def transform_connector_config(
+    connector_config: Dict, provided_configs: List[ProvidedConfig]
+) -> None:
+    """This method will update provided configs in connector config values, if any"""
+    lookupsByProvider = {}
+    for pconfig in provided_configs:
+        lookupsByProvider[f"${{{pconfig.provider}:{pconfig.path_key}}}"] = pconfig.value
+    for k, v in connector_config.items():
+        for key, value in lookupsByProvider.items():
+            if key in v:
+                connector_config[k] = connector_config[k].replace(key, value)
+
+
+# TODO: Find a more automated way to discover new platforms with 3 level naming hierarchy.
+def has_three_level_hierarchy(platform: str) -> bool:
+    return platform in ["postgres", "trino", "redshift", "snowflake"]
+
+
+@dataclass
+class BaseConnector:
+    connector_manifest: ConnectorManifest
+    config: KafkaConnectSourceConfig
+    report: KafkaConnectSourceReport
+
+    def extract_lineages(self) -> List[KafkaConnectLineage]:
+        return []
+
+    def extract_flow_property_bag(self) -> Optional[Dict[str, str]]:
+        return None