openmetadata-ingestion 1.5.15.0__py3-none-any.whl → 1.5.15.2__py3-none-any.whl

metadata/generated/schema/type/dailyCount.py

@@ -1,6 +1,6 @@
 # generated by datamodel-codegen:
 #   filename:  type/dailyCount.json
-#   timestamp: 2024-12-17T04:30:29+00:00
+#   timestamp: 2025-01-07T10:37:08+00:00
 
 from __future__ import annotations
 

metadata/generated/schema/type/databaseConnectionConfig.py

@@ -1,6 +1,6 @@
 # generated by datamodel-codegen:
 #   filename:  type/databaseConnectionConfig.json
-#   timestamp: 2024-12-17T04:30:29+00:00
+#   timestamp: 2025-01-07T10:37:08+00:00
 
 from __future__ import annotations
 

metadata/generated/schema/type/entityHierarchy.py

@@ -1,6 +1,6 @@
 # generated by datamodel-codegen:
 #   filename:  type/entityHierarchy.json
-#   timestamp: 2024-12-17T04:30:29+00:00
+#   timestamp: 2025-01-07T10:37:08+00:00
 
 from __future__ import annotations
 

metadata/generated/schema/type/entityHistory.py

@@ -1,6 +1,6 @@
 # generated by datamodel-codegen:
 #   filename:  type/entityHistory.json
-#   timestamp: 2024-12-17T04:30:29+00:00
+#   timestamp: 2025-01-07T10:37:08+00:00
 
 from __future__ import annotations
 

metadata/generated/schema/type/entityLineage.py

@@ -1,6 +1,6 @@
 # generated by datamodel-codegen:
 #   filename:  type/entityLineage.json
-#   timestamp: 2024-12-17T04:30:29+00:00
+#   timestamp: 2025-01-07T10:37:08+00:00
 
 from __future__ import annotations
 

metadata/generated/schema/type/entityReference.py

@@ -1,6 +1,6 @@
 # generated by datamodel-codegen:
 #   filename:  type/entityReference.json
-#   timestamp: 2024-12-17T04:30:29+00:00
+#   timestamp: 2025-01-07T10:37:08+00:00
 
 from __future__ import annotations
 

metadata/generated/schema/type/entityReferenceList.py

@@ -1,6 +1,6 @@
 # generated by datamodel-codegen:
 #   filename:  type/entityReferenceList.json
-#   timestamp: 2024-12-17T04:30:29+00:00
+#   timestamp: 2025-01-07T10:37:08+00:00
 
 from __future__ import annotations
 

metadata/generated/schema/type/entityRelationship.py

@@ -1,6 +1,6 @@
 # generated by datamodel-codegen:
 #   filename:  type/entityRelationship.json
-#   timestamp: 2024-12-17T04:30:29+00:00
+#   timestamp: 2025-01-07T10:37:08+00:00
 
 from __future__ import annotations
 

metadata/generated/schema/type/entityUsage.py

@@ -1,6 +1,6 @@
 # generated by datamodel-codegen:
 #   filename:  type/entityUsage.json
-#   timestamp: 2024-12-17T04:30:29+00:00
+#   timestamp: 2025-01-07T10:37:08+00:00
 
 from __future__ import annotations
 

metadata/generated/schema/type/filterPattern.py

@@ -1,6 +1,6 @@
 # generated by datamodel-codegen:
 #   filename:  type/filterPattern.json
-#   timestamp: 2024-12-17T04:30:29+00:00
+#   timestamp: 2025-01-07T10:37:08+00:00
 
 from __future__ import annotations
 

metadata/generated/schema/type/function.py

@@ -1,6 +1,6 @@
 # generated by datamodel-codegen:
 #   filename:  type/function.json
-#   timestamp: 2024-12-17T04:30:29+00:00
+#   timestamp: 2025-01-07T10:37:08+00:00
 
 from __future__ import annotations
 

metadata/generated/schema/type/include.py

@@ -1,6 +1,6 @@
 # generated by datamodel-codegen:
 #   filename:  type/include.json
-#   timestamp: 2024-12-17T04:30:29+00:00
+#   timestamp: 2025-01-07T10:37:08+00:00
 
 from __future__ import annotations
 

metadata/generated/schema/type/jdbcConnection.py

@@ -1,6 +1,6 @@
 # generated by datamodel-codegen:
 #   filename:  type/jdbcConnection.json
-#   timestamp: 2024-12-17T04:30:29+00:00
+#   timestamp: 2025-01-07T10:37:08+00:00
 
 from __future__ import annotations
 

metadata/generated/schema/type/lifeCycle.py

@@ -1,6 +1,6 @@
 # generated by datamodel-codegen:
 #   filename:  type/lifeCycle.json
-#   timestamp: 2024-12-17T04:30:29+00:00
+#   timestamp: 2025-01-07T10:37:08+00:00
 
 from __future__ import annotations
 

metadata/generated/schema/type/paging.py

@@ -1,6 +1,6 @@
 # generated by datamodel-codegen:
 #   filename:  type/paging.json
-#   timestamp: 2024-12-17T04:30:29+00:00
+#   timestamp: 2025-01-07T10:37:08+00:00
 
 from __future__ import annotations
 

metadata/generated/schema/type/profile.py

@@ -1,6 +1,6 @@
 # generated by datamodel-codegen:
 #   filename:  type/profile.json
-#   timestamp: 2024-12-17T04:30:29+00:00
+#   timestamp: 2025-01-07T10:37:08+00:00
 
 from __future__ import annotations
 

metadata/generated/schema/type/queryParserData.py

@@ -1,6 +1,6 @@
 # generated by datamodel-codegen:
 #   filename:  type/queryParserData.json
-#   timestamp: 2024-12-17T04:30:29+00:00
+#   timestamp: 2025-01-07T10:37:08+00:00
 
 from __future__ import annotations
 

metadata/generated/schema/type/reaction.py

@@ -1,6 +1,6 @@
 # generated by datamodel-codegen:
 #   filename:  type/reaction.json
-#   timestamp: 2024-12-17T04:30:29+00:00
+#   timestamp: 2025-01-07T10:37:08+00:00
 
 from __future__ import annotations
 

metadata/generated/schema/type/schedule.py

@@ -1,6 +1,6 @@
 # generated by datamodel-codegen:
 #   filename:  type/schedule.json
-#   timestamp: 2024-12-17T04:30:29+00:00
+#   timestamp: 2025-01-07T10:37:08+00:00
 
 from __future__ import annotations
 

metadata/generated/schema/type/schema.py

@@ -1,6 +1,6 @@
 # generated by datamodel-codegen:
 #   filename:  type/schema.json
-#   timestamp: 2024-12-17T04:30:29+00:00
+#   timestamp: 2025-01-07T10:37:08+00:00
 
 from __future__ import annotations
 

metadata/generated/schema/type/tableQuery.py

@@ -1,6 +1,6 @@
 # generated by datamodel-codegen:
 #   filename:  type/tableQuery.json
-#   timestamp: 2024-12-17T04:30:29+00:00
+#   timestamp: 2025-01-07T10:37:08+00:00
 
 from __future__ import annotations
 

metadata/generated/schema/type/tableUsageCount.py

@@ -1,6 +1,6 @@
 # generated by datamodel-codegen:
 #   filename:  type/tableUsageCount.json
-#   timestamp: 2024-12-17T04:30:29+00:00
+#   timestamp: 2025-01-07T10:37:08+00:00
 
 from __future__ import annotations
 

metadata/generated/schema/type/tagLabel.py

@@ -1,6 +1,6 @@
 # generated by datamodel-codegen:
 #   filename:  type/tagLabel.json
-#   timestamp: 2024-12-17T04:30:29+00:00
+#   timestamp: 2025-01-07T10:37:08+00:00
 
 from __future__ import annotations
 

metadata/generated/schema/type/usageDetails.py

@@ -1,6 +1,6 @@
 # generated by datamodel-codegen:
 #   filename:  type/usageDetails.json
-#   timestamp: 2024-12-17T04:30:29+00:00
+#   timestamp: 2025-01-07T10:37:08+00:00
 
 from __future__ import annotations
 

metadata/generated/schema/type/usageRequest.py

@@ -1,6 +1,6 @@
 # generated by datamodel-codegen:
 #   filename:  type/usageRequest.json
-#   timestamp: 2024-12-17T04:30:29+00:00
+#   timestamp: 2025-01-07T10:37:08+00:00
 
 from __future__ import annotations
 

metadata/generated/schema/type/votes.py

@@ -1,6 +1,6 @@
 # generated by datamodel-codegen:
 #   filename:  type/votes.json
-#   timestamp: 2024-12-17T04:30:29+00:00
+#   timestamp: 2025-01-07T10:37:08+00:00
 
 from __future__ import annotations
 

metadata/ingestion/ometa/mixins/user_mixin.py

@@ -13,6 +13,7 @@ Mixin class containing User specific methods
 
 To be used by OpenMetadata class
 """
+import json
 from functools import lru_cache
 from typing import Optional, Type
 
@@ -46,16 +47,29 @@ class OMetaUserMixin:
         )
 
     @staticmethod
-    def name_search_query_es(entity: Type[T]) -> str:
+    def name_search_query_es(entity: Type[T], name: str, from_: int, size: int) -> str:
         """
         Allow for more flexible lookup following what the UI is doing when searching users.
 
         We don't want to stick to `q=name:{name}` since in case a user is named `random.user`
         but looked as `Random User`, we want to find this match.
+
+        Search should only look in name and displayName fields and should not return bots.
         """
+        query_filter = {
+            "query": {
+                "query_string": {
+                    "query": f"{name} AND isBot:false",
+                    "fields": ["name", "displayName"],
+                    "default_operator": "AND",
+                    "fuzziness": "AUTO",
+                }
+            }
+        }
+
         return (
-            "/search/query?q={name} AND isBot:false&from={from_}&size={size}&index="
-            + ES_INDEX_MAP[entity.__name__]
+            f"""/search/query?query_filter={json.dumps(query_filter)}"""
+            f"&from={from_}&size={size}&index=" + ES_INDEX_MAP[entity.__name__]
         )
 
     def _search_by_email(
@@ -103,8 +117,8 @@ class OMetaUserMixin:
             fields: Optional field list to pass to ES request
         """
         if name:
-            query_string = self.name_search_query_es(entity=entity).format(
-                name=name, from_=from_count, size=size
+            query_string = self.name_search_query_es(
+                entity=entity, name=name, from_=from_count, size=size
             )
             return self.get_entity_from_es(
                 entity=entity, query_string=query_string, fields=fields

metadata/ingestion/source/dashboard/powerbi/client.py

@@ -127,7 +127,13 @@ class PowerBiApiClient:
             List[PowerBIDashboard]
         """
         try:
-            response_data = self.client.get(f"/myorg/groups/{group_id}/dashboards")
+            admin = "admin/" if self.config.useAdminApis else ""
+            response_data = self.client.get(
+                f"/myorg/{admin}groups/{group_id}/dashboards"
+            )
+            if not response_data:
+                logger.debug(f"No dashboards found for workspace_id: {group_id}")
+                return None
             response = DashboardsResponse(**response_data)
             return response.value
         except Exception as exc:  # pylint: disable=broad-except
@@ -142,7 +148,11 @@ class PowerBiApiClient:
             List[PowerBIReport]
         """
         try:
-            response_data = self.client.get(f"/myorg/groups/{group_id}/reports")
+            admin = "admin/" if self.config.useAdminApis else ""
+            response_data = self.client.get(f"/myorg/{admin}groups/{group_id}/reports")
+            if not response_data:
+                logger.debug(f"No reports found for workspace_id: {group_id}")
+                return None
             response = ReportsResponse(**response_data)
             return response.value
         except Exception as exc:  # pylint: disable=broad-except
@@ -157,7 +167,11 @@ class PowerBiApiClient:
             List[Dataset]
         """
         try:
-            response_data = self.client.get(f"/myorg/groups/{group_id}/datasets")
+            admin = "admin/" if self.config.useAdminApis else ""
+            response_data = self.client.get(f"/myorg/{admin}groups/{group_id}/datasets")
+            if not response_data:
+                logger.debug(f"No datasets found for workspace_id: {group_id}")
+                return None
             response = DatasetResponse(**response_data)
             return response.value
         except Exception as exc:  # pylint: disable=broad-except
@@ -174,9 +188,13 @@ class PowerBiApiClient:
             List[Tile]
         """
         try:
+            admin = "admin/" if self.config.useAdminApis else ""
             response_data = self.client.get(
-                f"/myorg/groups/{group_id}/dashboards/{dashboard_id}/tiles"
+                f"/myorg/{admin}dashboards/{dashboard_id}/tiles"
             )
+            if not response_data:
+                logger.debug(f"No dashboard tiles found for workspace_id: {group_id}")
+                return None
             response = TilesResponse(**response_data)
             return response.value
         except Exception as exc:  # pylint: disable=broad-except
@@ -216,6 +234,9 @@ class PowerBiApiClient:
             entities_per_page = self.config.pagination_entity_per_page
             params_data = {"$top": "1"}
             response_data = self.client.get(api_url, data=params_data)
+            if not response_data:
+                logger.debug("No groups/workspaces found")
+                return None
             response = GroupsResponse(**response_data)
             count = response.odata_count
             indexes = math.ceil(count / entities_per_page)
@@ -227,6 +248,9 @@ class PowerBiApiClient:
                     "$skip": str(index * entities_per_page),
                 }
                 response_data = self.client.get(api_url, data=params_data)
+                if not response_data:
+                    logger.debug("No more groups/workspaces found")
+                    continue
                 response = GroupsResponse(**response_data)
                 workspaces.extend(response.value)
             return workspaces
@@ -262,6 +286,7 @@ class PowerBiApiClient:
     def fetch_workspace_scan_status(
         self, scan_id: str
     ) -> Optional[WorkSpaceScanResponse]:
+        # deprecated in favour to avoide bulk data prepare
         """Get Workspace scan status by id method
         Args:
             scan_id:
@@ -280,6 +305,7 @@ class PowerBiApiClient:
         return None
 
     def fetch_workspace_scan_result(self, scan_id: str) -> Optional[Workspaces]:
+        # deprecated in favour to avoide bulk data prepare
         """Get Workspace scan result by id method
         Args:
             scan_id:
@@ -301,6 +327,7 @@ class PowerBiApiClient:
         """
         Method to poll the scan status endpoint until the timeout
         """
+        # deprecated in favour to avoide bulk data prepare
         min_sleep_time = 3
         if min_sleep_time > timeout:
             logger.info(f"Timeout is set to minimum sleep time: {timeout}")

metadata/ingestion/source/dashboard/powerbi/metadata.py

@@ -92,12 +92,6 @@ class PowerbiSource(DashboardServiceSource):
         self.datamodel_file_mappings = []
 
     def prepare(self):
-        if self.service_connection.useAdminApis:
-            groups = self.get_admin_workspace_data()
-        else:
-            groups = self.get_org_workspace_data()
-        if groups:
-            self.workspace_data = self.get_filtered_workspaces(groups)
         return super().prepare()
 
     def close(self):
@@ -123,91 +117,6 @@ class PowerbiSource(DashboardServiceSource):
             filtered_groups.append(group)
         return filtered_groups
 
-    def get_org_workspace_data(self) -> Optional[List[Group]]:
-        """
-        fetch all the group workspace ids
-        """
-        groups = self.client.api_client.fetch_all_workspaces()
-        for group in groups:
-            # add the dashboards to the groups
-            group.dashboards.extend(
-                self.client.api_client.fetch_all_org_dashboards(group_id=group.id) or []
-            )
-            for dashboard in group.dashboards:
-                # add the tiles to the dashboards
-                dashboard.tiles.extend(
-                    self.client.api_client.fetch_all_org_tiles(
-                        group_id=group.id, dashboard_id=dashboard.id
-                    )
-                    or []
-                )
-
-            # add the reports to the groups
-            group.reports.extend(
-                self.client.api_client.fetch_all_org_reports(group_id=group.id) or []
-            )
-
-            # add the datasets to the groups
-            group.datasets.extend(
-                self.client.api_client.fetch_all_org_datasets(group_id=group.id) or []
-            )
-            for dataset in group.datasets:
-                # add the tables to the datasets
-                dataset.tables.extend(
-                    self.client.api_client.fetch_dataset_tables(
-                        group_id=group.id, dataset_id=dataset.id
-                    )
-                    or []
-                )
-        return groups
-
-    def get_admin_workspace_data(self) -> Optional[List[Group]]:
-        """
-        fetch all the workspace ids
-        """
-        groups = []
-        workspaces = self.client.api_client.fetch_all_workspaces()
-        if workspaces:
-            workspace_id_list = [workspace.id for workspace in workspaces]
-
-            # Start the scan of the available workspaces for dashboard metadata
-            workspace_paginated_list = [
-                workspace_id_list[i : i + self.pagination_entity_per_page]
-                for i in range(
-                    0, len(workspace_id_list), self.pagination_entity_per_page
-                )
-            ]
-            count = 1
-            for workspace_ids_chunk in workspace_paginated_list:
-                logger.info(
-                    f"Scanning {count}/{len(workspace_paginated_list)} set of workspaces"
-                )
-                workspace_scan = self.client.api_client.initiate_workspace_scan(
-                    workspace_ids_chunk
-                )
-
-                # Keep polling the scan status endpoint to check if scan is succeeded
-                workspace_scan_status = self.client.api_client.wait_for_scan_complete(
-                    scan_id=workspace_scan.id
-                )
-                if workspace_scan_status:
-                    response = self.client.api_client.fetch_workspace_scan_result(
-                        scan_id=workspace_scan.id
-                    )
-                    groups.extend(
-                        [
-                            active_workspace
-                            for active_workspace in response.workspaces
-                            if active_workspace.state == "Active"
-                        ]
-                    )
-                else:
-                    logger.error("Error in fetching dashboards and charts")
-                count += 1
-        else:
-            logger.error("Unable to fetch any PowerBI workspaces")
-        return groups or None
-
     @classmethod
     def create(
         cls, config_dict, metadata: OpenMetadata, pipeline_name: Optional[str] = None
@@ -220,12 +129,51 @@ class PowerbiSource(DashboardServiceSource):
             )
         return cls(config, metadata)
 
+    def prepare_workspace_data(self, workspace: Group):
+        """prepare one workspace data at a time"""
+        # add the dashboards to the groups
+        workspace.dashboards.extend(
+            self.client.api_client.fetch_all_org_dashboards(group_id=workspace.id) or []
+        )
+        for dashboard in workspace.dashboards:
+            # add the tiles to the dashboards
+            dashboard.tiles.extend(
+                self.client.api_client.fetch_all_org_tiles(
+                    group_id=workspace.id, dashboard_id=dashboard.id
+                )
+                or []
+            )
+
+        # add the reports to the groups
+        workspace.reports.extend(
+            self.client.api_client.fetch_all_org_reports(group_id=workspace.id) or []
+        )
+
+        # add the datasets to the groups
+        workspace.datasets.extend(
+            self.client.api_client.fetch_all_org_datasets(group_id=workspace.id) or []
+        )
+        for dataset in workspace.datasets:
+            # add the tables to the datasets
+            dataset.tables.extend(
+                self.client.api_client.fetch_dataset_tables(
+                    group_id=workspace.id, dataset_id=dataset.id
+                )
+                or []
+            )
+
     def get_dashboard(self) -> Any:
         """
         Method to iterate through dashboard lists filter dashboards & yield dashboard details
         """
-        for workspace in self.workspace_data:
+        # fetch all workspaces/groups & apply filter pattern
+        all_workspaces = self.client.api_client.fetch_all_workspaces() or []
+        all_workspaces = self.get_filtered_workspaces(all_workspaces)
+        for workspace in all_workspaces:
+            # prepare additional data for specific workspace (datasets, reports, dashboards)
+            self.prepare_workspace_data(workspace)
             self.context.get().workspace = workspace
+            self.workspace_data.append(workspace)
             for dashboard in self.get_dashboards_list():
                 try:
                     dashboard_details = self.get_dashboard_details(dashboard)
@@ -309,54 +257,45 @@ class PowerbiSource(DashboardServiceSource):
             f"{workspace_id}/{chart_url_postfix}"
         )
 
-    def list_datamodels(self) -> Iterable[Dataset]:
+    def yield_datamodel(
+        self, dashboard_details: Union[PowerBIDashboard, PowerBIReport]
+    ) -> Iterable[Either[CreateDashboardRequest]]:
         """
-        Get All the Powerbi Datasets
+        Method to yield datamodel for each workspace
         """
-        if self.source_config.includeDataModels:
+        workspace_datasets = self.context.get().workspace.datasets
+        for dataset in workspace_datasets:
+            if filter_by_datamodel(
+                self.source_config.dataModelFilterPattern, dataset.name
+            ):
+                self.status.filter(dataset.name, "Data model filtered out.")
+                continue
             try:
-                for workspace in self.workspace_data:
-                    for dataset in workspace.datasets or []:
-                        if filter_by_datamodel(
-                            self.source_config.dataModelFilterPattern, dataset.name
-                        ):
-                            self.status.filter(dataset.name, "Data model filtered out.")
-                            continue
-                        yield dataset
-            except Exception as err:
-                logger.debug(traceback.format_exc())
-                logger.error(f"Unexpected error fetching PowerBI datasets - {err}")
-
-    def yield_bulk_datamodel(
-        self, dataset: Dataset
-    ) -> Iterable[Either[CreateDashboardDataModelRequest]]:
-        """
-        Method to fetch DataModels in bulk
-        """
-        try:
-            data_model_request = CreateDashboardDataModelRequest(
-                name=EntityName(dataset.id),
-                displayName=dataset.name,
-                description=Markdown(dataset.description)
-                if dataset.description
-                else None,
-                service=FullyQualifiedEntityName(self.context.get().dashboard_service),
-                dataModelType=DataModelType.PowerBIDataModel.value,
-                serviceType=DashboardServiceType.PowerBI.value,
-                columns=self._get_column_info(dataset),
-                project=self._fetch_dataset_workspace(dataset_id=dataset.id),
-            )
-            yield Either(right=data_model_request)
-            self.register_record_datamodel(datamodel_request=data_model_request)
+                data_model_request = CreateDashboardDataModelRequest(
+                    name=EntityName(dataset.id),
+                    displayName=dataset.name,
+                    description=Markdown(dataset.description)
+                    if dataset.description
+                    else None,
+                    service=FullyQualifiedEntityName(
+                        self.context.get().dashboard_service
+                    ),
+                    dataModelType=DataModelType.PowerBIDataModel.value,
+                    serviceType=DashboardServiceType.PowerBI.value,
+                    columns=self._get_column_info(dataset),
+                    project=self.get_project_name(dashboard_details),
+                )
+                yield Either(right=data_model_request)
+                self.register_record_datamodel(datamodel_request=data_model_request)
 
-        except Exception as exc:
-            yield Either(
-                left=StackTraceError(
-                    name=dataset.name,
-                    error=f"Error yielding Data Model [{dataset.name}]: {exc}",
-                    stackTrace=traceback.format_exc(),
+            except Exception as exc:
+                yield Either(
+                    left=StackTraceError(
+                        name=dataset.name,
+                        error=f"Error yielding Data Model [{dataset.name}]: {exc}",
+                        stackTrace=traceback.format_exc(),
+                    )
                 )
-            )
 
     def _get_child_columns(self, table: PowerBiTable) -> List[Column]:
         """

metadata/ingestion/source/database/common_db_source.py

@@ -225,6 +225,7 @@ class CommonDbSourceService(
             yield self.service_connection.databaseSchema
         else:
             for schema_name in self.inspector.get_schema_names():
+                logger.info(f"Processing Schema: {schema_name}")
                 yield schema_name
 
     def get_database_schema_names(self) -> Iterable[str]: