acryl-datahub 0.14.1.13rc5__py3-none-any.whl → 0.14.1.13rc6__py3-none-any.whl

{acryl_datahub-0.14.1.13rc5.dist-info → acryl_datahub-0.14.1.13rc6.dist-info}/RECORD

@@ -1,4 +1,4 @@
-datahub/__init__.py,sha256=sacWO6qm2tPLBhc25GFoFnt_AeiT0Qk9ZiibpHJbPhQ,577
+datahub/__init__.py,sha256=JvS6bVIee0O3OSc7IBHb7mEeuHYesjHcY2dgF-FuZMs,577
 datahub/__main__.py,sha256=pegIvQ9hzK7IhqVeUi1MeADSZ2QlP-D3K0OQdEg55RU,106
 datahub/entrypoints.py,sha256=3-qSfXAx3Z0FEkBV5tlO8fQr4xk4ySeDRMVTpS5Xd6A,7793
 datahub/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -97,7 +97,7 @@ datahub/configuration/git.py,sha256=s55eUHxKqVZgtVsISaDyS-1F4iZBiybbjYsjbp5LU5o,
 datahub/configuration/import_resolver.py,sha256=b4Ie9L7knN1LALEVMxTcNFSklDD6CVE-4Ipy4ZYhNYA,369
 datahub/configuration/json_loader.py,sha256=vIDnjwXWi9yHDO8KW64EupOzOb_sspehGCD7xGHzg84,302
 datahub/configuration/kafka.py,sha256=MlIwpd5FFyOyjdDXW_X9JTLNk7f988sPMgevkcZYVgI,2579
-datahub/configuration/kafka_consumer_config.py,sha256=DSwUU4HoqNyK4CNk9eIbX3eYsJMGQvORDiy1ZxkjlRc,1022
+datahub/configuration/kafka_consumer_config.py,sha256=14UWK6kTAnKTgHM43aeWjg67fddACsSLzhO6wgp6cm4,1175
 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
@@ -189,8 +189,8 @@ datahub/ingestion/source/demo_data.py,sha256=yzA_R-wfSX2WPz0i5ukYlscpmpb0Pt8D7Ek
 datahub/ingestion/source/elastic_search.py,sha256=qFUVNzynTVJTabASTjGMu8Qhf9UpNbEtSBFjaPQjBJE,22641
 datahub/ingestion/source/feast.py,sha256=NYaAjzLVRhmMKDawBwN0OL8AMyKDLsxOwEj3YFX0wIA,14244
 datahub/ingestion/source/file.py,sha256=pH-Qkjh5FQ2XvyYPE7Z8XEY4vUk_SUHxm8p8IxG12tU,15879
-datahub/ingestion/source/ge_data_profiler.py,sha256=7oUvvADX4t1WiXwOruCURh3sNEY_7I41wbwXFvKaKWM,63587
-datahub/ingestion/source/ge_profiling_config.py,sha256=WusEMGFPu17y99jTT-1tTOiN87Q1sY7nyxXvXnPs1-E,10489
+datahub/ingestion/source/ge_data_profiler.py,sha256=jORUlsmN2XtHm3QyltENvhEyt-CwbF2O548mFxtisxY,63587
+datahub/ingestion/source/ge_profiling_config.py,sha256=E65adlsUrs17mQB7WQnoe3QCjvbGaGoNNPMf8szNK6s,10648
 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
@@ -239,9 +239,9 @@ datahub/ingestion/source/bigquery_v2/bigquery_data_reader.py,sha256=DeT3v_Z82__8
 datahub/ingestion/source/bigquery_v2/bigquery_helper.py,sha256=QER3gY8e_k1_eNVj7cBso7ZzrWl_vO5PYSa6CpvqNx8,1554
 datahub/ingestion/source/bigquery_v2/bigquery_platform_resource_helper.py,sha256=8nuQ8hMuJEswWDZtV2RjbK8RvDJUzT_S74dnyPpGFdQ,4857
 datahub/ingestion/source/bigquery_v2/bigquery_queries.py,sha256=EoHo9twb0_QdX7Nvd1HJC1Yn0rqtrfR52EVk7Hu3XOQ,3296
-datahub/ingestion/source/bigquery_v2/bigquery_report.py,sha256=00GMkriZy7Iz46fXKe9SEIScvCKQEb0kgogY7GVwCSM,8114
-datahub/ingestion/source/bigquery_v2/bigquery_schema.py,sha256=rSG_tDmTg9qXVEkaVGG8X3zw0pKtk9TWDYmGPrD3M4o,31456
-datahub/ingestion/source/bigquery_v2/bigquery_schema_gen.py,sha256=vJt2Z573M0Hmdkb8LaNo5bIoqmkbkI29KFDFT8b70cE,51995
+datahub/ingestion/source/bigquery_v2/bigquery_report.py,sha256=WxiLPFc7LwZXNDYfV9oySUD43kc2GcOf_pUokp3vFNM,8098
+datahub/ingestion/source/bigquery_v2/bigquery_schema.py,sha256=QQk2xnyLCpywwRA3a2Pm95zJd0LgJUGbe5ht-5yadmQ,32352
+datahub/ingestion/source/bigquery_v2/bigquery_schema_gen.py,sha256=JkQqG8GrMnsp6efUCSv1Efc0ZUmdC6q5_M6wWIyg_dQ,51774
 datahub/ingestion/source/bigquery_v2/bigquery_test_connection.py,sha256=cATxwi5IPzj3BldRRAVcLqzSFmmYEPvqa7U0RFJbaAc,7645
 datahub/ingestion/source/bigquery_v2/common.py,sha256=Cxjf1a8ibkL_YRQeS0BqsjlyMgFJpaZ3iq_d7e8T8MQ,4030
 datahub/ingestion/source/bigquery_v2/lineage.py,sha256=Jg_pwnaj7l_KEcgq0enJXwrKh5jyUfBl4YB05YpkIVg,45415
@@ -287,7 +287,7 @@ datahub/ingestion/source/dremio/dremio_config.py,sha256=Mu9LjohVwVPdVgM53FhBDquJ
 datahub/ingestion/source/dremio/dremio_datahub_source_mapping.py,sha256=YkYC3-TB-Jn65z2GN_NMErQDovwU7krQ9b92DBh4uvY,3021
 datahub/ingestion/source/dremio/dremio_entities.py,sha256=cIupn6fRxYX3FrcsdoDTSmvOTHLuaoyuNEkHV70-ve0,14902
 datahub/ingestion/source/dremio/dremio_profiling.py,sha256=TAcnpo8ZRKhLDHnQSJzJg3YdwTSyEa73LUAzENs7wG4,12287
-datahub/ingestion/source/dremio/dremio_reporting.py,sha256=Lb60cv_4IIJSIJmHmCl2FlO57VFYM152WONMsSFUAF4,1289
+datahub/ingestion/source/dremio/dremio_reporting.py,sha256=IPgv7lOnhK6mQeqwRsPscKnXhzgVZG8Id3yNcsmG7nw,1273
 datahub/ingestion/source/dremio/dremio_source.py,sha256=vQTYxB-PQdoMsoEY69ewtfraDloKypHF6pXv8jbVlG4,25940
 datahub/ingestion/source/dremio/dremio_sql_queries.py,sha256=W0rcXawlwJOHNYr5o73rilMijtFOO3cVkn6pY-JLc6o,8186
 datahub/ingestion/source/dynamodb/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -387,7 +387,7 @@ datahub/ingestion/source/redshift/query.py,sha256=bY1D9RoOHaw89LgcXal7GYlJN0RG7P
 datahub/ingestion/source/redshift/redshift.py,sha256=j3yz9cct77IU2RaiaXDWiTZIGxoZGFUxGFWvNEVaw7E,44234
 datahub/ingestion/source/redshift/redshift_data_reader.py,sha256=zc69jwXHdF-w8J4Hq-ZQ6BjHQ75Ij2iNDMpoRJlcmlU,1724
 datahub/ingestion/source/redshift/redshift_schema.py,sha256=9IYeUsnISenq3eVB3k-s7zK8nInWDAYViFnDrNjtkb0,19149
-datahub/ingestion/source/redshift/report.py,sha256=RqoCB-K351J1_S55xDstnHsC-7cN7ngrruRBq85dn-A,2974
+datahub/ingestion/source/redshift/report.py,sha256=M19aUHBkd9n-BVBX4fRhyRNdVkN2b9Es6ZqInRx5ZGI,2958
 datahub/ingestion/source/redshift/usage.py,sha256=1Zqa_1OQYRI1l-5cHfk-VW2ik1A2AuL3_wjJDuFGBzs,17373
 datahub/ingestion/source/s3/__init__.py,sha256=HjqFPj11WtNFZM3kcVshlDb7kOsc19-l_3LM8PBjlJM,56
 datahub/ingestion/source/s3/config.py,sha256=Zs1nrBZKLImteZreIcSMMRLj8vBGgxakNDs96xf8g44,7847
@@ -427,7 +427,7 @@ datahub/ingestion/source/snowflake/snowflake_lineage_v2.py,sha256=w2CPm5XEU-KMUS
 datahub/ingestion/source/snowflake/snowflake_profiler.py,sha256=0DJiSwII6FY34urlBja2FW66NaVvhbBWmG0p7u8Xyrc,7548
 datahub/ingestion/source/snowflake/snowflake_queries.py,sha256=fu-8S9eADIXZcd_kHc6cBeMa-on9RF9qG3yqjJnS3DE,26085
 datahub/ingestion/source/snowflake/snowflake_query.py,sha256=oNmtg-ZVcZ3-w1X5t-JGv2qTH64Z0qzEnaZaRxbRquo,38035
-datahub/ingestion/source/snowflake/snowflake_report.py,sha256=jQv1wnexD6bOkmM8HXpdg-aP4pRHZjxE6MV1qDqx2b8,6435
+datahub/ingestion/source/snowflake/snowflake_report.py,sha256=KjNvYufQMVkFP7F5sEFumKorkiFAmFVCQ1jYqXr0ev0,6419
 datahub/ingestion/source/snowflake/snowflake_schema.py,sha256=fatrKpBUY9CnzXhLJcFlHkHGt0QWFhkYH9ZXwWoQCLA,20392
 datahub/ingestion/source/snowflake/snowflake_schema_gen.py,sha256=4A9DxtEoGtEeTEy2YbKxllLFjsRFWjFsFzWq2TqOASw,38838
 datahub/ingestion/source/snowflake/snowflake_shares.py,sha256=ud3Ah4qHrmSfpD8Od-gPdzwtON9dJa0eqHt-8Yr5h2Q,6366
@@ -446,21 +446,22 @@ datahub/ingestion/source/sql/hive.py,sha256=AgEo94zyBL-NLZxR5-jQlNwq_R9FQ4AUOe8w
 datahub/ingestion/source/sql/hive_metastore.py,sha256=PisLrswev583xW0xDJ5yfKWCWm_ZTl1OeuaMcv_SvXc,35865
 datahub/ingestion/source/sql/mariadb.py,sha256=Hm102kmfs_1rd4lsTYhzVMZq5S3B6cyfvpHSzJjqvMw,737
 datahub/ingestion/source/sql/mysql.py,sha256=nDWK4YbqomcJgnit9b8geUGrp_3eix4bt0_k94o7g-0,3350
-datahub/ingestion/source/sql/oracle.py,sha256=exJJvMSC42Oj0IiFtpAPFatWkRu9mVu8sd7ofOdanqU,22460
+datahub/ingestion/source/sql/oracle.py,sha256=ibBtjaneCFto-Rw3k2OxsbT3YHgux1aCtPtv5oA8St4,24533
 datahub/ingestion/source/sql/postgres.py,sha256=uC1kYEI8VdxiZ1Y9IxMWzwmg11wtMqYN0e2fkok1rxo,11972
 datahub/ingestion/source/sql/presto.py,sha256=PB-CS5MX2dSRFRHjlxfkLHGXLZXFNCsVAAyRBtY6HMg,3611
-datahub/ingestion/source/sql/sql_common.py,sha256=Qe481Pct1vfl-NVpgOufSEaNSMgJGD3bq1DPvjIkPTg,52164
+datahub/ingestion/source/sql/sql_common.py,sha256=Ux50vDfO8er_T9KL0unjLkPqvl49aei5E-nNMUKbPL4,50989
 datahub/ingestion/source/sql/sql_config.py,sha256=M-l_uXau0ODolLZHBzAXhy-Rq5yYxvJ6cLbCIea7Mww,9449
 datahub/ingestion/source/sql/sql_generic.py,sha256=9AERvkK8kdJUeDOzCYJDb93xdv6Z4DGho0NfeHj5Uyg,2740
-datahub/ingestion/source/sql/sql_generic_profiler.py,sha256=vWna43rv9ClfK9MBNTx8tdoUr35nD5d8ppgeamEEhSQ,12528
+datahub/ingestion/source/sql/sql_generic_profiler.py,sha256=6QbhkQH_F13GV1HsavVTq3BE9F7Pr_vfGOjCX2o2c60,11675
+datahub/ingestion/source/sql/sql_report.py,sha256=19YVvatcCZsBP533HWn0X9Y30jo4TUxSkQ9rYpMQpT4,2487
 datahub/ingestion/source/sql/sql_types.py,sha256=XcZo5CYo1kHVkvD8lDCFqWQxaLL_CzJC-kV1gvXaXiY,12676
 datahub/ingestion/source/sql/sql_utils.py,sha256=w9YFNm_qJNjOcWAWBI_lUoFMbd0wT8q0LoT7Ia71tIE,8100
 datahub/ingestion/source/sql/sqlalchemy_data_reader.py,sha256=FvHZ4JEK3aR2DYOBZiT_ZsAy12RjTu4t_KIR_92B11k,2644
 datahub/ingestion/source/sql/sqlalchemy_uri_mapper.py,sha256=KOpbmDIE2h1hyYEsbVHJi2B7FlsyUMTXZx4diyzltQg,1826
-datahub/ingestion/source/sql/teradata.py,sha256=PE6UeDNe-LjVzphfUImQTwCnASxDOQkM0QV1qB6D84Q,32524
+datahub/ingestion/source/sql/teradata.py,sha256=_MXXFgaVJWKR9dgGNka-CpzKYy919yDdex2qSrqeVdE,32508
 datahub/ingestion/source/sql/trino.py,sha256=FEn_BQ3pm23hKx94ek5kk5IXGNYcBqZEhllRJFUzfU8,17895
 datahub/ingestion/source/sql/two_tier_sql_source.py,sha256=YDrGBb5WKVls6qv17QU5foKrf71SydzEltc3WsVAhQc,5732
-datahub/ingestion/source/sql/vertica.py,sha256=pkx-1JDBmow7WhoEIEh0SLj7kff9L0zUOHDytoC43gk,33339
+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=fzpWjwexGvJgpd6Z4DCsK6Ld2vQCfPkD2M1xE4pU9Ec,29542
@@ -493,7 +494,7 @@ datahub/ingestion/source/unity/hive_metastore_proxy.py,sha256=IAWWJjaW0si_UF52Se
 datahub/ingestion/source/unity/proxy.py,sha256=2-pYQ-3B9UVUwO1yB9iTdi3DqgqZ2JrpQknLodI7UjM,18976
 datahub/ingestion/source/unity/proxy_profiling.py,sha256=WLqvYP6MziaisA4LYL4T_GA-kPt6Xdde7bfaYsjYw40,9663
 datahub/ingestion/source/unity/proxy_types.py,sha256=g4qhREewta0vapO7JJPHPli_ZXmtYVmGBNzt_TtfNAQ,9307
-datahub/ingestion/source/unity/report.py,sha256=Xi5wKqdJhEDRbq_hcvVEIxELeRj_iRqBw-rDV4owZVI,2804
+datahub/ingestion/source/unity/report.py,sha256=0Y-ciHVTI6ZKNCJ5zWoQh3Ze1c_GMqmTMKFwzXDuuOg,2788
 datahub/ingestion/source/unity/source.py,sha256=i2WU0H6Gvce51I3qWVOoEp6lZ1FAxEm_9u2qS6zmsL8,41482
 datahub/ingestion/source/unity/usage.py,sha256=r91-ishhv9QTNLevVhQ9HPZ47CRvVeeAMBtWuRsONxk,11089
 datahub/ingestion/source/usage/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -555,7 +556,7 @@ datahub/lite/lite_server.py,sha256=p9Oa2nNs65mqcssSIVOr7VOzWqfVstz6ZQEdT4f82S0,1
 datahub/lite/lite_util.py,sha256=pgBpT3vTO1YCQ2njZRNyicSkHYeEmQCt41BaXU8WvMo,4503
 datahub/metadata/__init__.py,sha256=AjhXPjI6cnpdcrBRrE5gOWo15vv2TTl2ctU4UAnUN7A,238
 datahub/metadata/_schema_classes.py,sha256=g7jG02LNEUUFRP76CCJhdi9JIsvbanWivbeWjb9B0p8,950122
-datahub/metadata/schema.avsc,sha256=0EO3TupbhhCHiH_SkLQi4u4bVXv7Oka9wLTcvTI3070,675487
+datahub/metadata/schema.avsc,sha256=YttbenOzBUCzHHXR3HztORZ746UckyicBk7IyXvG-yU,675487
 datahub/metadata/schema_classes.py,sha256=X5Jl5EaSxyHdXOQv14pJ5WkQALun4MRpJ4q12wVFE18,1299
 datahub/metadata/urns.py,sha256=nfrCTExR-k2P9w272WVtWSN3xW1VUJngPwP3xnvULjU,1217
 datahub/metadata/_urns/__init__.py,sha256=cOF3GHMDgPhmbLKbN02NPpuLGHSu0qNgQyBRv08eqF0,243
@@ -633,7 +634,7 @@ datahub/metadata/com/linkedin/pegasus2avro/view/__init__.py,sha256=-Le-jOqUJKv3p
 datahub/metadata/schemas/Access.avsc,sha256=gdEfWJLkvjIz-jzlceK4Dl5pBDdCHG423Ba_EYGQgUk,1562
 datahub/metadata/schemas/Actors.avsc,sha256=M76L2_Dlp7VyhVtu9__jhnh8rBNvNobtNJUfvl7bcPE,1188
 datahub/metadata/schemas/AssertionActions.avsc,sha256=zrvXzX2Nv_dmK6I3ZXCVWQ1bVs1q01Gl9sDRJA8oSDU,1618
-datahub/metadata/schemas/AssertionInfo.avsc,sha256=Rg6bgc5zk1PsP23TDaj3dI7HgKQiH8RdrLUoZ3sPQ8E,125083
+datahub/metadata/schemas/AssertionInfo.avsc,sha256=BRkjHzkTCjfqaYpm8EDiLtTAhN50yMkHH5eE3QLpGbY,125083
 datahub/metadata/schemas/AssertionKey.avsc,sha256=EjNaTyzGxtWzTsZd87P2ZSaGX5dn8Y7HGBdqvlQVrFI,638
 datahub/metadata/schemas/AssertionRunEvent.avsc,sha256=FUyV73bUliBC-a_XFUlfgh75o99-lu1fl36b2q8Pqx4,12886
 datahub/metadata/schemas/BrowsePaths.avsc,sha256=NR_4dKuJMk1X2RB4DLkHVSqyMQc4PvT7eR0n6lM5aOM,654
@@ -769,7 +770,7 @@ datahub/metadata/schemas/IncidentInfo.avsc,sha256=JCKSXCjTwwONte-GA4QhstlBn5Ditu
 datahub/metadata/schemas/IncidentKey.avsc,sha256=Pip__DyNNTal7NxryM3kFi9qHlwntp1rIA8Al8Zz264,542
 datahub/metadata/schemas/IncidentSource.avsc,sha256=lY_SarA3cM55KNENcB5z1Gu2MygxEl9l7R8LdMak9AQ,1199
 datahub/metadata/schemas/IncidentsSummary.avsc,sha256=NTYp-6Oe92ALApbM3759TJ5pLXRArsSriIPq-f7w9vI,4514
-datahub/metadata/schemas/InputFields.avsc,sha256=YkwSoAOU45W3ELJxypZ2GOvk5FNvKgx8JT7WHu6Pf-0,33671
+datahub/metadata/schemas/InputFields.avsc,sha256=jmmfYSqKTeyQGrIlgPxVMvTQmG4NYuriPMA8K14cM-4,33671
 datahub/metadata/schemas/InstitutionalMemory.avsc,sha256=vNeAoFSIH1jEDa2rEyTStUjWDvf53W9AvL7F8oh7isY,3785
 datahub/metadata/schemas/IntendedUse.avsc,sha256=IKZSWdvc0uAyyT-FtdQOGbMC-P7RS9cO0vOVKWT6fbw,1361
 datahub/metadata/schemas/InviteToken.avsc,sha256=8k_9MxHu9GVf7gvS0SlnQu7tJfpbXsRFdz6lQrFKPNc,737
@@ -789,7 +790,7 @@ datahub/metadata/schemas/MLModelKey.avsc,sha256=deK5u7b9S9-qYUNtlflj2OUxqS_PlUYW
 datahub/metadata/schemas/MLModelProperties.avsc,sha256=wGCQ-yMLnss-rRl-NigFPMLEesvSeK0t1iOblyG_m0U,8411
 datahub/metadata/schemas/MLPrimaryKeyKey.avsc,sha256=mX4CQcoN3FC_VQDBCkhlmJk4pfQKDrSeuqqCTTXTmq8,1092
 datahub/metadata/schemas/MLPrimaryKeyProperties.avsc,sha256=akhjegh2q_4pm4_C2mP0rWpCGVqmJ8Ta6X8lqNtbVbg,4468
-datahub/metadata/schemas/MetadataChangeEvent.avsc,sha256=tNPN762s7BwlrpoR389kKf8nEqZfAhmLade2pHmeJ7c,367471
+datahub/metadata/schemas/MetadataChangeEvent.avsc,sha256=y5J5nOdo_GJZnVkerZlbNJWfZqA_Uw-cW8GCCxI0J0s,367471
 datahub/metadata/schemas/MetadataChangeLog.avsc,sha256=mpdodpx25E6M1Gq_7slEcPAm-1Es5xPsoqV60HgO7zg,12167
 datahub/metadata/schemas/MetadataChangeProposal.avsc,sha256=EMfQrYsuHf1p6UvBjoLtfdTHGe-vGNJaCFEHz8hdKU0,9698
 datahub/metadata/schemas/Metrics.avsc,sha256=O7DJGjOwmHbb1x_Zj7AuM_HaHKjBvkfJKfUsX8icXD4,690
@@ -819,7 +820,7 @@ datahub/metadata/schemas/RoleProperties.avsc,sha256=tDw-WF1uBGIcrk38nOnXs3FCF_Yj
 datahub/metadata/schemas/SchemaFieldAliases.avsc,sha256=El_cxn0KUhMf2LGfMPzcZ6Xtths2wQOaF9fnM1KQmxQ,560
 datahub/metadata/schemas/SchemaFieldInfo.avsc,sha256=Gf9EGqrEf10554hd4Eut7T8ZdOR-9OHgDXVRhFo311o,800
 datahub/metadata/schemas/SchemaFieldKey.avsc,sha256=ClAugan-eR71rp38YJklEglca8EW5MMAxEQLoSX-L6Y,946
-datahub/metadata/schemas/SchemaMetadata.avsc,sha256=U2XEwkd-DV7TX8IA3dRebssv-xa9WJlGvlNQHWcBvnc,40849
+datahub/metadata/schemas/SchemaMetadata.avsc,sha256=1rUs2G3tpG02FNxRGMlRaW0FDeTEwS36Rmh2Obz4h40,40849
 datahub/metadata/schemas/Siblings.avsc,sha256=NTktntlHuA1InH3TgrspWlFBntYlqmp3erUd-JFMsps,842
 datahub/metadata/schemas/SourceCode.avsc,sha256=tUgo2rczO5x1fxw3fYNWQj-51vRNmNIj38b1wayA0aQ,1370
 datahub/metadata/schemas/Status.avsc,sha256=rPZSXSJdwnNywqNx2qll8cdt54aYgI-YUbRr3GK7h78,522
@@ -970,8 +971,8 @@ 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-0.14.1.13rc5.dist-info/METADATA,sha256=9ZZBowQ_PYKf6d4V6EHqTTlJDY77BqxSX8uKfiIqFT4,171138
-acryl_datahub-0.14.1.13rc5.dist-info/WHEEL,sha256=PZUExdf71Ui_so67QXpySuHtCi3-J3wvF4ORK6k_S8U,91
-acryl_datahub-0.14.1.13rc5.dist-info/entry_points.txt,sha256=VcQx0dnqaYLyeY_L5OaX7bLmmE-Il7TAXkxCKvEn2bA,9432
-acryl_datahub-0.14.1.13rc5.dist-info/top_level.txt,sha256=iLjSrLK5ox1YVYcglRUkcvfZPvKlobBWx7CTUXx8_GI,25
-acryl_datahub-0.14.1.13rc5.dist-info/RECORD,,
+acryl_datahub-0.14.1.13rc6.dist-info/METADATA,sha256=i-L9n8PCRIcSK6UAfHiUJxDRVEom4BHtjGf2ZdGR-Hc,171138
+acryl_datahub-0.14.1.13rc6.dist-info/WHEEL,sha256=PZUExdf71Ui_so67QXpySuHtCi3-J3wvF4ORK6k_S8U,91
+acryl_datahub-0.14.1.13rc6.dist-info/entry_points.txt,sha256=VcQx0dnqaYLyeY_L5OaX7bLmmE-Il7TAXkxCKvEn2bA,9432
+acryl_datahub-0.14.1.13rc6.dist-info/top_level.txt,sha256=iLjSrLK5ox1YVYcglRUkcvfZPvKlobBWx7CTUXx8_GI,25
+acryl_datahub-0.14.1.13rc6.dist-info/RECORD,,

datahub/__init__.py

@@ -3,7 +3,7 @@ import warnings
 
 # Published at https://pypi.org/project/acryl-datahub/.
 __package_name__ = "acryl-datahub"
-__version__ = "0.14.1.13rc5"
+__version__ = "0.14.1.13rc6"
 
 
 def is_dev_mode() -> bool:

datahub/configuration/kafka_consumer_config.py

@@ -30,6 +30,9 @@ class CallableConsumerConfig:
 
         call_back = self.get_call_back_attribute()
 
-        assert call_back  # to silent lint
+        assert isinstance(call_back, str), (
+            "oauth_cb must be a string representing python function reference "
+            "in the format <python-module>:<function-name>."
+        )
         # Set the callback
         self._config[CallableConsumerConfig.CALLBACK_ATTRIBUTE] = import_path(call_back)

datahub/ingestion/source/bigquery_v2/bigquery_report.py

@@ -8,7 +8,7 @@ import pydantic
 
 from datahub.ingestion.api.report import Report
 from datahub.ingestion.glossary.classification_mixin import ClassificationReportMixin
-from datahub.ingestion.source.sql.sql_generic_profiler import ProfilingSqlReport
+from datahub.ingestion.source.sql.sql_report import SQLSourceReport
 from datahub.ingestion.source_report.ingestion_stage import IngestionStageReport
 from datahub.ingestion.source_report.time_window import BaseTimeWindowReport
 from datahub.sql_parsing.sql_parsing_aggregator import SqlAggregatorReport
@@ -77,7 +77,7 @@ class BigQueryQueriesExtractorReport(Report):
 
 @dataclass
 class BigQueryV2Report(
-    ProfilingSqlReport,
+    SQLSourceReport,
     IngestionStageReport,
     BaseTimeWindowReport,
     ClassificationReportMixin,

datahub/ingestion/source/bigquery_v2/bigquery_schema.py

@@ -152,6 +152,21 @@ class BigqueryDataset:
     snapshots: List[BigqueryTableSnapshot] = field(default_factory=list)
     columns: List[BigqueryColumn] = field(default_factory=list)
 
+    # Some INFORMATION_SCHEMA views are not available for BigLake tables
+    # based on Amazon S3 and Blob Storage data.
+    # https://cloud.google.com/bigquery/docs/omni-introduction#limitations
+    # Omni Locations - https://cloud.google.com/bigquery/docs/omni-introduction#locations
+    def is_biglake_dataset(self) -> bool:
+        return self.location is not None and self.location.lower().startswith(
+            ("aws-", "azure-")
+        )
+
+    def supports_table_constraints(self) -> bool:
+        return not self.is_biglake_dataset()
+
+    def supports_table_partitions(self) -> bool:
+        return not self.is_biglake_dataset()
+
 
 @dataclass
 class BigqueryProject:
@@ -541,18 +556,26 @@ class BigQuerySchemaApi:
                         table_name=constraint.table_name,
                         type=constraint.constraint_type,
                         field_path=constraint.column_name,
-                        referenced_project_id=constraint.referenced_catalog
-                        if constraint.constraint_type == "FOREIGN KEY"
-                        else None,
-                        referenced_dataset=constraint.referenced_schema
-                        if constraint.constraint_type == "FOREIGN KEY"
-                        else None,
-                        referenced_table_name=constraint.referenced_table
-                        if constraint.constraint_type == "FOREIGN KEY"
-                        else None,
-                        referenced_column_name=constraint.referenced_column
-                        if constraint.constraint_type == "FOREIGN KEY"
-                        else None,
+                        referenced_project_id=(
+                            constraint.referenced_catalog
+                            if constraint.constraint_type == "FOREIGN KEY"
+                            else None
+                        ),
+                        referenced_dataset=(
+                            constraint.referenced_schema
+                            if constraint.constraint_type == "FOREIGN KEY"
+                            else None
+                        ),
+                        referenced_table_name=(
+                            constraint.referenced_table
+                            if constraint.constraint_type == "FOREIGN KEY"
+                            else None
+                        ),
+                        referenced_column_name=(
+                            constraint.referenced_column
+                            if constraint.constraint_type == "FOREIGN KEY"
+                            else None
+                        ),
                     )
                 )
             self.report.num_get_table_constraints_for_dataset_api_requests += 1

datahub/ingestion/source/bigquery_v2/bigquery_schema_gen.py

@@ -498,7 +498,10 @@ class BigQuerySchemaGenerator:
                 report=self.report,
                 rate_limiter=rate_limiter,
             )
-            if self.config.include_table_constraints:
+            if (
+                self.config.include_table_constraints
+                and bigquery_dataset.supports_table_constraints()
+            ):
                 constraints = self.schema_api.get_table_constraints_for_dataset(
                     project_id=project_id, dataset_name=dataset_name, report=self.report
                 )
@@ -1157,9 +1160,11 @@ class BigQuerySchemaGenerator:
             # fields=[],
             fields=self.gen_schema_fields(
                 columns,
-                table.constraints
-                if (isinstance(table, BigqueryTable) and table.constraints)
-                else [],
+                (
+                    table.constraints
+                    if (isinstance(table, BigqueryTable) and table.constraints)
+                    else []
+                ),
             ),
             foreignKeys=foreign_keys if foreign_keys else None,
         )
@@ -1180,13 +1185,9 @@ class BigQuerySchemaGenerator:
     ) -> Iterable[BigqueryTable]:
         # In bigquery there is no way to query all tables in a Project id
         with PerfTimer() as timer:
-            # PARTITIONS INFORMATION_SCHEMA view is not available for BigLake tables
-            # based on Amazon S3 and Blob Storage data.
-            # https://cloud.google.com/bigquery/docs/omni-introduction#limitations
-            # Omni Locations - https://cloud.google.com/bigquery/docs/omni-introduction#locations
-            with_partitions = self.config.have_table_data_read_permission and not (
-                dataset.location
-                and dataset.location.lower().startswith(("aws-", "azure-"))
+            with_partitions = (
+                self.config.have_table_data_read_permission
+                and dataset.supports_table_partitions()
             )
 
             # Partitions view throw exception if we try to query partition info for too many tables

datahub/ingestion/source/dremio/dremio_reporting.py

@@ -1,7 +1,7 @@
 from dataclasses import dataclass
 from datetime import datetime
 
-from datahub.ingestion.source.sql.sql_generic_profiler import ProfilingSqlReport
+from datahub.ingestion.source.sql.sql_report import SQLSourceReport
 from datahub.ingestion.source.state.stale_entity_removal_handler import (
     StaleEntityRemovalSourceReport,
 )
@@ -10,7 +10,7 @@ from datahub.ingestion.source_report.ingestion_stage import IngestionStageReport
 
 @dataclass
 class DremioSourceReport(
-    ProfilingSqlReport, StaleEntityRemovalSourceReport, IngestionStageReport
+    SQLSourceReport, StaleEntityRemovalSourceReport, IngestionStageReport
 ):
     num_containers_failed: int = 0
     num_datasets_failed: int = 0

datahub/ingestion/source/ge_data_profiler.py

@@ -55,7 +55,7 @@ from datahub.ingestion.source.profiling.common import (
     Cardinality,
     convert_to_cardinality,
 )
-from datahub.ingestion.source.sql.sql_common import SQLSourceReport
+from datahub.ingestion.source.sql.sql_report import SQLSourceReport
 from datahub.metadata.com.linkedin.pegasus2avro.schema import EditableSchemaMetadata
 from datahub.metadata.schema_classes import (
     DatasetFieldProfileClass,

datahub/ingestion/source/ge_profiling_config.py

@@ -125,12 +125,16 @@ class GEProfilingConfig(GEProfilingBaseConfig):
 
     profile_table_size_limit: Optional[int] = Field(
         default=5,
-        description="Profile tables only if their size is less then specified GBs. If set to `null`, no limit on the size of tables to profile. Supported only in `snowflake` and `BigQuery`",
+        description="Profile tables only if their size is less than specified GBs. If set to `null`, "
+        "no limit on the size of tables to profile. Supported only in `snowflake` and `BigQuery`"
+        "Supported for `oracle` based on calculated size from gathered stats.",
     )
 
     profile_table_row_limit: Optional[int] = Field(
         default=5000000,
-        description="Profile tables only if their row count is less then specified count. If set to `null`, no limit on the row count of tables to profile. Supported only in `snowflake` and `BigQuery`",
+        description="Profile tables only if their row count is less than specified count. If set to `null`, "
+        "no limit on the row count of tables to profile. Supported only in `snowflake` and `BigQuery`"
+        "Supported for `oracle` based on gathered stats.",
     )
 
     profile_table_row_count_estimate_only: bool = Field(

datahub/ingestion/source/redshift/report.py

@@ -3,7 +3,7 @@ from datetime import datetime
 from typing import Dict, Optional
 
 from datahub.ingestion.glossary.classification_mixin import ClassificationReportMixin
-from datahub.ingestion.source.sql.sql_generic_profiler import ProfilingSqlReport
+from datahub.ingestion.source.sql.sql_report import SQLSourceReport
 from datahub.ingestion.source_report.ingestion_stage import IngestionStageReport
 from datahub.ingestion.source_report.time_window import BaseTimeWindowReport
 from datahub.sql_parsing.sql_parsing_aggregator import SqlAggregatorReport
@@ -14,7 +14,7 @@ from datahub.utilities.stats_collections import TopKDict
 
 @dataclass
 class RedshiftReport(
-    ProfilingSqlReport,
+    SQLSourceReport,
     IngestionStageReport,
     BaseTimeWindowReport,
     ClassificationReportMixin,

datahub/ingestion/source/snowflake/snowflake_report.py

@@ -5,7 +5,7 @@ from typing import TYPE_CHECKING, Dict, List, MutableSet, Optional
 from datahub.ingestion.api.report import Report
 from datahub.ingestion.glossary.classification_mixin import ClassificationReportMixin
 from datahub.ingestion.source.snowflake.constants import SnowflakeEdition
-from datahub.ingestion.source.sql.sql_generic_profiler import ProfilingSqlReport
+from datahub.ingestion.source.sql.sql_report import SQLSourceReport
 from datahub.ingestion.source.state.stateful_ingestion_base import (
     StatefulIngestionReport,
 )
@@ -59,7 +59,7 @@ class SnowflakeUsageReport:
 
 
 @dataclass
-class SnowflakeReport(ProfilingSqlReport, BaseTimeWindowReport):
+class SnowflakeReport(SQLSourceReport, BaseTimeWindowReport):
     num_table_to_table_edges_scanned: int = 0
     num_table_to_view_edges_scanned: int = 0
     num_view_to_table_edges_scanned: int = 0

datahub/ingestion/source/sql/oracle.py

@@ -1,3 +1,4 @@
+import datetime
 import logging
 import re
 
@@ -631,3 +632,52 @@ class OracleSource(SQLAlchemySource):
             clear=False,
         ):
             return super().get_workunits()
+
+    def generate_profile_candidates(
+        self,
+        inspector: Inspector,
+        threshold_time: Optional[datetime.datetime],
+        schema: str,
+    ) -> Optional[List[str]]:
+        tables_table_name = (
+            "ALL_TABLES" if self.config.data_dictionary_mode == "ALL" else "DBA_TABLES"
+        )
+
+        # If stats are available , they are used even if they are stale.
+        # Assuming that the table would typically grow over time, this will ensure to filter
+        # large tables known at stats collection time from profiling candidates.
+        # If stats are not available (NULL), such tables are not filtered and are considered
+        # as profiling candidates.
+        cursor = inspector.bind.execute(
+            sql.text(
+                f"""SELECT
+                            t.OWNER,
+                            t.TABLE_NAME,
+                            t.NUM_ROWS,
+                            t.LAST_ANALYZED,
+                            COALESCE(t.NUM_ROWS * t.AVG_ROW_LEN, 0) / (1024 * 1024 * 1024) AS SIZE_GB
+                        FROM {tables_table_name} t
+                        WHERE t.OWNER = :owner
+                        AND (t.NUM_ROWS < :table_row_limit OR t.NUM_ROWS IS NULL)
+                        AND COALESCE(t.NUM_ROWS * t.AVG_ROW_LEN, 0) / (1024 * 1024 * 1024) < :table_size_limit
+                """
+            ),
+            dict(
+                owner=inspector.dialect.denormalize_name(schema),
+                table_row_limit=self.config.profiling.profile_table_row_limit,
+                table_size_limit=self.config.profiling.profile_table_size_limit,
+            ),
+        )
+
+        TABLE_NAME_COL_LOC = 1
+        return [
+            self.get_identifier(
+                schema=schema,
+                entity=inspector.dialect.normalize_name(row[TABLE_NAME_COL_LOC])
+                or _raise_err(
+                    ValueError(f"Invalid table name: {row[TABLE_NAME_COL_LOC]}")
+                ),
+                inspector=inspector,
+            )
+            for row in cursor
+        ]

datahub/ingestion/source/sql/sql_common.py

@@ -51,7 +51,6 @@ from datahub.ingestion.api.workunit import MetadataWorkUnit
 from datahub.ingestion.glossary.classification_mixin import (
     SAMPLE_SIZE_MULTIPLIER,
     ClassificationHandler,
-    ClassificationReportMixin,
 )
 from datahub.ingestion.source.common.data_reader import DataReader
 from datahub.ingestion.source.common.subtypes import (
@@ -59,6 +58,7 @@ from datahub.ingestion.source.common.subtypes import (
     DatasetSubTypes,
 )
 from datahub.ingestion.source.sql.sql_config import SQLCommonConfig
+from datahub.ingestion.source.sql.sql_report import SQLSourceReport
 from datahub.ingestion.source.sql.sql_utils import (
     add_table_to_schema_container,
     downgrade_schema_from_v2,
@@ -74,7 +74,6 @@ from datahub.ingestion.source.sql.sqlalchemy_data_reader import (
 )
 from datahub.ingestion.source.state.stale_entity_removal_handler import (
     StaleEntityRemovalHandler,
-    StaleEntityRemovalSourceReport,
 )
 from datahub.ingestion.source.state.stateful_ingestion_base import (
     StatefulIngestionSourceBase,
@@ -118,9 +117,7 @@ from datahub.sql_parsing.sqlglot_lineage import (
 )
 from datahub.telemetry import telemetry
 from datahub.utilities.file_backed_collections import FileBackedDict
-from datahub.utilities.lossy_collections import LossyList
 from datahub.utilities.registries.domain_registry import DomainRegistry
-from datahub.utilities.sqlalchemy_query_combiner import SQLAlchemyQueryCombinerReport
 from datahub.utilities.sqlalchemy_type_converter import (
     get_native_data_type_for_sqlalchemy_type,
 )
@@ -134,43 +131,6 @@ if TYPE_CHECKING:
 logger: logging.Logger = logging.getLogger(__name__)
 
 
-@dataclass
-class SQLSourceReport(StaleEntityRemovalSourceReport, ClassificationReportMixin):
-    tables_scanned: int = 0
-    views_scanned: int = 0
-    entities_profiled: int = 0
-    filtered: LossyList[str] = field(default_factory=LossyList)
-
-    query_combiner: Optional[SQLAlchemyQueryCombinerReport] = None
-
-    num_view_definitions_parsed: int = 0
-    num_view_definitions_failed_parsing: int = 0
-    num_view_definitions_failed_column_parsing: int = 0
-    view_definitions_parsing_failures: LossyList[str] = field(default_factory=LossyList)
-
-    def report_entity_scanned(self, name: str, ent_type: str = "table") -> None:
-        """
-        Entity could be a view or a table
-        """
-        if ent_type == "table":
-            self.tables_scanned += 1
-        elif ent_type == "view":
-            self.views_scanned += 1
-        else:
-            raise KeyError(f"Unknown entity {ent_type}.")
-
-    def report_entity_profiled(self, name: str) -> None:
-        self.entities_profiled += 1
-
-    def report_dropped(self, ent_name: str) -> None:
-        self.filtered.append(ent_name)
-
-    def report_from_query_combiner(
-        self, query_combiner_report: SQLAlchemyQueryCombinerReport
-    ) -> None:
-        self.query_combiner = query_combiner_report
-
-
 class SqlWorkUnit(MetadataWorkUnit):
     pass
 
@@ -352,7 +312,7 @@ class SQLAlchemySource(StatefulIngestionSourceBase, TestableSource):
 
     def __init__(self, config: SQLCommonConfig, ctx: PipelineContext, platform: str):
         super().__init__(config, ctx)
-        self.config = config
+        self.config: SQLCommonConfig = config
         self.platform = platform
         self.report: SQLSourceReport = SQLSourceReport()
         self.profile_metadata_info: ProfileMetadata = ProfileMetadata()
@@ -1282,17 +1242,22 @@ class SQLAlchemySource(StatefulIngestionSourceBase, TestableSource):
     def is_dataset_eligible_for_profiling(
         self,
         dataset_name: str,
-        sql_config: SQLCommonConfig,
+        schema: str,
         inspector: Inspector,
         profile_candidates: Optional[List[str]],
     ) -> bool:
-        return (
-            sql_config.table_pattern.allowed(dataset_name)
-            and sql_config.profile_pattern.allowed(dataset_name)
-        ) and (
-            profile_candidates is None
-            or (profile_candidates is not None and dataset_name in profile_candidates)
-        )
+        if not (
+            self.config.table_pattern.allowed(dataset_name)
+            and self.config.profile_pattern.allowed(dataset_name)
+        ):
+            self.report.profiling_skipped_table_profile_pattern[schema] += 1
+            return False
+
+        if profile_candidates is not None and dataset_name not in profile_candidates:
+            self.report.profiling_skipped_other[schema] += 1
+            return False
+
+        return True
 
     def loop_profiler_requests(
         self,
@@ -1307,7 +1272,7 @@ class SQLAlchemySource(StatefulIngestionSourceBase, TestableSource):
         if (
             sql_config.profiling.profile_if_updated_since_days is not None
             or sql_config.profiling.profile_table_size_limit is not None
-            or sql_config.profiling.profile_table_row_limit is None
+            or sql_config.profiling.profile_table_row_limit is not None
         ):
             try:
                 threshold_time: Optional[datetime.datetime] = None
@@ -1328,8 +1293,9 @@ class SQLAlchemySource(StatefulIngestionSourceBase, TestableSource):
                 schema=schema, entity=table, inspector=inspector
             )
             if not self.is_dataset_eligible_for_profiling(
-                dataset_name, sql_config, inspector, profile_candidates
+                dataset_name, schema, inspector, profile_candidates
             ):
+                self.report.num_tables_not_eligible_profiling[schema] += 1
                 if self.config.profiling.report_dropped_profiles:
                     self.report.report_dropped(f"profile of {dataset_name}")
                 continue