semantic-link-labs 0.11.1__py3-none-any.whl → 0.11.3__py3-none-any.whl

sempy_labs/_job_scheduler.py

@@ -1,7 +1,7 @@
 from sempy._utils._log import log
 import pandas as pd
 from typing import Optional, List
-from sempy_labs._helper_functions import (
+from ._helper_functions import (
     resolve_workspace_name_and_id,
     resolve_item_name_and_id,
     _update_dataframe_datatypes,
@@ -67,27 +67,28 @@ def list_item_job_instances(
     if not responses[0].get("value"):
         return df
 
-    dfs = []
+    rows = []
     for r in responses:
         for v in r.get("value", []):
             fail = v.get("failureReason", {})
-            new_data = {
-                "Job Instance Id": v.get("id"),
-                "Item Name": item_name,
-                "Item Id": v.get("itemId"),
-                "Item Type": type,
-                "Job Type": v.get("jobType"),
-                "Invoke Type": v.get("invokeType"),
-                "Status": v.get("status"),
-                "Root Activity Id": v.get("rootActivityId"),
-                "Start Time UTC": v.get("startTimeUtc"),
-                "End Time UTC": v.get("endTimeUtc"),
-                "Error Message": fail.get("message") if fail is not None else "",
-            }
-            dfs.append(pd.DataFrame(new_data, index=[0]))
+            rows.append(
+                {
+                    "Job Instance Id": v.get("id"),
+                    "Item Name": item_name,
+                    "Item Id": v.get("itemId"),
+                    "Item Type": type,
+                    "Job Type": v.get("jobType"),
+                    "Invoke Type": v.get("invokeType"),
+                    "Status": v.get("status"),
+                    "Root Activity Id": v.get("rootActivityId"),
+                    "Start Time UTC": v.get("startTimeUtc"),
+                    "End Time UTC": v.get("endTimeUtc"),
+                    "Error Message": fail.get("message") if fail is not None else "",
+                }
+            )
 
-    if dfs:
-        df = pd.concat(dfs, ignore_index=True)
+    if rows:
+        df = pd.DataFrame(rows, columns=list(columns.keys()))
         _update_dataframe_datatypes(dataframe=df, column_map=columns)
 
     return df
@@ -111,24 +112,25 @@ def _get_item_job_instance(url: str) -> pd.DataFrame:
 
     response = _base_api(request=url)
 
-    dfs = []
+    rows = []
     for v in response.json().get("value", []):
         fail = v.get("failureReason", {})
-        new_data = {
-            "Job Instance Id": v.get("id"),
-            "Item Id": v.get("itemId"),
-            "Job Type": v.get("jobType"),
-            "Invoke Type": v.get("invokeType"),
-            "Status": v.get("status"),
-            "Root Activity Id": v.get("rootActivityId"),
-            "Start Time UTC": v.get("startTimeUtc"),
-            "End Time UTC": v.get("endTimeUtc"),
-            "Error Message": fail.get("message") if fail is not None else "",
-        }
-        dfs.append(pd.DataFrame(new_data, index=[0]))
-
-    if dfs:
-        df = pd.concat(dfs, ignore_index=True)
+        rows.append(
+            {
+                "Job Instance Id": v.get("id"),
+                "Item Id": v.get("itemId"),
+                "Job Type": v.get("jobType"),
+                "Invoke Type": v.get("invokeType"),
+                "Status": v.get("status"),
+                "Root Activity Id": v.get("rootActivityId"),
+                "Start Time UTC": v.get("startTimeUtc"),
+                "End Time UTC": v.get("endTimeUtc"),
+                "Error Message": fail.get("message") if fail is not None else "",
+            }
+        )
+
+    if rows:
+        df = pd.DataFrame(rows, columns=list(columns.keys()))
         _update_dataframe_datatypes(dataframe=df, column_map=columns)
 
     return df
@@ -190,29 +192,29 @@ def list_item_schedules(
         request=f"v1/workspaces/{workspace_id}/items/{item_id}/jobs/{job_type}/schedules"
     )
 
-    dfs = []
+    rows = []
     for v in response.json().get("value", []):
         config = v.get("configuration", {})
         own = v.get("owner", {})
-        new_data = {
-            "Job Schedule Id": v.get("id"),
-            "Enabled": v.get("enabled"),
-            "Created Date Time": v.get("createdDateTime"),
-            "Start Date Time": config.get("startDateTime"),
-            "End Date Time": config.get("endDateTime"),
-            "Local Time Zone Id": config.get("localTimeZoneId"),
-            "Type": config.get("type"),
-            "Interval": config.get("interval"),
-            "Weekdays": config.get("weekdays"),
-            "Times": config.get("times"),
-            "Owner Id": own.get("id"),
-            "Owner Type": own.get("type"),
-        }
-
-        dfs.append(pd.DataFrame(new_data, index=[0]))
-
-    if dfs:
-        df = pd.concat(dfs, ignore_index=True)
+        rows.append(
+            {
+                "Job Schedule Id": v.get("id"),
+                "Enabled": v.get("enabled"),
+                "Created Date Time": v.get("createdDateTime"),
+                "Start Date Time": config.get("startDateTime"),
+                "End Date Time": config.get("endDateTime"),
+                "Local Time Zone Id": config.get("localTimeZoneId"),
+                "Type": config.get("type"),
+                "Interval": config.get("interval"),
+                "Weekdays": config.get("weekdays"),
+                "Times": config.get("times"),
+                "Owner Id": own.get("id"),
+                "Owner Type": own.get("type"),
+            }
+        )
+
+    if rows:
+        df = pd.DataFrame(rows, columns=list(columns.keys()))
         _update_dataframe_datatypes(dataframe=df, column_map=columns)
 
     return df

sempy_labs/_kql_databases.py

@@ -1,7 +1,6 @@
 import pandas as pd
 from typing import Optional
-from sempy_labs._helper_functions import (
-    resolve_workspace_name_and_id,
+from ._helper_functions import (
     _base_api,
     _create_dataframe,
     delete_item,
@@ -55,24 +54,24 @@ def list_kql_databases(workspace: Optional[str | UUID] = None) -> pd.DataFrame:
         client="fabric_sp",
     )
 
-    dfs = []
+    rows = []
     for r in responses:
         for v in r.get("value", []):
             prop = v.get("properties", {})
-
-            new_data = {
-                "KQL Database Name": v.get("displayName"),
-                "KQL Database Id": v.get("id"),
-                "Description": v.get("description"),
-                "Parent Eventhouse Item Id": prop.get("parentEventhouseItemId"),
-                "Query Service URI": prop.get("queryServiceUri"),
-                "Ingestion Service URI": prop.get("ingestionServiceUri"),
-                "Database Type": prop.get("databaseType"),
-            }
-            dfs.append(pd.DataFrame(new_data, index=[0]))
-
-    if dfs:
-        df = pd.concat(dfs, ignore_index=True)
+            rows.append(
+                {
+                    "KQL Database Name": v.get("displayName"),
+                    "KQL Database Id": v.get("id"),
+                    "Description": v.get("description"),
+                    "Parent Eventhouse Item Id": prop.get("parentEventhouseItemId"),
+                    "Query Service URI": prop.get("queryServiceUri"),
+                    "Ingestion Service URI": prop.get("ingestionServiceUri"),
+                    "Database Type": prop.get("databaseType"),
+                }
+            )
+
+    if rows:
+        df = pd.DataFrame(rows, columns=list(columns.keys()))
 
     return df
 

sempy_labs/_kql_querysets.py

@@ -1,7 +1,7 @@
 import pandas as pd
 import sempy_labs._icons as icons
 from typing import Optional
-from sempy_labs._helper_functions import (
+from ._helper_functions import (
     resolve_workspace_id,
     _base_api,
     _create_dataframe,
@@ -45,18 +45,19 @@ def list_kql_querysets(workspace: Optional[str | UUID] = None) -> pd.DataFrame:
         request=f"v1/workspaces/{workspace_id}/kqlQuerysets", uses_pagination=True
     )
 
-    dfs = []
+    rows = []
     for r in responses:
         for v in r.get("value", []):
-            new_data = {
-                "KQL Queryset Name": v.get("displayName"),
-                "KQL Queryset Id": v.get("id"),
-                "Description": v.get("description"),
-            }
-            dfs.append(pd.DataFrame(new_data, index=[0]))
-
-    if dfs:
-        df = pd.concat(dfs, ignore_index=True)
+            rows.append(
+                {
+                    "KQL Queryset Name": v.get("displayName"),
+                    "KQL Queryset Id": v.get("id"),
+                    "Description": v.get("description"),
+                }
+            )
+
+    if rows:
+        df = pd.DataFrame(rows, columns=list(columns.keys()))
 
     return df
 

sempy_labs/_kusto.py

@@ -5,8 +5,8 @@ from sempy._utils._log import log
 import sempy_labs._icons as icons
 from typing import Optional
 from uuid import UUID
-from sempy_labs._kql_databases import _resolve_cluster_uri
-from sempy_labs._helper_functions import resolve_item_id
+from ._kql_databases import _resolve_cluster_uri
+from ._helper_functions import resolve_item_id
 
 
 @log

sempy_labs/_labels.py

@@ -0,0 +1,126 @@
+import sempy.fabric as fabric
+import requests
+import pandas as pd
+from typing import Optional, Union
+from uuid import UUID
+from sempy.fabric.exceptions import FabricHTTPException
+from sempy._utils._log import log
+
+
+@log
+def list_item_labels(workspace: Optional[Union[str, UUID]] = None) -> pd.DataFrame:
+    """
+    List all items within a workspace and shows their sensitivity labels.
+
+    NOTE: This function uses an internal API and is subject to change/break without notice.
+
+    Parameters
+    ----------
+    workspace : str | uuid.UUID, default=None
+        The Fabric workspace name or ID.
+        Defaults to None which resolves to the workspace of the attached lakehouse
+        or if no lakehouse attached, resolves to the workspace of the notebook.
+    Returns
+    -------
+    pandas.DataFrame
+        A pandas dataframe showing a list of all items within a workspace and their sensitivity labels.
+    """
+
+    import notebookutils
+
+    token = notebookutils.credentials.getToken("pbi")
+    headers = {"Authorization": f"Bearer {token}"}
+
+    # Item types handled in special payload fields
+    grouped_types = {
+        "dashboards": "Dashboard",
+        "reports": "Report",
+        "models": "SemanticModel",
+        "dataflows": "Dataflow",
+        "datamarts": "Datamart",
+    }
+
+    # All other item types go into 'artifacts'
+    fabric_items = [
+        "Datamart",
+        "Lakehouse",
+        "Eventhouse",
+        "Environment",
+        "KQLDatabase",
+        "KQLQueryset",
+        "KQLDashboard",
+        "DataPipeline",
+        "Notebook",
+        "SparkJobDefinition",
+        "MLExperiment",
+        "MLModel",
+        "Warehouse",
+        "Eventstream",
+        "SQLEndpoint",
+        "MirroredWarehouse",
+        "MirroredDatabase",
+        "Reflex",
+        "GraphQLApi",
+        "MountedDataFactory",
+        "SQLDatabase",
+        "CopyJob",
+        "VariableLibrary",
+        "Dataflow",
+        "ApacheAirflowJob",
+        "WarehouseSnapshot",
+        "DigitalTwinBuilder",
+        "DigitalTwinBuilderFlow",
+        "MirroredAzureDatabricksCatalog",
+        "DataAgent",
+        "UserDataFunction",
+    ]
+
+    dfI = fabric.list_items(workspace=workspace)
+
+    payload = {
+        key: [{"artifactId": i} for i in dfI[dfI["Type"] == value]["Id"].tolist()]
+        for key, value in grouped_types.items()
+    }
+
+    # Add generic artifact types
+    artifact_ids = dfI[dfI["Type"].isin(fabric_items)]["Id"].tolist()
+    if artifact_ids:
+        payload["artifacts"] = [{"artifactId": i} for i in artifact_ids]
+
+    client = fabric.PowerBIRestClient()
+    response = client.get("/v1.0/myorg/capacities")
+    if response.status_code != 200:
+        raise FabricHTTPException("Failed to retrieve URL prefix.")
+    context = response.json().get("@odata.context")
+    prefix = context.split("/v1.0")[0]
+
+    response = requests.post(
+        f"{prefix}/metadata/informationProtection/artifacts",
+        json=payload,
+        headers=headers,
+    )
+    if response.status_code != 200:
+        raise FabricHTTPException(f"Failed to retrieve labels: {response.text}")
+    result = response.json()
+
+    label_keys = [
+        "artifactInformationProtections",
+        "datasetInformationProtections",
+        "reportInformationProtections",
+        "dashboardInformationProtections",
+    ]
+
+    rows = [
+        {
+            "Id": item.get("artifactObjectId"),
+            "Label Id": item.get("labelId"),
+            "Label Name": item.get("name"),
+            "Parent Label Name": item.get("parent", {}).get("name"),
+            "Label Description": item.get("tooltip"),
+        }
+        for key in label_keys
+        for item in result.get(key, [])
+    ]
+
+    df_labels = pd.DataFrame(rows)
+    return dfI.merge(df_labels, on="Id", how="left")

sempy_labs/_list_functions.py

@@ -1,5 +1,5 @@
 import sempy.fabric as fabric
-from sempy_labs._helper_functions import (
+from ._helper_functions import (
     resolve_workspace_name_and_id,
     create_relationship_name,
     format_dax_object_name,
@@ -1131,7 +1131,7 @@ def list_reports_using_semantic_model(
     dataset: str | UUID, workspace: Optional[str | UUID] = None
 ) -> pd.DataFrame:
     """
-    Shows a list of all the reports (in all workspaces) which use a given semantic model.
+    Shows a list of all the reports which use a given semantic model. This is limited to the reports which are in the same workspace as the semantic model.
 
     Parameters
     ----------

sempy_labs/_managed_private_endpoints.py

@@ -1,7 +1,7 @@
 import pandas as pd
 import sempy_labs._icons as icons
 from typing import Optional
-from sempy_labs._helper_functions import (
+from ._helper_functions import (
     resolve_workspace_name_and_id,
     _is_valid_uuid,
     _base_api,
@@ -118,23 +118,26 @@ def list_managed_private_endpoints(
         client="fabric_sp",
     )
 
-    dfs = []
+    rows = []
     for r in responses:
         for v in r.get("value", []):
             conn = v.get("connectionState", {})
-            new_data = {
-                "Managed Private Endpoint Name": v.get("name"),
-                "Managed Private Endpoint Id": v.get("id"),
-                "Target Private Link Resource Id": v.get("targetPrivateLinkResourceId"),
-                "Provisioning State": v.get("provisioningState"),
-                "Connection Status": conn.get("status"),
-                "Connection Description": conn.get("description"),
-                "Target Subresource Type": v.get("targetSubresourceType"),
-            }
-            dfs.append(pd.DataFrame(new_data, index=[0]))
-
-    if dfs:
-        df = pd.concat(dfs, ignore_index=True)
+            rows.append(
+                {
+                    "Managed Private Endpoint Name": v.get("name"),
+                    "Managed Private Endpoint Id": v.get("id"),
+                    "Target Private Link Resource Id": v.get(
+                        "targetPrivateLinkResourceId"
+                    ),
+                    "Provisioning State": v.get("provisioningState"),
+                    "Connection Status": conn.get("status"),
+                    "Connection Description": conn.get("description"),
+                    "Target Subresource Type": v.get("targetSubresourceType"),
+                }
+            )
+
+    if rows:
+        df = pd.DataFrame(rows, columns=list(columns.keys()))
 
     return df
 

sempy_labs/_mirrored_databases.py

@@ -1,6 +1,6 @@
 import pandas as pd
 from typing import Optional
-from sempy_labs._helper_functions import (
+from ._helper_functions import (
     resolve_workspace_name_and_id,
     _update_dataframe_datatypes,
     _base_api,
@@ -58,25 +58,26 @@ def list_mirrored_databases(workspace: Optional[str | UUID] = None) -> pd.DataFr
         client="fabric_sp",
     )
 
-    dfs = []
+    rows = []
     for r in responses:
         for v in r.get("value", []):
             prop = v.get("properties", {})
             sql = prop.get("sqlEndpointProperties", {})
-            new_data = {
-                "Mirrored Database Name": v.get("displayName"),
-                "Mirrored Database Id": v.get("id"),
-                "Description": v.get("description"),
-                "OneLake Tables Path": prop.get("oneLakeTablesPath"),
-                "SQL Endpoint Connection String": sql.get("connectionString"),
-                "SQL Endpoint Id": sql.get("id"),
-                "Provisioning Status": sql.get("provisioningStatus"),
-                "Default Schema": prop.get("defaultSchema"),
-            }
-            dfs.append(pd.DataFrame(new_data, index=[0]))
+            rows.append(
+                {
+                    "Mirrored Database Name": v.get("displayName"),
+                    "Mirrored Database Id": v.get("id"),
+                    "Description": v.get("description"),
+                    "OneLake Tables Path": prop.get("oneLakeTablesPath"),
+                    "SQL Endpoint Connection String": sql.get("connectionString"),
+                    "SQL Endpoint Id": sql.get("id"),
+                    "Provisioning Status": sql.get("provisioningStatus"),
+                    "Default Schema": prop.get("defaultSchema"),
+                }
+            )
 
-    if dfs:
-        df = pd.concat(dfs, ignore_index=True)
+    if rows:
+        df = pd.DataFrame(rows, columns=list(columns.keys()))
 
     return df
 

sempy_labs/_mirrored_warehouses.py

@@ -1,6 +1,6 @@
 import pandas as pd
 from typing import Optional
-from sempy_labs._helper_functions import (
+from ._helper_functions import (
     resolve_workspace_id,
     _base_api,
     _create_dataframe,
@@ -43,17 +43,18 @@ def list_mirrored_warehouses(workspace: Optional[str | UUID] = None) -> pd.DataF
         uses_pagination=True,
     )
 
-    dfs = []
+    rows = []
     for r in responses:
         for v in r.get("value", []):
-            new_data = {
-                "Mirrored Warehouse Name": v.get("displayName"),
-                "Mirrored Warehouse Id": v.get("id"),
-                "Description": v.get("description"),
-            }
-            dfs.append(pd.DataFrame(new_data, index=[0]))
-
-    if dfs:
-        df = pd.concat(dfs, ignore_index=True)
+            rows.append(
+                {
+                    "Mirrored Warehouse Name": v.get("displayName"),
+                    "Mirrored Warehouse Id": v.get("id"),
+                    "Description": v.get("description"),
+                }
+            )
+
+    if rows:
+        df = pd.DataFrame(rows, columns=list(columns.keys()))
 
     return df

sempy_labs/_ml_experiments.py

@@ -1,6 +1,6 @@
 import pandas as pd
 from typing import Optional
-from sempy_labs._helper_functions import (
+from ._helper_functions import (
     resolve_workspace_id,
     _base_api,
     delete_item,
@@ -46,22 +46,23 @@ def list_ml_experiments(workspace: Optional[str | UUID] = None) -> pd.DataFrame:
         uses_pagination=True,
     )
 
-    dfs = []
+    rows = []
     for r in responses:
         for v in r.get("value", []):
             model_id = v.get("id")
             modelName = v.get("displayName")
             desc = v.get("description")
 
-            new_data = {
-                "ML Experiment Name": modelName,
-                "ML Experiment Id": model_id,
-                "Description": desc,
-            }
-            dfs.append(pd.DataFrame(new_data, index=[0]))
+            rows.append(
+                {
+                    "ML Experiment Name": modelName,
+                    "ML Experiment Id": model_id,
+                    "Description": desc,
+                }
+            )
 
-    if dfs:
-        df = pd.concat(dfs, ignore_index=True)
+    if rows:
+        df = pd.DataFrame(rows, columns=list(columns.keys()))
 
     return df
 

sempy_labs/_model_auto_build.py

@@ -1,8 +1,8 @@
 import sempy.fabric as fabric
 import pandas as pd
-from sempy_labs.tom import connect_semantic_model
-from sempy_labs._generate_semantic_model import create_blank_semantic_model
-from sempy_labs.directlake._generate_shared_expression import generate_shared_expression
+from .tom import connect_semantic_model
+from ._generate_semantic_model import create_blank_semantic_model
+from .directlake._generate_shared_expression import generate_shared_expression
 from typing import Optional
 from sempy._utils._log import log
 

sempy_labs/_model_bpa.py

@@ -3,8 +3,8 @@ import pandas as pd
 import warnings
 import datetime
 from IPython.display import display, HTML
-from sempy_labs._model_dependencies import get_model_calc_dependencies
-from sempy_labs._helper_functions import (
+from ._model_dependencies import get_model_calc_dependencies
+from ._helper_functions import (
     format_dax_object_name,
     create_relationship_name,
     save_as_delta_table,
@@ -15,9 +15,9 @@ from sempy_labs._helper_functions import (
     resolve_workspace_name_and_id,
     _create_spark_session,
 )
-from sempy_labs.lakehouse import get_lakehouse_tables, lakehouse_attached
-from sempy_labs.tom import connect_semantic_model
-from sempy_labs._model_bpa_rules import model_bpa_rules
+from .lakehouse import get_lakehouse_tables, lakehouse_attached
+from .tom import connect_semantic_model
+from ._model_bpa_rules import model_bpa_rules
 from typing import Optional
 from sempy._utils._log import log
 import sempy_labs._icons as icons

sempy_labs/_model_bpa_bulk.py

@@ -1,7 +1,7 @@
 import sempy.fabric as fabric
 import pandas as pd
 import datetime
-from sempy_labs._helper_functions import (
+from ._helper_functions import (
     save_as_delta_table,
     resolve_workspace_capacity,
     retry,
@@ -9,11 +9,11 @@ from sempy_labs._helper_functions import (
     resolve_workspace_id,
     resolve_lakehouse_name_and_id,
 )
-from sempy_labs.lakehouse import (
+from .lakehouse import (
     get_lakehouse_tables,
     lakehouse_attached,
 )
-from sempy_labs._model_bpa import run_model_bpa
+from ._model_bpa import run_model_bpa
 from typing import Optional, List
 from sempy._utils._log import log
 import sempy_labs._icons as icons

sempy_labs/_model_dependencies.py

@@ -1,6 +1,6 @@
 import sempy.fabric as fabric
 import pandas as pd
-from sempy_labs._helper_functions import (
+from ._helper_functions import (
     format_dax_object_name,
     resolve_dataset_name_and_id,
     resolve_workspace_name_and_id,