acryl-datahub 0.15.0.1rc8__py3-none-any.whl → 0.15.0.1rc10__py3-none-any.whl

{acryl_datahub-0.15.0.1rc8.dist-info → acryl_datahub-0.15.0.1rc10.dist-info}/RECORD

@@ -1,4 +1,4 @@
-datahub/__init__.py,sha256=Ed_HdiA9eGLLG0fhJKPwruUxl4bgAPR8p2MDlRHqts8,576
+datahub/__init__.py,sha256=_-iwjV9mhNtK3Q_48sB1x7crxfllh3ay-QVv4WQ8458,577
 datahub/__main__.py,sha256=pegIvQ9hzK7IhqVeUi1MeADSZ2QlP-D3K0OQdEg55RU,106
 datahub/entrypoints.py,sha256=3-qSfXAx3Z0FEkBV5tlO8fQr4xk4ySeDRMVTpS5Xd6A,7793
 datahub/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -217,7 +217,7 @@ datahub/ingestion/source/abs/report.py,sha256=fzkTdTewYlWrTk4f2Cyl-e8RV4qw9wEVtm
 datahub/ingestion/source/abs/source.py,sha256=pzxW-R_cWGKPneEhX8JWdTZiX2k1kAZOPKgMxp9mAEI,24533
 datahub/ingestion/source/aws/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 datahub/ingestion/source/aws/aws_common.py,sha256=DfdQgkJ_s2isFx8WvqKTlAcBk4KE8SgfpmA5BgC3fgY,17716
-datahub/ingestion/source/aws/glue.py,sha256=fX0dtaVVq174ZS0aBJvZFYK8ligfZX5EU3pdS3j1KQs,56215
+datahub/ingestion/source/aws/glue.py,sha256=r7y1MPDK__BKX_mrJjVa_CEmSXM3Pa02gt19o0sSLE8,56815
 datahub/ingestion/source/aws/s3_boto_utils.py,sha256=Wyp9k9tapsCuw9dyH4FCXJr_wmeLaYFoCtKvrV6SEDk,3892
 datahub/ingestion/source/aws/s3_util.py,sha256=OFypcgmVC6jnZM90-gjcPpAMtTV1lbnreCaMhCzNlzs,2149
 datahub/ingestion/source/aws/sagemaker.py,sha256=Bl2tkBYnrindgx61VHYgNovUF_Kp_fXNcivQn28vC2w,5254
@@ -273,7 +273,7 @@ datahub/ingestion/source/datahub/datahub_source.py,sha256=2jDnsHEzpGhr00qQI9unSU
 datahub/ingestion/source/datahub/report.py,sha256=VHBfCbwFRzdLdB7hQG9ST4EiZxl_vBCU0XxGcZR6Xxs,940
 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=3bfcCi7xBvlCTGjnDCnyOShsxgVRn7wUYJOid_WT_Vk,17643
+datahub/ingestion/source/dbt/dbt_cloud.py,sha256=Joh4AIjlu-UVJw_Hu32bPxT9w25RX4JfUnUhVpiJcJw,18005
 datahub/ingestion/source/dbt/dbt_common.py,sha256=0ddiqNx9sUAGZYDQ8tSr5Qh5ti-kgC4saW1yRRNJXgg,80493
 datahub/ingestion/source/dbt/dbt_core.py,sha256=m6cA9vVd4Nh2arc-T2_xeQoxvreRbMhTDIJuYsx3wHc,22722
 datahub/ingestion/source/dbt/dbt_tests.py,sha256=Q5KISW_AOOWqyxmyOgJQquyX7xlfOqKu9WhrHoLKC0M,9881
@@ -302,9 +302,9 @@ datahub/ingestion/source/fivetran/fivetran.py,sha256=uKbM5czPz-6LOseoh1FwavWDIuL
 datahub/ingestion/source/fivetran/fivetran_log_api.py,sha256=EAak3hJpe75WZSgz6wP_CyAT5Cian2N4a-lb8x1NKHk,12776
 datahub/ingestion/source/fivetran/fivetran_query.py,sha256=vLrTj7e-0NxZ2U4bWTB57pih42WirqPlUvwtIRfStlQ,5275
 datahub/ingestion/source/gc/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-datahub/ingestion/source/gc/datahub_gc.py,sha256=AHlKGwDD-E_TEHcJIpRtwk6ikjT-KiyfTo-BXZnMSk0,12114
+datahub/ingestion/source/gc/datahub_gc.py,sha256=WOg3yIaNmwdbSTwytKeSfIUihsM7FMYBip9u2Dnwk3c,12849
 datahub/ingestion/source/gc/dataprocess_cleanup.py,sha256=u90XEmW1vRFbvp4CQ8ujPxTGJUyJqO2U6ApcI6mFrjE,16588
-datahub/ingestion/source/gc/execution_request_cleanup.py,sha256=cHJmxz4NmA7VjTX2iGEo3wZ_SDrjC_rCQcnRxKgfUVI,8713
+datahub/ingestion/source/gc/execution_request_cleanup.py,sha256=sZbdkg3MuPVGf8eeeRg_2khGMZ01QoH4dgJiTxf7Srg,9813
 datahub/ingestion/source/gc/soft_deleted_entity_cleanup.py,sha256=wRnRaIVUG483tY4nyDkEn6Xi2RL5MjrVvoCoZimqwSg,7514
 datahub/ingestion/source/gcs/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 datahub/ingestion/source/gcs/gcs_source.py,sha256=iwvj4JwjyVWRP1Vq106sUtQhh0GuOYVSu9zCa1wCZN0,6189
@@ -334,7 +334,7 @@ datahub/ingestion/source/looker/looker_common.py,sha256=KObx5ZTfldN2EO11eb1LrHI-
 datahub/ingestion/source/looker/looker_config.py,sha256=87WAgdJ_QWdTq25RBwgIqfc2kq7dubSpzbEtXb2ihMw,13182
 datahub/ingestion/source/looker/looker_connection.py,sha256=yDmC6lDsHmL2e_Pw8ULylwOIHPWPp_6gT1iyLvD0fTw,2075
 datahub/ingestion/source/looker/looker_constant.py,sha256=GMKYtNXlpojPxa9azridKfcGLSJwKdUCTesp7U8dIrQ,402
-datahub/ingestion/source/looker/looker_dataclasses.py,sha256=ULWLFWsV2cKmTuOFavD8QjEBmnXmvjyr8RbUB62DwJQ,12178
+datahub/ingestion/source/looker/looker_dataclasses.py,sha256=LjrP5m_A4HV-XeFlSNGVYNuyF0ulxp_qwB82Ss4Iycs,12200
 datahub/ingestion/source/looker/looker_file_loader.py,sha256=c1ewDrIb9VJg1o-asbwX9gL83kgL01vIETzzbmZIhmw,4267
 datahub/ingestion/source/looker/looker_lib_wrapper.py,sha256=0gaYjBv4wkbbLWVgvaAV6JyWAFb0utTG6TCve2d9xss,11511
 datahub/ingestion/source/looker/looker_liquid_tag.py,sha256=mO4G4MNA4YZFvZaDBpdiJ2vP3irC82kY34RdaK4Pbfs,3100
@@ -370,7 +370,7 @@ datahub/ingestion/source/powerbi/m_query/tree_function.py,sha256=h77DunhlgOP0fAg
 datahub/ingestion/source/powerbi/m_query/validator.py,sha256=crG-VZy2XPieiDliP9yVMgiFcc8b2xbZyDFEATXqEAQ,1155
 datahub/ingestion/source/powerbi/rest_api_wrapper/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 datahub/ingestion/source/powerbi/rest_api_wrapper/data_classes.py,sha256=xqAsnNUCP44Wd1rE1m_phbKtNCMJTFJfOX4_2varadg,8298
-datahub/ingestion/source/powerbi/rest_api_wrapper/data_resolver.py,sha256=O2XTVBdXteIgQF8Lss_t2RhRSsRMmMyWrAoNonDMQFI,39604
+datahub/ingestion/source/powerbi/rest_api_wrapper/data_resolver.py,sha256=8_IIYzcGQR5jcJ3NKg_tIa7VobUEBXzVpvFBaFPUToM,39598
 datahub/ingestion/source/powerbi/rest_api_wrapper/powerbi_api.py,sha256=3nGU-_KQe1WMIAPdxtuzulqpAreNsqi0vX0XdrddCU8,26184
 datahub/ingestion/source/powerbi/rest_api_wrapper/profiling_utils.py,sha256=bgcPheyqOj6KdRjDyANDK5yggItglcBIjbGFIwAxSds,1392
 datahub/ingestion/source/powerbi/rest_api_wrapper/query.py,sha256=VNw1Uvli6g0pnu9FpigYmnCdEPbVEipz7vdZU_WmHf4,616
@@ -429,21 +429,21 @@ datahub/ingestion/source/snowflake/constants.py,sha256=22n-0r04nuy-ImxWFFpmbrt_G
 datahub/ingestion/source/snowflake/oauth_config.py,sha256=ol9D3RmruGStJAeL8PYSQguSqcD2HfkjPkMF2AB_eZs,1277
 datahub/ingestion/source/snowflake/oauth_generator.py,sha256=fu2VnREGuJXeTqIV2jx4TwieVnznf83HQkrE0h2DGGM,3423
 datahub/ingestion/source/snowflake/snowflake_assertion.py,sha256=_l3k4aI9wvioE81xxdeizJn9nJCZ_nMIXgk9N6pEk5o,4803
-datahub/ingestion/source/snowflake/snowflake_config.py,sha256=_Ew2nJRoKC9e-SyrhOqn730c4FEhQE3U4bbY6RFV004,17973
+datahub/ingestion/source/snowflake/snowflake_config.py,sha256=jQGSa7ZQs3EsXB9ANShZ4xv9RqrhRfVHRSLeFiDwwxc,17974
 datahub/ingestion/source/snowflake/snowflake_connection.py,sha256=yzv-01FdmfDSCJY5rqKNNodXxzg3SS5DF7oA4WXArOA,17793
 datahub/ingestion/source/snowflake/snowflake_data_reader.py,sha256=ffR5E2uhD71FUMXd3XOg2rHwrp1rbbGEFTAbqKcmI2s,2195
 datahub/ingestion/source/snowflake/snowflake_lineage_v2.py,sha256=5Lpy_irZlbOFJbvVkgsZSBjdLCT3VZNjlEvttzSQAU4,21121
 datahub/ingestion/source/snowflake/snowflake_profiler.py,sha256=0DJiSwII6FY34urlBja2FW66NaVvhbBWmG0p7u8Xyrc,7548
-datahub/ingestion/source/snowflake/snowflake_queries.py,sha256=8QEihOfivalVR9vLo6vCUL-vnZfAGgMio0uhPYX0jTo,25883
-datahub/ingestion/source/snowflake/snowflake_query.py,sha256=885pyVnLf8wwTTuWkJ-Q01gKE7Xt518QPbFkrN-vd7o,38310
+datahub/ingestion/source/snowflake/snowflake_queries.py,sha256=Lhc5FAx8pXiUyfODGNkQJhjThSCIjPqG2R82dHN-jg0,26889
+datahub/ingestion/source/snowflake/snowflake_query.py,sha256=5po2FWz41UVowykJYbTFGxsltbmlHBCPcHG20VOhdOE,38469
 datahub/ingestion/source/snowflake/snowflake_report.py,sha256=_-rD7Q4MzKY8fYzJHSBnGX4gurwujL3UoRzcP_TZURs,6468
 datahub/ingestion/source/snowflake/snowflake_schema.py,sha256=z5ZPgh-TILAz0DeIwDxRCsj980CM2BbftXiFpM1dV_Y,21674
 datahub/ingestion/source/snowflake/snowflake_schema_gen.py,sha256=3AxvKfK9WV9x2f2XNuJ-Cmy4szmXKm1Ky0haRVvyC6w,42340
 datahub/ingestion/source/snowflake/snowflake_shares.py,sha256=maZyFkfrbVogEFM0tTKRiNp9c_1muv6YfleSd3q0umI,6341
 datahub/ingestion/source/snowflake/snowflake_summary.py,sha256=kTmuCtRnvHqM8WBYhWeK4XafJq3ssFL9kcS03jEeWT4,5506
 datahub/ingestion/source/snowflake/snowflake_tag.py,sha256=fyfWmFVz2WZrpTJWNIe9m0WpDHgeFrGPf8diORJZUwo,6212
-datahub/ingestion/source/snowflake/snowflake_usage_v2.py,sha256=PEmYNMXJRUvLQmVd8juVqjokfuSPuH9ppcM0ruXamxA,24807
-datahub/ingestion/source/snowflake/snowflake_utils.py,sha256=YczNEupY89jeegjR2_1pT4bPi9wQ69EIhGpzyCe9Jdg,12600
+datahub/ingestion/source/snowflake/snowflake_usage_v2.py,sha256=0rXgz8bvRiI9SYVMa0UGLeg_DcjqBy6kQsdq0Uq0HVk,24685
+datahub/ingestion/source/snowflake/snowflake_utils.py,sha256=MoI8-DR9tuMuHMBQcpDo4GFjvcoQZWLNkdFZsTkgK-M,12786
 datahub/ingestion/source/snowflake/snowflake_v2.py,sha256=hIWtzlxuSQ_3w48o4AF2l9CQOcWIe6AmD07I89sH2B0,31860
 datahub/ingestion/source/sql/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 datahub/ingestion/source/sql/athena.py,sha256=G3cIY8H_76lIUAzQWW2kLnZOEsfbakmojxbiHb3dYZ8,24059
@@ -517,7 +517,7 @@ datahub/ingestion/source_config/csv_enricher.py,sha256=IROxxfFJA56dHkmmbjjhb7h1p
 datahub/ingestion/source_config/operation_config.py,sha256=Q0NlqiEh4s4DFIII5NsAp5hxWTVyyJz-ldcQmH-B47s,3504
 datahub/ingestion/source_config/pulsar.py,sha256=sklDkh62CrWV-i7Ifh6R3T3smYVso6gyRJG8HVc6RdA,5533
 datahub/ingestion/source_report/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-datahub/ingestion/source_report/ingestion_stage.py,sha256=w6qTnJm_-eoTiGxwS7cFnhdIfsv8omC6H5e0qw5t4Jc,1587
+datahub/ingestion/source_report/ingestion_stage.py,sha256=gbYmnio3fAOsjh_RzU3j_5UGu7bYBwUM4bm7S8ID_IU,1649
 datahub/ingestion/source_report/pulsar.py,sha256=iKhzy644AjoFTV-gxyqBoXKMLwSMPxJFxU-3WDQRww0,1037
 datahub/ingestion/source_report/time_window.py,sha256=9yI5l2S1DcF7ClvUHLeN8m62I5vlhV9k-aQqSZh2l7w,229
 datahub/ingestion/transformer/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -982,8 +982,8 @@ datahub_provider/operators/datahub_assertion_operator.py,sha256=uvTQ-jk2F0sbqqxp
 datahub_provider/operators/datahub_assertion_sensor.py,sha256=lCBj_3x1cf5GMNpHdfkpHuyHfVxsm6ff5x2Z5iizcAo,140
 datahub_provider/operators/datahub_operation_operator.py,sha256=aevDp2FzX7FxGlXrR0khoHNbxbhKR2qPEX5e8O2Jyzw,174
 datahub_provider/operators/datahub_operation_sensor.py,sha256=8fcdVBCEPgqy1etTXgLoiHoJrRt_nzFZQMdSzHqSG7M,168
-acryl_datahub-0.15.0.1rc8.dist-info/METADATA,sha256=mW2V4Czvd-ZE_mUJX8XkNZxNwnBa-gLJxebl0KWsM2A,173642
-acryl_datahub-0.15.0.1rc8.dist-info/WHEEL,sha256=PZUExdf71Ui_so67QXpySuHtCi3-J3wvF4ORK6k_S8U,91
-acryl_datahub-0.15.0.1rc8.dist-info/entry_points.txt,sha256=xnPSPLK3bJGADxe4TDS4wL4u0FT_PGlahDa-ENYdYCQ,9512
-acryl_datahub-0.15.0.1rc8.dist-info/top_level.txt,sha256=iLjSrLK5ox1YVYcglRUkcvfZPvKlobBWx7CTUXx8_GI,25
-acryl_datahub-0.15.0.1rc8.dist-info/RECORD,,
+acryl_datahub-0.15.0.1rc10.dist-info/METADATA,sha256=GCgEH25gXF0roGuAivBGRw1IyiBv_Xv4wbWj9jGlpIo,173645
+acryl_datahub-0.15.0.1rc10.dist-info/WHEEL,sha256=PZUExdf71Ui_so67QXpySuHtCi3-J3wvF4ORK6k_S8U,91
+acryl_datahub-0.15.0.1rc10.dist-info/entry_points.txt,sha256=xnPSPLK3bJGADxe4TDS4wL4u0FT_PGlahDa-ENYdYCQ,9512
+acryl_datahub-0.15.0.1rc10.dist-info/top_level.txt,sha256=iLjSrLK5ox1YVYcglRUkcvfZPvKlobBWx7CTUXx8_GI,25
+acryl_datahub-0.15.0.1rc10.dist-info/RECORD,,

datahub/__init__.py

@@ -3,7 +3,7 @@ import warnings
 
 # Published at https://pypi.org/project/acryl-datahub/.
 __package_name__ = "acryl-datahub"
-__version__ = "0.15.0.1rc8"
+__version__ = "0.15.0.1rc10"
 
 
 def is_dev_mode() -> bool:

datahub/ingestion/source/aws/glue.py

@@ -52,6 +52,7 @@ from datahub.ingestion.api.decorators import (
     platform_name,
     support_status,
 )
+from datahub.ingestion.api.report import EntityFilterReport
 from datahub.ingestion.api.source import MetadataWorkUnitProcessor
 from datahub.ingestion.api.workunit import MetadataWorkUnit
 from datahub.ingestion.source.aws import s3_util
@@ -115,7 +116,6 @@ from datahub.utilities.hive_schema_to_avro import get_schema_fields_for_hive_col
 
 logger = logging.getLogger(__name__)
 
-
 DEFAULT_PLATFORM = "glue"
 VALID_PLATFORMS = [DEFAULT_PLATFORM, "athena"]
 
@@ -220,6 +220,7 @@ class GlueSourceConfig(
 class GlueSourceReport(StaleEntityRemovalSourceReport):
     tables_scanned = 0
     filtered: List[str] = dataclass_field(default_factory=list)
+    databases: EntityFilterReport = EntityFilterReport.field(type="database")
 
     num_job_script_location_missing: int = 0
     num_job_script_location_invalid: int = 0
@@ -668,6 +669,7 @@ class GlueSource(StatefulIngestionSourceBase):
         return MetadataWorkUnit(id=f'{job_name}-{node["Id"]}', mce=mce)
 
     def get_all_databases(self) -> Iterable[Mapping[str, Any]]:
+        logger.debug("Getting all databases")
         # see https://boto3.amazonaws.com/v1/documentation/api/latest/reference/services/glue/paginator/GetDatabases.html
         paginator = self.glue_client.get_paginator("get_databases")
 
@@ -684,10 +686,18 @@ class GlueSource(StatefulIngestionSourceBase):
             pattern += "[?!TargetDatabase]"
 
         for database in paginator_response.search(pattern):
-            if self.source_config.database_pattern.allowed(database["Name"]):
+            if (not self.source_config.database_pattern.allowed(database["Name"])) or (
+                self.source_config.catalog_id
+                and database.get("CatalogId")
+                and database.get("CatalogId") != self.source_config.catalog_id
+            ):
+                self.report.databases.dropped(database["Name"])
+            else:
+                self.report.databases.processed(database["Name"])
                 yield database
 
     def get_tables_from_database(self, database: Mapping[str, Any]) -> Iterable[Dict]:
+        logger.debug(f"Getting tables from database {database['Name']}")
         # see https://boto3.amazonaws.com/v1/documentation/api/latest/reference/services/glue/paginator/GetTables.html
         paginator = self.glue_client.get_paginator("get_tables")
         database_name = database["Name"]

datahub/ingestion/source/dbt/dbt_cloud.py

@@ -1,7 +1,7 @@
 import logging
 from datetime import datetime
 from json import JSONDecodeError
-from typing import Dict, List, Optional, Tuple
+from typing import Dict, List, Literal, Optional, Tuple
 from urllib.parse import urlparse
 
 import dateutil.parser
@@ -62,6 +62,11 @@ class DBTCloudConfig(DBTCommonConfig):
         description="The ID of the run to ingest metadata from. If not specified, we'll default to the latest run.",
     )
 
+    external_url_mode: Literal["explore", "ide"] = Field(
+        default="explore",
+        description='Where should the "View in dbt" link point to - either the "Explore" UI or the dbt Cloud IDE',
+    )
+
     @root_validator(pre=True)
     def set_metadata_endpoint(cls, values: dict) -> dict:
         if values.get("access_url") and not values.get("metadata_endpoint"):
@@ -527,5 +532,7 @@ class DBTCloudSource(DBTSourceBase, TestableSource):
         )
 
     def get_external_url(self, node: DBTNode) -> Optional[str]:
-        # TODO: Once dbt Cloud supports deep linking to specific files, we can use that.
-        return f"{self.config.access_url}/develop/{self.config.account_id}/projects/{self.config.project_id}"
+        if self.config.external_url_mode == "explore":
+            return f"{self.config.access_url}/explore/{self.config.account_id}/projects/{self.config.project_id}/environments/production/details/{node.dbt_name}"
+        else:
+            return f"{self.config.access_url}/develop/{self.config.account_id}/projects/{self.config.project_id}"

datahub/ingestion/source/gc/datahub_gc.py

@@ -34,6 +34,7 @@ from datahub.ingestion.source.gc.soft_deleted_entity_cleanup import (
     SoftDeletedEntitiesCleanupConfig,
     SoftDeletedEntitiesReport,
 )
+from datahub.ingestion.source_report.ingestion_stage import IngestionStageReport
 
 logger = logging.getLogger(__name__)
 
@@ -86,6 +87,7 @@ class DataHubGcSourceReport(
     DataProcessCleanupReport,
     SoftDeletedEntitiesReport,
     DatahubExecutionRequestCleanupReport,
+    IngestionStageReport,
 ):
     expired_tokens_revoked: int = 0
 
@@ -139,31 +141,40 @@ class DataHubGcSource(Source):
     ) -> Iterable[MetadataWorkUnit]:
         if self.config.cleanup_expired_tokens:
             try:
+                self.report.report_ingestion_stage_start("Expired Token Cleanup")
                 self.revoke_expired_tokens()
             except Exception as e:
                 self.report.failure("While trying to cleanup expired token ", exc=e)
         if self.config.truncate_indices:
             try:
+                self.report.report_ingestion_stage_start("Truncate Indices")
                 self.truncate_indices()
             except Exception as e:
                 self.report.failure("While trying to truncate indices ", exc=e)
         if self.config.soft_deleted_entities_cleanup.enabled:
             try:
+                self.report.report_ingestion_stage_start(
+                    "Soft Deleted Entities Cleanup"
+                )
                 self.soft_deleted_entities_cleanup.cleanup_soft_deleted_entities()
             except Exception as e:
                 self.report.failure(
                     "While trying to cleanup soft deleted entities ", exc=e
                 )
-        if self.config.execution_request_cleanup.enabled:
-            try:
-                self.execution_request_cleanup.run()
-            except Exception as e:
-                self.report.failure("While trying to cleanup execution request ", exc=e)
         if self.config.dataprocess_cleanup.enabled:
             try:
+                self.report.report_ingestion_stage_start("Data Process Cleanup")
                 yield from self.dataprocess_cleanup.get_workunits_internal()
             except Exception as e:
                 self.report.failure("While trying to cleanup data process ", exc=e)
+        if self.config.execution_request_cleanup.enabled:
+            try:
+                self.report.report_ingestion_stage_start("Execution request Cleanup")
+                self.execution_request_cleanup.run()
+            except Exception as e:
+                self.report.failure("While trying to cleanup execution request ", exc=e)
+        # Otherwise last stage's duration does not get calculated.
+        self.report.report_ingestion_stage_start("End")
         yield from []
 
     def truncate_indices(self) -> None:
@@ -281,6 +292,8 @@ class DataHubGcSource(Source):
             list_access_tokens = expired_tokens_res.get("listAccessTokens", {})
             tokens = list_access_tokens.get("tokens", [])
             total = list_access_tokens.get("total", 0)
+            if tokens == []:
+                break
             for token in tokens:
                 self.report.expired_tokens_revoked += 1
                 token_id = token["id"]

datahub/ingestion/source/gc/execution_request_cleanup.py

@@ -1,3 +1,4 @@
+import datetime
 import logging
 import time
 from typing import Any, Dict, Iterator, Optional
@@ -42,16 +43,28 @@ class DatahubExecutionRequestCleanupConfig(ConfigModel):
         description="Global switch for this cleanup task",
     )
 
+    runtime_limit_seconds: int = Field(
+        default=3600,
+        description="Maximum runtime in seconds for the cleanup task",
+    )
+
+    max_read_errors: int = Field(
+        default=10,
+        description="Maximum number of read errors before aborting",
+    )
+
     def keep_history_max_milliseconds(self):
         return self.keep_history_max_days * 24 * 3600 * 1000
 
 
 class DatahubExecutionRequestCleanupReport(SourceReport):
-    execution_request_cleanup_records_read: int = 0
-    execution_request_cleanup_records_preserved: int = 0
-    execution_request_cleanup_records_deleted: int = 0
-    execution_request_cleanup_read_errors: int = 0
-    execution_request_cleanup_delete_errors: int = 0
+    ergc_records_read: int = 0
+    ergc_records_preserved: int = 0
+    ergc_records_deleted: int = 0
+    ergc_read_errors: int = 0
+    ergc_delete_errors: int = 0
+    ergc_start_time: Optional[datetime.datetime] = None
+    ergc_end_time: Optional[datetime.datetime] = None
 
 
 class CleanupRecord(BaseModel):
@@ -124,6 +137,13 @@ class DatahubExecutionRequestCleanup:
         params.update(overrides)
 
         while True:
+            if self._reached_runtime_limit():
+                break
+            if self.report.ergc_read_errors >= self.config.max_read_errors:
+                self.report.failure(
+                    f"ergc({self.instance_id}): too many read errors, aborting."
+                )
+                break
             try:
                 url = f"{self.graph.config.server}/openapi/v2/entity/{DATAHUB_EXECUTION_REQUEST_ENTITY_NAME}"
                 response = self.graph._session.get(url, headers=headers, params=params)
@@ -141,7 +161,7 @@ class DatahubExecutionRequestCleanup:
                 logger.error(
                     f"ergc({self.instance_id}): failed to fetch next batch of execution requests: {e}"
                 )
-                self.report.execution_request_cleanup_read_errors += 1
+                self.report.ergc_read_errors += 1
 
     def _scroll_garbage_records(self):
         state: Dict[str, Dict] = {}
@@ -150,7 +170,7 @@ class DatahubExecutionRequestCleanup:
         running_guard_timeout = now_ms - 30 * 24 * 3600 * 1000
 
         for entry in self._scroll_execution_requests():
-            self.report.execution_request_cleanup_records_read += 1
+            self.report.ergc_records_read += 1
             key = entry.ingestion_source
 
             # Always delete corrupted records
@@ -171,7 +191,7 @@ class DatahubExecutionRequestCleanup:
 
             # Do not delete if number of requests is below minimum
             if state[key]["count"] < self.config.keep_history_min_count:
-                self.report.execution_request_cleanup_records_preserved += 1
+                self.report.ergc_records_preserved += 1
                 continue
 
             # Do not delete if number of requests do not exceed allowed maximum,
@@ -179,7 +199,7 @@ class DatahubExecutionRequestCleanup:
             if (state[key]["count"] < self.config.keep_history_max_count) and (
                 entry.requested_at > state[key]["cutoffTimestamp"]
             ):
-                self.report.execution_request_cleanup_records_preserved += 1
+                self.report.ergc_records_preserved += 1
                 continue
 
             # Do not delete if status is RUNNING or PENDING and created within last month. If the record is >month old and it did not
@@ -188,7 +208,7 @@ class DatahubExecutionRequestCleanup:
                 "RUNNING",
                 "PENDING",
             ]:
-                self.report.execution_request_cleanup_records_preserved += 1
+                self.report.ergc_records_preserved += 1
                 continue
 
             # Otherwise delete current record
@@ -200,7 +220,7 @@ class DatahubExecutionRequestCleanup:
                     f"record timestamp: {entry.requested_at}."
                 )
             )
-            self.report.execution_request_cleanup_records_deleted += 1
+            self.report.ergc_records_deleted += 1
             yield entry
 
     def _delete_entry(self, entry: CleanupRecord) -> None:
@@ -210,17 +230,31 @@ class DatahubExecutionRequestCleanup:
             )
             self.graph.delete_entity(entry.urn, True)
         except Exception as e:
-            self.report.execution_request_cleanup_delete_errors += 1
+            self.report.ergc_delete_errors += 1
             logger.error(
                 f"ergc({self.instance_id}): failed to delete ExecutionRequest {entry.request_id}: {e}"
             )
 
+    def _reached_runtime_limit(self) -> bool:
+        if (
+            self.config.runtime_limit_seconds
+            and self.report.ergc_start_time
+            and (
+                datetime.datetime.now() - self.report.ergc_start_time
+                >= datetime.timedelta(seconds=self.config.runtime_limit_seconds)
+            )
+        ):
+            logger.info(f"ergc({self.instance_id}): max runtime reached.")
+            return True
+        return False
+
     def run(self) -> None:
         if not self.config.enabled:
             logger.info(
                 f"ergc({self.instance_id}): ExecutionRequest cleaner is disabled."
             )
             return
+        self.report.ergc_start_time = datetime.datetime.now()
 
         logger.info(
             (
@@ -232,8 +266,11 @@ class DatahubExecutionRequestCleanup:
         )
 
         for entry in self._scroll_garbage_records():
+            if self._reached_runtime_limit():
+                break
             self._delete_entry(entry)
 
+        self.report.ergc_end_time = datetime.datetime.now()
         logger.info(
             f"ergc({self.instance_id}): Finished cleanup of ExecutionRequest records."
         )

datahub/ingestion/source/looker/looker_dataclasses.py

@@ -186,16 +186,16 @@ class LookerModel:
                 f"traversal_path={traversal_path}, included_files = {included_files}, seen_so_far: {seen_so_far}"
             )
             if "*" not in inc and not included_files:
-                reporter.report_failure(
+                reporter.warning(
                     title="Error Resolving Include",
-                    message=f"Cannot resolve include {inc}",
-                    context=f"Path: {path}",
+                    message="Cannot resolve included file",
+                    context=f"Include: {inc}, path: {path}, traversal_path: {traversal_path}",
                 )
             elif not included_files:
-                reporter.report_failure(
+                reporter.warning(
                     title="Error Resolving Include",
-                    message=f"Did not resolve anything for wildcard include {inc}",
-                    context=f"Path: {path}",
+                    message="Did not find anything matching the wildcard include",
+                    context=f"Include: {inc}, path: {path}, traversal_path: {traversal_path}",
                 )
             # only load files that we haven't seen so far
             included_files = [x for x in included_files if x not in seen_so_far]
@@ -231,9 +231,7 @@ class LookerModel:
                                 source_config,
                                 reporter,
                                 seen_so_far,
-                                traversal_path=traversal_path
-                                + "."
-                                + pathlib.Path(included_file).stem,
+                                traversal_path=f"{traversal_path} -> {pathlib.Path(included_file).stem}",
                             )
                         )
                 except Exception as e:

datahub/ingestion/source/powerbi/rest_api_wrapper/data_resolver.py

@@ -84,13 +84,14 @@ class DataResolverBase(ABC):
         tenant_id: str,
         metadata_api_timeout: int,
     ):
-        self.__access_token: Optional[str] = None
-        self.__access_token_expiry_time: Optional[datetime] = None
-        self.__tenant_id = tenant_id
+        self._access_token: Optional[str] = None
+        self._access_token_expiry_time: Optional[datetime] = None
+
+        self._tenant_id = tenant_id
         # Test connection by generating access token
         logger.info(f"Trying to connect to {self._get_authority_url()}")
         # Power-Bi Auth (Service Principal Auth)
-        self.__msal_client = msal.ConfidentialClientApplication(
+        self._msal_client = msal.ConfidentialClientApplication(
             client_id,
             client_credential=client_secret,
             authority=DataResolverBase.AUTHORITY + tenant_id,
@@ -168,18 +169,18 @@ class DataResolverBase(ABC):
         pass
 
     def _get_authority_url(self):
-        return f"{DataResolverBase.AUTHORITY}{self.__tenant_id}"
+        return f"{DataResolverBase.AUTHORITY}{self._tenant_id}"
 
     def get_authorization_header(self):
         return {Constant.Authorization: self.get_access_token()}
 
-    def get_access_token(self):
-        if self.__access_token is not None and not self._is_access_token_expired():
-            return self.__access_token
+    def get_access_token(self) -> str:
+        if self._access_token is not None and not self._is_access_token_expired():
+            return self._access_token
 
         logger.info("Generating PowerBi access token")
 
-        auth_response = self.__msal_client.acquire_token_for_client(
+        auth_response = self._msal_client.acquire_token_for_client(
             scopes=[DataResolverBase.SCOPE]
         )
 
@@ -193,24 +194,24 @@ class DataResolverBase(ABC):
 
         logger.info("Generated PowerBi access token")
 
-        self.__access_token = "Bearer {}".format(
+        self._access_token = "Bearer {}".format(
             auth_response.get(Constant.ACCESS_TOKEN)
         )
         safety_gap = 300
-        self.__access_token_expiry_time = datetime.now() + timedelta(
+        self._access_token_expiry_time = datetime.now() + timedelta(
             seconds=(
                 max(auth_response.get(Constant.ACCESS_TOKEN_EXPIRY, 0) - safety_gap, 0)
             )
         )
 
-        logger.debug(f"{Constant.PBIAccessToken}={self.__access_token}")
+        logger.debug(f"{Constant.PBIAccessToken}={self._access_token}")
 
-        return self.__access_token
+        return self._access_token
 
     def _is_access_token_expired(self) -> bool:
-        if not self.__access_token_expiry_time:
+        if not self._access_token_expiry_time:
             return True
-        return self.__access_token_expiry_time < datetime.now()
+        return self._access_token_expiry_time < datetime.now()
 
     def get_dashboards(self, workspace: Workspace) -> List[Dashboard]:
         """

datahub/ingestion/source/snowflake/snowflake_config.py

@@ -138,12 +138,20 @@ class SnowflakeIdentifierConfig(
         description="Whether to convert dataset urns to lowercase.",
     )
 
-
-class SnowflakeUsageConfig(BaseUsageConfig):
     email_domain: Optional[str] = pydantic.Field(
         default=None,
         description="Email domain of your organization so users can be displayed on UI appropriately.",
     )
+
+    email_as_user_identifier: bool = Field(
+        default=True,
+        description="Format user urns as an email, if the snowflake user's email is set. If `email_domain` is "
+        "provided, generates email addresses for snowflake users with unset emails, based on their "
+        "username.",
+    )
+
+
+class SnowflakeUsageConfig(BaseUsageConfig):
     apply_view_usage_to_tables: bool = pydantic.Field(
         default=False,
         description="Whether to apply view's usage to its base tables. If set to True, usage is applied to base tables only.",
@@ -267,13 +275,6 @@ class SnowflakeV2Config(
         " Map of share name -> details of share.",
     )
 
-    email_as_user_identifier: bool = Field(
-        default=True,
-        description="Format user urns as an email, if the snowflake user's email is set. If `email_domain` is "
-        "provided, generates email addresses for snowflake users with unset emails, based on their "
-        "username.",
-    )
-
     include_assertion_results: bool = Field(
         default=False,
         description="Whether to ingest assertion run results for assertions created using Datahub"