acryl-datahub 1.2.0.2rc3__py3-none-any.whl → 1.2.0.3__py3-none-any.whl

{acryl_datahub-1.2.0.2rc3.dist-info → acryl_datahub-1.2.0.3.dist-info}/RECORD

@@ -1,7 +1,7 @@
-acryl_datahub-1.2.0.2rc3.dist-info/licenses/LICENSE,sha256=9xNHpsD0uYF5ONzXsKDCuHHB-xbiCrSbueWXqrTNsxk,11365
+acryl_datahub-1.2.0.3.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=cyLeAlWzIql-O65xt-MALgl-0jJ-qmzJ-gFq-t6FkdE,323
+datahub/_version.py,sha256=3vbyl4pDs10qjxTeqdbfjmpJqYoyU66BOXzc2ni_rKU,320
 datahub/entrypoints.py,sha256=9Qf-37rNnTzbGlx8S75OCDazIclFp6zWNcCEL1zCZto,9015
 datahub/errors.py,sha256=p5rFAdAGVCk4Lqolol1YvthceadUSwpaCxLXRcyCCFQ,676
 datahub/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -132,7 +132,7 @@ datahub/emitter/mcp_builder.py,sha256=8IwJAlolQkPpMqQJPLtGrsUqAcuFNs98nrI5iYUxga
 datahub/emitter/mcp_patch_builder.py,sha256=u7cpW6DkiN7KpLapmMaXgL_FneoN69boxiANbVgMdSI,4564
 datahub/emitter/request_helper.py,sha256=2Sij9VJqgA7xZI6I7IuxsA8ioakbz0FJ3gvazxU_z3M,5738
 datahub/emitter/response_helper.py,sha256=qGm45n43CepW7j6kP9wTXuP-U-SZnn7hQdJTdVaoqhQ,7504
-datahub/emitter/rest_emitter.py,sha256=lMqjtDyPOArIrNgL47kq1cbB4xiR17CHfRRxpGYriDY,38793
+datahub/emitter/rest_emitter.py,sha256=za2b8C0f8Mpo8E7DVh3jNENYlNMTV0nwdC3FLm8n2DQ,39532
 datahub/emitter/serialization_helper.py,sha256=q12Avmf70Vy4ttQGMJoTKlE5EsybMKNg2w3MQeZiHvk,3652
 datahub/emitter/sql_parsing_builder.py,sha256=Cr5imZrm3dYDSCACt5MFscgHCtVbHTD6IjUmsvsKoEs,11991
 datahub/emitter/synchronized_file_emitter.py,sha256=s4ATuxalI4GDAkrZTaGSegxBdvvNPZ9jRSdtElU0kNs,1805
@@ -181,7 +181,7 @@ datahub/ingestion/glossary/classifier.py,sha256=daLxnVv_JlfB_jBOxH5LrU_xQRndrsGo
 datahub/ingestion/glossary/classifier_registry.py,sha256=yFOYLQhDgCLqXYMG3L1BquXafeLcZDcmp8meyw6k9ts,307
 datahub/ingestion/glossary/datahub_classifier.py,sha256=O7wm6gQT1Jf2QSKdWjJQbS5oSzJwplXzfza26Gdq5Mg,7555
 datahub/ingestion/graph/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-datahub/ingestion/graph/client.py,sha256=b23UCgszAFcW_UjNBEvY5c3oqMNGifz2445vl2IkKyo,74224
+datahub/ingestion/graph/client.py,sha256=xUURT6KxwOhwuAbUznxrOzmGuXxHI-3MmDgJQHFpaGk,74671
 datahub/ingestion/graph/config.py,sha256=rmkcqAL8fJoY9QyAeS0Xm8HvwHzV3pCjY-Om-50JJTI,1015
 datahub/ingestion/graph/connections.py,sha256=9462L0ZWGKURyypAln25eMPhK3pcufBar9tNDoqspXs,741
 datahub/ingestion/graph/entity_versioning.py,sha256=nrcNz0Qm6kpE6oTu_mrYUQDx14KPspBTc6R9SyFUY6c,6901
@@ -201,7 +201,7 @@ datahub/ingestion/sink/blackhole.py,sha256=-jYcWo4i8q7312bCIoHrGr7nT9JdPvA7c4jvS
 datahub/ingestion/sink/console.py,sha256=TZfhA0Ec2eNCrMH7RRy2JOdUE-U-hkoIQrPm1CmKLQs,591
 datahub/ingestion/sink/datahub_kafka.py,sha256=_cjuXu5I6G0zJ2UK7hMbaKjMPZXeIwRMgm7CVeTiNtc,2578
 datahub/ingestion/sink/datahub_lite.py,sha256=7u2aWm7ENLshKHl-PkjJg6Mrw4bWs8sTfKIBz4mm8Ak,1879
-datahub/ingestion/sink/datahub_rest.py,sha256=DOhtTHqKpmqgI3rUY9ri2QZAyXYDFINWMG6ne7VYUXI,13463
+datahub/ingestion/sink/datahub_rest.py,sha256=QrtR-hJ6yljN1quXcjoUHdAmJueZclrFZFrhU7c4YJM,13563
 datahub/ingestion/sink/file.py,sha256=SxXJPJpkIGoaqRjCcSmj2ZE3xE4rLlBABBGwpTj5LWI,3271
 datahub/ingestion/sink/sink_registry.py,sha256=JRBWx8qEYg0ubSTyhqwgSWctgxwyp6fva9GoN2LwBao,490
 datahub/ingestion/source/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -227,7 +227,7 @@ datahub/ingestion/source/pulsar.py,sha256=u5F8QnCLJsht5-7XCiUTsnfhCPIpKVB_l32CgM
 datahub/ingestion/source/redash.py,sha256=YxjSad-X_wPmxYH8dJmFz_VCFhiLTCTSlK99WdvcYiA,30653
 datahub/ingestion/source/salesforce.py,sha256=Pa_w1XszxFd8fyhpSWOfc2nOnevHwwstIvnRrQT4R9M,40584
 datahub/ingestion/source/source_registry.py,sha256=a2mLjJPLkSI-gYCTb_7U7Jo4D8jGknNQ_yScPIihXFk,1208
-datahub/ingestion/source/sql_queries.py,sha256=1SdEZGAmojfWbU1xKbezH6uqwRd2G0rgpK_Sh9MRj1U,11791
+datahub/ingestion/source/sql_queries.py,sha256=9ICUC6tpXpxvtwfK-9lytJzFcLe8MrNlciwy9DIFM-4,13764
 datahub/ingestion/source/superset.py,sha256=oi7F2jlvkVr9ItJ_r1Jm4bYfXHYu4vPAFPMPaGJKB84,50608
 datahub/ingestion/source/abs/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 datahub/ingestion/source/abs/config.py,sha256=mBQe0JTaP-Rcv4HnMUUySoYbSr4r3jDEMioxaXHnxXU,6709
@@ -301,7 +301,7 @@ datahub/ingestion/source/datahub/report.py,sha256=VHBfCbwFRzdLdB7hQG9ST4EiZxl_vB
 datahub/ingestion/source/datahub/state.py,sha256=PZoT7sSK1wadVf5vN6phrgr7I6LL7ePP-EJjP1OO0bQ,3507
 datahub/ingestion/source/dbt/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 datahub/ingestion/source/dbt/dbt_cloud.py,sha256=4gWOFSX0YU8EAJgO4J47NBE4QbNtJ-5nUe66vry-oGc,18160
-datahub/ingestion/source/dbt/dbt_common.py,sha256=ByCqzjkToXgfhOyxxc6VEuD8BZbYbPsD5yrLRMMPUcI,85640
+datahub/ingestion/source/dbt/dbt_common.py,sha256=3NcCYsJSDfC5j7ajC_Mr3MnA_sF9DTq1ka6ft3b0u6A,85997
 datahub/ingestion/source/dbt/dbt_core.py,sha256=WVI2ZYXOMxgFzJnJqsqmEGS-5xdfiVIDsCb78lvSeQ0,24930
 datahub/ingestion/source/dbt/dbt_tests.py,sha256=pOZJaP4VsbaE5j4qVlE_E3ifno_KQpidfGTvOi5fr6I,9839
 datahub/ingestion/source/debug/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -356,7 +356,7 @@ datahub/ingestion/source/hex/constants.py,sha256=8hUTMWyG5keTNfXoLu_Dh413Hw_mGGJ
 datahub/ingestion/source/hex/hex.py,sha256=tUYNcvwKVoQuRWv4KhcDnMeOpICh4JwhD8oF988Tjg4,13199
 datahub/ingestion/source/hex/mapper.py,sha256=N3mTlEcrOmhv9ia1dnHGFgFJD2ddyTtU3H5IUbb-UxU,13344
 datahub/ingestion/source/hex/model.py,sha256=S9bUhfFcjzuio2dBS6HzSyRVPiSJvRvMQ0qyVrjV5-E,1766
-datahub/ingestion/source/hex/query_fetcher.py,sha256=0VqDfviyfR14gUHvIBovCXEqwW4ftFehPSB2VzaYk14,13312
+datahub/ingestion/source/hex/query_fetcher.py,sha256=r9UvF_qwswkRlNY7AI8p46eqAYSxVtjVE2e7eO4XagA,13384
 datahub/ingestion/source/iceberg/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 datahub/ingestion/source/iceberg/iceberg.py,sha256=BNDGooK9cmqpOjzkV1u4rpsduVPNWg_97Uca6aLurNU,35431
 datahub/ingestion/source/iceberg/iceberg_common.py,sha256=CD_yHQ_wEgivyLQUTRO9BZJB29S7j5fUVllki-BPwUU,12292
@@ -499,7 +499,7 @@ datahub/ingestion/source/snowflake/snowflake_v2.py,sha256=asZW8DztIB1TcGzOoZFmK6
 datahub/ingestion/source/snowflake/stored_proc_lineage.py,sha256=rOb78iHiWiK8v8WdVs1xDwVut4Y0OHmszej6IopQfCo,5341
 datahub/ingestion/source/sql/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 datahub/ingestion/source/sql/athena.py,sha256=TPKwL9oRiZlVnqIsOSBWUEwyvoW-1ssXvY4PfjxOR6g,28175
-datahub/ingestion/source/sql/athena_properties_extractor.py,sha256=n2SvqeUbNWxiWWdkDs8VYlUPlLwfZzZy9AIa-V4D7AY,28531
+datahub/ingestion/source/sql/athena_properties_extractor.py,sha256=OS2E2HD7xTn0MBy__pIvjKXMfGp02Zf93hQRAPMXE_Y,28533
 datahub/ingestion/source/sql/clickhouse.py,sha256=zd5qE6XPw0AXtY_71-n0yz4ua69xP3oxMuIoabAuT3Q,25987
 datahub/ingestion/source/sql/cockroachdb.py,sha256=WoOKCq7YjsuzSPm1SmKIYZ9CrvlSF8zWmP1fNHn4G3Q,1360
 datahub/ingestion/source/sql/druid.py,sha256=_tzgTa5jhPUXk6WCmS7p10feCwJm6yUFcOgMZA-OcE8,2922
@@ -524,7 +524,7 @@ datahub/ingestion/source/sql/sqlalchemy_uri_mapper.py,sha256=KOpbmDIE2h1hyYEsbVH
 datahub/ingestion/source/sql/teradata.py,sha256=xL_c_UEM_JT-xoMw5Nb5UvSNBUfTGol5CpOkgK5Bsjk,65412
 datahub/ingestion/source/sql/trino.py,sha256=zIfQ6GvW8Sbw4sxqsTcnibT51STka_nzNYvmld6HfHw,18947
 datahub/ingestion/source/sql/two_tier_sql_source.py,sha256=AB3Gtx4omAy_08zadHQpmUGmIGufkZ6o_ihWNnfvzYc,5783
-datahub/ingestion/source/sql/vertica.py,sha256=MeohL8j68ISES1RhrBXLQlkT_YqgT-AvHRxuVCJSMbE,33458
+datahub/ingestion/source/sql/vertica.py,sha256=blnu1-H7vnSQD3ZD5QTotoQ2DQJWJeR0uxz_clxiPGo,33518
 datahub/ingestion/source/sql/mssql/__init__.py,sha256=1agpl8S_uDW40olkhCX_W19dbr5GO9qgjS3R7pLRZSk,87
 datahub/ingestion/source/sql/mssql/job_models.py,sha256=nAo3rciu-w2-dXCz6_ekDEbGMEjCMEfh8WvSfXoF2l0,9359
 datahub/ingestion/source/sql/mssql/source.py,sha256=Uise_u6yXKU__9B_U3D3yObWNIVDzrz2AgEDZOlk6bQ,43101
@@ -558,11 +558,11 @@ datahub/ingestion/source/unity/config.py,sha256=7QosoBthg9kirHfXev_vhefkobUxYnp1
 datahub/ingestion/source/unity/connection_test.py,sha256=B143Wb28fS0V4GhygU9hzKqiArWBjsQO54IUCPf23dc,2586
 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
-datahub/ingestion/source/unity/proxy.py,sha256=jfQ1N8Xrp08zeYN2j74YTweusygXtK4Q-5_FBbwCVTE,22803
+datahub/ingestion/source/unity/proxy.py,sha256=iZ2ftKOXkxpFr0_2bEYEm31ci9OZJWFYgna3DNLCXrQ,26706
 datahub/ingestion/source/unity/proxy_profiling.py,sha256=WLqvYP6MziaisA4LYL4T_GA-kPt6Xdde7bfaYsjYw40,9663
 datahub/ingestion/source/unity/proxy_types.py,sha256=qrvHiwPzl5cPX-KRvcIGGeJVdr0I8XUQmoAI6ErZ-v8,9371
 datahub/ingestion/source/unity/report.py,sha256=XFT9oQfvEB4RkTvWGgFOoQuLPUN_AIoPXZ79xeDhGHQ,2831
-datahub/ingestion/source/unity/source.py,sha256=47sWCYb3pd21RjIqs9NH4h6VMtF_YMvqS9-6cegGi1w,49980
+datahub/ingestion/source/unity/source.py,sha256=udK1_WI7RO2Uzx9xis0mx264nHXDiMeP4Kah3-CFXis,49832
 datahub/ingestion/source/unity/tag_entities.py,sha256=iWl6nRAWSye1hoFDx_Xh4aT53PN0sGzlX7n1-oTVUv8,11568
 datahub/ingestion/source/unity/usage.py,sha256=0wETBAaZvHI_EGgBlxX3bKsVHEAdnUV8_bKI_lbyWjY,11500
 datahub/ingestion/source/usage/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -627,7 +627,7 @@ datahub/lite/lite_server.py,sha256=p9Oa2nNs65mqcssSIVOr7VOzWqfVstz6ZQEdT4f82S0,1
 datahub/lite/lite_util.py,sha256=G0LQHKkyEb1pc_q183g6hflShclGx7kikgMaOxtVVcs,4545
 datahub/metadata/__init__.py,sha256=AjhXPjI6cnpdcrBRrE5gOWo15vv2TTl2ctU4UAnUN7A,238
 datahub/metadata/_internal_schema_classes.py,sha256=Zh2volhvkUCENRavXDwPsmwfRe62k8_O6f5QT8_bh-g,1051205
-datahub/metadata/schema.avsc,sha256=4X6Jx5TFcOGY8Qxdm-FSgbGkzG2wND992brsxwgumSU,737966
+datahub/metadata/schema.avsc,sha256=u5iUlz9AnFfJijjJ9xcZx3MoiBfxWSmhr7pZIOg0tMo,738363
 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
@@ -781,7 +781,7 @@ datahub/metadata/schemas/DataHubUpgradeResult.avsc,sha256=VydVb4yqjIviR73-T6TooF
 datahub/metadata/schemas/DataHubViewInfo.avsc,sha256=U3fBIoG9ietLUpOknfQGNekqBdPQYwvhhv9RQv6gEeg,11642
 datahub/metadata/schemas/DataHubViewKey.avsc,sha256=p53axIdSVbubo3r23Vpsed7NqRcQBMGveVikEHAVAok,424
 datahub/metadata/schemas/DataJobInfo.avsc,sha256=Bc9qdDcXI0GQdEgNTpgHaBbnrppDKQ-1xR26diOSVIQ,7488
-datahub/metadata/schemas/DataJobInputOutput.avsc,sha256=H1O8eAzZV34tvULdu67iBSWkdn08rt7wS208b8Nisbk,15268
+datahub/metadata/schemas/DataJobInputOutput.avsc,sha256=BYKImZ8kQQHqWbSBMKXWD0tGi96yzUt8zJFW3_twVVM,15575
 datahub/metadata/schemas/DataJobKey.avsc,sha256=S7egH8jWjKW52MG6Pg7plDoP15XfTTiMde5V6nR6ycE,1624
 datahub/metadata/schemas/DataPlatformInfo.avsc,sha256=WGPFumBNHbR75vsLrivnRCbBc8vSCuxDw2UlylMieh4,2686
 datahub/metadata/schemas/DataPlatformInstance.avsc,sha256=SNd3v_YyyLaDflv8Rd5cQR9GrVuky_cDTkYM6FqJiM8,1058
@@ -884,7 +884,7 @@ datahub/metadata/schemas/MLModelProperties.avsc,sha256=hDCBHxGe-cmCBeU1k0ANuQlKj
 datahub/metadata/schemas/MLPrimaryKeyKey.avsc,sha256=F3lgpMnHBhXsqGncHE9x06P-0RiNCrzbUUWlMkPJxFI,1132
 datahub/metadata/schemas/MLPrimaryKeyProperties.avsc,sha256=URIuOpS93RVk8MZVcbZ-dmTwu_cN3KSOKxSR8fm-eTo,6744
 datahub/metadata/schemas/MLTrainingRunProperties.avsc,sha256=WGgj0MuQrGD4UgvyHCJHzTnHja2LlJTOr1gLu8SySj0,4269
-datahub/metadata/schemas/MetadataChangeEvent.avsc,sha256=l3tVuQces7sKrwWsaIJrn3nMRUiCl3MHqCJJHcw7Ylc,377705
+datahub/metadata/schemas/MetadataChangeEvent.avsc,sha256=oNK0N8WrBsM_AoZkdYAMJQlhYzbao_QWaAMOjqEvPBw,378228
 datahub/metadata/schemas/MetadataChangeLog.avsc,sha256=soCmgrcEBE5yS-mQIm-RIefhb74ONj9Fqayxa0-59KE,13254
 datahub/metadata/schemas/MetadataChangeProposal.avsc,sha256=pT14vUmpj7VJ8hinQ0pcCUtRKx6RAGHWh1eJixkqaE8,12647
 datahub/metadata/schemas/Metrics.avsc,sha256=O7DJGjOwmHbb1x_Zj7AuM_HaHKjBvkfJKfUsX8icXD4,690
@@ -933,7 +933,7 @@ datahub/metadata/schemas/TestInfo.avsc,sha256=rye90gdY_lxZt_1gpa_Xum923CJgDU6i_e
 datahub/metadata/schemas/TestKey.avsc,sha256=eL-S4Z8EuN1JEXV1t4fy3LwmdA2dJURasFcKygP2rLY,421
 datahub/metadata/schemas/TestResults.avsc,sha256=uspC95AzRvz2_AgHVb5-fxELm5u8NmBTaFVJvGunmh0,5178
 datahub/metadata/schemas/TrainingData.avsc,sha256=7p7sFBA_UyV5IbNU5qLgS3vVu70yevKCfJKSGmTzVTg,2069
-datahub/metadata/schemas/UpstreamLineage.avsc,sha256=iaeFRbL2aVSYFwj-HQHyfIVaHRrK3kLbkkLXgIfJTsk,10639
+datahub/metadata/schemas/UpstreamLineage.avsc,sha256=dtpI7KUv9kYyGZmIlKfR2zLwgqsHO5P20egvIeup1EU,11000
 datahub/metadata/schemas/UsageAggregation.avsc,sha256=QaF6lyWGUq8IlRel2h4qIXOXCMxBhrwjoaUELsd-I6g,4538
 datahub/metadata/schemas/VersionInfo.avsc,sha256=9gMcZ8tjuhgcZiq2gOAp_EOV9q9jvuOgfph6m6v_X7c,1189
 datahub/metadata/schemas/VersionProperties.avsc,sha256=ME8V01JzG8lEsLXgYWnSYCehmpPcvv1UbE5Y8-8Ys9k,8022
@@ -1101,8 +1101,8 @@ 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-1.2.0.2rc3.dist-info/METADATA,sha256=ixYC_JxEXERi_Ik-6tXxNn5W0EMN_poTxliZ99bCS6o,182014
-acryl_datahub-1.2.0.2rc3.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-acryl_datahub-1.2.0.2rc3.dist-info/entry_points.txt,sha256=bnGf6eX9UhiW8yVHtt6MJCVcmLErvrVQxTJAayA-PKc,9885
-acryl_datahub-1.2.0.2rc3.dist-info/top_level.txt,sha256=iLjSrLK5ox1YVYcglRUkcvfZPvKlobBWx7CTUXx8_GI,25
-acryl_datahub-1.2.0.2rc3.dist-info/RECORD,,
+acryl_datahub-1.2.0.3.dist-info/METADATA,sha256=_FyY3RlWzBgv9L5qGdq8iSnRgFNIWwv9QdcQbMW-BEY,182005
+acryl_datahub-1.2.0.3.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+acryl_datahub-1.2.0.3.dist-info/entry_points.txt,sha256=bnGf6eX9UhiW8yVHtt6MJCVcmLErvrVQxTJAayA-PKc,9885
+acryl_datahub-1.2.0.3.dist-info/top_level.txt,sha256=iLjSrLK5ox1YVYcglRUkcvfZPvKlobBWx7CTUXx8_GI,25
+acryl_datahub-1.2.0.3.dist-info/RECORD,,

datahub/_version.py

@@ -1,6 +1,6 @@
 # Published at https://pypi.org/project/acryl-datahub/.
 __package_name__ = "acryl-datahub"
-__version__ = "1.2.0.2rc3"
+__version__ = "1.2.0.3"
 
 
 def is_dev_mode() -> bool:

datahub/emitter/rest_emitter.py

@@ -95,7 +95,7 @@ TRACE_INITIAL_BACKOFF = 1.0  # Start with 1 second
 TRACE_MAX_BACKOFF = 300.0  # Cap at 5 minutes
 TRACE_BACKOFF_FACTOR = 2.0  # Double the wait time each attempt
 
-# The limit is 16mb. We will use a max of 15mb to have some space
+# The limit is 16,000,000 bytes. We will use a max of 15mb to have some space
 # for overhead like request headers.
 # This applies to pretty much all calls to GMS.
 INGEST_MAX_PAYLOAD_BYTES = int(
@@ -586,6 +586,11 @@ class DataHubRestEmitter(Closeable, Emitter):
             "systemMetadata": system_metadata_obj,
         }
         payload = json.dumps(snapshot)
+        if len(payload) > INGEST_MAX_PAYLOAD_BYTES:
+            logger.warning(
+                f"MCE object has size {len(payload)} that exceeds the max payload size of {INGEST_MAX_PAYLOAD_BYTES}, "
+                "so this metadata will likely fail to be emitted."
+            )
 
         self._emit_generic(url, payload)
 
@@ -764,16 +769,24 @@ class DataHubRestEmitter(Closeable, Emitter):
         url = f"{self._gms_server}/aspects?action=ingestProposalBatch"
 
         mcp_objs = [pre_json_transform(mcp.to_obj()) for mcp in mcps]
+        if len(mcp_objs) == 0:
+            return 0
 
         # As a safety mechanism, we need to make sure we don't exceed the max payload size for GMS.
         # If we will exceed the limit, we need to break it up into chunks.
-        mcp_obj_chunks: List[List[str]] = []
-        current_chunk_size = INGEST_MAX_PAYLOAD_BYTES
+        mcp_obj_chunks: List[List[str]] = [[]]
+        current_chunk_size = 0
         for mcp_obj in mcp_objs:
+            mcp_identifier = f"{mcp_obj.get('entityUrn')}-{mcp_obj.get('aspectName')}"
             mcp_obj_size = len(json.dumps(mcp_obj))
             if _DATAHUB_EMITTER_TRACE:
                 logger.debug(
-                    f"Iterating through object with size {mcp_obj_size} (type: {mcp_obj.get('aspectName')}"
+                    f"Iterating through object ({mcp_identifier}) with size {mcp_obj_size}"
+                )
+            if mcp_obj_size > INGEST_MAX_PAYLOAD_BYTES:
+                logger.warning(
+                    f"MCP object {mcp_identifier} has size {mcp_obj_size} that exceeds the max payload size of {INGEST_MAX_PAYLOAD_BYTES}, "
+                    "so this metadata will likely fail to be emitted."
                 )
 
             if (
@@ -786,7 +799,7 @@ class DataHubRestEmitter(Closeable, Emitter):
                 current_chunk_size = 0
             mcp_obj_chunks[-1].append(mcp_obj)
             current_chunk_size += mcp_obj_size
-        if len(mcp_obj_chunks) > 0:
+        if len(mcp_obj_chunks) > 1 or _DATAHUB_EMITTER_TRACE:
             logger.debug(
                 f"Decided to send {len(mcps)} MCP batch in {len(mcp_obj_chunks)} chunks"
             )

datahub/ingestion/graph/client.py

@@ -76,7 +76,15 @@ from datahub.metadata.schema_classes import (
     SystemMetadataClass,
     TelemetryClientIdClass,
 )
-from datahub.metadata.urns import CorpUserUrn, Urn
+from datahub.metadata.urns import (
+    CorpUserUrn,
+    MlFeatureTableUrn,
+    MlFeatureUrn,
+    MlModelGroupUrn,
+    MlModelUrn,
+    MlPrimaryKeyUrn,
+    Urn,
+)
 from datahub.telemetry.telemetry import telemetry_instance
 from datahub.utilities.perf_timer import PerfTimer
 from datahub.utilities.str_enum import StrEnum
@@ -118,8 +126,16 @@ def entity_type_to_graphql(entity_type: str) -> str:
     """Convert the entity types into GraphQL "EntityType" enum values."""
 
     # Hard-coded special cases.
-    if entity_type == CorpUserUrn.ENTITY_TYPE:
-        return "CORP_USER"
+    special_cases = {
+        CorpUserUrn.ENTITY_TYPE: "CORP_USER",
+        MlModelUrn.ENTITY_TYPE: "MLMODEL",
+        MlModelGroupUrn.ENTITY_TYPE: "MLMODEL_GROUP",
+        MlFeatureTableUrn.ENTITY_TYPE: "MLFEATURE_TABLE",
+        MlFeatureUrn.ENTITY_TYPE: "MLFEATURE",
+        MlPrimaryKeyUrn.ENTITY_TYPE: "MLPRIMARY_KEY",
+    }
+    if entity_type in special_cases:
+        return special_cases[entity_type]
 
     # Convert camelCase to UPPER_UNDERSCORE.
     entity_type = (

datahub/ingestion/sink/datahub_rest.py

@@ -92,6 +92,7 @@ class DatahubRestSinkConfig(DatahubClientConfig):
 @dataclasses.dataclass
 class DataHubRestSinkReport(SinkReport):
     mode: Optional[RestSinkMode] = None
+    endpoint: Optional[RestSinkEndpoint] = None
     max_threads: Optional[int] = None
     gms_version: Optional[str] = None
     pending_requests: int = 0
@@ -142,6 +143,7 @@ class DatahubRestSink(Sink[DatahubRestSinkConfig, DataHubRestSinkReport]):
 
         self.report.gms_version = gms_config.service_version
         self.report.mode = self.config.mode
+        self.report.endpoint = self.config.endpoint
         self.report.max_threads = self.config.max_threads
         logger.debug("Setting env variables to override config")
         logger.debug("Setting gms config")

datahub/ingestion/source/dbt/dbt_common.py

@@ -120,6 +120,7 @@ logger = logging.getLogger(__name__)
 DBT_PLATFORM = "dbt"
 
 _DEFAULT_ACTOR = mce_builder.make_user_urn("unknown")
+_DBT_MAX_COMPILED_CODE_LENGTH = 1 * 1024 * 1024  # 1MB
 
 
 @dataclass
@@ -1684,6 +1685,12 @@ class DBTSourceBase(StatefulIngestionSourceBase):
     def get_external_url(self, node: DBTNode) -> Optional[str]:
         pass
 
+    @staticmethod
+    def _truncate_code(code: str, max_length: int) -> str:
+        if len(code) > max_length:
+            return code[:max_length] + "..."
+        return code
+
     def _create_view_properties_aspect(
         self, node: DBTNode
     ) -> Optional[ViewPropertiesClass]:
@@ -1695,6 +1702,9 @@ class DBTSourceBase(StatefulIngestionSourceBase):
             compiled_code = try_format_query(
                 node.compiled_code, platform=self.config.target_platform
             )
+            compiled_code = self._truncate_code(
+                compiled_code, _DBT_MAX_COMPILED_CODE_LENGTH
+            )
 
         materialized = node.materialization in {"table", "incremental", "snapshot"}
         view_properties = ViewPropertiesClass(

datahub/ingestion/source/hex/query_fetcher.py

@@ -97,7 +97,7 @@ class HexQueryFetcher:
             if not query_urns or not entities_by_urn:
                 self.report.warning(
                     title="No Queries found with Hex as origin",
-                    message="No lineage because of no Queries found with Hex as origin in the given time range; you may consider extending the time range to fetch more queries.",
+                    message="No lineage because of no Queries found with Hex as origin in the given time range. You may need to set use_queries_v2: true on your warehouse ingestion or you may consider extending the time range to fetch more queries.",
                     context=str(
                         dict(
                             workspace_name=self.workspace_name,

datahub/ingestion/source/sql/athena_properties_extractor.py

@@ -99,10 +99,10 @@ class AthenaPropertiesExtractor:
     """A class to extract properties from Athena CREATE TABLE statements."""
 
     CREATE_TABLE_REGEXP = re.compile(
-        "(CREATE TABLE[\s\n]*)(.*?)(\s*\()", re.MULTILINE | re.IGNORECASE
+        r"(CREATE TABLE[\s\n]*)(.*?)(\s*\()", re.MULTILINE | re.IGNORECASE
     )
     PARTITIONED_BY_REGEXP = re.compile(
-        "(PARTITIONED BY[\s\n]*\()((?:[^()]|\([^)]*\))*?)(\))",
+        r"(PARTITIONED BY[\s\n]*\()((?:[^()]|\([^)]*\))*?)(\))",
         re.MULTILINE | re.IGNORECASE,
     )
 

datahub/ingestion/source/sql/vertica.py

@@ -4,6 +4,7 @@ from dataclasses import dataclass
 from typing import TYPE_CHECKING, Any, Dict, Iterable, List, Optional, Set, Tuple, Union
 
 import pydantic
+import pytest
 from pydantic.class_validators import validator
 from vertica_sqlalchemy_dialect.base import VerticaInspector
 
@@ -55,6 +56,8 @@ from datahub.utilities import config_clean
 
 if TYPE_CHECKING:
     from datahub.ingestion.source.ge_data_profiler import GEProfilerRequest
+
+pytestmark = pytest.mark.integration_batch_4
 logger: logging.Logger = logging.getLogger(__name__)
 
 

datahub/ingestion/source/sql_queries.py

@@ -2,12 +2,13 @@ import json
 import logging
 import os
 from dataclasses import dataclass
-from datetime import datetime, timezone
+from datetime import datetime
 from functools import partial
-from typing import Iterable, List, Optional, Union
+from typing import ClassVar, Iterable, List, Optional, Union
 
-from pydantic import Field
+from pydantic import BaseModel, Field, validator
 
+from datahub.configuration.datetimes import parse_user_datetime
 from datahub.configuration.source_common import (
     EnvConfigMixin,
     PlatformInstanceConfigMixin,
@@ -35,7 +36,7 @@ from datahub.ingestion.api.workunit import MetadataWorkUnit
 from datahub.ingestion.graph.client import DataHubGraph
 from datahub.ingestion.source.usage.usage_common import BaseUsageConfig
 from datahub.ingestion.source_report.ingestion_stage import IngestionStageReport
-from datahub.metadata.urns import CorpUserUrn
+from datahub.metadata.urns import CorpUserUrn, DatasetUrn
 from datahub.sql_parsing.schema_resolver import SchemaResolver
 from datahub.sql_parsing.sql_parsing_aggregator import (
     KnownQueryLineageInfo,
@@ -208,19 +209,40 @@ class SqlQueriesSource(Source):
     def _add_query_to_aggregator(self, query_entry: "QueryEntry") -> None:
         """Add a query to the SQL parsing aggregator."""
         try:
-            # If we have explicit lineage, use it directly
-            if query_entry.upstream_tables or query_entry.downstream_tables:
+            # If we have both upstream and downstream tables, use explicit lineage
+            if query_entry.upstream_tables and query_entry.downstream_tables:
                 logger.debug("Using explicit lineage from query file")
                 for downstream_table in query_entry.downstream_tables:
                     known_lineage = KnownQueryLineageInfo(
                         query_text=query_entry.query,
-                        downstream=downstream_table,
-                        upstreams=query_entry.upstream_tables,
+                        downstream=str(downstream_table),
+                        upstreams=[str(urn) for urn in query_entry.upstream_tables],
                         timestamp=query_entry.timestamp,
                         session_id=query_entry.session_id,
                     )
                     self.aggregator.add_known_query_lineage(known_lineage)
             else:
+                # Warn if only partial lineage information is provided
+                # XOR: true if exactly one of upstream_tables or downstream_tables is provided
+                if bool(query_entry.upstream_tables) ^ bool(
+                    query_entry.downstream_tables
+                ):
+                    query_preview = (
+                        query_entry.query[:150] + "..."
+                        if len(query_entry.query) > 150
+                        else query_entry.query
+                    )
+                    missing_upstream = (
+                        "Missing upstream. " if not query_entry.upstream_tables else ""
+                    )
+                    missing_downstream = (
+                        "Missing downstream. "
+                        if not query_entry.downstream_tables
+                        else ""
+                    )
+                    logger.info(
+                        f"Only partial lineage information provided, falling back to SQL parsing for complete lineage detection. {missing_upstream}{missing_downstream}Query: {query_preview}"
+                    )
                 # No explicit lineage, rely on parsing
                 observed_query = ObservedQuery(
                     query=query_entry.query,
@@ -243,46 +265,66 @@ class SqlQueriesSource(Source):
             )
 
 
-@dataclass
-class QueryEntry:
+class QueryEntry(BaseModel):
     query: str
-    timestamp: Optional[datetime]
-    user: Optional[CorpUserUrn]
-    operation_type: Optional[str]
-    downstream_tables: List[str]
-    upstream_tables: List[str]
+    timestamp: Optional[datetime] = None
+    user: Optional[CorpUserUrn] = None
+    operation_type: Optional[str] = None
+    downstream_tables: List[DatasetUrn] = Field(default_factory=list)
+    upstream_tables: List[DatasetUrn] = Field(default_factory=list)
     session_id: Optional[str] = None
 
+    # Validation context for URN creation
+    _validation_context: ClassVar[Optional[SqlQueriesSourceConfig]] = None
+
+    class Config:
+        arbitrary_types_allowed = True
+
+    @validator("timestamp", pre=True)
+    def parse_timestamp(cls, v):
+        return None if v is None else parse_user_datetime(str(v))
+
+    @validator("user", pre=True)
+    def parse_user(cls, v):
+        if v is None:
+            return None
+
+        return v if isinstance(v, CorpUserUrn) else CorpUserUrn(v)
+
+    @validator("downstream_tables", "upstream_tables", pre=True)
+    def parse_tables(cls, v):
+        if not v:
+            return []
+
+        result = []
+        for item in v:
+            if isinstance(item, DatasetUrn):
+                result.append(item)
+            elif isinstance(item, str):
+                # Skip empty/whitespace-only strings
+                if item and item.strip():
+                    # Convert to URN using validation context
+                    assert cls._validation_context, (
+                        "Validation context must be set for URN creation"
+                    )
+                    urn_string = make_dataset_urn_with_platform_instance(
+                        name=item,
+                        platform=cls._validation_context.platform,
+                        platform_instance=cls._validation_context.platform_instance,
+                        env=cls._validation_context.env,
+                    )
+                    result.append(DatasetUrn.from_string(urn_string))
+
+        return result
+
     @classmethod
     def create(
         cls, entry_dict: dict, *, config: SqlQueriesSourceConfig
     ) -> "QueryEntry":
-        return cls(
-            query=entry_dict["query"],
-            timestamp=(
-                datetime.fromtimestamp(entry_dict["timestamp"], tz=timezone.utc)
-                if "timestamp" in entry_dict
-                else None
-            ),
-            user=CorpUserUrn(entry_dict["user"]) if "user" in entry_dict else None,
-            operation_type=entry_dict.get("operation_type"),
-            downstream_tables=[
-                make_dataset_urn_with_platform_instance(
-                    name=table,
-                    platform=config.platform,
-                    platform_instance=config.platform_instance,
-                    env=config.env,
-                )
-                for table in entry_dict.get("downstream_tables", [])
-            ],
-            upstream_tables=[
-                make_dataset_urn_with_platform_instance(
-                    name=table,
-                    platform=config.platform,
-                    platform_instance=config.platform_instance,
-                    env=config.env,
-                )
-                for table in entry_dict.get("upstream_tables", [])
-            ],
-            session_id=entry_dict.get("session_id"),
-        )
+        """Create QueryEntry from dict with config context."""
+        # Set validation context for URN creation
+        cls._validation_context = config
+        try:
+            return cls.parse_obj(entry_dict)
+        finally:
+            cls._validation_context = None