semantic-link-labs 0.8.0__py3-none-any.whl → 0.8.2__py3-none-any.whl

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

@@ -314,7 +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,
 ):
     """
@@ -341,9 +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:

sempy_labs/_helper_functions.py

@@ -3,6 +3,7 @@ import re
 import json
 import base64
 import time
+import uuid
 from sempy.fabric.exceptions import FabricHTTPException
 import pandas as pd
 from functools import wraps
@@ -16,7 +17,7 @@ from azure.core.credentials import TokenCredential, AccessToken
 
 def create_abfss_path(
     lakehouse_id: UUID, lakehouse_workspace_id: UUID, delta_table_name: str
-):
+) -> str:
     """
     Creates an abfss path for a delta table in a Fabric lakehouse.
 
@@ -38,7 +39,7 @@ def create_abfss_path(
     return f"abfss://{lakehouse_workspace_id}@onelake.dfs.fabric.microsoft.com/{lakehouse_id}/Tables/{delta_table_name}"
 
 
-def format_dax_object_name(table: str, column: str):
+def format_dax_object_name(table: str, column: str) -> str:
     """
     Formats a table/column combination to the 'Table Name'[Column Name] format.
 
@@ -60,7 +61,7 @@ def format_dax_object_name(table: str, column: str):
 
 def create_relationship_name(
     from_table: str, from_column: str, to_table: str, to_column: str
-):
+) -> str:
     """
     Formats a relationship's table/columns into a fully qualified name.
 
@@ -88,7 +89,7 @@ def create_relationship_name(
     )
 
 
-def resolve_report_id(report: str, workspace: Optional[str] = None):
+def resolve_report_id(report: str, workspace: Optional[str] = None) -> UUID:
     """
     Obtains the ID of the Power BI report.
 
@@ -116,7 +117,7 @@ def resolve_report_id(report: str, workspace: Optional[str] = None):
     return obj
 
 
-def resolve_report_name(report_id: UUID, workspace: Optional[str] = None):
+def resolve_report_name(report_id: UUID, workspace: Optional[str] = None) -> str:
     """
     Obtains the name of the Power BI report.
 
@@ -146,7 +147,7 @@ def resolve_report_name(report_id: UUID, workspace: Optional[str] = None):
     return obj
 
 
-def resolve_dataset_id(dataset: str, workspace: Optional[str] = None):
+def resolve_dataset_id(dataset: str, workspace: Optional[str] = None) -> UUID:
     """
     Obtains the ID of the semantic model.
 
@@ -176,7 +177,7 @@ def resolve_dataset_id(dataset: str, workspace: Optional[str] = None):
     return obj
 
 
-def resolve_dataset_name(dataset_id: UUID, workspace: Optional[str] = None):
+def resolve_dataset_name(dataset_id: UUID, workspace: Optional[str] = None) -> str:
     """
     Obtains the name of the semantic model.
 
@@ -208,7 +209,7 @@ def resolve_dataset_name(dataset_id: UUID, workspace: Optional[str] = None):
 
 def resolve_lakehouse_name(
     lakehouse_id: Optional[UUID] = None, workspace: Optional[str] = None
-):
+) -> str:
     """
     Obtains the name of the Fabric lakehouse.
 
@@ -242,7 +243,7 @@ def resolve_lakehouse_name(
     return obj
 
 
-def resolve_lakehouse_id(lakehouse: str, workspace: Optional[str] = None):
+def resolve_lakehouse_id(lakehouse: str, workspace: Optional[str] = None) -> UUID:
     """
     Obtains the ID of the Fabric lakehouse.
 
@@ -321,7 +322,7 @@ def get_direct_lake_sql_endpoint(dataset: str, workspace: Optional[str] = None)
         return sqlEndpointId
 
 
-def generate_embedded_filter(filter: str):
+def generate_embedded_filter(filter: str) -> str:
     """
     Converts the filter expression to a filter expression which can be used by a Power BI embedded URL.
 
@@ -390,7 +391,7 @@ def save_as_delta_table(
     dataframe,
     delta_table_name: str,
     write_mode: str,
-    merge_schema: Optional[bool] = False,
+    merge_schema: bool = False,
     schema: Optional[dict] = None,
     lakehouse: Optional[str] = None,
     workspace: Optional[str] = None,
@@ -869,7 +870,7 @@ def lro(
     response,
     status_codes: Optional[List[str]] = [200, 202],
     sleep_time: Optional[int] = 1,
-    return_status_code: Optional[bool] = False,
+    return_status_code: bool = False,
 ):
 
     if response.status_code not in status_codes:
@@ -922,6 +923,19 @@ def pagination(client, response):
 
 
 def resolve_deployment_pipeline_id(deployment_pipeline: str) -> UUID:
+    """
+    Obtains the Id for a given deployment pipeline.
+
+    Parameters
+    ----------
+    deployment_pipeline : str
+        The deployment pipeline name
+
+    Returns
+    -------
+    UUID
+        The deployment pipeline Id.
+    """
 
     from sempy_labs._deployment_pipelines import list_deployment_pipelines
 
@@ -943,7 +957,7 @@ class FabricTokenCredential(TokenCredential):
         scopes: str,
         claims: Optional[str] = None,
         tenant_id: Optional[str] = None,
-        enable_cae: Optional[bool] = False,
+        enable_cae: bool = False,
         **kwargs: any,
     ) -> AccessToken:
 
@@ -968,15 +982,26 @@ def get_adls_client(account_name):
     return service_client
 
 
-def resolve_warehouse_id(warehouse: str, workspace: Optional[str]):
+def resolve_warehouse_id(warehouse: str, workspace: Optional[str]) -> UUID:
+    """
+    Obtains the Id for a given warehouse.
+
+    Parameters
+    ----------
+    warehouse : str
+        The warehouse name
+
+    Returns
+    -------
+    UUID
+        The warehouse Id.
+    """
 
     workspace = fabric.resolve_workspace_name(workspace)
-    warehouse_id = fabric.resolve_item_id(
+    return fabric.resolve_item_id(
         item_name=warehouse, type="Warehouse", workspace=workspace
     )
 
-    return warehouse_id
-
 
 def get_language_codes(languages: str | List[str]):
 
@@ -1024,6 +1049,7 @@ def get_azure_token_credentials(
 
 def convert_to_alphanumeric_lowercase(input_string):
 
+    # Removes non-alphanumeric characters
     cleaned_string = re.sub(r"[^a-zA-Z0-9]", "", input_string)
     cleaned_string = cleaned_string.lower()
 
@@ -1038,16 +1064,81 @@ def resolve_environment_id(environment: str, workspace: Optional[str] = None) ->
     ----------
     environment: str
         Name of the environment.
+
+    Returns
+    -------
+    UUID
+        The environment Id.
     """
-    from sempy_labs._environments import list_environments
 
-    (workspace, workspace_id) = resolve_workspace_name_and_id(workspace)
+    workspace = fabric.resolve_workspace_name(workspace)
+    return fabric.resolve_item_id(
+        item_name=environment, type="Environment", workspace=workspace
+    )
 
-    dfE = list_environments(workspace=workspace)
-    dfE_filt = dfE[dfE["Environment Name"] == environment]
-    if len(dfE_filt) == 0:
-        raise ValueError(
-            f"{icons.red_dot} The '{environment}' environment does not exist within the '{workspace}' workspace."
-        )
 
-    return dfE_filt["Environment Id"].iloc[0]
+def make_clickable(val):
+
+    return f'<a target="_blank" href="{val}">{val}</a>'
+
+
+def convert_to_friendly_case(text: str) -> str:
+    """
+    Converts a string of pascal/camel/snake case to business-friendly case.
+
+    Parameters
+    ----------
+    text : str
+        The text to convert.
+
+    Returns
+    -------
+    str
+        Text converted into a business-friendly text.
+    """
+    if text is not None:
+        text = text.replace("_", " ")
+        # Insert space before each capital letter, avoiding double spaces
+        text = re.sub(r"(?<!\s)(?=[A-Z])", " ", text)
+        # Strip leading/trailing whitespace and capitalize the first letter of each word
+        text = text.strip().title()
+
+    return text
+
+
+def resolve_notebook_id(notebook: str, workspace: Optional[str] = None) -> UUID:
+    """
+    Obtains the notebook Id for a given notebook.
+
+    Parameters
+    ----------
+    notebook: str
+        Name of the notebook.
+
+    Returns
+    -------
+    UUID
+        The notebook Id.
+    """
+
+    workspace = fabric.resolve_workspace_name(workspace)
+    return fabric.resolve_item_id(
+        item_name=notebook, type="Notebook", workspace=workspace
+    )
+
+
+def generate_guid():
+
+    return str(uuid.uuid4())
+
+
+def get_max_run_id(lakehouse: str, table_name: str) -> int:
+
+    from pyspark.sql import SparkSession
+
+    spark = SparkSession.builder.getOrCreate()
+    query = f"SELECT MAX(RunId) FROM {lakehouse}.{table_name}"
+    dfSpark = spark.sql(query)
+    max_run_id = dfSpark.collect()[0][0]
+
+    return max_run_id