acryl-datahub 1.2.0.11rc4__py3-none-any.whl → 1.3.0__py3-none-any.whl

{acryl_datahub-1.2.0.11rc4.dist-info → acryl_datahub-1.3.0.dist-info}/RECORD

@@ -1,7 +1,7 @@
-acryl_datahub-1.2.0.11rc4.dist-info/licenses/LICENSE,sha256=9xNHpsD0uYF5ONzXsKDCuHHB-xbiCrSbueWXqrTNsxk,11365
+acryl_datahub-1.3.0.dist-info/licenses/LICENSE,sha256=9xNHpsD0uYF5ONzXsKDCuHHB-xbiCrSbueWXqrTNsxk,11365
 datahub/__init__.py,sha256=aq_i5lVREmoLfYIqcx_pEQicO855YlhD19tWc1eZZNI,59
 datahub/__main__.py,sha256=pegIvQ9hzK7IhqVeUi1MeADSZ2QlP-D3K0OQdEg55RU,106
-datahub/_version.py,sha256=_VILFvBE67asqk9L6Hqvhg65t1Q8zAbMrsKHYLWBj4I,324
+datahub/_version.py,sha256=9bBnOhXKK0Kz9kBFa9_js_7Pj_9YvV8did9BXYK34H8,318
 datahub/entrypoints.py,sha256=9Qf-37rNnTzbGlx8S75OCDazIclFp6zWNcCEL1zCZto,9015
 datahub/errors.py,sha256=p5rFAdAGVCk4Lqolol1YvthceadUSwpaCxLXRcyCCFQ,676
 datahub/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -72,7 +72,7 @@ datahub/cli/cli_utils.py,sha256=0jTTAKuDZ8GzZwGHYytcT_MPR3Rb2DAcbr9n1H2T2sE,1617
 datahub/cli/config_utils.py,sha256=EeBGfhmf4AxYoTfnZ4GSiGIgpzJFkduNjN_FwmxZGhA,4889
 datahub/cli/container_cli.py,sha256=D0zWP3_3aww8_RTkMugOoOlILz3dPJ0TE9asQDLCm6E,1697
 datahub/cli/delete_cli.py,sha256=0YJeWuXPGY0kbSn1AXK1-8SfCGBxb78ZbO53RAgyjQg,26515
-datahub/cli/docker_check.py,sha256=CE6YNdX4XsXT8GYiQOLbOLi2x_-kK2aQqmTl0ZP0Uu4,12976
+datahub/cli/docker_check.py,sha256=Iy5zFww7ZX-kdpBjqxW1s827DGalka2LLlxT2f1KU6g,12978
 datahub/cli/docker_cli.py,sha256=3pzoe_qbWLhG27-M2wBU5MLLJM0xPlmC-EyoueoQEL4,33091
 datahub/cli/env_utils.py,sha256=RQzjg4JE29hjPt4v7p-RuqoOr99w8E3DBHWiN2Sm7T4,252
 datahub/cli/exists_cli.py,sha256=1cUYNh3GqNgVHWTrfMRGJoo9tFZNXcLetMaDbLaig6o,1233
@@ -151,13 +151,14 @@ datahub/ingestion/api/registry.py,sha256=LbdZr89465Lj7ptQRVB4vI1JR1igWABvQFj9-WX
 datahub/ingestion/api/report.py,sha256=1w63Y2yN49IaDLZaIvXEjRU3yVb_9t3wzymSI-fumZM,18959
 datahub/ingestion/api/report_helpers.py,sha256=WbUC1kQeaKqIagGV3XzfPmPs7slAT1mfNY4og2BH2A8,994
 datahub/ingestion/api/sink.py,sha256=bureB3_sFXNISCM4yZSqhxMHW-ctDkAQqA0lJgQhJQ4,6047
-datahub/ingestion/api/source.py,sha256=JASs7WygVB6g-tcwtchaftzv3lNtlVM31lEa242pn44,21853
+datahub/ingestion/api/source.py,sha256=SKQFnA2OTT4jcy59ae1KF_ZFa_nIyFzRohkZJKixjIk,22712
 datahub/ingestion/api/source_helpers.py,sha256=XT9y5HgfVeF52jrX39vlLn1SdXpLVyT2Su8oGNsddYo,21148
+datahub/ingestion/api/source_protocols.py,sha256=llWgfxDquowIovgWqfhdiS1dzUQ3Y_SmCaq501S-NLc,768
 datahub/ingestion/api/transform.py,sha256=X0GpjMJzYkLuZx8MTWxH50cWGm9rGsnn3k188mmC8J8,582
 datahub/ingestion/api/workunit.py,sha256=e8n8RfSjHZZm2R4ShNH0UuMtUkMjyqqM2j2t7oL74lo,6327
 datahub/ingestion/api/auto_work_units/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 datahub/ingestion/api/auto_work_units/auto_dataset_properties_aspect.py,sha256=ID_6N3nWl2qohsSGizUCqo3d2MNyDeVbyWroQpSOSsc,5059
-datahub/ingestion/api/auto_work_units/auto_ensure_aspect_size.py,sha256=0BwkpLhORbsiTHq0g_N_1cVVoZYdLR3qz02mNmsV9-M,4444
+datahub/ingestion/api/auto_work_units/auto_ensure_aspect_size.py,sha256=-667F-xWArmeVaW-3mGsoIMNKPrnLx6KM4OfzMGsMOo,18064
 datahub/ingestion/autogenerated/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 datahub/ingestion/autogenerated/capability_summary.json,sha256=9Ns5gYfVq0LYogaYtb0ioDPfu8SVhftiq9R7l0irQwg,111506
 datahub/ingestion/autogenerated/lineage.json,sha256=8BdZF-5V5kJbX4mfFav8Zg-jHjzfkAEGk-pu1atLN4I,10029
@@ -227,7 +228,7 @@ datahub/ingestion/source/pulsar.py,sha256=u5F8QnCLJsht5-7XCiUTsnfhCPIpKVB_l32CgM
 datahub/ingestion/source/redash.py,sha256=C4cDikWymbL88fDqaIPX5WA3f2sIEtH7bmhJKkmXJsM,30652
 datahub/ingestion/source/salesforce.py,sha256=dMQ2jMu9P8r0rmREQA6KuFgAbegJ7WnHpUmMaUfHPDI,40942
 datahub/ingestion/source/source_registry.py,sha256=a2mLjJPLkSI-gYCTb_7U7Jo4D8jGknNQ_yScPIihXFk,1208
-datahub/ingestion/source/sql_queries.py,sha256=mhEIbNywHpZKcX22ENdJolD3z5x4TNR5gXAEmX7ejfQ,14666
+datahub/ingestion/source/sql_queries.py,sha256=RexNsG-COCiKNyL0mfoeNoMrkXxmB5UBOSJKJnHNHy0,14563
 datahub/ingestion/source/superset.py,sha256=qZ1SMeejwiM_ZkPlERXi3OSmabWcrsJSxZe98Eo9tqA,57866
 datahub/ingestion/source/abs/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 datahub/ingestion/source/abs/config.py,sha256=WW9JWbzqAJDblAcJKtNeuBHqOeJsB57lW2PqSD65-BU,6729
@@ -266,9 +267,9 @@ 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=9_sfX8BE2vt9RjBMyq27UxCxBaSlD5o3L4gQxrwlPvA,4961
 datahub/ingestion/source/bigquery_v2/bigquery_queries.py,sha256=2syDMaRpYEbtGUVejVAK5d6g8HqM54ZyEM908uLJ55o,3393
-datahub/ingestion/source/bigquery_v2/bigquery_report.py,sha256=v7_zkZzymKPmZKWAxnxmvmHC-8TQVGHUT-pBQFNehqc,7962
+datahub/ingestion/source/bigquery_v2/bigquery_report.py,sha256=zlTkqOmt5zxnO40rVTYHF3fclj4OVlLtqUXwW5WIIcM,7855
 datahub/ingestion/source/bigquery_v2/bigquery_schema.py,sha256=zbYb1EYnCJxgvsU8oT_76l0q_BW1exVjMWM1GAgd1nc,32600
-datahub/ingestion/source/bigquery_v2/bigquery_schema_gen.py,sha256=c9a-SlZDOYNiS__vC5ezVVNM0UHasXWxWNRZkkP_aOo,51552
+datahub/ingestion/source/bigquery_v2/bigquery_schema_gen.py,sha256=_NLFRRXsrxMZ8Vjg2jVL4Pg1_NGt9hzn9EWBooJZ8so,51566
 datahub/ingestion/source/bigquery_v2/bigquery_test_connection.py,sha256=cATxwi5IPzj3BldRRAVcLqzSFmmYEPvqa7U0RFJbaAc,7645
 datahub/ingestion/source/bigquery_v2/common.py,sha256=IinOy-RO4UZGxSf5scaN02672BzZuNsjJZ56axti6iI,4016
 datahub/ingestion/source/bigquery_v2/lineage.py,sha256=jju14mJbAUMA_K3j2yq-TdZV202cjd5rBAsDPJGEVno,44900
@@ -280,8 +281,8 @@ datahub/ingestion/source/cassandra/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQe
 datahub/ingestion/source/cassandra/cassandra.py,sha256=pNy61Z4kTqL_wGcWIYee5fnZiuJDseDcRcQwsxeAssk,14487
 datahub/ingestion/source/cassandra/cassandra_api.py,sha256=wCJx-1ZByGMgPkORBO420sGucKkxXXE4pOLWXxdpMIw,14222
 datahub/ingestion/source/cassandra/cassandra_config.py,sha256=w9LBiT8XrGvXlrvpcAU_xm82GiE4nUfEg-VKIX6MRMY,4446
-datahub/ingestion/source/cassandra/cassandra_profiling.py,sha256=FdgPK_8s8otTOJDqNM4rpF6Mn4lFWbnjTaKEChzn2iE,11011
-datahub/ingestion/source/cassandra/cassandra_utils.py,sha256=j-LidYkaCTmGnpUVNLsax_c3z32PsQbsbHeYojygd1s,5105
+datahub/ingestion/source/cassandra/cassandra_profiling.py,sha256=nNQwjParCnvhT9nF-uwGtKmAR0dBS9eqAxfknV1CKiA,11022
+datahub/ingestion/source/cassandra/cassandra_utils.py,sha256=-BsrK1R5jCQs-kUJYVj1x5zm_rG4teCYwS_r-OT3mCE,5002
 datahub/ingestion/source/common/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 datahub/ingestion/source/common/data_platforms.py,sha256=HhuP3YIEi2WpyKDjUU8RiM0a2qjHWQcvc8kcqub0cVo,548
 datahub/ingestion/source/common/data_reader.py,sha256=XbSxiRTYrk6seOz0ZjVjzSpGvP8lEjmqXrNI4cdYYmQ,1819
@@ -319,8 +320,8 @@ datahub/ingestion/source/dremio/dremio_config.py,sha256=6Re-CIkLxi90VfBCeUTZ4bBv
 datahub/ingestion/source/dremio/dremio_datahub_source_mapping.py,sha256=MQk8BAHLufN69CntFfOV8K59A_AvLC-vwMS33Jw8bBg,3069
 datahub/ingestion/source/dremio/dremio_entities.py,sha256=1gZrNqTp3Pm6vqGDQaWt3HkxEuHKxpGYQ4geVoFvxWI,15147
 datahub/ingestion/source/dremio/dremio_profiling.py,sha256=TAcnpo8ZRKhLDHnQSJzJg3YdwTSyEa73LUAzENs7wG4,12287
-datahub/ingestion/source/dremio/dremio_reporting.py,sha256=YRKM6PvoJYHLBXmOGwkgou_8x8_oA2xaqTWWoVuwFMY,2247
-datahub/ingestion/source/dremio/dremio_source.py,sha256=GZnpJhuqxCzDz4tTklFt2dSfF-L6rMhlvzGuvvibD7k,25563
+datahub/ingestion/source/dremio/dremio_reporting.py,sha256=UEj-6FMdIWsry5535_kM2hLze5aPRMatTwvI0Bd2BSo,2140
+datahub/ingestion/source/dremio/dremio_source.py,sha256=JFgzQiYcIkKcyiTJstYdfNxIVCGAcbi198kPQ55bYso,25596
 datahub/ingestion/source/dremio/dremio_sql_queries.py,sha256=wA1hqKk9cKMJDyEdZRQcDDLZPGYwuNqrvleUHTkWgrQ,10508
 datahub/ingestion/source/dynamodb/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 datahub/ingestion/source/dynamodb/data_reader.py,sha256=vC77KpcP8LJN0g8wsPRDVw4sebv0ZWIP3tJkEIHaomA,3120
@@ -333,13 +334,13 @@ datahub/ingestion/source/excel/report.py,sha256=oEkeI8J6is7zB9iz4RqASu_-Q5xl36lA
 datahub/ingestion/source/excel/source.py,sha256=w_vOz4UD7BcXBBDKoo81_6-QFeOPITuXqkfjIMHCQj4,23827
 datahub/ingestion/source/excel/util.py,sha256=YYmadYuCiT-4_MfQM0YSE7wuDcE0k8o2KrlOKM9Z6eI,406
 datahub/ingestion/source/fivetran/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-datahub/ingestion/source/fivetran/config.py,sha256=vjN90fT98paJEZyJgw7UCapVfujiDH9_iPX8jUbOEWE,9087
+datahub/ingestion/source/fivetran/config.py,sha256=6yriUMtTPMZUHqbZ9gzyFduPVt6CxzirdYSg4k-ziYI,10285
 datahub/ingestion/source/fivetran/data_classes.py,sha256=ecdUJH5BEze0yv-uFpKWPNaNmV1gORDA2XMFk0zhcBw,595
-datahub/ingestion/source/fivetran/fivetran.py,sha256=s8wcECtmuugUoZ0Zdthq0SIPpTLvziZXuhhUX9bJ5N4,14492
-datahub/ingestion/source/fivetran/fivetran_log_api.py,sha256=PNzuykiiFTU8FhBIfUbW6udURZpz_35aq7rfffbpIfA,13010
-datahub/ingestion/source/fivetran/fivetran_query.py,sha256=WE7kZ54zR1RKg_GNXHoKKEBiyw7PhNp-Ei8Y4OMXXGc,5608
+datahub/ingestion/source/fivetran/fivetran.py,sha256=Up5wbLk7hBk9b0pqcHwW6b0H52UJj90cmLhn0QJeZ4g,14416
+datahub/ingestion/source/fivetran/fivetran_log_api.py,sha256=-ibtfgxFv08P5_X5PVqV4CocxAjRWmY858esQL5OaAQ,13697
+datahub/ingestion/source/fivetran/fivetran_query.py,sha256=VJTka6cdIzlqy0aWyviMO2uSHcL0ZQFTCefUnnjv_Bk,6578
 datahub/ingestion/source/gc/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-datahub/ingestion/source/gc/datahub_gc.py,sha256=EXO-Stj6gGMLTSTbSBC-C3_zpjpQtFN9pAMWR95ma0I,12830
+datahub/ingestion/source/gc/datahub_gc.py,sha256=nJ6QbHnTPL0MamWxNTZA26FMZsnmvUdUwnQcDS81K9s,12723
 datahub/ingestion/source/gc/dataprocess_cleanup.py,sha256=mUWcMt-_FL1SYGIgI4lGZDZGXspUUTv__5GN1W2oJ3s,17118
 datahub/ingestion/source/gc/execution_request_cleanup.py,sha256=y-9ZIs_DZPUzYH1CI6HmaAZg3olNNA7MjT8HrCqAI0k,11159
 datahub/ingestion/source/gc/soft_deleted_entity_cleanup.py,sha256=4-qQR_2HGIYU8kC2hRIsJyKKMb9lKq4B6paJm_abUk4,12628
@@ -355,13 +356,13 @@ datahub/ingestion/source/grafana/grafana_api.py,sha256=pSbaHGPQ4HajCyVnvfEjl9zr2
 datahub/ingestion/source/grafana/grafana_config.py,sha256=Xyt4jY9vKJuu99PX6cpOZ3WANTn00aUTYvItIPVC6XQ,3683
 datahub/ingestion/source/grafana/grafana_source.py,sha256=tUYW0bXvnwhfBpSRQh4KobhOThXhezdH4hy2IPBkgag,21727
 datahub/ingestion/source/grafana/lineage.py,sha256=qDWCiceOotVApOpcGhRK9OTqyRJIPqXcJi6CKnfK8z0,7178
-datahub/ingestion/source/grafana/models.py,sha256=MqMGdQKjvn0cdvryEyX54w8zGZwMiBdUAvhFM1TNv1I,4401
-datahub/ingestion/source/grafana/report.py,sha256=LTRxjXYCYHwOaj1zrenCDAvFBE5U5tAv6Wh5LlfsgfE,2963
+datahub/ingestion/source/grafana/models.py,sha256=cOEYJ5DpmGkQKxqBq3iQE6D7aFLRGjGY6cbSP8gkFss,4676
+datahub/ingestion/source/grafana/report.py,sha256=gNXKwGYCO6PLiqiM1K_Hv11vJuzxqcxiPNWdCY6dKNQ,2860
 datahub/ingestion/source/grafana/types.py,sha256=Bz0-FIPBXHaBjfFHYGJhE20c2vYZwAsXr70MVGjSu6s,443
 datahub/ingestion/source/hex/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 datahub/ingestion/source/hex/api.py,sha256=rKr6GmhIs98_SQZYG4egZlS049WH4ZxW2-7Ueq8692Q,12940
 datahub/ingestion/source/hex/constants.py,sha256=8hUTMWyG5keTNfXoLu_Dh413Hw_mGGJX1atiiDZyKtg,271
-datahub/ingestion/source/hex/hex.py,sha256=LI6P5YHXl8eoveWUbjwIDf0pU2bvrdQXE0Q_tKSCw90,13435
+datahub/ingestion/source/hex/hex.py,sha256=NaMibmvFXoCD84G0-asEDILbiluZyulbZZg23moP0hI,13328
 datahub/ingestion/source/hex/mapper.py,sha256=IyDAE-TzZUji3ICI_9gkYC3dQN3gl6kERRWNVRk80fQ,13905
 datahub/ingestion/source/hex/model.py,sha256=eri4aRo1eXcE2SWjzCnPFMhzPTiJ8w8zC4GN7Lgpr74,1864
 datahub/ingestion/source/hex/query_fetcher.py,sha256=r9UvF_qwswkRlNY7AI8p46eqAYSxVtjVE2e7eO4XagA,13384
@@ -451,10 +452,10 @@ datahub/ingestion/source/redshift/exception.py,sha256=dxzYUIv5B_FAWhOuzG2u5We7FX
 datahub/ingestion/source/redshift/lineage.py,sha256=nqrvWJqaI493i1hIZ_7patrdOb16sZrgSSGapdMcEiU,31710
 datahub/ingestion/source/redshift/profile.py,sha256=H1Xtc2rXScUv4w0b2BbM7POjYEwqIql_rpWvlumY_EM,4309
 datahub/ingestion/source/redshift/query.py,sha256=HKobQ-0crARgT8Mkfe-WBqVR9ZadYCZ9DGaUoEHHHww,48234
-datahub/ingestion/source/redshift/redshift.py,sha256=zalndYg_LK5aJ8cX_ZuXLcTYajtlavmV-dmQIsjGxjg,41260
+datahub/ingestion/source/redshift/redshift.py,sha256=RN8rao3j7nocnnD6oPcEju09-8mOZTE4vFkgy_13Az8,41293
 datahub/ingestion/source/redshift/redshift_data_reader.py,sha256=zc69jwXHdF-w8J4Hq-ZQ6BjHQ75Ij2iNDMpoRJlcmlU,1724
 datahub/ingestion/source/redshift/redshift_schema.py,sha256=7F-l_omOuKMuGE_rBWXVPG_GWXFKnCMzC4frNxZB9cs,24800
-datahub/ingestion/source/redshift/report.py,sha256=O3QFozHlmMbH9b7KxbqhgTgr_0tCryj6FIzMiN6kRxw,3044
+datahub/ingestion/source/redshift/report.py,sha256=aCFDFUbz5xde8b_eRIHSBiELoo9LZFtDpp2lSadiPHU,2937
 datahub/ingestion/source/redshift/usage.py,sha256=Q7R-caJovLXv33uZepMGX5Cvm4DqQSLZdiL_s-p06wU,17473
 datahub/ingestion/source/s3/__init__.py,sha256=HjqFPj11WtNFZM3kcVshlDb7kOsc19-l_3LM8PBjlJM,56
 datahub/ingestion/source/s3/config.py,sha256=lElFXgEpKDT9SVoiXvtx98wV6Gp880qP4pLQaOGJGOo,7828
@@ -500,9 +501,9 @@ datahub/ingestion/source/snowflake/snowflake_lineage_v2.py,sha256=nam-bYV6wL9LfR
 datahub/ingestion/source/snowflake/snowflake_profiler.py,sha256=PmQi-qDlRhdJ-PsJ7x-EScIiswWRAxDDOKHydvN3mTY,7404
 datahub/ingestion/source/snowflake/snowflake_queries.py,sha256=lAMA--X3nbWFdNs1DTHNm7crctB3RilX_pB-zy47piI,45528
 datahub/ingestion/source/snowflake/snowflake_query.py,sha256=wLDaYZrWJ0794KKn69rB_QF0_8Bzu5l_7L6mD77KVc4,40469
-datahub/ingestion/source/snowflake/snowflake_report.py,sha256=GPuQTOaR8SCqMBme6Q55vX4zzT4m3ELmp83rp_grQA0,6808
+datahub/ingestion/source/snowflake/snowflake_report.py,sha256=fA6C-p9wM-jyTsXE_suTbCtrE_lle-5LI52S7wFYf00,6701
 datahub/ingestion/source/snowflake/snowflake_schema.py,sha256=Dh_p0WpSaWOFMCsBgd3FpkQ_65k3QPq2VUnapp2VKuY,41431
-datahub/ingestion/source/snowflake/snowflake_schema_gen.py,sha256=tojh0BQibKfoSqszXiyoQRoLy3g0g4tntyRpZmsjOYk,59084
+datahub/ingestion/source/snowflake/snowflake_schema_gen.py,sha256=-JBfYgAXKMbVYu3f2viQoOQ0O2wv6GWfw1giOiETbpc,59091
 datahub/ingestion/source/snowflake/snowflake_shares.py,sha256=maZyFkfrbVogEFM0tTKRiNp9c_1muv6YfleSd3q0umI,6341
 datahub/ingestion/source/snowflake/snowflake_summary.py,sha256=5Li4H8KuS4qBKR98L2P-JZI79UXsOjcAFxZZyio9NU0,5787
 datahub/ingestion/source/snowflake/snowflake_tag.py,sha256=eA9xh-G1Ydr1OwUUtrbXUWp26hE1jF0zvyKNky_i_nQ,8887
@@ -521,10 +522,10 @@ datahub/ingestion/source/sql/hive.py,sha256=SPmAWlk63V-s-loBTU2hXsQA7xA4sa0iPK6p
 datahub/ingestion/source/sql/hive_metastore.py,sha256=UBB7mV2eKuCxv3voi0F3tqF2MyRObSYxArAxETZfO4E,35997
 datahub/ingestion/source/sql/mariadb.py,sha256=om6QoG5UtDldt1N6AfIWp3T-HXNaaqFmpz2i0JAemfM,654
 datahub/ingestion/source/sql/mysql.py,sha256=_KhTODU7mqAoJOlrvRdPa7ihQkYLkgrZwaseQbasotM,5358
-datahub/ingestion/source/sql/oracle.py,sha256=oCQEJ6zG9RnQLYPZrJ4Xuhz5pJlaB9-PcaeudebTsfk,29960
+datahub/ingestion/source/sql/oracle.py,sha256=nKMM1O67SkxCgT781eENl5xXpIR8_p5joTSdAYzQwHY,29988
 datahub/ingestion/source/sql/postgres.py,sha256=blkO6bI0eDKFK8UNwUYcYtm_ObrQuWVSy5GyfdhL5dg,14274
 datahub/ingestion/source/sql/presto.py,sha256=58py4M3UYxkGpbBFA1o96H154eUhD2dBm1hpxxYlYYM,4256
-datahub/ingestion/source/sql/sql_common.py,sha256=2m3eq_Yn1KPi8x_E0J3vpiuND7BOpnA0zAid4jXaMJw,57383
+datahub/ingestion/source/sql/sql_common.py,sha256=EZGoeGlOYZoOrXOiKDI-S1mw-sPVV33PZQ_mPJlEvRc,57759
 datahub/ingestion/source/sql/sql_config.py,sha256=u3nGZYYl1WtaxfNsDU5bglgZ5Jq3Fxk9xei_CUIAXB0,8222
 datahub/ingestion/source/sql/sql_generic.py,sha256=9AERvkK8kdJUeDOzCYJDb93xdv6Z4DGho0NfeHj5Uyg,2740
 datahub/ingestion/source/sql/sql_generic_profiler.py,sha256=Zr39j4SI1fPTx1JdopVJyBslFnyp3lZCeb1th9eEB5c,11723
@@ -534,7 +535,7 @@ datahub/ingestion/source/sql/sql_utils.py,sha256=q-Bsk6WxlsRtrw9RXBxvqI3zuaMTC_F
 datahub/ingestion/source/sql/sqlalchemy_data_reader.py,sha256=FvHZ4JEK3aR2DYOBZiT_ZsAy12RjTu4t_KIR_92B11k,2644
 datahub/ingestion/source/sql/sqlalchemy_uri.py,sha256=u0ZvgdJjXZdo_vl7YIQfYuuWbGwpnH6OSozI2e8ZV4I,858
 datahub/ingestion/source/sql/sqlalchemy_uri_mapper.py,sha256=KOpbmDIE2h1hyYEsbVHJi2B7FlsyUMTXZx4diyzltQg,1826
-datahub/ingestion/source/sql/teradata.py,sha256=zIPYQQQ89cSZCy6XYHn9VcfTImRQw6AWY62aAfm49sE,65610
+datahub/ingestion/source/sql/teradata.py,sha256=Cij6ZKkkXoJaaSOdQQzBI0QtCC7lGRgUuT9TdC5_YTM,65507
 datahub/ingestion/source/sql/trino.py,sha256=o5hm84iwRHO59TD2LaEqYgF2LYIcSUIKmlgu1VudGBY,19254
 datahub/ingestion/source/sql/two_tier_sql_source.py,sha256=xlpQ9thbEn6uta6eVMzsHzmXFGg30VWInYwg0URgTK4,5784
 datahub/ingestion/source/sql/vertica.py,sha256=LUpIzDpzFRtMcXCSG2EC5CBZbveBOvnB27P_pDrXC9o,33501
@@ -560,14 +561,15 @@ datahub/ingestion/source/state_provider/datahub_ingestion_checkpointing_provider
 datahub/ingestion/source/state_provider/file_ingestion_checkpointing_provider.py,sha256=DziD57PbHn2Tcy51tYXCG-GQgyTGMUxnkuzVS_xihFY,4079
 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=BgR_-IuzUYuaSV3EOvMcefwBZ_h0dYAvNEn5Dv6meA4,158448
+datahub/ingestion/source/tableau/tableau.py,sha256=OpAiVincp7x4XNHHB8HJWTG6By8cDQOgqa1vhg-78w4,158341
 datahub/ingestion/source/tableau/tableau_common.py,sha256=2vE7DIigPvMNcTCWSou0tliaVy9MgFR1qwqnE4pilw8,27086
 datahub/ingestion/source/tableau/tableau_constant.py,sha256=2WPAHN-GAR83_c3eTTNd8cy0-zC8GIXeUdSxX_mNdas,2608
 datahub/ingestion/source/tableau/tableau_server_wrapper.py,sha256=wsVD0SkGUwb-H9_g0aDclKwYkcoxugaWyAcyAMgBCAU,1136
 datahub/ingestion/source/tableau/tableau_validation.py,sha256=Hjbfc1AMIkGgzo5ffWXtNRjrxSxzHvw7-dYZDt4d3WE,1819
 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=LX379ZW7A3Xhf3PmJoe5af6lFSuRHnJAzPzmnU7HWq8,20353
+datahub/ingestion/source/unity/config.py,sha256=lHvr-PGVcZ0P_2e0RuwmfSRlQRJ81astx4hQZkNrX_k,18713
+datahub/ingestion/source/unity/connection.py,sha256=iCsQhZ1vxzv1qQKTl_sFUZdmBLLIrNdu2X2V8hT7IGI,2441
 datahub/ingestion/source/unity/connection_test.py,sha256=Dwpz4AIc6ZDwq6pWmRCSCuDUgNjPP_bVAVJumgAAS4w,2661
 datahub/ingestion/source/unity/ge_profiler.py,sha256=NBRHZceq-f95iUn7u0h7cgcd9nAc48Aa-lmp_BqE0As,8409
 datahub/ingestion/source/unity/hive_metastore_proxy.py,sha256=IAWWJjaW0si_UF52Se2D7wmdYRY_afUG4QlVmQu6xaw,15351
@@ -576,7 +578,7 @@ datahub/ingestion/source/unity/proxy.py,sha256=7TG1B9vdVdM3mmVkHDaLv2AXFfMkx1o8g
 datahub/ingestion/source/unity/proxy_patch.py,sha256=gVYl5Fm_ase0iwBf3yDg7PE3bbTOl92RR-JgofHNkus,12374
 datahub/ingestion/source/unity/proxy_profiling.py,sha256=WLqvYP6MziaisA4LYL4T_GA-kPt6Xdde7bfaYsjYw40,9663
 datahub/ingestion/source/unity/proxy_types.py,sha256=dp7fRqIjaFCn6ivbgXOGHcw9bQQhZg6u-fdTK053oFM,10163
-datahub/ingestion/source/unity/report.py,sha256=_2frKPv_2RRFcCfqlKOks3YR5lrUMIa3zdFJtNO-m6E,3394
+datahub/ingestion/source/unity/report.py,sha256=wa5ER1hLc-362iWS9MNwDJf_adfAb3tfge_O3wSAaTc,3291
 datahub/ingestion/source/unity/source.py,sha256=fC8pgacaXr9AQlwmz9FynJMJgNQ9MsDFbxUGxQRVtWo,57897
 datahub/ingestion/source/unity/tag_entities.py,sha256=-Z-XYc1XhquE-Eoksn9v0o11ZjV9CWz8n6zeXLbzluQ,7275
 datahub/ingestion/source/unity/usage.py,sha256=0wETBAaZvHI_EGgBlxX3bKsVHEAdnUV8_bKI_lbyWjY,11500
@@ -593,7 +595,7 @@ datahub/ingestion/source_config/csv_enricher.py,sha256=IROxxfFJA56dHkmmbjjhb7h1p
 datahub/ingestion/source_config/operation_config.py,sha256=hxF2RM0jk0HUPXYiliMniXBC-wz-ZPcs90ZGLfHT8rE,3924
 datahub/ingestion/source_config/pulsar.py,sha256=zi3QTAw8CzzuwXgU-GUCuLyneT5pxHsLqZFyd15ECYs,5604
 datahub/ingestion/source_report/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-datahub/ingestion/source_report/ingestion_stage.py,sha256=SU_FKFZhShZATLcFr735i_hWpdqNGdAWoZxh22p3P1k,1787
+datahub/ingestion/source_report/ingestion_stage.py,sha256=0MY39QetRovYd1iBNSy0OW11YyaOsPaqhQi-1svmAcY,3106
 datahub/ingestion/source_report/pulsar.py,sha256=f6CMNw8TyPp3tuSGsLLPEhSvoQLXwxtaaM6GmNvsANU,1119
 datahub/ingestion/source_report/time_window.py,sha256=9yI5l2S1DcF7ClvUHLeN8m62I5vlhV9k-aQqSZh2l7w,229
 datahub/ingestion/transformer/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -642,8 +644,8 @@ datahub/lite/lite_registry.py,sha256=bpH0kasP-LtwwUFNA2QsOIehfekAYfJtN-AkQLmSWnw
 datahub/lite/lite_server.py,sha256=p9Oa2nNs65mqcssSIVOr7VOzWqfVstz6ZQEdT4f82S0,1949
 datahub/lite/lite_util.py,sha256=G0LQHKkyEb1pc_q183g6hflShclGx7kikgMaOxtVVcs,4545
 datahub/metadata/__init__.py,sha256=AjhXPjI6cnpdcrBRrE5gOWo15vv2TTl2ctU4UAnUN7A,238
-datahub/metadata/_internal_schema_classes.py,sha256=FYFjU83woitdWMNTk-fZhtCfuUVLv05-syASUGMVwGM,1069868
-datahub/metadata/schema.avsc,sha256=AS5vIh4JGmKVeY_b0fNjUihKBmACH0voLdyxuDqqAXo,771809
+datahub/metadata/_internal_schema_classes.py,sha256=1UZsNj9XmThYFXbG39BVKlaTTFywzayhVVon6svD3kM,1076970
+datahub/metadata/schema.avsc,sha256=P6j7fiukfv03ZW8gis3m3mVKGlSV2JhgMcmrtf5sU7Q,775491
 datahub/metadata/schema_classes.py,sha256=tPT8iHCak4IsZi_oL0nirbPpI8ETTPTZzapqLRpeKU4,1326
 datahub/metadata/urns.py,sha256=nfrCTExR-k2P9w272WVtWSN3xW1VUJngPwP3xnvULjU,1217
 datahub/metadata/_urns/__init__.py,sha256=cOF3GHMDgPhmbLKbN02NPpuLGHSu0qNgQyBRv08eqF0,243
@@ -704,7 +706,7 @@ datahub/metadata/com/linkedin/pegasus2avro/ownership/__init__.py,sha256=r813MW_b
 datahub/metadata/com/linkedin/pegasus2avro/persona/__init__.py,sha256=Y0iT9AeLsLAVzbcXk1hlqqUSPzSjNwn6DqvKxtsLq6A,305
 datahub/metadata/com/linkedin/pegasus2avro/platform/__init__.py,sha256=gsAIuTxzfJdI7a9ybZlgMIHMAYksM1SxGxXjtySgKSc,202
 datahub/metadata/com/linkedin/pegasus2avro/platform/event/__init__.py,sha256=gsAIuTxzfJdI7a9ybZlgMIHMAYksM1SxGxXjtySgKSc,202
-datahub/metadata/com/linkedin/pegasus2avro/platform/event/v1/__init__.py,sha256=O8ngP2_Di9VUQELe4wr3CAL1UfceN0K0F_rgTBEfUvo,383
+datahub/metadata/com/linkedin/pegasus2avro/platform/event/v1/__init__.py,sha256=r4N_gf1o1AUux8hE1e_y6Aq27DaVOMF5U8GuATGlCuY,631
 datahub/metadata/com/linkedin/pegasus2avro/platformresource/__init__.py,sha256=O8Zf6PhoTHFyf6hzAyqYASRyfFfdZiuvpLx7Ygw73WE,415
 datahub/metadata/com/linkedin/pegasus2avro/policy/__init__.py,sha256=NOszM_xottEFQwmlDYkdci1oRddIadcNKd9w5EvuikU,917
 datahub/metadata/com/linkedin/pegasus2avro/post/__init__.py,sha256=FFiWH2BSo057ZwsnFKjpCoAMo9szvC7Vn_RzGTSLnY0,518
@@ -926,6 +928,7 @@ datahub/metadata/schemas/QueryKey.avsc,sha256=VI4oIHvAO7f0lN_7V3QVuBfHcPz31c57Xt
 datahub/metadata/schemas/QueryProperties.avsc,sha256=26Q3zzuzJbUCUG7IJ3q_OEdcNbyzloZzDJWPbv3GQAk,5589
 datahub/metadata/schemas/QuerySubjects.avsc,sha256=PDM6Ek1AkjwLGDk17Rjg7KVtE2tbgFpc1XTGkhoG4MA,1437
 datahub/metadata/schemas/QueryUsageStatistics.avsc,sha256=z1gfAnXdBoPEeERi5RESjrdBuS6AcIdqdN5JqWOSuNo,6192
+datahub/metadata/schemas/RelationshipChangeEvent.avsc,sha256=il7yiTXf9nkZvSyqH8GUu0j2jws_n-QlABXThLJ871c,8288
 datahub/metadata/schemas/RoleKey.avsc,sha256=Uas5jFViSHXhFqq8D4P6-UXqywOth3coztjQ5wA7wL0,449
 datahub/metadata/schemas/RoleMembership.avsc,sha256=Al3LXKRowCiHhgTfwr3a-piID3Ld5kN-6-e9edTZ0uU,570
 datahub/metadata/schemas/RoleProperties.avsc,sha256=tDw-WF1uBGIcrk38nOnXs3FCF_YjBhScarJbreQvwjE,3037
@@ -940,7 +943,7 @@ datahub/metadata/schemas/Status.avsc,sha256=rPZSXSJdwnNywqNx2qll8cdt54aYgI-YUbRr
 datahub/metadata/schemas/StructuredProperties.avsc,sha256=qe45sKZ9XrLcf15Gt03Ttzt2J_kJYHvN-DAOSErSYuY,7028
 datahub/metadata/schemas/StructuredPropertyDefinition.avsc,sha256=a-6TaOQ4A7LDFLshmaFRBcXjz11p4vM0Q3X35GN4Zo0,11737
 datahub/metadata/schemas/StructuredPropertyKey.avsc,sha256=lp7tQBgeriEU1YMQ6a4-6aUGSWDqNl00lLDym97j1yI,618
-datahub/metadata/schemas/StructuredPropertySettings.avsc,sha256=EDNlXfT1TqogfulCanIc-nuYO9ZxRFOGzD9tl3ZJdB8,3732
+datahub/metadata/schemas/StructuredPropertySettings.avsc,sha256=oHPbDuV_Wr_zR9vmTwZZKRzeaBx5nyqN1zn0cfIRhuQ,4044
 datahub/metadata/schemas/SubTypes.avsc,sha256=bhXbzK020zDyQno97Xp05vmoMeZ82IGu2jz7pWDo3RQ,655
 datahub/metadata/schemas/SystemMetadata.avsc,sha256=XEU32-oZsyVwMii-DlQSVDaUTfKQ9n7K0ChMJ07KHvQ,4457
 datahub/metadata/schemas/TagKey.avsc,sha256=BfckMlx-wg_LV1_PFVgItfNBPtCQ8_erGeQM4LzOXmY,640
@@ -1123,8 +1126,8 @@ 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-1.2.0.11rc4.dist-info/METADATA,sha256=SxpOrYaLX-58eO685hRF4fMeo3zkiDS0yFIVNELypnI,184162
-acryl_datahub-1.2.0.11rc4.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-acryl_datahub-1.2.0.11rc4.dist-info/entry_points.txt,sha256=pzsBoTx-D-iTcmpX8oCGCyzlHP2112EygUMzZWz56M8,10105
-acryl_datahub-1.2.0.11rc4.dist-info/top_level.txt,sha256=iLjSrLK5ox1YVYcglRUkcvfZPvKlobBWx7CTUXx8_GI,25
-acryl_datahub-1.2.0.11rc4.dist-info/RECORD,,
+acryl_datahub-1.3.0.dist-info/METADATA,sha256=4oWnajuLBUpYiIu7a_J7r6ddL3EWumCUI_yiesFjvgk,184417
+acryl_datahub-1.3.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+acryl_datahub-1.3.0.dist-info/entry_points.txt,sha256=pzsBoTx-D-iTcmpX8oCGCyzlHP2112EygUMzZWz56M8,10105
+acryl_datahub-1.3.0.dist-info/top_level.txt,sha256=iLjSrLK5ox1YVYcglRUkcvfZPvKlobBWx7CTUXx8_GI,25
+acryl_datahub-1.3.0.dist-info/RECORD,,

datahub/_version.py

@@ -1,6 +1,6 @@
 # Published at https://pypi.org/project/acryl-datahub/.
 __package_name__ = "acryl-datahub"
-__version__ = "1.2.0.11rc4"
+__version__ = "1.3.0"
 
 
 def is_dev_mode() -> bool:

datahub/cli/docker_check.py

@@ -13,7 +13,7 @@ import yaml
 from datahub.configuration.common import ExceptionWithProps
 
 # Docker seems to under-report memory allocated, so we also need a bit of buffer to account for it.
-MIN_MEMORY_NEEDED = 4  # GB
+MIN_MEMORY_NEEDED = 4.3  # GB
 MIN_DISK_SPACE_NEEDED = 13  # GB
 
 DOCKER_COMPOSE_PROJECT_NAME = os.getenv("DATAHUB_COMPOSE_PROJECT_NAME", "datahub")

datahub/ingestion/api/auto_work_units/auto_ensure_aspect_size.py

@@ -1,5 +1,6 @@
 import json
 import logging
+import os
 from typing import TYPE_CHECKING, Iterable, List
 
 from datahub.emitter.rest_emitter import INGEST_MAX_PAYLOAD_BYTES
@@ -7,15 +8,36 @@ from datahub.emitter.serialization_helper import pre_json_transform
 from datahub.ingestion.api.workunit import MetadataWorkUnit
 from datahub.metadata.schema_classes import (
     DatasetProfileClass,
+    QueryPropertiesClass,
+    QuerySubjectsClass,
     SchemaFieldClass,
     SchemaMetadataClass,
+    UpstreamLineageClass,
 )
 
 if TYPE_CHECKING:
     from datahub.ingestion.api.source import SourceReport
 
+
+# TODO: ordering
+# In the cases where we trim collections of data (e.g. fields in schema, upstream lineage, query subjects), given
+# those collections are typically unordered, we should consider sorting them by some criteria (e.g. size, alphabetically)
+# so that the trimming is deterministic and predictable and more importantly consistent across executions.
+# In the case of schemaMetadata, that's more relevant as currently we may be trimming fields while adding nested ones,
+# which may lead to poorly schema rendering in the UI.
+
 logger = logging.getLogger(__name__)
 
+DEFAULT_QUERY_PROPERTIES_STATEMENT_MAX_PAYLOAD_BYTES = 5 * 1024 * 1024  # 5MB
+QUERY_PROPERTIES_STATEMENT_MAX_PAYLOAD_BYTES = int(
+    os.environ.get(
+        "QUERY_PROPERTIES_STATEMENT_MAX_PAYLOAD_BYTES",
+        DEFAULT_QUERY_PROPERTIES_STATEMENT_MAX_PAYLOAD_BYTES,
+    )
+)
+
+QUERY_STATEMENT_TRUNCATION_BUFFER = 100
+
 
 class EnsureAspectSizeProcessor:
     def __init__(
@@ -81,6 +103,274 @@ class EnsureAspectSizeProcessor:
 
         schema.fields = accepted_fields
 
+    def ensure_query_subjects_size(
+        self, entity_urn: str, query_subjects: QuerySubjectsClass
+    ) -> None:
+        """
+        Ensure query subjects aspect does not exceed allowed size by removing column-level lineage first,
+        then table lineage if necessary.
+        """
+        if not query_subjects.subjects:
+            return
+
+        total_subjects_size = 0
+        accepted_table_level_subjects = []
+        accepted_column_level_subjects = []
+        column_level_subjects_with_sizes = []
+        table_level_subjects_with_sizes = []
+
+        # Separate column-level and table-level subjects
+        for subject in query_subjects.subjects:
+            subject_size = len(json.dumps(pre_json_transform(subject.to_obj())))
+
+            if subject.entity.startswith("urn:li:schemaField:"):
+                column_level_subjects_with_sizes.append((subject, subject_size))
+            else:
+                table_level_subjects_with_sizes.append((subject, subject_size))
+
+        # Once we find one that doesn't fit, stop everything else to prevent inconsistencies
+        first_skip_done = False
+
+        # First, try to include all table-level subjects
+        for subject, subject_size in table_level_subjects_with_sizes:
+            if total_subjects_size + subject_size < self.payload_constraint:
+                accepted_table_level_subjects.append(subject)
+                total_subjects_size += subject_size
+            else:
+                first_skip_done = True
+                break
+
+        # Then, add column-level subjects if there's remaining space
+        # Only process if we successfully included all table-level subjects
+        if not first_skip_done:
+            for subject, subject_size in column_level_subjects_with_sizes:
+                if total_subjects_size + subject_size < self.payload_constraint:
+                    accepted_column_level_subjects.append(subject)
+                    total_subjects_size += subject_size
+                else:
+                    first_skip_done = True
+                    break
+
+        if first_skip_done:
+            # Log aggregate warnings
+            table_level_skipped_count = len(table_level_subjects_with_sizes) - len(
+                accepted_table_level_subjects
+            )
+            column_level_skipped_count = len(column_level_subjects_with_sizes) - len(
+                accepted_column_level_subjects
+            )
+
+            self._maybe_warn_query_subjects(
+                entity_urn, table_level_skipped_count, "table-level lineage subjects"
+            )
+            self._maybe_warn_query_subjects(
+                entity_urn, column_level_skipped_count, "column-level lineage subjects"
+            )
+
+        query_subjects.subjects = (
+            accepted_table_level_subjects + accepted_column_level_subjects
+        )
+
+    def _maybe_warn_query_subjects(
+        self, entity_urn: str, skipped_count: int, item_type: str
+    ) -> None:
+        """Log warning for query subjects truncation if any items were skipped."""
+        if skipped_count > 0:
+            self.report.warning(
+                title="Query subjects truncated due to size constraint",
+                message="Query subjects contained too much data and would have caused ingestion to fail",
+                context=f"Skipped {skipped_count} {item_type} for {entity_urn} due to aspect size constraints",
+            )
+
+    def _maybe_warn_upstream_lineage(
+        self, entity_urn: str, skipped_count: int, item_type: str
+    ) -> None:
+        """Log warning for upstream lineage truncation if any items were skipped."""
+        if skipped_count > 0:
+            self.report.warning(
+                title="Upstream lineage truncated due to size constraint",
+                message="Upstream lineage contained too much data and would have caused ingestion to fail",
+                context=f"Skipped {skipped_count} {item_type} for {entity_urn} due to aspect size constraints",
+            )
+
+    def ensure_upstream_lineage_size(  # noqa: C901
+        self, entity_urn: str, upstream_lineage: UpstreamLineageClass
+    ) -> None:
+        """
+        Ensure upstream lineage aspect does not exceed allowed size by removing lineage in priority order:
+        first NONE fine-grained lineages (lowest priority), then FIELD_SET fine-grained lineages,
+        then DATASET fine-grained lineages, and finally upstreams (highest priority).
+        """
+        if not upstream_lineage.fineGrainedLineages and not upstream_lineage.upstreams:
+            return
+
+        total_lineage_size = 0
+        accepted_upstreams = []
+        accepted_dataset_fg_lineages = []
+        accepted_field_set_fg_lineages = []
+        accepted_none_fg_lineages = []
+        upstream_items_with_sizes = []
+        dataset_fg_items_with_sizes = []
+        field_set_fg_items_with_sizes = []
+        none_fg_items_with_sizes = []
+
+        # Add upstreams (highest priority)
+        if upstream_lineage.upstreams:
+            for upstream in upstream_lineage.upstreams:
+                upstream_size = len(json.dumps(pre_json_transform(upstream.to_obj())))
+                upstream_items_with_sizes.append((upstream, upstream_size))
+
+        # Separate fine-grained lineage items by upstreamType: DATASET > FIELD_SET > NONE
+        if upstream_lineage.fineGrainedLineages:
+            for fg_lineage in upstream_lineage.fineGrainedLineages:
+                fg_lineage_size = len(
+                    json.dumps(pre_json_transform(fg_lineage.to_obj()))
+                )
+
+                upstream_type_str = str(fg_lineage.upstreamType)
+                if upstream_type_str == "DATASET":
+                    dataset_fg_items_with_sizes.append((fg_lineage, fg_lineage_size))
+                elif upstream_type_str == "FIELD_SET":
+                    field_set_fg_items_with_sizes.append((fg_lineage, fg_lineage_size))
+                elif upstream_type_str == "NONE":
+                    none_fg_items_with_sizes.append((fg_lineage, fg_lineage_size))
+
+        # Once we find one that doesn't fit, stop everything else to prevent inconsistencies
+        first_skip_done = False
+
+        # First, include all upstreams (highest priority)
+        for item, item_size in upstream_items_with_sizes:
+            if total_lineage_size + item_size < self.payload_constraint:
+                accepted_upstreams.append(item)
+                total_lineage_size += item_size
+            else:
+                first_skip_done = True
+                break
+
+        # Second, include DATASET fine-grained lineages if no upstreams were skipped
+        if not first_skip_done:
+            for fg_lineage, fg_lineage_size in dataset_fg_items_with_sizes:
+                if total_lineage_size + fg_lineage_size < self.payload_constraint:
+                    accepted_dataset_fg_lineages.append(fg_lineage)
+                    total_lineage_size += fg_lineage_size
+                else:
+                    first_skip_done = True
+                    break
+
+        # Third, include FIELD_SET fine-grained lineages if no higher priority items were skipped
+        if not first_skip_done:
+            for fg_lineage, fg_lineage_size in field_set_fg_items_with_sizes:
+                if total_lineage_size + fg_lineage_size < self.payload_constraint:
+                    accepted_field_set_fg_lineages.append(fg_lineage)
+                    total_lineage_size += fg_lineage_size
+                else:
+                    first_skip_done = True
+                    break
+
+        # Finally, include NONE fine-grained lineages if no higher priority items were skipped
+        if not first_skip_done:
+            for fg_lineage, fg_lineage_size in none_fg_items_with_sizes:
+                if total_lineage_size + fg_lineage_size < self.payload_constraint:
+                    accepted_none_fg_lineages.append(fg_lineage)
+                    total_lineage_size += fg_lineage_size
+                else:
+                    first_skip_done = True
+                    break
+
+        # Log aggregate warnings instead of per-item warnings
+        if first_skip_done:
+            upstreams_skipped_count = len(upstream_items_with_sizes) - len(
+                accepted_upstreams
+            )
+            dataset_fg_skipped_count = len(dataset_fg_items_with_sizes) - len(
+                accepted_dataset_fg_lineages
+            )
+            field_set_fg_skipped_count = len(field_set_fg_items_with_sizes) - len(
+                accepted_field_set_fg_lineages
+            )
+            none_fg_skipped_count = len(none_fg_items_with_sizes) - len(
+                accepted_none_fg_lineages
+            )
+
+            self._maybe_warn_upstream_lineage(
+                entity_urn, upstreams_skipped_count, "upstream datasets"
+            )
+            self._maybe_warn_upstream_lineage(
+                entity_urn,
+                dataset_fg_skipped_count,
+                "dataset-level fine-grained lineages",
+            )
+            self._maybe_warn_upstream_lineage(
+                entity_urn,
+                field_set_fg_skipped_count,
+                "field-set-level fine-grained lineages",
+            )
+            self._maybe_warn_upstream_lineage(
+                entity_urn, none_fg_skipped_count, "none-level fine-grained lineages"
+            )
+
+        # Combine all accepted fine-grained lineages
+        accepted_fine_grained_lineages = (
+            accepted_dataset_fg_lineages
+            + accepted_field_set_fg_lineages
+            + accepted_none_fg_lineages
+        )
+
+        upstream_lineage.upstreams = accepted_upstreams
+        upstream_lineage.fineGrainedLineages = (
+            accepted_fine_grained_lineages if accepted_fine_grained_lineages else None
+        )
+
+    def ensure_query_properties_size(
+        self, entity_urn: str, query_properties: QueryPropertiesClass
+    ) -> None:
+        """
+        Ensure query properties aspect does not exceed allowed size by truncating the query statement value.
+        Uses a configurable max payload size that is the minimum between QUERY_PROPERTIES_STATEMENT_MAX_PAYLOAD_BYTES
+        and INGEST_MAX_PAYLOAD_BYTES.
+
+        We have found surprisingly large query statements (e.g. 20MB+) that caused ingestion to fail;
+        that was INSERT INTO VALUES with huge list of values.
+        """
+        if not query_properties.statement or not query_properties.statement.value:
+            return
+
+        max_payload_size = min(
+            QUERY_PROPERTIES_STATEMENT_MAX_PAYLOAD_BYTES, self.payload_constraint
+        )
+
+        current_size = len(json.dumps(pre_json_transform(query_properties.to_obj())))
+
+        if current_size < max_payload_size:
+            return
+
+        reduction_needed = (
+            current_size - max_payload_size + QUERY_STATEMENT_TRUNCATION_BUFFER
+        )
+
+        statement_value_size = len(query_properties.statement.value)
+        original_statement_size = statement_value_size
+
+        # Only truncate if reduction is actually needed and possible
+        if statement_value_size > reduction_needed > 0:
+            new_statement_length = statement_value_size - reduction_needed
+            truncated_statement = query_properties.statement.value[
+                :new_statement_length
+            ]
+
+            truncation_message = f"... [original value was {original_statement_size} bytes and truncated to {new_statement_length} bytes]"
+            query_properties.statement.value = truncated_statement + truncation_message
+
+            self.report.warning(
+                title="Query properties truncated due to size constraint",
+                message="Query properties contained too much data and would have caused ingestion to fail",
+                context=f"Query statement was truncated from {original_statement_size} to {new_statement_length} characters for {entity_urn} due to aspect size constraints",
+            )
+        else:
+            logger.warning(
+                f"Cannot truncate query statement for {entity_urn} as it is smaller than or equal to the required reduction size {reduction_needed}. That means that 'ensure_query_properties_size' must be extended to trim other fields different than statement."
+            )
+
     def ensure_aspect_size(
         self,
         stream: Iterable[MetadataWorkUnit],
@@ -96,4 +386,10 @@ class EnsureAspectSizeProcessor:
                 self.ensure_schema_metadata_size(wu.get_urn(), schema)
             elif profile := wu.get_aspect_of_type(DatasetProfileClass):
                 self.ensure_dataset_profile_size(wu.get_urn(), profile)
+            elif query_subjects := wu.get_aspect_of_type(QuerySubjectsClass):
+                self.ensure_query_subjects_size(wu.get_urn(), query_subjects)
+            elif upstream_lineage := wu.get_aspect_of_type(UpstreamLineageClass):
+                self.ensure_upstream_lineage_size(wu.get_urn(), upstream_lineage)
+            elif query_properties := wu.get_aspect_of_type(QueryPropertiesClass):
+                self.ensure_query_properties_size(wu.get_urn(), query_properties)
             yield wu