semantic-link-labs 0.7.4__py3-none-any.whl → 0.8.1__py3-none-any.whl

sempy_labs/_connections.py

@@ -2,7 +2,6 @@ import sempy.fabric as fabric
 import pandas as pd
 from sempy.fabric.exceptions import FabricHTTPException
 from typing import Optional
-import sempy_labs._icons as icons
 from sempy_labs._helper_functions import pagination
 
 
@@ -77,8 +76,9 @@ def list_connections() -> pd.DataFrame:
     return df
 
 
-def list_item_connections(item_name: str, item_type: str, workspace: Optional[str] = None) -> pd.DataFrame:
-
+def list_item_connections(
+    item_name: str, item_type: str, workspace: Optional[str] = None
+) -> pd.DataFrame:
     """
     Shows the list of connections that the specified item is connected to.
 
@@ -104,7 +104,9 @@ def list_item_connections(item_name: str, item_type: str, workspace: Optional[st
     workspace = fabric.resolve_workspace_name(workspace)
     workspace_id = fabric.resolve_workspace_id(workspace)
     item_type = item_type[0].upper() + item_type[1:]
-    item_id = fabric.resolve_item_id(item_name=item_name, type=item_type, workspace=workspace)
+    item_id = fabric.resolve_item_id(
+        item_name=item_name, type=item_type, workspace=workspace
+    )
 
     client = fabric.FabricRestClient()
     response = client.post(f"/v1/workspaces/{workspace_id}/items/{item_id}/connections")
@@ -123,17 +125,17 @@ def list_item_connections(item_name: str, item_type: str, workspace: Optional[st
     if response.status_code != 200:
         raise FabricHTTPException(response)
 
-    respnoses = pagination(client, response)
+    responses = pagination(client, response)
 
-    for r in respnoses:
-        for v in r.get('value', []):
+    for r in responses:
+        for v in r.get("value", []):
             new_data = {
-                "Connection Name": v.get('displayName'),
-                "Connection Id": v.get('id'),
-                "Connectivity Type": v.get('connectivityType'),
-                "Connection Type": v.get('connectionDetails', {}).get('type'),
-                "Connection Path": v.get('connectionDetails', {}).get('path'),
-                "Gateway Id": v.get('gatewayId'),
+                "Connection Name": v.get("displayName"),
+                "Connection Id": v.get("id"),
+                "Connectivity Type": v.get("connectivityType"),
+                "Connection Type": v.get("connectionDetails", {}).get("type"),
+                "Connection Path": v.get("connectionDetails", {}).get("path"),
+                "Gateway Id": v.get("gatewayId"),
             }
 
             df = pd.concat([df, pd.DataFrame(new_data, index=[0])], ignore_index=True)

sempy_labs/_data_pipelines.py

@@ -0,0 +1,118 @@
+import sempy.fabric as fabric
+import pandas as pd
+import sempy_labs._icons as icons
+from typing import Optional
+from sempy_labs._helper_functions import (
+    resolve_workspace_name_and_id,
+    lro,
+    pagination,
+)
+from sempy.fabric.exceptions import FabricHTTPException
+
+
+def list_data_pipelines(workspace: Optional[str] = None) -> pd.DataFrame:
+    """
+    Shows the data pipelines within a workspace.
+
+    Parameters
+    ----------
+    workspace : str, default=None
+        The Fabric workspace name.
+        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 the data pipelines within a workspace.
+    """
+
+    df = pd.DataFrame(columns=["Data Pipeline Name", "Data Pipeline ID", "Description"])
+
+    (workspace, workspace_id) = resolve_workspace_name_and_id(workspace)
+
+    client = fabric.FabricRestClient()
+    response = client.get(f"/v1/workspaces/{workspace_id}/dataPipelines")
+    if response.status_code != 200:
+        raise FabricHTTPException(response)
+
+    responses = pagination(client, response)
+
+    for r in responses:
+        for v in r.get("value", []):
+            new_data = {
+                "Data Pipeline Name": v.get("displayName"),
+                "Data Pipeline ID": v.get("id"),
+                "Description": v.get("description"),
+            }
+            df = pd.concat([df, pd.DataFrame(new_data, index=[0])], ignore_index=True)
+
+    return df
+
+
+def create_data_pipeline(
+    name: str, description: Optional[str] = None, workspace: Optional[str] = None
+):
+    """
+    Creates a Fabric data pipeline.
+
+    Parameters
+    ----------
+    name: str
+        Name of the data pipeline.
+    description : str, default=None
+        A description of the environment.
+    workspace : str, default=None
+        The Fabric workspace name.
+        Defaults to None which resolves to the workspace of the attached lakehouse
+        or if no lakehouse attached, resolves to the workspace of the notebook.
+    """
+
+    (workspace, workspace_id) = resolve_workspace_name_and_id(workspace)
+
+    request_body = {"displayName": name}
+
+    if description:
+        request_body["description"] = description
+
+    client = fabric.FabricRestClient()
+    response = client.post(
+        f"/v1/workspaces/{workspace_id}/dataPipelines", json=request_body
+    )
+
+    lro(client, response, status_codes=[201, 202])
+
+    print(
+        f"{icons.green_dot} The '{name}' data pipeline has been created within the '{workspace}' workspace."
+    )
+
+
+def delete_data_pipeline(name: str, workspace: Optional[str] = None):
+    """
+    Deletes a Fabric data pipeline.
+
+    Parameters
+    ----------
+    name: str
+        Name of the data pipeline.
+    workspace : str, default=None
+        The Fabric workspace name.
+        Defaults to None which resolves to the workspace of the attached lakehouse
+        or if no lakehouse attached, resolves to the workspace of the notebook.
+    """
+
+    (workspace, workspace_id) = resolve_workspace_name_and_id(workspace)
+
+    item_id = fabric.resolve_item_id(
+        item_name=name, type="DataPipeline", workspace=workspace
+    )
+
+    client = fabric.FabricRestClient()
+    response = client.delete(f"/v1/workspaces/{workspace_id}/dataPipelines/{item_id}")
+
+    if response.status_code != 200:
+        raise FabricHTTPException(response)
+
+    print(
+        f"{icons.green_dot} The '{name}' data pipeline within the '{workspace}' workspace has been deleted."
+    )

sempy_labs/_documentation.py

@@ -0,0 +1,144 @@
+import sempy
+import sempy.fabric as fabric
+import pandas as pd
+from typing import List, Optional
+
+
+def list_all_items(workspaces: Optional[str | List[str]] = None):
+
+    df = pd.DataFrame(
+        columns=[
+            "Workspace Name",
+            "Workspace Id",
+            "Item Name",
+            "Item Type",
+            "Description",
+        ]
+    )
+
+    if isinstance(workspaces, str):
+        workspaces = [workspaces]
+
+    dfW = fabric.list_workspaces()
+    if workspaces is not None:
+        dfW = dfW[dfW["Name"].isin(workspaces)]
+
+    for _, r in dfW.iterrows():
+        workspace_name = r["Name"]
+        workspace_id = r["Id"]
+        dfI = fabric.list_items(workspace=workspace_name)
+        for _, r2 in dfI.iterrows():
+
+            new_data = {
+                "Workspace Name": workspace_name,
+                "Workspace Id": workspace_id,
+                "Item Name": r2["Name"],
+                "Item Type": r2["Type"],
+                "Description": r2["Description"],
+            }
+            df = pd.concat([df, pd.DataFrame(new_data, index=[0])], ignore_index=True)
+
+    return df
+
+
+def data_dictionary(dataset: str, workspace: Optional[str | None] = None):
+
+    from sempy_labs.tom import connect_semantic_model
+
+    sempy.fabric._client._utils._init_analysis_services()
+    import Microsoft.AnalysisServices.Tabular as TOM
+
+    df = pd.DataFrame(
+        columns=[
+            "Workspace Name",
+            "Model Name",
+            "Table Name",
+            "Object Type",
+            "Object Name",
+            "Hidden Flag",
+            "Description",
+            "Display Folder",
+            "Measure Formula",
+        ]
+    )
+
+    with connect_semantic_model(
+        dataset=dataset, readonly=True, workspace=workspace
+    ) as tom:
+        for t in tom.model.Tables:
+            expr = None
+            if tom.is_calculated_table(table_name=t.Name):
+                pName = next(p.Name for p in t.Partitions)
+                expr = t.Partitions[pName].Source.Expression
+
+            new_data = {
+                "Workspace Name": workspace,
+                "Model Name": dataset,
+                "Table Name": t.Name,
+                "Object Type": t.ObjectType,
+                "Object Name": t.Name,
+                "Hidden Flag": t.IsHidden,
+                "Description": t.Description,
+                "Display Folder": None,
+                "Measure Formula": expr,
+            }
+            df = pd.concat([df, pd.DataFrame(new_data, index=[0])], ignore_index=True)
+            cols = [c for c in t.Columns if c.Type != TOM.ColumnType.RowNumber]
+            for c in cols:
+
+                def get_calc_column_expression(table_name, column_name):
+                    expr = None
+                    if tom.is_calculated_column(
+                        table_name=table_name, column_name=column_name
+                    ):
+                        expr = c.Expression
+                    return expr
+
+                new_data = {
+                    "Workspace Name": workspace,
+                    "Model Name": dataset,
+                    "Table Name": t.Name,
+                    "Object Type": c.ObjectType,
+                    "Object Name": c.Name,
+                    "Hidden Flag": c.IsHidden,
+                    "Description": c.Description,
+                    "Display Folder": c.DisplayFolder,
+                    "Measure Formula": get_calc_column_expression(t.Name, c.Name),
+                }
+                df = pd.concat(
+                    [df, pd.DataFrame(new_data, index=[0])], ignore_index=True
+                )
+            for m in t.Measures:
+                new_data = {
+                    "Workspace Name": workspace,
+                    "Model Name": dataset,
+                    "Table Name": t.Name,
+                    "Object Type": m.ObjectType,
+                    "Object Name": m.Name,
+                    "Hidden Flag": m.IsHidden,
+                    "Description": m.Description,
+                    "Display Folder": m.DisplayFolder,
+                    "Measure Formula": m.Expression,
+                }
+                df = pd.concat(
+                    [df, pd.DataFrame(new_data, index=[0])], ignore_index=True
+                )
+
+            if t.CalculationGroup is not None:
+                for ci in t.CalculationGroup.CalculationItems:
+                    new_data = {
+                        "Workspace Name": workspace,
+                        "Model Name": dataset,
+                        "Table Name": t.Name,
+                        "Object Type": "Calculation Item",
+                        "Object Name": ci.Name,
+                        "Hidden Flag": t.IsHidden,
+                        "Description": ci.Description,
+                        "Display Folder": None,
+                        "Measure Formula": ci.Expression,
+                    }
+                    df = pd.concat(
+                        [df, pd.DataFrame(new_data, index=[0])], ignore_index=True
+                    )
+
+    return df

sempy_labs/_eventhouses.py

@@ -0,0 +1,118 @@
+import sempy.fabric as fabric
+import pandas as pd
+import sempy_labs._icons as icons
+from typing import Optional
+from sempy_labs._helper_functions import (
+    resolve_workspace_name_and_id,
+    lro,
+    pagination,
+)
+from sempy.fabric.exceptions import FabricHTTPException
+
+
+def create_eventhouse(
+    name: str, description: Optional[str] = None, workspace: Optional[str] = None
+):
+    """
+    Creates a Fabric eventhouse.
+
+    Parameters
+    ----------
+    name: str
+        Name of the eventhouse.
+    description : str, default=None
+        A description of the environment.
+    workspace : str, default=None
+        The Fabric workspace name.
+        Defaults to None which resolves to the workspace of the attached lakehouse
+        or if no lakehouse attached, resolves to the workspace of the notebook.
+    """
+
+    (workspace, workspace_id) = resolve_workspace_name_and_id(workspace)
+
+    request_body = {"displayName": name}
+
+    if description:
+        request_body["description"] = description
+
+    client = fabric.FabricRestClient()
+    response = client.post(
+        f"/v1/workspaces/{workspace_id}/eventhouses", json=request_body
+    )
+
+    lro(client, response, status_codes=[201, 202])
+
+    print(
+        f"{icons.green_dot} The '{name}' eventhouse has been created within the '{workspace}' workspace."
+    )
+
+
+def list_eventhouses(workspace: Optional[str] = None) -> pd.DataFrame:
+    """
+    Shows the eventhouses within a workspace.
+
+    Parameters
+    ----------
+    workspace : str, default=None
+        The Fabric workspace name.
+        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 the eventhouses within a workspace.
+    """
+
+    df = pd.DataFrame(columns=["Eventhouse Name", "Eventhouse Id", "Description"])
+
+    (workspace, workspace_id) = resolve_workspace_name_and_id(workspace)
+
+    client = fabric.FabricRestClient()
+    response = client.get(f"/v1/workspaces/{workspace_id}/eventhouses")
+    if response.status_code != 200:
+        raise FabricHTTPException(response)
+
+    responses = pagination(client, response)
+
+    for r in responses:
+        for v in r.get("value", []):
+            new_data = {
+                "Eventhouse Name": v.get("displayName"),
+                "Eventhouse Id": v.get("id"),
+                "Description": v.get("description"),
+            }
+            df = pd.concat([df, pd.DataFrame(new_data, index=[0])], ignore_index=True)
+
+    return df
+
+
+def delete_eventhouse(name: str, workspace: Optional[str] = None):
+    """
+    Deletes a Fabric eventhouse.
+
+    Parameters
+    ----------
+    name: str
+        Name of the eventhouse.
+    workspace : str, default=None
+        The Fabric workspace name.
+        Defaults to None which resolves to the workspace of the attached lakehouse
+        or if no lakehouse attached, resolves to the workspace of the notebook.
+    """
+
+    (workspace, workspace_id) = resolve_workspace_name_and_id(workspace)
+
+    item_id = fabric.resolve_item_id(
+        item_name=name, type="Eventhouse", workspace=workspace
+    )
+
+    client = fabric.FabricRestClient()
+    response = client.delete(f"/v1/workspaces/{workspace_id}/eventhouses/{item_id}")
+
+    if response.status_code != 200:
+        raise FabricHTTPException(response)
+
+    print(
+        f"{icons.green_dot} The '{name}' eventhouse within the '{workspace}' workspace has been deleted."
+    )

sempy_labs/_eventstreams.py

@@ -0,0 +1,118 @@
+import sempy.fabric as fabric
+import pandas as pd
+import sempy_labs._icons as icons
+from typing import Optional
+from sempy_labs._helper_functions import (
+    resolve_workspace_name_and_id,
+    lro,
+    pagination,
+)
+from sempy.fabric.exceptions import FabricHTTPException
+
+
+def list_eventstreams(workspace: Optional[str] = None) -> pd.DataFrame:
+    """
+    Shows the eventstreams within a workspace.
+
+    Parameters
+    ----------
+    workspace : str, default=None
+        The Fabric workspace name.
+        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 the eventstreams within a workspace.
+    """
+
+    df = pd.DataFrame(columns=["Eventstream Name", "Eventstream Id", "Description"])
+
+    (workspace, workspace_id) = resolve_workspace_name_and_id(workspace)
+
+    client = fabric.FabricRestClient()
+    response = client.get(f"/v1/workspaces/{workspace_id}/eventstreams")
+    if response.status_code != 200:
+        raise FabricHTTPException(response)
+
+    responses = pagination(client, response)
+
+    for r in responses:
+        for v in r.get("value", []):
+            new_data = {
+                "Eventstream Name": v.get("displayName"),
+                "Eventstream Id": v.get("id"),
+                "Description": v.get("description"),
+            }
+            df = pd.concat([df, pd.DataFrame(new_data, index=[0])], ignore_index=True)
+
+    return df
+
+
+def create_eventstream(
+    name: str, description: Optional[str] = None, workspace: Optional[str] = None
+):
+    """
+    Creates a Fabric eventstream.
+
+    Parameters
+    ----------
+    name: str
+        Name of the eventstream.
+    description : str, default=None
+        A description of the environment.
+    workspace : str, default=None
+        The Fabric workspace name.
+        Defaults to None which resolves to the workspace of the attached lakehouse
+        or if no lakehouse attached, resolves to the workspace of the notebook.
+    """
+
+    (workspace, workspace_id) = resolve_workspace_name_and_id(workspace)
+
+    request_body = {"displayName": name}
+
+    if description:
+        request_body["description"] = description
+
+    client = fabric.FabricRestClient()
+    response = client.post(
+        f"/v1/workspaces/{workspace_id}/eventstreams", json=request_body
+    )
+
+    lro(client, response, status_codes=[201, 202])
+
+    print(
+        f"{icons.green_dot} The '{name}' eventstream has been created within the '{workspace}' workspace."
+    )
+
+
+def delete_eventstream(name: str, workspace: Optional[str] = None):
+    """
+    Deletes a Fabric eventstream.
+
+    Parameters
+    ----------
+    name: str
+        Name of the eventstream.
+    workspace : str, default=None
+        The Fabric workspace name.
+        Defaults to None which resolves to the workspace of the attached lakehouse
+        or if no lakehouse attached, resolves to the workspace of the notebook.
+    """
+
+    (workspace, workspace_id) = resolve_workspace_name_and_id(workspace)
+
+    item_id = fabric.resolve_item_id(
+        item_name=name, type="Eventstream", workspace=workspace
+    )
+
+    client = fabric.FabricRestClient()
+    response = client.delete(f"/v1/workspaces/{workspace_id}/eventstreams/{item_id}")
+
+    if response.status_code != 200:
+        raise FabricHTTPException(response)
+
+    print(
+        f"{icons.green_dot} The '{name}' eventstream within the '{workspace}' workspace has been deleted."
+    )

sempy_labs/_generate_semantic_model.py

@@ -20,7 +20,7 @@ def create_blank_semantic_model(
     dataset: str,
     compatibility_level: int = 1605,
     workspace: Optional[str] = None,
-    overwrite: Optional[bool] = True,
+    overwrite: bool = True,
 ):
     """
     Creates a new blank semantic model (no tables/columns etc.).
@@ -212,8 +212,8 @@ def deploy_semantic_model(
     source_workspace: Optional[str] = None,
     target_dataset: Optional[str] = None,
     target_workspace: Optional[str] = None,
-    refresh_target_dataset: Optional[bool] = True,
-    overwrite: Optional[bool] = False,
+    refresh_target_dataset: bool = True,
+    overwrite: bool = False,
 ):
     """
     Deploys a semantic model based on an existing semantic model.

sempy_labs/_git.py

@@ -132,19 +132,18 @@ def get_git_status(workspace: Optional[str] = None) -> pd.DataFrame:
     client = fabric.FabricRestClient()
     response = client.get(f"/v1/workspaces/{workspace_id}/git/status")
 
-    if response not in [200, 202]:
+    if response.status_code not in [200, 202]:
         raise FabricHTTPException(response)
 
     result = lro(client, response).json()
 
-    for v in result.get("value", []):
-        changes = v.get("changes", [])
+    for changes in result.get("changes", []):
         item_metadata = changes.get("itemMetadata", {})
         item_identifier = item_metadata.get("itemIdentifier", {})
 
         new_data = {
-            "Workspace Head": v.get("workspaceHead"),
-            "Remote Commit Hash": v.get("remoteCommitHash"),
+            "Workspace Head": result.get("workspaceHead"),
+            "Remote Commit Hash": result.get("remoteCommitHash"),
             "Object ID": item_identifier.get("objectId"),
             "Logical ID": item_identifier.get("logicalId"),
             "Item Type": item_metadata.get("itemType"),
@@ -199,21 +198,21 @@ def get_git_connection(workspace: Optional[str] = None) -> pd.DataFrame:
     if response.status_code != 200:
         raise FabricHTTPException(response)
 
-    for v in response.json().get("value", []):
-        provider_details = v.get("gitProviderDetails", {})
-        sync_details = v.get("gitSyncDetails", {})
-        new_data = {
-            "Organization Name": provider_details.get("organizationName"),
-            "Project Name": provider_details.get("projectName"),
-            "Git Provider Type": provider_details.get("gitProviderType"),
-            "Repository Name": provider_details.get("repositoryName"),
-            "Branch Name": provider_details.get("branchName"),
-            "Directory Name": provider_details.get("directoryName"),
-            "Workspace Head": sync_details.get("head"),
-            "Last Sync Time": sync_details.get("lastSyncTime"),
-            "Git Conneciton State": v.get("gitConnectionState"),
-        }
-        df = pd.concat([df, pd.DataFrame(new_data, index=[0])], ignore_index=True)
+    r = response.json()
+    provider_details = r.get("gitProviderDetails", {})
+    sync_details = r.get("gitSyncDetails", {})
+    new_data = {
+        "Organization Name": provider_details.get("organizationName"),
+        "Project Name": provider_details.get("projectName"),
+        "Git Provider Type": provider_details.get("gitProviderType"),
+        "Repository Name": provider_details.get("repositoryName"),
+        "Branch Name": provider_details.get("branchName"),
+        "Directory Name": provider_details.get("directoryName"),
+        "Workspace Head": sync_details.get("head"),
+        "Last Sync Time": sync_details.get("lastSyncTime"),
+        "Git Connection State": r.get("gitConnectionState"),
+    }
+    df = pd.concat([df, pd.DataFrame(new_data, index=[0])], ignore_index=True)
 
     return df
 
@@ -237,7 +236,7 @@ def initialize_git_connection(workspace: Optional[str] = None):
     client = fabric.FabricRestClient()
     response = client.post(f"/v1/workspaces/{workspace_id}/git/initializeConnection")
 
-    if response not in [200, 202]:
+    if response.status_code not in [200, 202]:
         raise FabricHTTPException(response)
 
     lro(client, response)
@@ -315,7 +314,7 @@ def update_from_git(
     remote_commit_hash: str,
     conflict_resolution_policy: str,
     workspace_head: Optional[str] = None,
-    allow_override: Optional[bool] = False,
+    allow_override: bool = False,
     workspace: Optional[str] = None,
 ):
     """
@@ -342,9 +341,9 @@ def update_from_git(
     workspace, workspace_id = resolve_workspace_name_and_id(workspace)
 
     conflict_resolution_policies = ["PreferWorkspace", "PreferRemote"]
-    if "remote" in conflict_resolution_policies.lower():
+    if "remote" in [policy.lower() for policy in conflict_resolution_policies]:
         conflict_resolution_policies = "PreferRemote"
-    elif "workspace" in conflict_resolution_policies.lower():
+    elif "workspace" in [policy.lower() for policy in conflict_resolution_policies]:
         conflict_resolution_policies = "PreferWorkspace"
 
     if conflict_resolution_policy not in conflict_resolution_policies: