acryl-datahub 1.1.0.3rc2__py3-none-any.whl → 1.1.0.4rc2__py3-none-any.whl

datahub/ingestion/graph/client.py

@@ -906,6 +906,7 @@ class DataHubGraph(DatahubRestEmitter, EntityVersioningAPI):
         batch_size: int = 5000,
         extraFilters: Optional[List[RawSearchFilterRule]] = None,
         extra_or_filters: Optional[RawSearchFilter] = None,
+        skip_cache: bool = False,
     ) -> Iterable[str]:
         """Fetch all urns that match all of the given filters.
 
@@ -924,6 +925,7 @@ class DataHubGraph(DatahubRestEmitter, EntityVersioningAPI):
             Note that this requires browsePathV2 aspects (added in 0.10.4+).
         :param status: Filter on the deletion status of the entity. The default is only return non-soft-deleted entities.
         :param extraFilters: Additional filters to apply. If specified, the results will match all of the filters.
+        :param skip_cache: Whether to bypass caching. Defaults to False.
 
         :return: An iterable of urns that match the filters.
         """
@@ -951,7 +953,8 @@ class DataHubGraph(DatahubRestEmitter, EntityVersioningAPI):
                 $query: String!,
                 $orFilters: [AndFilterInput!],
                 $batchSize: Int!,
-                $scrollId: String) {
+                $scrollId: String,
+                $skipCache: Boolean!) {
 
                 scrollAcrossEntities(input: {
                     query: $query,
@@ -962,6 +965,7 @@ class DataHubGraph(DatahubRestEmitter, EntityVersioningAPI):
                     searchFlags: {
                         skipHighlighting: true
                         skipAggregates: true
+                        skipCache: $skipCache
                     }
                 }) {
                     nextScrollId
@@ -980,6 +984,7 @@ class DataHubGraph(DatahubRestEmitter, EntityVersioningAPI):
             "query": query,
             "orFilters": orFilters,
             "batchSize": batch_size,
+            "skipCache": skip_cache,
         }
 
         for entity in self._scroll_across_entities(graphql_query, variables):
@@ -1085,7 +1090,7 @@ class DataHubGraph(DatahubRestEmitter, EntityVersioningAPI):
             "query": query,
             "orFilters": or_filters_final,
             "batchSize": batch_size,
-            "skipCache": "true" if skip_cache else "false",
+            "skipCache": skip_cache,
             "fetchExtraFields": extra_source_fields,
         }
 
@@ -1429,6 +1434,41 @@ class DataHubGraph(DatahubRestEmitter, EntityVersioningAPI):
         related_aspects = response.get("relatedAspects", [])
         return reference_count, related_aspects
 
+    def restore_indices(
+        self,
+        urn_pattern: str,
+        aspect: Optional[str] = None,
+        start: Optional[int] = None,
+        batch_size: Optional[int] = None,
+    ) -> str:
+        """Restore the indices for a given urn or urn-like pattern.
+
+        Args:
+            urn_pattern: The exact URN or a pattern (with % for wildcard) to match URNs.
+            aspect: Optional aspect string to restore indices for a specific aspect.
+            start: Optional integer to decide which row number of sql store to restore from. Default: 0.
+            batch_size: Optional integer to decide how many rows to restore. Default: 10.
+
+        Returns:
+            A string containing the result of the restore indices operation. This format is subject to change.
+        """
+        if "%" in urn_pattern:
+            payload_obj: dict = {"urnLike": urn_pattern}
+        else:
+            payload_obj = {"urn": urn_pattern}
+        if aspect is not None:
+            payload_obj["aspect"] = aspect
+        if start is not None:
+            payload_obj["start"] = start
+        if batch_size is not None:
+            payload_obj["batchSize"] = batch_size
+        raw_result = self._post_generic(
+            f"{self._gms_server}/operations?action=restoreIndices", payload_obj
+        )
+        result = raw_result["value"]
+        logger.debug(f"Restore indices result: {result}")
+        return result
+
     @functools.lru_cache
     def _make_schema_resolver(
         self,

datahub/ingestion/source/bigquery_v2/bigquery.py

@@ -99,6 +99,7 @@ def cleanup(config: BigQueryV2Config) -> None:
     SourceCapability.PARTITION_SUPPORT,
     "Enabled by default, partition keys and clustering keys are supported.",
 )
+@capability(SourceCapability.TEST_CONNECTION, "Enabled by default")
 class BigqueryV2Source(StatefulIngestionSourceBase, TestableSource):
     def __init__(self, ctx: PipelineContext, config: BigQueryV2Config):
         super().__init__(config, ctx)

datahub/ingestion/source/bigquery_v2/common.py

@@ -63,7 +63,7 @@ class BigQueryIdentifierBuilder:
         )
 
     def gen_user_urn(self, user_email: str) -> str:
-        return make_user_urn(user_email.split("@")[0])
+        return make_user_urn(user_email)
 
     def make_data_platform_urn(self) -> str:
         return make_data_platform_urn(self.platform)

datahub/ingestion/source/dbt/dbt_cloud.py

@@ -9,7 +9,9 @@ import requests
 from pydantic import Field, root_validator
 
 from datahub.ingestion.api.decorators import (
+    SourceCapability,
     SupportStatus,
+    capability,
     config_class,
     platform_name,
     support_status,
@@ -261,6 +263,7 @@ query DatahubMetadataQuery_{type}($jobId: BigInt!, $runId: BigInt) {{
 @platform_name("dbt")
 @config_class(DBTCloudConfig)
 @support_status(SupportStatus.CERTIFIED)
+@capability(SourceCapability.TEST_CONNECTION, "Enabled by default")
 class DBTCloudSource(DBTSourceBase, TestableSource):
     config: DBTCloudConfig
 

datahub/ingestion/source/dbt/dbt_common.py

@@ -823,7 +823,9 @@ def get_column_type(
 @platform_name("dbt")
 @config_class(DBTCommonConfig)
 @support_status(SupportStatus.CERTIFIED)
-@capability(SourceCapability.DELETION_DETECTION, "Enabled via stateful ingestion")
+@capability(
+    SourceCapability.DELETION_DETECTION, "Enabled by default via stateful ingestion"
+)
 @capability(SourceCapability.LINEAGE_COARSE, "Enabled by default")
 @capability(
     SourceCapability.LINEAGE_FINE,

datahub/ingestion/source/dbt/dbt_core.py

@@ -15,7 +15,9 @@ from datahub.configuration.git import GitReference
 from datahub.configuration.validate_field_rename import pydantic_renamed_field
 from datahub.ingestion.api.common import PipelineContext
 from datahub.ingestion.api.decorators import (
+    SourceCapability,
     SupportStatus,
+    capability,
     config_class,
     platform_name,
     support_status,
@@ -464,6 +466,7 @@ def load_run_results(
 @platform_name("dbt")
 @config_class(DBTCoreConfig)
 @support_status(SupportStatus.CERTIFIED)
+@capability(SourceCapability.TEST_CONNECTION, "Enabled by default")
 class DBTCoreSource(DBTSourceBase, TestableSource):
     config: DBTCoreConfig
     report: DBTCoreReport

datahub/ingestion/source/file.py

@@ -18,7 +18,9 @@ from datahub.configuration.validate_field_rename import pydantic_renamed_field
 from datahub.emitter.mcp import MetadataChangeProposalWrapper
 from datahub.ingestion.api.common import PipelineContext
 from datahub.ingestion.api.decorators import (
+    SourceCapability,
     SupportStatus,
+    capability,
     config_class,
     platform_name,
     support_status,
@@ -187,6 +189,7 @@ class FileSourceReport(StaleEntityRemovalSourceReport):
 @platform_name("Metadata File")
 @config_class(FileSourceConfig)
 @support_status(SupportStatus.CERTIFIED)
+@capability(SourceCapability.TEST_CONNECTION, "Enabled by default")
 class GenericFileSource(StatefulIngestionSourceBase, TestableSource):
     """
     This plugin pulls metadata from a previously generated file.

datahub/ingestion/source/ge_profiling_config.py

@@ -125,6 +125,7 @@ class GEProfilingConfig(GEProfilingBaseConfig):
         description="Profile table only if it has been updated since these many number of days. "
         "If set to `null`, no constraint of last modified time for tables to profile. "
         "Supported only in `snowflake` and `BigQuery`.",
+        schema_extra={"supported_sources": ["snowflake", "bigquery"]},
     )
 
     profile_table_size_limit: Optional[int] = Field(
@@ -132,6 +133,9 @@ class GEProfilingConfig(GEProfilingBaseConfig):
         description="Profile tables only if their size is less than specified GBs. If set to `null`, "
         "no limit on the size of tables to profile. Supported only in `Snowflake`, `BigQuery` and "
         "`Databricks`. Supported for `Oracle` based on calculated size from gathered stats.",
+        schema_extra={
+            "supported_sources": ["snowflake", "bigquery", "unity-catalog", "oracle"]
+        },
     )
 
     profile_table_row_limit: Optional[int] = Field(
@@ -139,12 +143,14 @@ class GEProfilingConfig(GEProfilingBaseConfig):
         description="Profile tables only if their row count is less than specified count. "
         "If set to `null`, no limit on the row count of tables to profile. Supported only in "
         "`Snowflake`, `BigQuery`. Supported for `Oracle` based on gathered stats.",
+        schema_extra={"supported_sources": ["snowflake", "bigquery", "oracle"]},
     )
 
     profile_table_row_count_estimate_only: bool = Field(
         default=False,
         description="Use an approximate query for row count. This will be much faster but slightly "
         "less accurate. Only supported for Postgres and MySQL. ",
+        schema_extra={"supported_sources": ["postgres", "mysql"]},
     )
 
     # The query combiner enables us to combine multiple queries into a single query,
@@ -161,27 +167,32 @@ class GEProfilingConfig(GEProfilingBaseConfig):
         default=True,
         description="Whether to profile partitioned tables. Only BigQuery and Aws Athena supports this. "
         "If enabled, latest partition data is used for profiling.",
+        schema_extra={"supported_sources": ["athena", "bigquery"]},
     )
     partition_datetime: Optional[datetime.datetime] = Field(
         default=None,
         description="If specified, profile only the partition which matches this datetime. "
         "If not specified, profile the latest partition. Only Bigquery supports this.",
+        schema_extra={"supported_sources": ["bigquery"]},
     )
     use_sampling: bool = Field(
         default=True,
         description="Whether to profile column level stats on sample of table. Only BigQuery and Snowflake support this. "
         "If enabled, profiling is done on rows sampled from table. Sampling is not done for smaller tables. ",
+        schema_extra={"supported_sources": ["bigquery", "snowflake"]},
     )
 
     sample_size: int = Field(
         default=10000,
         description="Number of rows to be sampled from table for column level profiling."
         "Applicable only if `use_sampling` is set to True.",
+        schema_extra={"supported_sources": ["bigquery", "snowflake"]},
     )
 
     profile_external_tables: bool = Field(
         default=False,
         description="Whether to profile external tables. Only Snowflake and Redshift supports this.",
+        schema_extra={"supported_sources": ["redshift", "snowflake"]},
     )
 
     tags_to_ignore_sampling: Optional[List[str]] = pydantic.Field(

datahub/ingestion/source/iceberg/iceberg.py

@@ -134,7 +134,9 @@ logging.getLogger("azure.core.pipeline.policies.http_logging_policy").setLevel(
     SourceCapability.OWNERSHIP,
     "Automatically ingests ownership information from table properties based on `user_ownership_property` and `group_ownership_property`",
 )
-@capability(SourceCapability.DELETION_DETECTION, "Enabled via stateful ingestion")
+@capability(
+    SourceCapability.DELETION_DETECTION, "Enabled by default via stateful ingestion"
+)
 class IcebergSource(StatefulIngestionSourceBase):
     """
     ## Integration Details

datahub/ingestion/source/kafka/kafka.py

@@ -189,6 +189,22 @@ class KafkaConnectionTest:
     SourceCapability.SCHEMA_METADATA,
     "Schemas associated with each topic are extracted from the schema registry. Avro and Protobuf (certified), JSON (incubating). Schema references are supported.",
 )
+@capability(
+    SourceCapability.DATA_PROFILING,
+    "Not supported",
+    supported=False,
+)
+@capability(
+    SourceCapability.LINEAGE_COARSE,
+    "Not supported. If you use Kafka Connect, the kafka-connect source can generate lineage.",
+    supported=False,
+)
+@capability(
+    SourceCapability.LINEAGE_FINE,
+    "Not supported",
+    supported=False,
+)
+@capability(SourceCapability.TEST_CONNECTION, "Enabled by default")
 class KafkaSource(StatefulIngestionSourceBase, TestableSource):
     """
     This plugin extracts the following:

datahub/ingestion/source/looker/looker_source.py

@@ -126,6 +126,7 @@ logger = logging.getLogger(__name__)
     SourceCapability.USAGE_STATS,
     "Enabled by default, configured using `extract_usage_history`",
 )
+@capability(SourceCapability.TEST_CONNECTION, "Enabled by default")
 class LookerDashboardSource(TestableSource, StatefulIngestionSourceBase):
     """
     This plugin extracts the following:

datahub/ingestion/source/powerbi/powerbi.py

@@ -1253,6 +1253,7 @@ class Mapper:
     SourceCapability.DATA_PROFILING,
     "Optionally enabled via configuration profiling.enabled",
 )
+@capability(SourceCapability.TEST_CONNECTION, "Enabled by default")
 class PowerBiDashboardSource(StatefulIngestionSourceBase, TestableSource):
     """
     This plugin extracts the following:

datahub/ingestion/source/qlik_sense/qlik_sense.py

@@ -109,6 +109,7 @@ logger = logging.getLogger(__name__)
     "Enabled by default, configured using `ingest_owner`",
 )
 @capability(SourceCapability.SCHEMA_METADATA, "Enabled by default")
+@capability(SourceCapability.TEST_CONNECTION, "Enabled by default")
 class QlikSenseSource(StatefulIngestionSourceBase, TestableSource):
     """
     This plugin extracts the following:

datahub/ingestion/source/redshift/redshift.py

@@ -140,12 +140,15 @@ logger: logging.Logger = logging.getLogger(__name__)
     SourceCapability.USAGE_STATS,
     "Enabled by default, can be disabled via configuration `include_usage_statistics`",
 )
-@capability(SourceCapability.DELETION_DETECTION, "Enabled via stateful ingestion")
+@capability(
+    SourceCapability.DELETION_DETECTION, "Enabled by default via stateful ingestion"
+)
 @capability(
     SourceCapability.CLASSIFICATION,
     "Optionally enabled via `classification.enabled`",
     supported=True,
 )
+@capability(SourceCapability.TEST_CONNECTION, "Enabled by default")
 class RedshiftSource(StatefulIngestionSourceBase, TestableSource):
     """
     This plugin extracts the following:

datahub/ingestion/source/sac/sac.py

@@ -178,7 +178,9 @@ class SACSourceReport(StaleEntityRemovalSourceReport):
     SourceCapability.LINEAGE_COARSE,
     "Enabled by default (only for Live Data Models)",
 )
-@capability(SourceCapability.DELETION_DETECTION, "Enabled via stateful ingestion")
+@capability(
+    SourceCapability.DELETION_DETECTION, "Enabled by default via stateful ingestion"
+)
 @capability(
     SourceCapability.SCHEMA_METADATA,
     "Enabled by default (only for Import Data Models)",

datahub/ingestion/source/sigma/sigma.py

@@ -105,6 +105,7 @@ logger = logging.getLogger(__name__)
     SourceCapability.OWNERSHIP,
     "Enabled by default, configured using `ingest_owner`",
 )
+@capability(SourceCapability.TEST_CONNECTION, "Enabled by default")
 class SigmaSource(StatefulIngestionSourceBase, TestableSource):
     """
     This plugin extracts the following:

datahub/ingestion/source/snowflake/snowflake_config.py

@@ -154,14 +154,11 @@ class SnowflakeIdentifierConfig(
 
     email_domain: Optional[str] = pydantic.Field(
         default=None,
-        description="Email domain of your organization so users can be displayed on UI appropriately.",
+        description="Email domain of your organization so users can be displayed on UI appropriately. This is used only if we cannot infer email ID.",
     )
 
-    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.",
+    _email_as_user_identifier = pydantic_removed_field(
+        "email_as_user_identifier",
     )
 
 

datahub/ingestion/source/snowflake/snowflake_summary.py

@@ -20,6 +20,7 @@ from datahub.ingestion.source.snowflake.snowflake_schema_gen import (
     SnowflakeSchemaGenerator,
 )
 from datahub.ingestion.source.snowflake.snowflake_utils import (
+    SnowflakeFilter,
     SnowflakeIdentifierBuilder,
 )
 from datahub.ingestion.source_report.time_window import BaseTimeWindowReport
@@ -81,6 +82,10 @@ class SnowflakeSummarySource(Source):
             profiler=None,
             aggregator=None,
             snowsight_url_builder=None,
+            filters=SnowflakeFilter(
+                filter_config=self.config,
+                structured_reporter=self.report,
+            ),
         )
 
         # Databases.

datahub/ingestion/source/snowflake/snowflake_utils.py

@@ -325,15 +325,10 @@ class SnowflakeIdentifierBuilder:
         user_email: Optional[str],
     ) -> str:
         if user_email:
-            return self.snowflake_identifier(
-                user_email
-                if self.identifier_config.email_as_user_identifier is True
-                else user_email.split("@")[0]
-            )
+            return self.snowflake_identifier(user_email)
         return self.snowflake_identifier(
             f"{user_name}@{self.identifier_config.email_domain}"
-            if self.identifier_config.email_as_user_identifier is True
-            and self.identifier_config.email_domain is not None
+            if self.identifier_config.email_domain is not None
             else user_name
         )
 

datahub/ingestion/source/snowflake/snowflake_v2.py

@@ -131,6 +131,7 @@ logger: logging.Logger = logging.getLogger(__name__)
     "Optionally enabled via `classification.enabled`",
     supported=True,
 )
+@capability(SourceCapability.TEST_CONNECTION, "Enabled by default")
 class SnowflakeV2Source(
     SnowflakeCommonMixin,
     StatefulIngestionSourceBase,
@@ -311,6 +312,7 @@ class SnowflakeV2Source(
                 SourceCapability.PLATFORM_INSTANCE,
                 SourceCapability.DOMAINS,
                 SourceCapability.DELETION_DETECTION,
+                SourceCapability.TEST_CONNECTION,
             )
         ]
 

datahub/ingestion/source/sql/clickhouse.py

@@ -379,7 +379,9 @@ clickhouse_datetime_format = "%Y-%m-%d %H:%M:%S"
 @platform_name("ClickHouse")
 @config_class(ClickHouseConfig)
 @support_status(SupportStatus.CERTIFIED)
-@capability(SourceCapability.DELETION_DETECTION, "Enabled via stateful ingestion")
+@capability(
+    SourceCapability.DELETION_DETECTION, "Enabled by default via stateful ingestion"
+)
 @capability(SourceCapability.DATA_PROFILING, "Optionally enabled via configuration")
 class ClickHouseSource(TwoTierSQLAlchemySource):
     """

datahub/ingestion/source/sql/cockroachdb.py

@@ -26,7 +26,6 @@ class CockroachDBConfig(PostgresConfig):
 @capability(SourceCapability.PLATFORM_INSTANCE, "Enabled by default")
 @capability(SourceCapability.DOMAINS, "Supported via the `domain` config field")
 @capability(SourceCapability.DATA_PROFILING, "Optionally enabled via configuration")
-@capability(SourceCapability.DELETION_DETECTION, "Enabled via stateful ingestion")
 class CockroachDBSource(PostgresSource):
     config: CockroachDBConfig
 

datahub/ingestion/source/sql/hana.py

@@ -27,7 +27,9 @@ class HanaConfig(BasicSQLAlchemyConfig):
 @capability(SourceCapability.PLATFORM_INSTANCE, "Enabled by default")
 @capability(SourceCapability.DOMAINS, "Supported via the `domain` config field")
 @capability(SourceCapability.DATA_PROFILING, "Optionally enabled via configuration")
-@capability(SourceCapability.DELETION_DETECTION, "Enabled via stateful ingestion")
+@capability(
+    SourceCapability.DELETION_DETECTION, "Enabled by default via stateful ingestion"
+)
 class HanaSource(SQLAlchemySource):
     def __init__(self, config: HanaConfig, ctx: PipelineContext):
         super().__init__(config, ctx, "hana")

datahub/ingestion/source/sql/hive_metastore.py

@@ -161,7 +161,9 @@ class HiveMetastore(BasicSQLAlchemyConfig):
 @platform_name("Hive Metastore")
 @config_class(HiveMetastore)
 @support_status(SupportStatus.CERTIFIED)
-@capability(SourceCapability.DELETION_DETECTION, "Enabled via stateful ingestion")
+@capability(
+    SourceCapability.DELETION_DETECTION, "Enabled by default via stateful ingestion"
+)
 @capability(SourceCapability.DATA_PROFILING, "Not Supported", False)
 @capability(SourceCapability.CLASSIFICATION, "Not Supported", False)
 @capability(

datahub/ingestion/source/sql/mariadb.py

@@ -15,7 +15,6 @@ from datahub.ingestion.source.sql.mysql import MySQLConfig, MySQLSource
 @capability(SourceCapability.PLATFORM_INSTANCE, "Enabled by default")
 @capability(SourceCapability.DOMAINS, "Supported via the `domain` config field")
 @capability(SourceCapability.DATA_PROFILING, "Optionally enabled via configuration")
-@capability(SourceCapability.DELETION_DETECTION, "Enabled via stateful ingestion")
 class MariaDBSource(MySQLSource):
     def get_platform(self):
         return "mariadb"

datahub/ingestion/source/sql/mssql/source.py

@@ -174,7 +174,14 @@ class SQLServerConfig(BasicSQLAlchemyConfig):
 @capability(SourceCapability.DOMAINS, "Supported via the `domain` config field")
 @capability(SourceCapability.DATA_PROFILING, "Optionally enabled via configuration")
 @capability(SourceCapability.DESCRIPTIONS, "Enabled by default")
-@capability(SourceCapability.DELETION_DETECTION, "Enabled via stateful ingestion")
+@capability(
+    SourceCapability.LINEAGE_COARSE,
+    "Enabled by default to get lineage for stored procedures via `include_lineage` and for views via `include_view_lineage`",
+)
+@capability(
+    SourceCapability.LINEAGE_FINE,
+    "Enabled by default to get lineage for stored procedures via `include_lineage` and for views via `include_view_column_lineage`",
+)
 class SQLServerSource(SQLAlchemySource):
     """
     This plugin extracts the following:

datahub/ingestion/source/sql/mysql.py

@@ -65,7 +65,6 @@ class MySQLConfig(MySQLConnectionConfig, TwoTierSQLAlchemyConfig):
 @capability(SourceCapability.PLATFORM_INSTANCE, "Enabled by default")
 @capability(SourceCapability.DOMAINS, "Supported via the `domain` config field")
 @capability(SourceCapability.DATA_PROFILING, "Optionally enabled via configuration")
-@capability(SourceCapability.DELETION_DETECTION, "Enabled via stateful ingestion")
 class MySQLSource(TwoTierSQLAlchemySource):
     """
     This plugin extracts the following:

datahub/ingestion/source/sql/postgres.py

@@ -131,7 +131,6 @@ class PostgresConfig(BasePostgresConfig):
 @capability(SourceCapability.DOMAINS, "Enabled by default")
 @capability(SourceCapability.PLATFORM_INSTANCE, "Enabled by default")
 @capability(SourceCapability.DATA_PROFILING, "Optionally enabled via configuration")
-@capability(SourceCapability.LINEAGE_COARSE, "Optionally enabled via configuration")
 class PostgresSource(SQLAlchemySource):
     """
     This plugin extracts the following:

datahub/ingestion/source/sql/sql_common.py

@@ -302,6 +302,18 @@ class ProfileMetadata:
     "Enabled by default",
     supported=True,
 )
+@capability(
+    SourceCapability.LINEAGE_COARSE,
+    "Enabled by default to get lineage for views via `include_view_lineage`",
+)
+@capability(
+    SourceCapability.LINEAGE_FINE,
+    "Enabled by default to get lineage for views via `include_view_column_lineage`",
+)
+@capability(SourceCapability.TEST_CONNECTION, "Enabled by default")
+@capability(
+    SourceCapability.DELETION_DETECTION, "Enabled by default via stateful ingestion"
+)
 class SQLAlchemySource(StatefulIngestionSourceBase, TestableSource):
     """A Base class for all SQL Sources that use SQLAlchemy to extend"""
 

datahub/ingestion/source/tableau/tableau.py

@@ -879,6 +879,7 @@ def report_user_role(report: TableauSourceReport, server: Server) -> None:
     SourceCapability.LINEAGE_FINE,
     "Enabled by default, configure using `extract_column_level_lineage`",
 )
+@capability(SourceCapability.TEST_CONNECTION, "Enabled by default")
 class TableauSource(StatefulIngestionSourceBase, TestableSource):
     platform = "tableau"
 

datahub/ingestion/source/unity/source.py

@@ -162,6 +162,7 @@ logger: logging.Logger = logging.getLogger(__name__)
     "Optionally enabled via `stateful_ingestion.remove_stale_metadata`",
     supported=True,
 )
+@capability(SourceCapability.TEST_CONNECTION, "Enabled by default")
 @support_status(SupportStatus.INCUBATING)
 class UnityCatalogSource(StatefulIngestionSourceBase, TestableSource):
     """

datahub/ingestion/source/usage/clickhouse_usage.py

@@ -85,7 +85,9 @@ class ClickHouseUsageConfig(ClickHouseConfig, BaseUsageConfig, EnvConfigMixin):
 @platform_name("ClickHouse")
 @config_class(ClickHouseUsageConfig)
 @support_status(SupportStatus.CERTIFIED)
-@capability(SourceCapability.DELETION_DETECTION, "Enabled via stateful ingestion")
+@capability(
+    SourceCapability.DELETION_DETECTION, "Enabled by default via stateful ingestion"
+)
 @capability(SourceCapability.DATA_PROFILING, "Optionally enabled via configuration")
 @dataclasses.dataclass
 class ClickHouseUsageSource(Source):

datahub/metadata/_internal_schema_classes.py

@@ -4590,6 +4590,15 @@ class FabricTypeClass(object):
     RVW = "RVW"
     """Designates review fabrics"""
     
+    PRD = "PRD"
+    """Alternative Prod spelling"""
+    
+    TST = "TST"
+    """Alternative Test spelling"""
+    
+    SIT = "SIT"
+    """System Integration Testing"""
+    
     SANDBOX = "SANDBOX"
     """Designates sandbox fabrics"""
     
@@ -21504,6 +21513,7 @@ class DataHubResourceFilterClass(DictWrapper):
         resources: Union[None, List[str]]=None,
         allResources: Optional[bool]=None,
         filter: Union[None, "PolicyMatchFilterClass"]=None,
+        privilegeConstraints: Union[None, "PolicyMatchFilterClass"]=None,
     ):
         super().__init__()
         
@@ -21515,12 +21525,14 @@ class DataHubResourceFilterClass(DictWrapper):
         else:
             self.allResources = allResources
         self.filter = filter
+        self.privilegeConstraints = privilegeConstraints
     
     def _restore_defaults(self) -> None:
         self.type = self.RECORD_SCHEMA.fields_dict["type"].default
         self.resources = self.RECORD_SCHEMA.fields_dict["resources"].default
         self.allResources = self.RECORD_SCHEMA.fields_dict["allResources"].default
         self.filter = self.RECORD_SCHEMA.fields_dict["filter"].default
+        self.privilegeConstraints = self.RECORD_SCHEMA.fields_dict["privilegeConstraints"].default
     
     
     @property
@@ -21565,6 +21577,16 @@ class DataHubResourceFilterClass(DictWrapper):
         self._inner_dict['filter'] = value
     
     
+    @property
+    def privilegeConstraints(self) -> Union[None, "PolicyMatchFilterClass"]:
+        """Constraints around what sub-resources operations are allowed to modify, i.e. NOT_EQUALS - cannot modify a particular defined tag, EQUALS - can only modify a particular defined tag, STARTS_WITH - can only modify a tag starting with xyz"""
+        return self._inner_dict.get('privilegeConstraints')  # type: ignore
+    
+    @privilegeConstraints.setter
+    def privilegeConstraints(self, value: Union[None, "PolicyMatchFilterClass"]) -> None:
+        self._inner_dict['privilegeConstraints'] = value
+    
+    
 class DataHubRoleInfoClass(_Aspect):
     """Information about a DataHub Role."""
 
@@ -21633,6 +21655,9 @@ class PolicyMatchConditionClass(object):
     STARTS_WITH = "STARTS_WITH"
     """Whether the field value starts with the value"""
     
+    NOT_EQUALS = "NOT_EQUALS"
+    """Whether the field does not match the value"""
+    
     
     
 class PolicyMatchCriterionClass(DictWrapper):