acryl-datahub 0.14.1.13rc7__py3-none-any.whl → 0.14.1.13rc9__py3-none-any.whl

{acryl_datahub-0.14.1.13rc7.dist-info → acryl_datahub-0.14.1.13rc9.dist-info}/RECORD

@@ -1,4 +1,4 @@
-datahub/__init__.py,sha256=iJWtbGzvLO2Ab_1AQTeXndrbJHFOcpOmE_RHQzAvOEo,577
+datahub/__init__.py,sha256=Qii_Ygk-5SdmcNm5lZWzqq41uil0D4isccAfgzqcyu8,577
 datahub/__main__.py,sha256=pegIvQ9hzK7IhqVeUi1MeADSZ2QlP-D3K0OQdEg55RU,106
 datahub/entrypoints.py,sha256=3-qSfXAx3Z0FEkBV5tlO8fQr4xk4ySeDRMVTpS5Xd6A,7793
 datahub/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -189,8 +189,8 @@ datahub/ingestion/source/demo_data.py,sha256=yzA_R-wfSX2WPz0i5ukYlscpmpb0Pt8D7Ek
 datahub/ingestion/source/elastic_search.py,sha256=qFUVNzynTVJTabASTjGMu8Qhf9UpNbEtSBFjaPQjBJE,22641
 datahub/ingestion/source/feast.py,sha256=NYaAjzLVRhmMKDawBwN0OL8AMyKDLsxOwEj3YFX0wIA,14244
 datahub/ingestion/source/file.py,sha256=pH-Qkjh5FQ2XvyYPE7Z8XEY4vUk_SUHxm8p8IxG12tU,15879
-datahub/ingestion/source/ge_data_profiler.py,sha256=jORUlsmN2XtHm3QyltENvhEyt-CwbF2O548mFxtisxY,63587
-datahub/ingestion/source/ge_profiling_config.py,sha256=E65adlsUrs17mQB7WQnoe3QCjvbGaGoNNPMf8szNK6s,10648
+datahub/ingestion/source/ge_data_profiler.py,sha256=JqTonv8y7Re4Rfn2YKOEaLufiiAOWKfK1XQvJfV5dvs,64126
+datahub/ingestion/source/ge_profiling_config.py,sha256=P-9pd20koFvpxeEL_pqFvKWWz-qnpZ6XkELUyBKr7is,10807
 datahub/ingestion/source/glue_profiling_config.py,sha256=vpMJH4Lf_qgR32BZy58suabri1yV5geaAPjzg2eORDc,2559
 datahub/ingestion/source/ldap.py,sha256=Vnzg8tpwBYeyM-KBVVsUJvGZGBMJiCJ_i_FhxaFRQ9A,18627
 datahub/ingestion/source/metabase.py,sha256=oemiMdzjfr82Hx6rdwTNBzFM8962LDkosYh7SD_I5cY,31717
@@ -240,12 +240,12 @@ datahub/ingestion/source/bigquery_v2/bigquery_helper.py,sha256=QER3gY8e_k1_eNVj7
 datahub/ingestion/source/bigquery_v2/bigquery_platform_resource_helper.py,sha256=8nuQ8hMuJEswWDZtV2RjbK8RvDJUzT_S74dnyPpGFdQ,4857
 datahub/ingestion/source/bigquery_v2/bigquery_queries.py,sha256=EoHo9twb0_QdX7Nvd1HJC1Yn0rqtrfR52EVk7Hu3XOQ,3296
 datahub/ingestion/source/bigquery_v2/bigquery_report.py,sha256=WxiLPFc7LwZXNDYfV9oySUD43kc2GcOf_pUokp3vFNM,8098
-datahub/ingestion/source/bigquery_v2/bigquery_schema.py,sha256=QQk2xnyLCpywwRA3a2Pm95zJd0LgJUGbe5ht-5yadmQ,32352
-datahub/ingestion/source/bigquery_v2/bigquery_schema_gen.py,sha256=JkQqG8GrMnsp6efUCSv1Efc0ZUmdC6q5_M6wWIyg_dQ,51774
+datahub/ingestion/source/bigquery_v2/bigquery_schema.py,sha256=tyKPfxg88ERX6z7Q5lCmJS-H7cgsWRUwM2epqe62bI0,32277
+datahub/ingestion/source/bigquery_v2/bigquery_schema_gen.py,sha256=Sv6BrK62nu3xpgjYGE-x1xdSTouvvnKDJtazPobhiKQ,50813
 datahub/ingestion/source/bigquery_v2/bigquery_test_connection.py,sha256=cATxwi5IPzj3BldRRAVcLqzSFmmYEPvqa7U0RFJbaAc,7645
 datahub/ingestion/source/bigquery_v2/common.py,sha256=Cxjf1a8ibkL_YRQeS0BqsjlyMgFJpaZ3iq_d7e8T8MQ,4030
 datahub/ingestion/source/bigquery_v2/lineage.py,sha256=Jg_pwnaj7l_KEcgq0enJXwrKh5jyUfBl4YB05YpkIVg,45415
-datahub/ingestion/source/bigquery_v2/profiler.py,sha256=ddNnPsc9NaraWYy4HctL0y83QtsyiiHx7zE9DgY8hTQ,11140
+datahub/ingestion/source/bigquery_v2/profiler.py,sha256=8-yAoq8sX0E6VIwr75YbM8wITRNhGfxgte9BCeGNkMM,10681
 datahub/ingestion/source/bigquery_v2/queries.py,sha256=B2vJLZYfwM1J5JAckijKJTxLhDYA0yw3kfzj5oRQB5c,20151
 datahub/ingestion/source/bigquery_v2/queries_extractor.py,sha256=xLf-vCUAnNuDdTHghxJvPOyGeA_XLCW3r-xj-8cfn3Q,19528
 datahub/ingestion/source/bigquery_v2/usage.py,sha256=xHb-gsugshoyzwScOQ5DHxZhoA-K0e4EbfSeVTLs428,40543
@@ -319,7 +319,7 @@ datahub/ingestion/source/identity/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeR
 datahub/ingestion/source/identity/azure_ad.py,sha256=GdmJFD4UMsb5353Z7phXRf-YsXR2woGLRJwBXUkgXq0,28809
 datahub/ingestion/source/identity/okta.py,sha256=PnRokWLG8wSoNZlXJiRZiW6APTEHO09q4n2j_l6m3V0,30756
 datahub/ingestion/source/kafka/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-datahub/ingestion/source/kafka/kafka.py,sha256=wC5tZ31fvXWLjse9qH3YONPhMxXIZ9QV9vbBcWDAP_w,25352
+datahub/ingestion/source/kafka/kafka.py,sha256=D54QXYoEQJYVb7oWyvLVCGbJunS8ZTGYlMMdaBqpmMs,25475
 datahub/ingestion/source/kafka/kafka_connect.py,sha256=5KUlhn3876c41Z3kx5l4oJhbu0ekXZQRdxmu52vb_v8,55167
 datahub/ingestion/source/kafka/kafka_schema_registry_base.py,sha256=13XjSwqyVhH1CJUFHAbWdmmv_Rw0Ju_9HQdBmIzPNNA,566
 datahub/ingestion/source/looker/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -410,8 +410,8 @@ datahub/ingestion/source/schema_inference/object.py,sha256=Aibf4dY4dXb4P9zfcNGnI
 datahub/ingestion/source/schema_inference/parquet.py,sha256=CdqsNuiabLLCulWbuPMssijeFmKLv3M5MKFIhlatpWA,3456
 datahub/ingestion/source/sigma/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 datahub/ingestion/source/sigma/config.py,sha256=zGh0ZU2Ty5NHfNXAVwFxVkK4NlsNSxtAyfCgMJJvzdc,3795
-datahub/ingestion/source/sigma/data_classes.py,sha256=kaSuWs0TaDCCsyRbHaKq8LknE5I42VOJ4hQXt5SKFg0,1974
-datahub/ingestion/source/sigma/sigma.py,sha256=PgFoSj0O309iL8kMT4jGnN9sTTtpM6kJoCLa84vckPg,22412
+datahub/ingestion/source/sigma/data_classes.py,sha256=YZkkzwftV34mq5c_4jlC2PCSiRKt4hvHjmqikLQhl1I,2012
+datahub/ingestion/source/sigma/sigma.py,sha256=DZCxMgIx-uJp6poFG85KFygRCyFDkkM4KXtBbUsgkHk,24094
 datahub/ingestion/source/sigma/sigma_api.py,sha256=jUkKbtqX3eRdfriruJE5KFT9aM7DCbvhmwfPzveYIiM,17814
 datahub/ingestion/source/slack/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 datahub/ingestion/source/slack/slack.py,sha256=C_3iXUS72h7HALhBW_AIyi3nNOqzyh7Ogflr-qI5ZEE,12946
@@ -464,7 +464,7 @@ datahub/ingestion/source/sql/two_tier_sql_source.py,sha256=YDrGBb5WKVls6qv17QU5f
 datahub/ingestion/source/sql/vertica.py,sha256=_9OgSgIgqBml0av063rb8nACiT3SAmzpw0ouyF91wv8,33382
 datahub/ingestion/source/sql/mssql/__init__.py,sha256=1agpl8S_uDW40olkhCX_W19dbr5GO9qgjS3R7pLRZSk,87
 datahub/ingestion/source/sql/mssql/job_models.py,sha256=eMyR0Efl5kvi7QNgNXzd5_6PdDKYly_552Y8OGSj9PY,6012
-datahub/ingestion/source/sql/mssql/source.py,sha256=fzpWjwexGvJgpd6Z4DCsK6Ld2vQCfPkD2M1xE4pU9Ec,29542
+datahub/ingestion/source/sql/mssql/source.py,sha256=lOfvNUGfxLmgCAops2jwm1OTBvJxgBivHcEj-9DEaAE,30390
 datahub/ingestion/source/sql/mssql/stored_procedure_lineage.py,sha256=RpnvKPalAAaOD_eUg8bZ4VkGTSeLFWuy0mefwc4s3x8,2837
 datahub/ingestion/source/state/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 datahub/ingestion/source/state/checkpoint.py,sha256=x9Xww-MIFXSKjeg1tOZXE72LehCm5OfKy3HfucgIRWM,8833
@@ -971,8 +971,8 @@ 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-0.14.1.13rc7.dist-info/METADATA,sha256=GLfCmMbHHo7KoYo_AKEO6D8Cty0VP2obvuJ5sSSclMo,171138
-acryl_datahub-0.14.1.13rc7.dist-info/WHEEL,sha256=PZUExdf71Ui_so67QXpySuHtCi3-J3wvF4ORK6k_S8U,91
-acryl_datahub-0.14.1.13rc7.dist-info/entry_points.txt,sha256=VcQx0dnqaYLyeY_L5OaX7bLmmE-Il7TAXkxCKvEn2bA,9432
-acryl_datahub-0.14.1.13rc7.dist-info/top_level.txt,sha256=iLjSrLK5ox1YVYcglRUkcvfZPvKlobBWx7CTUXx8_GI,25
-acryl_datahub-0.14.1.13rc7.dist-info/RECORD,,
+acryl_datahub-0.14.1.13rc9.dist-info/METADATA,sha256=CvAHjZi0HfaRrZKhjpu6Rp_n-3c2oYSPb8A54uw9zNQ,171138
+acryl_datahub-0.14.1.13rc9.dist-info/WHEEL,sha256=PZUExdf71Ui_so67QXpySuHtCi3-J3wvF4ORK6k_S8U,91
+acryl_datahub-0.14.1.13rc9.dist-info/entry_points.txt,sha256=VcQx0dnqaYLyeY_L5OaX7bLmmE-Il7TAXkxCKvEn2bA,9432
+acryl_datahub-0.14.1.13rc9.dist-info/top_level.txt,sha256=iLjSrLK5ox1YVYcglRUkcvfZPvKlobBWx7CTUXx8_GI,25
+acryl_datahub-0.14.1.13rc9.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__ = "0.14.1.13rc7"
+__version__ = "0.14.1.13rc9"
 
 
 def is_dev_mode() -> bool:

datahub/ingestion/source/bigquery_v2/bigquery_schema.py

@@ -118,7 +118,6 @@ class BigqueryTable(BaseTable):
     active_billable_bytes: Optional[int] = None
     long_term_billable_bytes: Optional[int] = None
     partition_info: Optional[PartitionInfo] = None
-    columns_ignore_from_profiling: List[str] = field(default_factory=list)
     external: bool = False
     constraints: List[BigqueryTableConstraint] = field(default_factory=list)
     table_type: Optional[str] = None

datahub/ingestion/source/bigquery_v2/bigquery_schema_gen.py

@@ -598,18 +598,6 @@ class BigQuerySchemaGenerator:
                     dataset_name=dataset_name,
                 )
 
-    # This method is used to generate the ignore list for datatypes the profiler doesn't support we have to do it here
-    # because the profiler doesn't have access to columns
-    def generate_profile_ignore_list(self, columns: List[BigqueryColumn]) -> List[str]:
-        ignore_list: List[str] = []
-        for column in columns:
-            if not column.data_type or any(
-                word in column.data_type.lower()
-                for word in ["array", "struct", "geography", "json"]
-            ):
-                ignore_list.append(column.field_path)
-        return ignore_list
-
     def _process_table(
         self,
         table: BigqueryTable,
@@ -631,15 +619,6 @@ class BigQuerySchemaGenerator:
             )
         table.column_count = len(columns)
 
-        # We only collect profile ignore list if profiling is enabled and profile_table_level_only is false
-        if (
-            self.config.is_profiling_enabled()
-            and not self.config.profiling.profile_table_level_only
-        ):
-            table.columns_ignore_from_profiling = self.generate_profile_ignore_list(
-                columns
-            )
-
         if not table.column_count:
             logger.warning(
                 f"Table doesn't have any column or unable to get columns for table: {table_identifier}"

datahub/ingestion/source/bigquery_v2/profiler.py

@@ -166,12 +166,6 @@ WHERE
                 normalized_table_name = BigqueryTableIdentifier(
                     project_id=project_id, dataset=dataset, table=table.name
                 ).get_table_name()
-                for column in table.columns_ignore_from_profiling:
-                    # Profiler has issues with complex types (array, struct, geography, json), so we deny those types from profiling
-                    # We also filter columns without data type as it means that column is part of a complex type.
-                    self.config.profile_pattern.deny.append(
-                        f"^{normalized_table_name}.{column}$"
-                    )
 
                 if table.external and not self.config.profiling.profile_external_tables:
                     self.report.profiling_skipped_other[f"{project_id}.{dataset}"] += 1

datahub/ingestion/source/ge_data_profiler.py

@@ -7,6 +7,7 @@ import dataclasses
 import functools
 import json
 import logging
+import re
 import threading
 import traceback
 import unittest.mock
@@ -123,6 +124,8 @@ ProfilerTypeMapping.BINARY_TYPE_NAMES.append("LargeBinary")
 
 _datasource_connection_injection_lock = threading.Lock()
 
+NORMALIZE_TYPE_PATTERN = re.compile(r"^(.*?)(?:[\[<(].*)?$")
+
 
 @contextlib.contextmanager
 def _inject_connection_into_datasource(conn: Connection) -> Iterator[None]:
@@ -165,11 +168,9 @@ def get_column_unique_count_dh_patch(self: SqlAlchemyDataset, column: str) -> in
         return convert_to_json_serializable(element_values.fetchone()[0])
     elif self.engine.dialect.name.lower() == BIGQUERY:
         element_values = self.engine.execute(
-            sa.select(
-                [
-                    sa.func.coalesce(sa.text(f"APPROX_COUNT_DISTINCT(`{column}`)")),
-                ]
-            ).select_from(self._table)
+            sa.select(sa.func.APPROX_COUNT_DISTINCT(sa.column(column))).select_from(
+                self._table
+            )
         )
         return convert_to_json_serializable(element_values.fetchone()[0])
     elif self.engine.dialect.name.lower() == SNOWFLAKE:
@@ -378,6 +379,9 @@ class _SingleDatasetProfiler(BasicDatasetProfilerBase):
                 f"{self.dataset_name}.{col}"
             ):
                 ignored_columns_by_pattern.append(col)
+            # We try to ignore nested columns as well
+            elif not self.config.profile_nested_fields and "." in col:
+                ignored_columns_by_pattern.append(col)
             elif col_dict.get("type") and self._should_ignore_column(col_dict["type"]):
                 ignored_columns_by_type.append(col)
             else:
@@ -407,9 +411,18 @@ class _SingleDatasetProfiler(BasicDatasetProfilerBase):
         return columns_to_profile
 
     def _should_ignore_column(self, sqlalchemy_type: sa.types.TypeEngine) -> bool:
-        return str(sqlalchemy_type) in _get_column_types_to_ignore(
-            self.dataset.engine.dialect.name
-        )
+        # We don't profiles columns with None types
+        if str(sqlalchemy_type) == "NULL":
+            return True
+
+        sql_type = str(sqlalchemy_type)
+
+        match = re.match(NORMALIZE_TYPE_PATTERN, sql_type)
+
+        if match:
+            sql_type = match.group(1)
+
+        return sql_type in _get_column_types_to_ignore(self.dataset.engine.dialect.name)
 
     @_run_with_query_combiner
     def _get_column_type(self, column_spec: _SingleColumnSpec, column: str) -> None:
@@ -1397,6 +1410,8 @@ class DatahubGEProfiler:
 def _get_column_types_to_ignore(dialect_name: str) -> List[str]:
     if dialect_name.lower() == POSTGRESQL:
         return ["JSON"]
+    elif dialect_name.lower() == BIGQUERY:
+        return ["ARRAY", "STRUCT", "GEOGRAPHY", "JSON"]
 
     return []
 

datahub/ingestion/source/ge_profiling_config.py

@@ -188,6 +188,11 @@ class GEProfilingConfig(GEProfilingBaseConfig):
         ),
     )
 
+    profile_nested_fields: bool = Field(
+        default=False,
+        description="Whether to profile complex types like structs, arrays and maps. ",
+    )
+
     @pydantic.root_validator(pre=True)
     def deprecate_bigquery_temp_table_schema(cls, values):
         # TODO: Update docs to remove mention of this field.

datahub/ingestion/source/kafka/kafka.py

@@ -157,7 +157,9 @@ def get_kafka_consumer(
     if CallableConsumerConfig.is_callable_config(connection.consumer_config):
         # As per documentation, we need to explicitly call the poll method to make sure OAuth callback gets executed
         # https://docs.confluent.io/platform/current/clients/confluent-kafka-python/html/index.html#kafka-client-configuration
+        logger.debug("Initiating polling for kafka consumer")
         consumer.poll(timeout=30)
+        logger.debug("Initiated polling for kafka consumer")
 
     return consumer
 

datahub/ingestion/source/sigma/data_classes.py

@@ -80,6 +80,7 @@ class Workbook(BaseModel):
     path: str
     latestVersion: int
     workspaceId: Optional[str] = None
+    description: Optional[str] = None
     pages: List[Page] = []
     badge: Optional[str] = None
 

datahub/ingestion/source/sigma/sigma.py

@@ -4,7 +4,12 @@ from typing import Dict, Iterable, List, Optional
 import datahub.emitter.mce_builder as builder
 from datahub.configuration.common import ConfigurationError
 from datahub.emitter.mcp import MetadataChangeProposalWrapper
-from datahub.emitter.mcp_builder import add_entity_to_container, gen_containers
+from datahub.emitter.mcp_builder import (
+    add_entity_to_container,
+    add_owner_to_entity_wu,
+    add_tags_to_entity_wu,
+    gen_containers,
+)
 from datahub.ingestion.api.common import PipelineContext
 from datahub.ingestion.api.decorators import (
     SourceCapability,
@@ -59,12 +64,14 @@ from datahub.metadata.com.linkedin.pegasus2avro.dataset import (
     UpstreamLineage,
 )
 from datahub.metadata.schema_classes import (
+    AuditStampClass,
     BrowsePathEntryClass,
     BrowsePathsV2Class,
     ChangeAuditStampsClass,
     ChartInfoClass,
     DashboardInfoClass,
     DataPlatformInstanceClass,
+    EdgeClass,
     GlobalTagsClass,
     InputFieldClass,
     InputFieldsClass,
@@ -74,6 +81,7 @@ from datahub.metadata.schema_classes import (
     SchemaFieldClass,
     SchemaFieldDataTypeClass,
     StringTypeClass,
+    SubTypesClass,
     TagAssociationClass,
 )
 from datahub.sql_parsing.sqlglot_lineage import create_lineage_sql_parsed_result
@@ -257,11 +265,6 @@ class SigmaSource(StatefulIngestionSourceBase, TestableSource):
         entries = [
             BrowsePathEntryClass(id=parent_entity_urn, urn=parent_entity_urn)
         ] + [BrowsePathEntryClass(id=path) for path in paths]
-        if self.config.platform_instance:
-            urn = builder.make_dataplatform_instance_urn(
-                self.platform, self.config.platform_instance
-            )
-            entries = [BrowsePathEntryClass(id=urn, urn=urn)] + entries
         return MetadataChangeProposalWrapper(
             entityUrn=entity_urn,
             aspect=BrowsePathsV2Class(entries),
@@ -424,11 +427,11 @@ class SigmaSource(StatefulIngestionSourceBase, TestableSource):
         elements: List[Element],
         workbook: Workbook,
         all_input_fields: List[InputFieldClass],
+        paths: List[str],
     ) -> Iterable[MetadataWorkUnit]:
         """
         Map Sigma page element to Datahub Chart
         """
-
         for element in elements:
             chart_urn = builder.make_chart_urn(
                 platform=self.platform,
@@ -459,11 +462,14 @@ class SigmaSource(StatefulIngestionSourceBase, TestableSource):
                 ),
             ).as_workunit()
 
-            yield from add_entity_to_container(
-                container_key=self._gen_workbook_key(workbook.workbookId),
-                entity_type="chart",
-                entity_urn=chart_urn,
-            )
+            if workbook.workspaceId:
+                yield self._gen_entity_browsepath_aspect(
+                    entity_urn=chart_urn,
+                    parent_entity_urn=builder.make_container_urn(
+                        self._gen_workspace_key(workbook.workspaceId)
+                    ),
+                    paths=paths + [workbook.name],
+                )
 
             # Add sigma dataset's upstream dataset urn mapping
             for dataset_urn, upstream_dataset_urns in inputs.items():
@@ -494,7 +500,9 @@ class SigmaSource(StatefulIngestionSourceBase, TestableSource):
 
             all_input_fields.extend(element_input_fields)
 
-    def _gen_pages_workunit(self, workbook: Workbook) -> Iterable[MetadataWorkUnit]:
+    def _gen_pages_workunit(
+        self, workbook: Workbook, paths: List[str]
+    ) -> Iterable[MetadataWorkUnit]:
         """
         Map Sigma workbook page to Datahub dashboard
         """
@@ -505,20 +513,23 @@ class SigmaSource(StatefulIngestionSourceBase, TestableSource):
 
             yield self._gen_dashboard_info_workunit(page)
 
-            yield from add_entity_to_container(
-                container_key=self._gen_workbook_key(workbook.workbookId),
-                entity_type="dashboard",
-                entity_urn=dashboard_urn,
-            )
-
             dpi_aspect = self._gen_dataplatform_instance_aspect(dashboard_urn)
             if dpi_aspect:
                 yield dpi_aspect
 
             all_input_fields: List[InputFieldClass] = []
 
+            if workbook.workspaceId:
+                yield self._gen_entity_browsepath_aspect(
+                    entity_urn=dashboard_urn,
+                    parent_entity_urn=builder.make_container_urn(
+                        self._gen_workspace_key(workbook.workspaceId)
+                    ),
+                    paths=paths + [workbook.name],
+                )
+
             yield from self._gen_elements_workunit(
-                page.elements, workbook, all_input_fields
+                page.elements, workbook, all_input_fields, paths
             )
 
             yield MetadataChangeProposalWrapper(
@@ -531,42 +542,89 @@ class SigmaSource(StatefulIngestionSourceBase, TestableSource):
         Map Sigma Workbook to Datahub container
         """
         owner_username = self.sigma_api.get_user_name(workbook.createdBy)
-        workbook_key = self._gen_workbook_key(workbook.workbookId)
-        yield from gen_containers(
-            container_key=workbook_key,
-            name=workbook.name,
-            sub_types=[BIContainerSubTypes.SIGMA_WORKBOOK],
-            parent_container_key=(
-                self._gen_workspace_key(workbook.workspaceId)
-                if workbook.workspaceId
-                else None
+
+        dashboard_urn = self._gen_dashboard_urn(workbook.workbookId)
+
+        yield self._gen_entity_status_aspect(dashboard_urn)
+
+        lastModified = AuditStampClass(
+            time=int(workbook.updatedAt.timestamp() * 1000),
+            actor="urn:li:corpuser:datahub",
+        )
+        created = AuditStampClass(
+            time=int(workbook.createdAt.timestamp() * 1000),
+            actor="urn:li:corpuser:datahub",
+        )
+
+        dashboard_info_cls = DashboardInfoClass(
+            title=workbook.name,
+            description=workbook.description if workbook.description else "",
+            dashboards=[
+                EdgeClass(
+                    destinationUrn=self._gen_dashboard_urn(page.get_urn_part()),
+                    sourceUrn=dashboard_urn,
+                )
+                for page in workbook.pages
+            ],
+            externalUrl=workbook.url,
+            lastModified=ChangeAuditStampsClass(
+                created=created, lastModified=lastModified
             ),
-            extra_properties={
+            customProperties={
                 "path": workbook.path,
                 "latestVersion": str(workbook.latestVersion),
             },
-            owner_urn=(
-                builder.make_user_urn(owner_username)
-                if self.config.ingest_owner and owner_username
-                else None
-            ),
-            external_url=workbook.url,
-            tags=[workbook.badge] if workbook.badge else None,
-            created=int(workbook.createdAt.timestamp() * 1000),
-            last_modified=int(workbook.updatedAt.timestamp() * 1000),
         )
+        yield MetadataChangeProposalWrapper(
+            entityUrn=dashboard_urn, aspect=dashboard_info_cls
+        ).as_workunit()
+
+        # Set subtype
+        yield MetadataChangeProposalWrapper(
+            entityUrn=dashboard_urn,
+            aspect=SubTypesClass(typeNames=[BIContainerSubTypes.SIGMA_WORKBOOK]),
+        ).as_workunit()
+
+        # Ownership
+        owner_urn = (
+            builder.make_user_urn(owner_username)
+            if self.config.ingest_owner and owner_username
+            else None
+        )
+        if owner_urn:
+            yield from add_owner_to_entity_wu(
+                entity_type="dashboard",
+                entity_urn=dashboard_urn,
+                owner_urn=owner_urn,
+            )
+
+        # Tags
+        tags = [workbook.badge] if workbook.badge else None
+        if tags:
+            yield from add_tags_to_entity_wu(
+                entity_type="dashboard",
+                entity_urn=dashboard_urn,
+                tags=sorted(tags),
+            )
 
         paths = workbook.path.split("/")[1:]
-        if len(paths) > 0 and workbook.workspaceId:
+        if workbook.workspaceId:
             yield self._gen_entity_browsepath_aspect(
-                entity_urn=builder.make_container_urn(workbook_key),
+                entity_urn=dashboard_urn,
                 parent_entity_urn=builder.make_container_urn(
                     self._gen_workspace_key(workbook.workspaceId)
                 ),
-                paths=paths,
+                paths=paths + [workbook.name],
             )
 
-        yield from self._gen_pages_workunit(workbook)
+            if len(paths) == 0:
+                yield from add_entity_to_container(
+                    container_key=self._gen_workspace_key(workbook.workspaceId),
+                    entity_type="dashboard",
+                    entity_urn=dashboard_urn,
+                )
+
+        yield from self._gen_pages_workunit(workbook, paths)
 
     def _gen_sigma_dataset_upstream_lineage_workunit(
         self,

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

@@ -50,6 +50,7 @@ from datahub.ingestion.source.sql.sql_config import (
     BasicSQLAlchemyConfig,
     make_sqlalchemy_uri,
 )
+from datahub.ingestion.source.sql.sql_report import SQLSourceReport
 from datahub.metadata.schema_classes import (
     BooleanTypeClass,
     NumberTypeClass,
@@ -78,6 +79,11 @@ class SQLServerConfig(BasicSQLAlchemyConfig):
     include_stored_procedures_code: bool = Field(
         default=True, description="Include information about object code."
     )
+    procedure_pattern: AllowDenyPattern = Field(
+        default=AllowDenyPattern.allow_all(),
+        description="Regex patterns for stored procedures to filter in ingestion."
+        "Specify regex to match the entire procedure name in database.schema.procedure_name format. e.g. to match all procedures starting with customer in Customer database and public schema, use the regex 'Customer.public.customer.*'",
+    )
     include_jobs: bool = Field(
         default=True,
         description="Include ingest of MSSQL Jobs. Requires access to the 'msdb' and 'sys' schema.",
@@ -164,6 +170,8 @@ class SQLServerSource(SQLAlchemySource):
     If you do use pyodbc, make sure to change the source type from `mssql` to `mssql-odbc` so that we pull in the right set of dependencies. This will be needed in most cases where encryption is required, such as managed SQL Server services in Azure.
     """
 
+    report: SQLSourceReport
+
     def __init__(self, config: SQLServerConfig, ctx: PipelineContext):
         super().__init__(config, ctx, "mssql")
         # Cache the table and column descriptions
@@ -416,10 +424,16 @@ class SQLServerSource(SQLAlchemySource):
         data_flow = MSSQLDataFlow(entity=mssql_default_job)
         with inspector.engine.connect() as conn:
             procedures_data_list = self._get_stored_procedures(conn, db_name, schema)
-            procedures = [
-                StoredProcedure(flow=mssql_default_job, **procedure_data)
-                for procedure_data in procedures_data_list
-            ]
+            procedures: List[StoredProcedure] = []
+            for procedure_data in procedures_data_list:
+                procedure_full_name = f"{db_name}.{schema}.{procedure_data['name']}"
+                if not self.config.procedure_pattern.allowed(procedure_full_name):
+                    self.report.report_dropped(procedure_full_name)
+                    continue
+                procedures.append(
+                    StoredProcedure(flow=mssql_default_job, **procedure_data)
+                )
+
             if procedures:
                 yield from self.construct_flow_workunits(data_flow=data_flow)
             for procedure in procedures: