acryl-datahub 1.2.0.1__py3-none-any.whl → 1.2.0.2rc1__py3-none-any.whl

{acryl_datahub-1.2.0.1.dist-info → acryl_datahub-1.2.0.2rc1.dist-info}/RECORD

@@ -1,7 +1,7 @@
-acryl_datahub-1.2.0.1.dist-info/licenses/LICENSE,sha256=9xNHpsD0uYF5ONzXsKDCuHHB-xbiCrSbueWXqrTNsxk,11365
+acryl_datahub-1.2.0.2rc1.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=Fjtqaraj595j7RFLjvpnFYKEC5JdGREvvHD_hnrl5ek,320
+datahub/_version.py,sha256=1ST8gBZ8wWcQFJrAhpY_re_rMWhON0s6EftssFUvWKw,323
 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=emL16tSbG7j7EzTlK1H6gew7iAUxYwR5za_r8eWo1Qs,38723
+datahub/emitter/rest_emitter.py,sha256=lMqjtDyPOArIrNgL47kq1cbB4xiR17CHfRRxpGYriDY,38793
 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
@@ -227,14 +227,14 @@ 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=iQxiRpqbseR7pQ9rswqVjdYusCNAtkU5WAMUWPJrQsI,9505
+datahub/ingestion/source/sql_queries.py,sha256=4n8lTmfNtcH_qkGvnmPwidWCzfnjtWiBcd4AzAJGvbo,11810
 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
 datahub/ingestion/source/abs/datalake_profiler_config.py,sha256=Rkf64evufyVGPiE4VK8QAjzBiJFu85tOGMmJ0lJZ2Og,3600
 datahub/ingestion/source/abs/profiling.py,sha256=yKNCKpr6w7qpCH-baeSkNE9VjkN6eBot_weD-2_Jxzk,17579
 datahub/ingestion/source/abs/report.py,sha256=CkRjsNn0Pab-ZPllxz3IUJI_r3x0T6urJePa_hJKi5U,586
-datahub/ingestion/source/abs/source.py,sha256=FvncxJG2ZjQ4Q5JeYo4zVYuqEBsfvHOP4ZSjy_CKG90,24826
+datahub/ingestion/source/abs/source.py,sha256=uqMpvHmje3VPJRujW7l3Zmb0t3yFl91remXvznLuMO0,23783
 datahub/ingestion/source/apply/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 datahub/ingestion/source/apply/datahub_apply.py,sha256=xTD-Iq3UHhxcz61RwNuI2kJjRrnQEfZFSgvS1X6loV4,7703
 datahub/ingestion/source/aws/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -288,7 +288,7 @@ datahub/ingestion/source/common/gcp_credentials_config.py,sha256=_NapGkAqZMbXNCl
 datahub/ingestion/source/common/subtypes.py,sha256=x8dv9SN23Y8t5oq7SUuQWUPAH8KM3KfTT27ma9XgrM0,4551
 datahub/ingestion/source/data_lake_common/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 datahub/ingestion/source/data_lake_common/config.py,sha256=qUk83B01hjuBKHvVz8SmXnVCy5eFj-2-2QLEOrAdbgk,359
-datahub/ingestion/source/data_lake_common/data_lake_utils.py,sha256=55mK0nsehqGDTUOol9Oi3jZs8Pb04PIsHdC2WPP0dkg,6576
+datahub/ingestion/source/data_lake_common/data_lake_utils.py,sha256=IYr5y8vy_6CtMtITqzn6OqovzH1cpe1i30M-75PouXo,7768
 datahub/ingestion/source/data_lake_common/object_store.py,sha256=i9Hgb8Ww23QD_jEjzj_2qxA8Nr56krnZfo1qyOWmH9M,23608
 datahub/ingestion/source/data_lake_common/path_spec.py,sha256=ekJAr4-PE2RhzQnmKb2xcSs_YncC1Dz95-UrXI67Vos,23584
 datahub/ingestion/source/datahub/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -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=QDttgzZQowsiZGq9EN7zGSbitUR17F3vo-JMkF8pJbw,82264
+datahub/ingestion/source/dbt/dbt_common.py,sha256=ByCqzjkToXgfhOyxxc6VEuD8BZbYbPsD5yrLRMMPUcI,85640
 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
@@ -367,7 +367,7 @@ datahub/ingestion/source/kafka_connect/sink_connectors.py,sha256=QTMY0FmOHkTxfIC
 datahub/ingestion/source/kafka_connect/source_connectors.py,sha256=A9q-u5IoV35swvoyMrzT75FVV9-SBeYGhLKDYRge-IQ,23845
 datahub/ingestion/source/looker/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 datahub/ingestion/source/looker/lkml_patched.py,sha256=XShEU7Wbz0DubDhYMjKf9wjKZrBJa2XPg9MIjp8rPhk,733
-datahub/ingestion/source/looker/looker_common.py,sha256=wwCRHyd0F799CEBboryQ4TZV057krnY2nMJOkUWc268,64765
+datahub/ingestion/source/looker/looker_common.py,sha256=flWAl0LYY--FoCS_5bgHNThACukQ4WYVLhfiYfsF74I,66447
 datahub/ingestion/source/looker/looker_config.py,sha256=eVKw1nn9D8hUFdRfNyT3MtzL8w-zWhFeokiwSnNKQuc,13607
 datahub/ingestion/source/looker/looker_connection.py,sha256=yDmC6lDsHmL2e_Pw8ULylwOIHPWPp_6gT1iyLvD0fTw,2075
 datahub/ingestion/source/looker/looker_constant.py,sha256=GMKYtNXlpojPxa9azridKfcGLSJwKdUCTesp7U8dIrQ,402
@@ -446,7 +446,7 @@ datahub/ingestion/source/s3/config.py,sha256=lElFXgEpKDT9SVoiXvtx98wV6Gp880qP4pL
 datahub/ingestion/source/s3/datalake_profiler_config.py,sha256=FfrcgK-JEF94vw-l3q6pN6FENXb-wZzW2w1VUZVkwW8,3620
 datahub/ingestion/source/s3/profiling.py,sha256=yKNCKpr6w7qpCH-baeSkNE9VjkN6eBot_weD-2_Jxzk,17579
 datahub/ingestion/source/s3/report.py,sha256=9Ej1UCChw963UpGw1-7asi5vFrOM232gfgG8bRdKPp0,667
-datahub/ingestion/source/s3/source.py,sha256=DuJ5G0S2ukZFRL-aO8b4ihzhTlxvbzbj2_GyS8zLb7s,60968
+datahub/ingestion/source/s3/source.py,sha256=4_6VDBKIYTiS6fqU4BuGQ4XlJuD_1ehK7jb4TyMiv0c,59908
 datahub/ingestion/source/sac/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 datahub/ingestion/source/sac/sac.py,sha256=0s_JxHGOhit3Wvgbg7qQi-Z9j9_TgBX_I1yOR3L6-rA,30243
 datahub/ingestion/source/sac/sac_common.py,sha256=-xQTDBtgH56AnpRXWGDnlmQqUuLRx-7wF1U1kQFWtX8,998
@@ -501,7 +501,7 @@ datahub/ingestion/source/sql/hive_metastore.py,sha256=jpAgND_n2W6VCF_KMElXV5Gnd4
 datahub/ingestion/source/sql/mariadb.py,sha256=om6QoG5UtDldt1N6AfIWp3T-HXNaaqFmpz2i0JAemfM,654
 datahub/ingestion/source/sql/mysql.py,sha256=34Vu3otULxUY0-JUEYdZw2aoyuTlc9KLcoJdQxe2yJs,3267
 datahub/ingestion/source/sql/oracle.py,sha256=BGrHln5OQ6gq7LTqY8e4ySS5-uJaJEan0TU1778ZEYs,29963
-datahub/ingestion/source/sql/postgres.py,sha256=t-28dTWLa3c_NgWlGS9ZVNFlZLxd6xTSguIKP4S4NHs,11887
+datahub/ingestion/source/sql/postgres.py,sha256=fynj84tlNl0FO1I_2GkmeuFQ1HexL_woG0fAK3zHEzw,19019
 datahub/ingestion/source/sql/presto.py,sha256=tATa0M2q0PjUC_E9W_jSUsmKTP7cVJayLgrFMzG_eao,4223
 datahub/ingestion/source/sql/sql_common.py,sha256=qIH0Wnz8XvJDlYuS71X3XC5BfpeHkSGzpwn1aqPVY0o,52130
 datahub/ingestion/source/sql/sql_config.py,sha256=u3nGZYYl1WtaxfNsDU5bglgZ5Jq3Fxk9xei_CUIAXB0,8222
@@ -618,8 +618,8 @@ 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=V43yFMGVycJf0UV_b-ZAaOigWedg_iItFj3rOoIx3Ro,1046990
-datahub/metadata/schema.avsc,sha256=NlFTKx_U18Je4-BV3GAKS6wlEZrBTRUt-UF9gUH-5z0,735189
+datahub/metadata/_internal_schema_classes.py,sha256=i3KQdgYqA-gWAIlNa63f9OL1D5e_pmDtBjGKZxPsNIM,1050332
+datahub/metadata/schema.avsc,sha256=q7trioUW-inMl6LMviL9GqpngzbraV6q-SSQmTZ3USA,737396
 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
@@ -673,7 +673,7 @@ datahub/metadata/com/linkedin/pegasus2avro/metadata/query/filter/__init__.py,sha
 datahub/metadata/com/linkedin/pegasus2avro/metadata/snapshot/__init__.py,sha256=OPboF8SV11wGnjvWQB-rxtB0otMdCsE7Tcy7xkOUgz8,2358
 datahub/metadata/com/linkedin/pegasus2avro/ml/__init__.py,sha256=gsAIuTxzfJdI7a9ybZlgMIHMAYksM1SxGxXjtySgKSc,202
 datahub/metadata/com/linkedin/pegasus2avro/ml/metadata/__init__.py,sha256=qefB0n1xilQHCPla80b39wdjHOYoVtzBJT2jGc2szkM,3309
-datahub/metadata/com/linkedin/pegasus2avro/module/__init__.py,sha256=Np5zhmoMzMEIioN7bPwPZkXBh_0aTvcEaVAdL0qrzSE,1108
+datahub/metadata/com/linkedin/pegasus2avro/module/__init__.py,sha256=oJb5Lp4Rxo2fxiVqbH_m6wcfIDN49iLuL2RxJvIe-Kc,1218
 datahub/metadata/com/linkedin/pegasus2avro/mxe/__init__.py,sha256=LqGp9QTLk_tiSsbHMGSUH7uPG00Bf_qQIMiU7vtO4Tk,973
 datahub/metadata/com/linkedin/pegasus2avro/notebook/__init__.py,sha256=BcjOsz4YeHQbLLBb4Im4uJ7ux1hGHquQDmiIOiDXVtE,901
 datahub/metadata/com/linkedin/pegasus2avro/ownership/__init__.py,sha256=r813MW_bkP1ZpC2NJf7uCHEOapjebl611c90vryKX4A,302
@@ -732,7 +732,7 @@ datahub/metadata/schemas/CorpUserCredentials.avsc,sha256=S7FkV9K_DGxhb4GFYbM5_lP
 datahub/metadata/schemas/CorpUserEditableInfo.avsc,sha256=6IrqWidbHP7mRryfVlWAQU0JS34THHTM8_aIKWqClUE,3843
 datahub/metadata/schemas/CorpUserInfo.avsc,sha256=oObOza-5FLjZyCjj0FN4MNV1DodgTwJSV4APduAggjk,3955
 datahub/metadata/schemas/CorpUserKey.avsc,sha256=01sbbdr8G-ZP1yc2UfY3gR-YN6b7AvDbCbNpZJ-02J4,1025
-datahub/metadata/schemas/CorpUserSettings.avsc,sha256=ff-rvW3ihwo6s9usvStx0aXTmCNmcR1TjggDxhbCacc,6529
+datahub/metadata/schemas/CorpUserSettings.avsc,sha256=38_ZXslpkgJC1PlRxPnas9cHBi5dQYUcsl1X4WSn5Gc,6806
 datahub/metadata/schemas/CorpUserStatus.avsc,sha256=yqojAXEQ9CjRhY58RPyTUxzmFbHSANGGaMMbqiYZZIE,2538
 datahub/metadata/schemas/Cost.avsc,sha256=o4kYZSss2uEwJ6gCA9fhBUoyD5xUqcSxz78vkIXXzGQ,1494
 datahub/metadata/schemas/DashboardInfo.avsc,sha256=li2lSV6R4V-nz6foOi-NYxt_8ShHWfoKRw6M2BG5530,12907
@@ -752,7 +752,7 @@ datahub/metadata/schemas/DataHubIngestionSourceInfo.avsc,sha256=4wac7sluRIq-0ZjO
 datahub/metadata/schemas/DataHubIngestionSourceKey.avsc,sha256=TGmm9WEGTaABs7kt5Uc-N-kbc5Sd-2sQwx-JpfAptvw,545
 datahub/metadata/schemas/DataHubOpenAPISchemaKey.avsc,sha256=q6ZyMoxInwmrkrXkUgMe-i-WZzAxbjcvJ-EI99SnEp8,599
 datahub/metadata/schemas/DataHubPageModuleKey.avsc,sha256=NyFN8cVO6s6rtgoLGJJGfcPfpGr5PfmZlIhM6ajldfQ,460
-datahub/metadata/schemas/DataHubPageModuleProperties.avsc,sha256=NldfplvG_NKnbu1x0A1T6oTYKoTcGf_saa9AYFrcsTs,7618
+datahub/metadata/schemas/DataHubPageModuleProperties.avsc,sha256=_tbXEufCkviQxmhgB7quEq5Qm6693Z6no_9B624ryX4,8757
 datahub/metadata/schemas/DataHubPageTemplateKey.avsc,sha256=0sVqwL97Rp8YHPytp2RqUP5hIW048hmT2hPNP5k6arc,472
 datahub/metadata/schemas/DataHubPageTemplateProperties.avsc,sha256=0ndN64UNAADL6G_GVjJLHbe_dBnWhVRjtI3MilOlHQc,5651
 datahub/metadata/schemas/DataHubPersonaInfo.avsc,sha256=OUvbTgPQsBtzkDDb9pxHXpQ6A7dkL77ZnCXZ-MLEG14,227
@@ -876,9 +876,9 @@ 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=kwEwLUSPuqdrx_7uOX2XnEZ6Olm4p2ezYt0bTQSgaTk,377034
-datahub/metadata/schemas/MetadataChangeLog.avsc,sha256=Cf5eECeShCA_XHFr2MRhRQpPE61F6Xv-z1jjoBLJLgc,12239
-datahub/metadata/schemas/MetadataChangeProposal.avsc,sha256=tvO5cGIqZAIvUbMon1RAKgSY4E0jvBqT5VmLWAuNGkY,9770
+datahub/metadata/schemas/MetadataChangeEvent.avsc,sha256=l3tVuQces7sKrwWsaIJrn3nMRUiCl3MHqCJJHcw7Ylc,377705
+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
 datahub/metadata/schemas/NativeGroupMembership.avsc,sha256=9mh9tzyj3ErmTIhX7ERRUm78j1QtGwXUl9UuIXPndBg,588
 datahub/metadata/schemas/NotebookContent.avsc,sha256=ck3yDt0qK5Hn3-mWTNLlYnohXCs6kMUUWPXm7o1JEWE,12496
@@ -916,7 +916,7 @@ datahub/metadata/schemas/StructuredPropertyDefinition.avsc,sha256=a-6TaOQ4A7LDFL
 datahub/metadata/schemas/StructuredPropertyKey.avsc,sha256=lp7tQBgeriEU1YMQ6a4-6aUGSWDqNl00lLDym97j1yI,618
 datahub/metadata/schemas/StructuredPropertySettings.avsc,sha256=EDNlXfT1TqogfulCanIc-nuYO9ZxRFOGzD9tl3ZJdB8,3732
 datahub/metadata/schemas/SubTypes.avsc,sha256=bhXbzK020zDyQno97Xp05vmoMeZ82IGu2jz7pWDo3RQ,655
-datahub/metadata/schemas/SystemMetadata.avsc,sha256=wDVdpa9LSAlMzHIiWw-fMLHTCrxcJdnDOY_n5CDNTN8,2068
+datahub/metadata/schemas/SystemMetadata.avsc,sha256=XEU32-oZsyVwMii-DlQSVDaUTfKQ9n7K0ChMJ07KHvQ,4457
 datahub/metadata/schemas/TagKey.avsc,sha256=BfckMlx-wg_LV1_PFVgItfNBPtCQ8_erGeQM4LzOXmY,640
 datahub/metadata/schemas/TagProperties.avsc,sha256=Qzttxd7BB38JUwwl7tZzIV1Warnh-uQO-Ahw9Sd-vH4,883
 datahub/metadata/schemas/TelemetryClientId.avsc,sha256=GScej0kXFZxoBUcRVrVynzArFSYQpO_dnhY5Po5dlx0,408
@@ -954,7 +954,7 @@ datahub/sdk/mlmodel.py,sha256=cO5R8BYVljmQ0w33RIOuZmj4nq8OJCDVAZGTQI6YFS8,12628
 datahub/sdk/mlmodelgroup.py,sha256=wlZZHny0UORpF0fRYuVkWLSQwIHX_fWl5lPb1NKR6dM,8194
 datahub/sdk/resolver_client.py,sha256=nKMAZJt2tRSGfKSzoREIh43PXqjM3umLiYkYHJjo1io,3243
 datahub/sdk/search_client.py,sha256=hlk40VnD3eT88hMgwXAUv31-ENbDe50P-gsXUnGSNeo,3512
-datahub/sdk/search_filters.py,sha256=xk19K7V6Y3YflNqNXgMTn_BpaRuoFhlub7w4tLjQlc8,15619
+datahub/sdk/search_filters.py,sha256=Z0f44KNOjmpmeaPweZUlvcDxNuyTckCHGJX8JIygiYY,17230
 datahub/secret/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 datahub/secret/datahub_secret_store.py,sha256=xyNAZY62d6KSz_kYF9wN7RDMLvNhu2ayOzcYvubOX1E,2519
 datahub/secret/datahub_secrets_client.py,sha256=nDmhziKdvseJHlaDVUcAwK8Fv8maeAaG-ktZtWG2b70,1316
@@ -982,7 +982,7 @@ datahub/sql_parsing/fingerprint_utils.py,sha256=3hGiexaQXnE7eZLxo-t7hlTyVQz7womb
 datahub/sql_parsing/query_types.py,sha256=FKjDzszZzsrCfYfm7dgD6T_8865qxWl767fdGyHWBh4,2720
 datahub/sql_parsing/schema_resolver.py,sha256=ISuingLcQnOJZkNXBkc73uPwYUbbOtERAjgGhJajDiQ,10782
 datahub/sql_parsing/split_statements.py,sha256=OIQXA9e4k3G9Z1y7rbgdtZhMWt4FPnq41cE8Jkm9cBY,9542
-datahub/sql_parsing/sql_parsing_aggregator.py,sha256=ewRHmRT8a9e0D0c-6JioNNjrgeOwfa-8eQFTMmQTl1s,71928
+datahub/sql_parsing/sql_parsing_aggregator.py,sha256=1gDSf8n6AkINZbhWdcPw7JjeIPMJgAIep1XFQMOPR6Q,71991
 datahub/sql_parsing/sql_parsing_common.py,sha256=cZ4WvVyHZuXDGjnBvKMX2_fz2EMextB5WQWcK0_saBo,3155
 datahub/sql_parsing/sql_parsing_result_utils.py,sha256=prwWTj1EB2fRPv1eMB4EkpFNafIYAt-X8TIK0NWqank,796
 datahub/sql_parsing/sqlglot_lineage.py,sha256=oG7Zx2aOpm1tBQQowPgSufGlMpm5DaMGKTwk7gIkhX0,61450
@@ -1003,7 +1003,7 @@ datahub/testing/mcp_diff.py,sha256=1BpQ3hST46cOQi1SmKdsto3j6x6Sk6yHm0vG1w9IDL0,1
 datahub/testing/pytest_hooks.py,sha256=eifmj0M68AIfjTn_-0vtaBkKl75vNKMjsbYX-pJqmGY,1417
 datahub/testing/sdk_v2_helpers.py,sha256=FooqGn5PfdJJrCFm3x_uh02IMhDdLjqEf64W16WdvE0,424
 datahub/upgrade/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-datahub/upgrade/upgrade.py,sha256=bxGjfLU-hSQXS9Q1RlhWeJMETTGKqLNGFDPtcheCO4o,18474
+datahub/upgrade/upgrade.py,sha256=zA28UAgxVzPRiCnjbZ6PqSflozMyomTkmGetX6DXC6E,18583
 datahub/utilities/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 datahub/utilities/_custom_package_loader.py,sha256=9kgPE7Y77E-hNee8l4sKtVby-btUNum3dBfDixMzcVA,2059
 datahub/utilities/_markupsafe_compat.py,sha256=QX7c9KiHs56ASl7bJlgR4FAf3CGiY94zIr0h6Ak15To,444
@@ -1093,8 +1093,8 @@ 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-1.2.0.1.dist-info/METADATA,sha256=-gp-iQ4Mqm6pNM6VWTNdAia94Hw6PmteDamE363gWEk,181884
-acryl_datahub-1.2.0.1.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-acryl_datahub-1.2.0.1.dist-info/entry_points.txt,sha256=bnGf6eX9UhiW8yVHtt6MJCVcmLErvrVQxTJAayA-PKc,9885
-acryl_datahub-1.2.0.1.dist-info/top_level.txt,sha256=iLjSrLK5ox1YVYcglRUkcvfZPvKlobBWx7CTUXx8_GI,25
-acryl_datahub-1.2.0.1.dist-info/RECORD,,
+acryl_datahub-1.2.0.2rc1.dist-info/METADATA,sha256=dvJ_JwbJKfu4voRemOG8bC2x4cXQUyNPu9cmz68Ehvg,181893
+acryl_datahub-1.2.0.2rc1.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+acryl_datahub-1.2.0.2rc1.dist-info/entry_points.txt,sha256=bnGf6eX9UhiW8yVHtt6MJCVcmLErvrVQxTJAayA-PKc,9885
+acryl_datahub-1.2.0.2rc1.dist-info/top_level.txt,sha256=iLjSrLK5ox1YVYcglRUkcvfZPvKlobBWx7CTUXx8_GI,25
+acryl_datahub-1.2.0.2rc1.dist-info/RECORD,,

datahub/_version.py

@@ -1,6 +1,6 @@
 # Published at https://pypi.org/project/acryl-datahub/.
 __package_name__ = "acryl-datahub"
-__version__ = "1.2.0.1"
+__version__ = "1.2.0.2rc1"
 
 
 def is_dev_mode() -> bool:

datahub/emitter/rest_emitter.py

@@ -98,7 +98,9 @@ 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
 # for overhead like request headers.
 # This applies to pretty much all calls to GMS.
-INGEST_MAX_PAYLOAD_BYTES = 15 * 1024 * 1024
+INGEST_MAX_PAYLOAD_BYTES = int(
+    os.getenv("DATAHUB_REST_EMITTER_BATCH_MAX_PAYLOAD_BYTES", 15 * 1024 * 1024)
+)
 
 # This limit is somewhat arbitrary. All GMS endpoints will timeout
 # and return a 500 if processing takes too long. To avoid sending

datahub/ingestion/source/abs/source.py

@@ -44,7 +44,10 @@ from datahub.ingestion.source.azure.abs_utils import (
     get_key_prefix,
     strip_abs_prefix,
 )
-from datahub.ingestion.source.data_lake_common.data_lake_utils import ContainerWUCreator
+from datahub.ingestion.source.data_lake_common.data_lake_utils import (
+    ContainerWUCreator,
+    add_partition_columns_to_schema,
+)
 from datahub.ingestion.source.schema_inference import avro, csv_tsv, json, parquet
 from datahub.ingestion.source.state.stale_entity_removal_handler import (
     StaleEntityRemovalHandler,
@@ -53,10 +56,7 @@ from datahub.ingestion.source.state.stateful_ingestion_base import (
     StatefulIngestionSourceBase,
 )
 from datahub.metadata.com.linkedin.pegasus2avro.schema import (
-    SchemaField,
-    SchemaFieldDataType,
     SchemaMetadata,
-    StringTypeClass,
 )
 from datahub.metadata.schema_classes import (
     DataPlatformInstanceClass,
@@ -223,36 +223,12 @@ class ABSSource(StatefulIngestionSourceBase):
         fields = sorted(fields, key=lambda f: f.fieldPath)
 
         if self.source_config.add_partition_columns_to_schema:
-            self.add_partition_columns_to_schema(
+            add_partition_columns_to_schema(
                 fields=fields, path_spec=path_spec, full_path=table_data.full_path
             )
 
         return fields
 
-    def add_partition_columns_to_schema(
-        self, path_spec: PathSpec, full_path: str, fields: List[SchemaField]
-    ) -> None:
-        vars = path_spec.get_named_vars(full_path)
-        if vars is not None and "partition" in vars:
-            for partition in vars["partition"].values():
-                partition_arr = partition.split("=")
-                if len(partition_arr) != 2:
-                    logger.debug(
-                        f"Could not derive partition key from partition field {partition}"
-                    )
-                    continue
-                partition_key = partition_arr[0]
-                fields.append(
-                    SchemaField(
-                        fieldPath=f"{partition_key}",
-                        nativeDataType="string",
-                        type=SchemaFieldDataType(StringTypeClass()),
-                        isPartitioningKey=True,
-                        nullable=True,
-                        recursive=False,
-                    )
-                )
-
     def _create_table_operation_aspect(self, table_data: TableData) -> OperationClass:
         reported_time = int(time.time() * 1000)
 

datahub/ingestion/source/data_lake_common/data_lake_utils.py

@@ -25,10 +25,16 @@ from datahub.ingestion.source.data_lake_common.object_store import (
     get_object_store_bucket_name,
     get_object_store_for_uri,
 )
+from datahub.ingestion.source.data_lake_common.path_spec import PathSpec
 from datahub.ingestion.source.gcs.gcs_utils import (
     get_gcs_prefix,
     is_gcs_uri,
 )
+from datahub.metadata.schema_classes import (
+    SchemaFieldClass,
+    SchemaFieldDataTypeClass,
+    StringTypeClass,
+)
 
 # hide annoying debug errors from py4j
 logging.getLogger("py4j").setLevel(logging.ERROR)
@@ -39,6 +45,37 @@ PLATFORM_GCS = "gcs"
 PLATFORM_ABS = "abs"
 
 
+def add_partition_columns_to_schema(
+    path_spec: PathSpec, full_path: str, fields: List[SchemaFieldClass]
+) -> None:
+    # Check if using fieldPath v2 format
+    is_fieldpath_v2 = any(
+        field.fieldPath.startswith("[version=2.0]") for field in fields
+    )
+
+    # Extract partition information from path
+    partition_keys = path_spec.get_partition_from_path(full_path)
+    if not partition_keys:
+        return
+
+    # Add partition fields to schema
+    for partition_key in partition_keys:
+        fields.append(
+            SchemaFieldClass(
+                fieldPath=(
+                    f"{partition_key[0]}"
+                    if not is_fieldpath_v2
+                    else f"[version=2.0].[type=string].{partition_key[0]}"
+                ),
+                nativeDataType="string",
+                type=SchemaFieldDataTypeClass(StringTypeClass()),
+                isPartitioningKey=True,
+                nullable=False,
+                recursive=False,
+            )
+        )
+
+
 class ContainerWUCreator:
     processed_containers: List[str]
 

datahub/ingestion/source/dbt/dbt_common.py

@@ -145,6 +145,9 @@ class DBTSourceReport(StaleEntityRemovalSourceReport):
 
     nodes_filtered: LossyList[str] = field(default_factory=LossyList)
 
+    duplicate_sources_dropped: Optional[int] = None
+    duplicate_sources_references_updated: Optional[int] = None
+
 
 class EmitDirective(ConfigEnum):
     """A holder for directives for emission for specific types of entities"""
@@ -370,6 +373,12 @@ class DBTCommonConfig(
         "Set to False to skip it for engines like AWS Athena where it's not required.",
     )
 
+    drop_duplicate_sources: bool = Field(
+        default=True,
+        description="When enabled, drops sources that have the same name in the target platform as a model. "
+        "This ensures that lineage is generated reliably, but will lose any documentation associated only with the source.",
+    )
+
     @validator("target_platform")
     def validate_target_platform_value(cls, target_platform: str) -> str:
         if target_platform.lower() == DBT_PLATFORM:
@@ -509,7 +518,7 @@ class DBTNode:
     raw_code: Optional[str]
 
     dbt_adapter: str
-    dbt_name: str
+    dbt_name: str  # dbt unique identifier
     dbt_file_path: Optional[str]
     dbt_package_name: Optional[str]  # this is pretty much always present
 
@@ -975,6 +984,8 @@ class DBTSourceBase(StatefulIngestionSourceBase):
         self._infer_schemas_and_update_cll(all_nodes_map)
 
         nodes = self._filter_nodes(all_nodes)
+        nodes = self._drop_duplicate_sources(nodes)
+
         non_test_nodes = [
             dataset_node for dataset_node in nodes if dataset_node.node_type != "test"
         ]
@@ -1000,7 +1011,7 @@ class DBTSourceBase(StatefulIngestionSourceBase):
         return self.config.node_name_pattern.allowed(key)
 
     def _filter_nodes(self, all_nodes: List[DBTNode]) -> List[DBTNode]:
-        nodes = []
+        nodes: List[DBTNode] = []
         for node in all_nodes:
             key = node.dbt_name
 
@@ -1012,6 +1023,62 @@ class DBTSourceBase(StatefulIngestionSourceBase):
 
         return nodes
 
+    def _drop_duplicate_sources(self, original_nodes: List[DBTNode]) -> List[DBTNode]:
+        """Detect and correct cases where a model and source have the same name.
+
+        In these cases, we don't want to generate both because they'll have the same
+        urn and hence overwrite each other. Instead, we drop the source and update
+        references to it to point at the model.
+
+        The risk here is that the source might have documentation that'd be lost,
+        which is why we maintain optionality with a config flag.
+        """
+        if not self.config.drop_duplicate_sources:
+            return original_nodes
+
+        self.report.duplicate_sources_dropped = 0
+        self.report.duplicate_sources_references_updated = 0
+
+        # Pass 1 - find all model names in the warehouse.
+        warehouse_model_names: Dict[str, str] = {}  # warehouse name -> model unique id
+        for node in original_nodes:
+            if node.node_type == "model" and node.exists_in_target_platform:
+                warehouse_model_names[node.get_db_fqn()] = node.dbt_name
+
+        # Pass 2 - identify + drop duplicate sources.
+        source_references_to_update: Dict[
+            str, str
+        ] = {}  # source unique id -> model unique id
+        nodes: List[DBTNode] = []
+        for node in original_nodes:
+            if (
+                node.node_type == "source"
+                and node.exists_in_target_platform
+                and (model_name := warehouse_model_names.get(node.get_db_fqn()))
+            ):
+                self.report.warning(
+                    title="Duplicate model and source names detected",
+                    message="We found a dbt model and dbt source with the same name. To ensure reliable lineage generation, the source node was ignored. "
+                    "If you associated documentation/tags/other metadata with the source, it will be lost. "
+                    "To avoid this, you should remove the source node from your dbt project and replace any `source(<source_name>)` calls with `ref(<model_name>)`.",
+                    context=f"{node.dbt_name} (called {node.get_db_fqn()} in {self.config.target_platform}) duplicates {model_name}",
+                )
+                self.report.duplicate_sources_dropped += 1
+                source_references_to_update[node.dbt_name] = model_name
+            else:
+                nodes.append(node)
+
+        # Pass 3 - update references to the dropped sources.
+        for node in nodes:
+            for i, current_upstream in enumerate(node.upstream_nodes):
+                if current_upstream in source_references_to_update:
+                    node.upstream_nodes[i] = source_references_to_update[
+                        current_upstream
+                    ]
+                    self.report.duplicate_sources_references_updated += 1
+
+        return nodes
+
     @staticmethod
     def _to_schema_info(schema_fields: List[SchemaField]) -> SchemaInfo:
         return {column.fieldPath: column.nativeDataType for column in schema_fields}

datahub/ingestion/source/looker/looker_common.py

@@ -242,13 +242,19 @@ class LookerViewId:
 
         dataset_name = config.view_naming_pattern.replace_variables(n_mapping)
 
-        return builder.make_dataset_urn_with_platform_instance(
+        generated_urn = builder.make_dataset_urn_with_platform_instance(
             platform=config.platform_name,
             name=dataset_name,
             platform_instance=config.platform_instance,
             env=config.env,
         )
 
+        logger.debug(
+            f"LookerViewId.get_urn for view '{self.view_name}': project='{self.project_name}', model='{self.model_name}', file_path='{self.file_path}', dataset_name='{dataset_name}', generated_urn='{generated_urn}'"
+        )
+
+        return generated_urn
+
     def get_browse_path(self, config: LookerCommonConfig) -> str:
         browse_path = config.view_browse_pattern.replace_variables(
             self.get_mapping(config)
@@ -452,15 +458,36 @@ class ExploreUpstreamViewField:
         )
 
 
-def create_view_project_map(view_fields: List[ViewField]) -> Dict[str, str]:
+def create_view_project_map(
+    view_fields: List[ViewField],
+    explore_primary_view: Optional[str] = None,
+    explore_project_name: Optional[str] = None,
+) -> Dict[str, str]:
     """
     Each view in a model has unique name.
     Use this function in scope of a model.
+
+    Args:
+        view_fields: List of ViewField objects
+        explore_primary_view: The primary view name of the explore (explore.view_name)
+        explore_project_name: The project name of the explore (explore.project_name)
     """
     view_project_map: Dict[str, str] = {}
     for view_field in view_fields:
         if view_field.view_name is not None and view_field.project_name is not None:
-            view_project_map[view_field.view_name] = view_field.project_name
+            # Override field-level project assignment for the primary view when different
+            if (
+                view_field.view_name == explore_primary_view
+                and explore_project_name is not None
+                and explore_project_name != view_field.project_name
+            ):
+                logger.debug(
+                    f"Overriding project assignment for primary view '{view_field.view_name}': "
+                    f"field-level project '{view_field.project_name}' → explore-level project '{explore_project_name}'"
+                )
+                view_project_map[view_field.view_name] = explore_project_name
+            else:
+                view_project_map[view_field.view_name] = view_field.project_name
 
     return view_project_map
 
@@ -953,6 +980,9 @@ class LookerExplore:
                         f"Could not resolve view {view_name} for explore {dict['name']} in model {model_name}"
                     )
                 else:
+                    logger.debug(
+                        f"LookerExplore.from_dict adding upstream view for explore '{dict['name']}' (model='{model_name}'): view_name='{view_name}', info[0].project='{info[0].project}'"
+                    )
                     upstream_views.append(
                         ProjectInclude(project=info[0].project, include=view_name)
                     )
@@ -981,6 +1011,7 @@ class LookerExplore:
     ) -> Optional["LookerExplore"]:
         try:
             explore = client.lookml_model_explore(model, explore_name)
+
             views: Set[str] = set()
             lkml_fields: List[LookmlModelExploreField] = (
                 explore_field_set_to_lkml_fields(explore)
@@ -1117,7 +1148,11 @@ class LookerExplore:
                                 )
                             )
 
-            view_project_map: Dict[str, str] = create_view_project_map(view_fields)
+            view_project_map: Dict[str, str] = create_view_project_map(
+                view_fields,
+                explore_primary_view=explore.view_name,
+                explore_project_name=explore.project_name,
+            )
             if view_project_map:
                 logger.debug(f"views and their projects: {view_project_map}")
 
@@ -1289,6 +1324,7 @@ class LookerExplore:
                     if self.upstream_views_file_path[view_ref.include] is not None
                     else ViewFieldValue.NOT_AVAILABLE.value
                 )
+
                 view_urn = LookerViewId(
                     project_name=(
                         view_ref.project

datahub/ingestion/source/s3/source.py

@@ -41,7 +41,10 @@ from datahub.ingestion.source.aws.s3_util import (
     get_key_prefix,
     strip_s3_prefix,
 )
-from datahub.ingestion.source.data_lake_common.data_lake_utils import ContainerWUCreator
+from datahub.ingestion.source.data_lake_common.data_lake_utils import (
+    ContainerWUCreator,
+    add_partition_columns_to_schema,
+)
 from datahub.ingestion.source.data_lake_common.object_store import (
     create_object_store_adapter,
 )
@@ -58,9 +61,7 @@ from datahub.ingestion.source.state.stateful_ingestion_base import (
 )
 from datahub.metadata.com.linkedin.pegasus2avro.common import TimeStamp
 from datahub.metadata.com.linkedin.pegasus2avro.schema import (
-    SchemaField,
     SchemaMetadata,
-    StringTypeClass,
 )
 from datahub.metadata.schema_classes import (
     DataPlatformInstanceClass,
@@ -70,7 +71,6 @@ from datahub.metadata.schema_classes import (
     OtherSchemaClass,
     PartitionsSummaryClass,
     PartitionSummaryClass,
-    SchemaFieldDataTypeClass,
     _Aspect,
 )
 from datahub.telemetry import stats, telemetry
@@ -474,7 +474,7 @@ class S3Source(StatefulIngestionSourceBase):
             fields = sorted(fields, key=lambda f: f.fieldPath)
 
         if self.source_config.add_partition_columns_to_schema and table_data.partitions:
-            self.add_partition_columns_to_schema(
+            add_partition_columns_to_schema(
                 fields=fields, path_spec=path_spec, full_path=table_data.full_path
             )
 
@@ -510,34 +510,6 @@ class S3Source(StatefulIngestionSourceBase):
         else:
             return None
 
-    def add_partition_columns_to_schema(
-        self, path_spec: PathSpec, full_path: str, fields: List[SchemaField]
-    ) -> None:
-        is_fieldpath_v2 = False
-        for field in fields:
-            if field.fieldPath.startswith("[version=2.0]"):
-                is_fieldpath_v2 = True
-                break
-        partition_keys = path_spec.get_partition_from_path(full_path)
-        if not partition_keys:
-            return None
-
-        for partition_key in partition_keys:
-            fields.append(
-                SchemaField(
-                    fieldPath=(
-                        f"{partition_key[0]}"
-                        if not is_fieldpath_v2
-                        else f"[version=2.0].[type=string].{partition_key[0]}"
-                    ),
-                    nativeDataType="string",
-                    type=SchemaFieldDataTypeClass(StringTypeClass()),
-                    isPartitioningKey=True,
-                    nullable=True,
-                    recursive=False,
-                )
-            )
-
     def get_table_profile(
         self, table_data: TableData, dataset_urn: str
     ) -> Iterable[MetadataWorkUnit]: