semantic-link-labs 0.9.4__py3-none-any.whl → 0.9.6__py3-none-any.whl

sempy_labs/lakehouse/_shortcuts.py

@@ -1,21 +1,25 @@
 import sempy.fabric as fabric
+import pandas as pd
 from sempy_labs._helper_functions import (
-    resolve_lakehouse_name,
-    resolve_lakehouse_id,
+    resolve_lakehouse_name_and_id,
     resolve_workspace_name_and_id,
     _base_api,
+    _create_dataframe,
+    resolve_workspace_name,
 )
+from sempy._utils._log import log
 from typing import Optional
 import sempy_labs._icons as icons
-from sempy.fabric.exceptions import FabricHTTPException
 from uuid import UUID
+from sempy.fabric.exceptions import FabricHTTPException
 
 
+@log
 def create_shortcut_onelake(
     table_name: str,
-    source_lakehouse: str,
+    source_lakehouse: str | UUID,
     source_workspace: str | UUID,
-    destination_lakehouse: str,
+    destination_lakehouse: Optional[str | UUID] = None,
     destination_workspace: Optional[str | UUID] = None,
     shortcut_name: Optional[str] = None,
     source_path: str = "Tables",
@@ -30,12 +34,13 @@ def create_shortcut_onelake(
     ----------
     table_name : str
         The table name for which a shortcut will be created.
-    source_lakehouse : str
+    source_lakehouse : str | uuid.UUID
         The Fabric lakehouse in which the table resides.
     source_workspace : str | uuid.UUID
         The name or ID of the Fabric workspace in which the source lakehouse exists.
-    destination_lakehouse : str
+    destination_lakehouse : str | uuid.UUID, default=None
         The Fabric lakehouse in which the shortcut will be created.
+        Defaults to None which resolves to the lakehouse attached to the notebook.
     destination_workspace : str | uuid.UUID, default=None
         The name or ID of the Fabric workspace in which the shortcut will be created.
         Defaults to None which resolves to the workspace of the attached lakehouse
@@ -62,21 +67,18 @@ def create_shortcut_onelake(
     (source_workspace_name, source_workspace_id) = resolve_workspace_name_and_id(
         source_workspace
     )
-    source_lakehouse_id = resolve_lakehouse_id(source_lakehouse, source_workspace_id)
-    source_lakehouse_name = fabric.resolve_item_name(
-        item_id=source_lakehouse_id, type="Lakehouse", workspace=source_workspace_id
-    )
 
-    (destination_workspace_name, destination_workspace_id) = resolve_workspace_name_and_id(
-        destination_workspace
+    (source_lakehouse_name, source_lakehouse_id) = resolve_lakehouse_name_and_id(
+        lakehouse=source_lakehouse, workspace=source_workspace_id
     )
-    destination_lakehouse_id = resolve_lakehouse_id(
-        destination_lakehouse, destination_workspace
+
+    (destination_workspace_name, destination_workspace_id) = (
+        resolve_workspace_name_and_id(destination_workspace)
     )
-    destination_lakehouse_name = fabric.resolve_item_name(
-        item_id=destination_lakehouse_id,
-        type="Lakehouse",
-        workspace=destination_workspace_id,
+    (destination_lakehouse_name, destination_lakehouse_id) = (
+        resolve_lakehouse_name_and_id(
+            lakehouse=destination_lakehouse, workspace=destination_workspace_id
+        )
     )
 
     if shortcut_name is None:
@@ -84,18 +86,39 @@ def create_shortcut_onelake(
 
     source_full_path = f"{source_path}/{table_name}"
 
+    actual_shortcut_name = shortcut_name.replace(" ", "")
+
     payload = {
         "path": destination_path,
-        "name": shortcut_name.replace(" ", ""),
+        "name": actual_shortcut_name,
         "target": {
             "oneLake": {
-                "workspaceId": source_workspace_id,
                 "itemId": source_lakehouse_id,
                 "path": source_full_path,
+                "workspaceId": source_workspace_id,
             }
         },
     }
 
+    # Check if the shortcut already exists
+    try:
+        response = _base_api(
+            request=f"/v1/workspaces/{destination_workspace_id}/items/{destination_lakehouse_id}/shortcuts/{destination_path}/{actual_shortcut_name}"
+        )
+        response_json = response.json()
+        del response_json["target"]["type"]
+        if response_json.get("target") == payload.get("target"):
+            print(
+                f"{icons.info} The '{actual_shortcut_name}' shortcut already exists in the '{destination_lakehouse_name}' lakehouse within the '{destination_workspace_name}' workspace."
+            )
+            return
+        else:
+            raise ValueError(
+                f"{icons.red_dot} The '{actual_shortcut_name}' shortcut already exists in the '{destination_lakehouse_name} lakehouse within the '{destination_workspace_name}' workspace but has a different source."
+            )
+    except FabricHTTPException:
+        pass
+
     _base_api(
         request=f"/v1/workspaces/{destination_workspace_id}/items/{destination_lakehouse_id}/shortcuts",
         payload=payload,
@@ -146,17 +169,14 @@ def create_shortcut(
 
     sourceTitle = source_titles[source]
 
-    (workspace, workspace_id) = resolve_workspace_name_and_id(workspace)
-
-    if lakehouse is None:
-        lakehouse_id = fabric.get_lakehouse_id()
-    else:
-        lakehouse_id = resolve_lakehouse_id(lakehouse, workspace)
+    (workspace_name, workspace_id) = resolve_workspace_name_and_id(workspace)
+    (lakehouse_name, lakehouse_id) = resolve_lakehouse_name_and_id(
+        lakehouse=lakehouse, workspace=workspace_id
+    )
 
-    client = fabric.FabricRestClient()
     shortcutActualName = shortcut_name.replace(" ", "")
 
-    request_body = {
+    payload = {
         "path": "Tables",
         "name": shortcutActualName,
         "target": {
@@ -168,22 +188,16 @@ def create_shortcut(
         },
     }
 
-    try:
-        response = client.post(
-            f"/v1/workspaces/{workspace_id}/items/{lakehouse_id}/shortcuts",
-            json=request_body,
-        )
-        if response.status_code == 201:
-            print(
-                f"{icons.green_dot} The shortcut '{shortcutActualName}' was created in the '{lakehouse}' lakehouse within"
-                f" the '{workspace} workspace. It is based on the '{subpath}' table in '{sourceTitle}'."
-            )
-        else:
-            print(response.status_code)
-    except Exception as e:
-        raise ValueError(
-            f"{icons.red_dot} Failed to create a shortcut for the '{shortcut_name}' table."
-        ) from e
+    _base_api(
+        request=f"/v1/workspaces/{workspace_id}/items/{lakehouse_id}/shortcuts",
+        method="post",
+        payload=payload,
+        status_codes=201,
+    )
+    print(
+        f"{icons.green_dot} The shortcut '{shortcutActualName}' was created in the '{lakehouse_name}' lakehouse within"
+        f" the '{workspace_name}' workspace. It is based on the '{subpath}' table in '{sourceTitle}'."
+    )
 
 
 def delete_shortcut(
@@ -203,7 +217,7 @@ def delete_shortcut(
         The name of the shortcut.
     shortcut_path : str = "Tables"
         The path of the shortcut to be deleted. Must start with either "Files" or "Tables". Examples: Tables/FolderName/SubFolderName; Files/FolderName/SubFolderName.
-    lakehouse : str, default=None
+    lakehouse : str | uuid.UUID, default=None
         The Fabric lakehouse name in which the shortcut resides.
         Defaults to None which resolves to the lakehouse attached to the notebook.
     workspace : str | UUID, default=None
@@ -213,20 +227,15 @@ def delete_shortcut(
     """
 
     (workspace_name, workspace_id) = resolve_workspace_name_and_id(workspace)
+    (lakehouse_name, lakehouse_id) = resolve_lakehouse_name_and_id(
+        lakehouse=lakehouse, workspace=workspace_id
+    )
 
-    if lakehouse is None:
-        lakehouse_id = fabric.get_lakehouse_id()
-        lakehouse = resolve_lakehouse_name(lakehouse_id, workspace_id)
-    else:
-        lakehouse_id = resolve_lakehouse_id(lakehouse, workspace_id)
-
-    client = fabric.FabricRestClient()
-    response = client.delete(
-        f"/v1/workspaces/{workspace_id}/items/{lakehouse_id}/shortcuts/{shortcut_path}/{shortcut_name}"
+    _base_api(
+        request=f"/v1/workspaces/{workspace_id}/items/{lakehouse_id}/shortcuts/{shortcut_path}/{shortcut_name}",
+        method="delete",
     )
 
-    if response.status_code != 200:
-        raise FabricHTTPException(response)
     print(
         f"{icons.green_dot} The '{shortcut_name}' shortcut in the '{lakehouse}' within the '{workspace_name}' workspace has been deleted."
     )
@@ -258,3 +267,135 @@ def reset_shortcut_cache(workspace: Optional[str | UUID] = None):
     print(
         f"{icons.green_dot} The shortcut cache has been reset for the '{workspace_name}' workspace."
     )
+
+
+@log
+def list_shortcuts(
+    lakehouse: Optional[str | UUID] = None,
+    workspace: Optional[str | UUID] = None,
+    path: Optional[str] = None,
+) -> pd.DataFrame:
+    """
+    Shows all shortcuts which exist in a Fabric lakehouse and their properties.
+
+    Parameters
+    ----------
+    lakehouse : str | uuid.UUID, default=None
+        The Fabric lakehouse name or ID.
+        Defaults to None which resolves to the lakehouse attached to the notebook.
+    workspace : str | uuid.UUID, default=None
+        The name or ID of the Fabric workspace in which lakehouse resides.
+        Defaults to None which resolves to the workspace of the attached lakehouse
+        or if no lakehouse attached, resolves to the workspace of the notebook.
+    path: str, default=None
+        The path within lakehouse where to look for shortcuts. If provied, must start with either "Files" or "Tables". Examples: Tables/FolderName/SubFolderName; Files/FolderName/SubFolderName.
+        Defaults to None which will retun all shortcuts on the given lakehouse
+
+    Returns
+    -------
+    pandas.DataFrame
+        A pandas dataframe showing all the shortcuts which exist in the specified lakehouse.
+    """
+
+    (workspace_name, workspace_id) = resolve_workspace_name_and_id(workspace)
+    (lakehouse_name, lakehouse_id) = resolve_lakehouse_name_and_id(
+        lakehouse=lakehouse, workspace=workspace_id
+    )
+
+    columns = {
+        "Shortcut Name": "string",
+        "Shortcut Path": "string",
+        "Source Type": "string",
+        "Source Workspace Id": "string",
+        "Source Workspace Name": "string",
+        "Source Item Id": "string",
+        "Source Item Name": "string",
+        "Source Item Type": "string",
+        "OneLake Path": "string",
+        "Connection Id": "string",
+        "Location": "string",
+        "Bucket": "string",
+        "SubPath": "string",
+        "Source Properties Raw": "string",
+    }
+    df = _create_dataframe(columns=columns)
+
+    # To improve performance create a dataframe to cache all items for a given workspace
+    itm_clms = {
+        "Id": "string",
+        "Display Name": "string",
+        "Description": "string",
+        "Type": "string",
+        "Workspace Id": "string",
+    }
+    source_items_df = _create_dataframe(columns=itm_clms)
+
+    url = f"/v1/workspaces/{workspace_id}/items/{lakehouse_id}/shortcuts"
+
+    if path is not None:
+        url += f"?parentPath={path}"
+
+    responses = _base_api(
+        request=url,
+        uses_pagination=True,
+    )
+
+    sources = {
+        "AdlsGen2": "adlsGen2",
+        "AmazonS3": "amazonS3",
+        "Dataverse": "dataverse",
+        "ExternalDataShare": "externalDataShare",
+        "GoogleCloudStorage": "googleCloudStorage",
+        "OneLake": "oneLake",
+        "S3Compatible": "s3Compatible",
+    }
+
+    for r in responses:
+        for i in r.get("value", []):
+            tgt = i.get("target", {})
+            tgt_type = tgt.get("type")
+            connection_id = tgt.get(sources.get(tgt_type), {}).get("connectionId")
+            location = tgt.get(sources.get(tgt_type), {}).get("location")
+            sub_path = tgt.get(sources.get(tgt_type), {}).get("subpath")
+            source_workspace_id = tgt.get(sources.get(tgt_type), {}).get("workspaceId")
+            source_item_id = tgt.get(sources.get(tgt_type), {}).get("itemId")
+            bucket = tgt.get(sources.get(tgt_type), {}).get("bucket")
+            source_workspace_name = (
+                resolve_workspace_name(workspace_id=source_workspace_id)
+                if source_workspace_id is not None
+                else None
+            )
+            # Cache and use it to getitem type and name
+            source_item_type = None
+            source_item_name = None
+            dfI = source_items_df[
+                source_items_df["Workspace Id"] == source_workspace_id
+            ]
+            if dfI.empty:
+                dfI = fabric.list_items(workspace=source_workspace_id)
+                source_items_df = pd.concat([source_items_df, dfI], ignore_index=True)
+
+            dfI_filt = dfI[dfI["Id"] == source_item_id]
+            if not dfI_filt.empty:
+                source_item_type = dfI_filt["Type"].iloc[0]
+                source_item_name = dfI_filt["Display Name"].iloc[0]
+
+            new_data = {
+                "Shortcut Name": i.get("name"),
+                "Shortcut Path": i.get("path"),
+                "Source Type": tgt_type,
+                "Source Workspace Id": source_workspace_id,
+                "Source Workspace Name": source_workspace_name,
+                "Source Item Id": source_item_id,
+                "Source Item Name": source_item_name,
+                "Source Item Type": source_item_type,
+                "OneLake Path": tgt.get(sources.get("oneLake"), {}).get("path"),
+                "Connection Id": connection_id,
+                "Location": location,
+                "Bucket": bucket,
+                "SubPath": sub_path,
+                "Source Properties Raw": str(tgt),
+            }
+            df = pd.concat([df, pd.DataFrame(new_data, index=[0])], ignore_index=True)
+
+    return df

sempy_labs/migration/_migration_validation.py

@@ -42,10 +42,6 @@ def migration_validation(
             f"{icons.red_dot} The 'dataset' and 'new_dataset' parameters are both set to '{dataset}'. These parameters must be set to different values."
         )
 
-    workspace = fabric.resolve_workspace_name(workspace)
-    if new_dataset_workspace is None:
-        new_dataset_workspace = workspace
-
     icons.sll_tags.append("DirectLakeMigration")
 
     dfA = list_semantic_model_objects(dataset=dataset, workspace=workspace)

sempy_labs/report/_download_report.py

@@ -3,10 +3,11 @@ import sempy_labs._icons as icons
 from typing import Optional
 from sempy_labs._helper_functions import (
     resolve_workspace_name_and_id,
-    resolve_lakehouse_name,
+    resolve_lakehouse_name_and_id,
     _base_api,
     resolve_item_id,
     _mount,
+    resolve_workspace_name,
 )
 from sempy_labs.lakehouse._lakehouse import lakehouse_attached
 from uuid import UUID
@@ -44,11 +45,8 @@ def download_report(
         )
 
     (workspace_name, workspace_id) = resolve_workspace_name_and_id(workspace)
-    lakehouse_id = fabric.get_lakehouse_id()
-    lakehouse_workspace = fabric.resolve_workspace_name()
-    lakehouse_name = resolve_lakehouse_name(
-        lakehouse_id=lakehouse_id, workspace=lakehouse_workspace
-    )
+    (lakehouse_name, lakehouse_id) = resolve_lakehouse_name_and_id()
+    lakehouse_workspace = resolve_workspace_name()
 
     download_types = ["LiveConnect", "IncludeModel"]
     if download_type not in download_types:

sempy_labs/report/_generate_report.py

@@ -11,6 +11,7 @@ from sempy_labs._helper_functions import (
     _update_dataframe_datatypes,
     _base_api,
     resolve_item_id,
+    get_item_definition,
 )
 import sempy_labs._icons as icons
 from sempy._utils._log import log
@@ -178,7 +179,9 @@ def update_report_from_reportjson(
 
 
 def get_report_definition(
-    report: str, workspace: Optional[str | UUID] = None, return_dataframe: bool = True
+    report: str | UUID,
+    workspace: Optional[str | UUID] = None,
+    return_dataframe: bool = True,
 ) -> pd.DataFrame | dict:
     """
     Gets the collection of definition files of a report.
@@ -187,8 +190,8 @@ def get_report_definition(
 
     Parameters
     ----------
-    report : str
-        Name of the report.
+    report : str | uuid.UUID
+        Name or ID of the report.
     workspace : str | uuid.UUID, default=None
         The Fabric workspace name or ID in which the report resides.
         Defaults to None which resolves to the workspace of the attached lakehouse
@@ -198,25 +201,14 @@ def get_report_definition(
 
     Returns
     -------
-    pandas.DataFrame | dict
+    pandas.DataFrame
         The collection of report definition files within a pandas dataframe.
     """
 
-    (workspace_name, workspace_id) = resolve_workspace_name_and_id(workspace)
-    report_id = resolve_item_id(item=report, type="Report", workspace=workspace)
-
-    result = _base_api(
-        request=f"/v1/workspaces/{workspace_id}/reports/{report_id}/getDefinition",
-        method="post",
-        lro_return_json=True,
-        status_codes=None,
+    return get_item_definition(
+        item=report, type="Report", workspace=workspace, return_dataframe=True
     )
 
-    if return_dataframe:
-        return pd.json_normalize(result["definition"]["parts"])
-    else:
-        return result
-
 
 @log
 def create_model_bpa_report(
@@ -327,9 +319,9 @@ def _create_report(
 
     from sempy_labs.report import report_rebind
 
-    report_workspace = fabric.resolve_workspace_name(report_workspace)
-    report_workspace_id = fabric.resolve_workspace_id(report_workspace)
-    dataset_workspace = fabric.resolve_workspace_name(dataset_workspace)
+    (report_workspace_name, report_workspace_id) = resolve_workspace_name_and_id(
+        workspace=report_workspace
+    )
 
     dfR = fabric.list_reports(workspace=report_workspace)
     dfR_filt = dfR[dfR["Name"] == report]
@@ -346,7 +338,7 @@ def _create_report(
         )
 
         print(
-            f"{icons.green_dot} The '{report}' report has been created within the '{report_workspace}'"
+            f"{icons.green_dot} The '{report}' report has been created within the '{report_workspace_name}'"
         )
         updated_report = True
     # Update the report if it exists
@@ -360,12 +352,12 @@ def _create_report(
             status_codes=None,
         )
         print(
-            f"{icons.green_dot} The '{report}' report has been updated within the '{report_workspace}'"
+            f"{icons.green_dot} The '{report}' report has been updated within the '{report_workspace_name}'"
         )
         updated_report = True
     else:
         raise ValueError(
-            f"{icons.red_dot} The '{report}' report within the '{report_workspace}' workspace already exists and the 'overwrite' parameter was set to False."
+            f"{icons.red_dot} The '{report}' report within the '{report_workspace_name}' workspace already exists and the 'overwrite' parameter was set to False."
         )
 
     # Rebind the report to the semantic model to make sure it is pointed at the correct semantic model

sempy_labs/report/_report_bpa.py

@@ -1,4 +1,3 @@
-import sempy.fabric as fabric
 from typing import Optional
 import pandas as pd
 import datetime
@@ -7,8 +6,7 @@ from sempy_labs.report import ReportWrapper, report_bpa_rules
 from sempy_labs._helper_functions import (
     format_dax_object_name,
     save_as_delta_table,
-    resolve_report_id,
-    resolve_lakehouse_name,
+    resolve_item_name_and_id,
     resolve_workspace_capacity,
     _get_column_aggregate,
     resolve_workspace_name_and_id,
@@ -54,9 +52,7 @@ def run_report_bpa(
         A pandas dataframe in HTML format showing report objects which violated the best practice analyzer rules.
     """
 
-    (workspace_name, workspace_id) = resolve_workspace_name_and_id(workspace)
-
-    rpt = ReportWrapper(report=report, workspace=workspace_id)
+    rpt = ReportWrapper(report=report, workspace=workspace)
 
     dfCV = rpt.list_custom_visuals()
     dfP = rpt.list_pages()
@@ -149,7 +145,7 @@ def run_report_bpa(
             df_output["Description"] = row["Description"]
             df_output["URL"] = row["URL"]
             df_output["Report URL"] = helper.get_web_url(
-                report=report, workspace=workspace_id
+                report=report, workspace=workspace
             )
 
             page_mapping_dict = dfP.set_index("Page Display Name")["Page URL"].to_dict()
@@ -205,31 +201,28 @@ def run_report_bpa(
 
         now = datetime.datetime.now()
         delta_table_name = "reportbparesults"
-        lakehouse_id = fabric.get_lakehouse_id()
-        lake_workspace = fabric.resolve_workspace_name()
-        lakehouse = resolve_lakehouse_name(
-            lakehouse_id=lakehouse_id, workspace=lake_workspace
-        )
-
-        lakeT = get_lakehouse_tables(lakehouse=lakehouse, workspace=lake_workspace)
+        lakeT = get_lakehouse_tables()
         lakeT_filt = lakeT[lakeT["Table Name"] == delta_table_name]
 
         if len(lakeT_filt) == 0:
             runId = 1
         else:
-            max_run_id = _get_column_aggregate(
-                lakehouse=lakehouse, table_name=delta_table_name
-            )
+            max_run_id = _get_column_aggregate(table_name=delta_table_name)
             runId = max_run_id + 1
 
+        (workspace_name, workspace_id) = resolve_workspace_name_and_id(workspace)
+        (report_name, report_id) = resolve_item_name_and_id(
+            item=report, type="Report", workspace=workspace_id
+        )
+
         export_df = finalDF.copy()
         capacity_id, capacity_name = resolve_workspace_capacity(workspace=workspace_id)
         export_df["Capacity Name"] = capacity_name
         export_df["Capacity Id"] = capacity_id
         export_df["Workspace Name"] = workspace_name
         export_df["Workspace Id"] = workspace_id
-        export_df["Report Name"] = report
-        export_df["Report Id"] = resolve_report_id(report, workspace_id)
+        export_df["Report Name"] = report_name
+        export_df["Report Id"] = report_id
         export_df["RunId"] = runId
         export_df["Timestamp"] = now
         export_df["RunId"] = export_df["RunId"].astype(int)

sempy_labs/report/_report_functions.py

@@ -18,6 +18,7 @@ from sempy_labs._helper_functions import (
     _base_api,
     _create_spark_session,
     _mount,
+    resolve_workspace_id,
 )
 from typing import List, Optional, Union
 from sempy._utils._log import log
@@ -192,7 +193,7 @@ def clone_report(
         target_workspace = workspace_name
         target_workspace_id = workspace_id
     else:
-        target_workspace_id = fabric.resolve_workspace_id(target_workspace)
+        target_workspace_id = resolve_workspace_id(workspace=target_workspace)
 
     if target_dataset is not None:
         if target_dataset_workspace is None:

sempy_labs/report/_report_rebind.py

@@ -1,9 +1,9 @@
-import sempy.fabric as fabric
 from sempy_labs._helper_functions import (
     resolve_dataset_id,
     resolve_workspace_name_and_id,
     resolve_report_id,
     _base_api,
+    resolve_dataset_name_and_id,
 )
 from typing import Optional, List
 from sempy._utils._log import log
@@ -104,10 +104,12 @@ def report_rebind_all(
             f"{icons.red_dot} The 'dataset' and 'new_dataset' parameters are both set to '{dataset}'. These parameters must be set to different values."
         )
 
-    dataset_workspace = fabric.resolve_workspace_name(dataset_workspace)
-
-    if new_dataset_workpace is None:
-        new_dataset_workpace = dataset_workspace
+    (dataset_name, dataset_id) = resolve_dataset_name_and_id(
+        dataset=dataset, workspace=dataset_workspace
+    )
+    (dataset_workspace_name, dataset_workspace_id) = resolve_workspace_name_and_id(
+        workspace=dataset_workspace
+    )
 
     if isinstance(report_workspace, str):
         report_workspace = [report_workspace]
@@ -118,7 +120,7 @@ def report_rebind_all(
 
     if len(dfR) == 0:
         print(
-            f"{icons.info} The '{dataset}' semantic model within the '{dataset_workspace}' workspace has no dependent reports."
+            f"{icons.info} The '{dataset_name}' semantic model within the '{dataset_workspace_name}' workspace has no dependent reports."
         )
         return