semantic-link-labs 0.7.3__py3-none-any.whl → 0.8.0__py3-none-any.whl

sempy_labs/_connections.py

@@ -1,6 +1,146 @@
 import sempy.fabric as fabric
 import pandas as pd
 from sempy.fabric.exceptions import FabricHTTPException
+from typing import Optional
+from sempy_labs._helper_functions import pagination
+
+
+def list_connections() -> pd.DataFrame:
+    """
+    Lists all available connections.
+
+    Returns
+    -------
+    pandas.DataFrame
+        A pandas dataframe showing all available connections.
+    """
+
+    client = fabric.FabricRestClient()
+    response = client.get("/v1/connections")
+
+    if response.status_code != 200:
+        raise FabricHTTPException(response)
+
+    df = pd.DataFrame(
+        columns=[
+            "Connection Id",
+            "Connection Name",
+            "Gateway Id",
+            "Connectivity Type",
+            "Connection Path",
+            "Connection Type",
+            "Privacy Level",
+            "Credential Type",
+            "Single Sign on Type",
+            "Connection Encyrption",
+            "Skip Test Connection",
+        ]
+    )
+
+    for i in response.json().get("value", []):
+        connection_details = i.get("connectionDetails", {})
+        credential_details = i.get("credentialDetails", {})
+
+        new_data = {
+            "Connection Id": i.get("id"),
+            "Connection Name": i.get("displayName"),
+            "Gateway Id": i.get("gatewayId"),
+            "Connectivity Type": i.get("connectivityType"),
+            "Connection Path": connection_details.get("path"),
+            "Connection Type": connection_details.get("type"),
+            "Privacy Level": i.get("privacyLevel"),
+            "Credential Type": (
+                credential_details.get("credentialType") if credential_details else None
+            ),
+            "Single Sign On Type": (
+                credential_details.get("singleSignOnType")
+                if credential_details
+                else None
+            ),
+            "Connection Encryption": (
+                credential_details.get("connectionEncryption")
+                if credential_details
+                else None
+            ),
+            "Skip Test Connection": (
+                credential_details.get("skipTestConnection")
+                if credential_details
+                else None
+            ),
+        }
+
+        df = pd.concat([df, pd.DataFrame(new_data, index=[0])], ignore_index=True)
+    bool_cols = ["Skip Test Connection"]
+    df[bool_cols] = df[bool_cols].astype(bool)
+
+    return df
+
+
+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.
+
+    Parameters
+    ----------
+    item_name : str
+        The item name.
+    item_type : str
+        The `item type <https://learn.microsoft.com/rest/api/fabric/core/items/update-item?tabs=HTTP#itemtype>`_.
+    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 list of connections that the specified item is connected to.
+    """
+
+    # https://learn.microsoft.com/en-us/rest/api/fabric/core/items/list-item-connections?tabs=HTTP
+
+    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
+    )
+
+    client = fabric.FabricRestClient()
+    response = client.post(f"/v1/workspaces/{workspace_id}/items/{item_id}/connections")
+
+    df = pd.DataFrame(
+        columns=[
+            "Connection Name",
+            "Connection Id",
+            "Connectivity Type",
+            "Connection Type",
+            "Connection Path",
+            "Gateway Id",
+        ]
+    )
+
+    if response.status_code != 200:
+        raise FabricHTTPException(response)
+
+    responses = pagination(client, response)
+
+    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"),
+            }
+
+            df = pd.concat([df, pd.DataFrame(new_data, index=[0])], ignore_index=True)
+
+    return df
 
 
 def create_connection_cloud(

sempy_labs/_environments.py

@@ -0,0 +1,156 @@
+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_environment(
+    environment: str, description: Optional[str] = None, workspace: Optional[str] = None
+):
+    """
+    Creates a Fabric environment.
+
+    Parameters
+    ----------
+    environment: str
+        Name of the environment.
+    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": environment}
+
+    if description:
+        request_body["description"] = description
+
+    client = fabric.FabricRestClient()
+    response = client.post(
+        f"/v1/workspaces/{workspace_id}/environments", json=request_body
+    )
+
+    lro(client, response, status_codes=[201, 202])
+
+    print(
+        f"{icons.green_dot} The '{environment}' environment has been created within the '{workspace}' workspace."
+    )
+
+
+def list_environments(workspace: Optional[str] = None) -> pd.DataFrame:
+    """
+    Shows the environments 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 environments within a workspace.
+    """
+
+    df = pd.DataFrame(columns=["Environment Name", "Environment Id", "Description"])
+
+    (workspace, workspace_id) = resolve_workspace_name_and_id(workspace)
+
+    client = fabric.FabricRestClient()
+    response = client.get(f"/v1/workspaces/{workspace_id}/environments")
+    if response.status_code != 200:
+        raise FabricHTTPException(response)
+
+    responses = pagination(client, response)
+
+    for r in responses:
+        for v in r.get("value", []):
+            new_data = {
+                "Environment Name": v.get("displayName"),
+                "Environment 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_environment(environment: str, workspace: Optional[str] = None):
+    """
+    Deletes a Fabric environment.
+
+    Parameters
+    ----------
+    environment: str
+        Name 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.
+    """
+
+    from sempy_labs._helper_functions import resolve_environment_id
+
+    (workspace, workspace_id) = resolve_workspace_name_and_id(workspace)
+    environment_id = resolve_environment_id(
+        environment=environment, workspace=workspace
+    )
+
+    client = fabric.FabricRestClient()
+    response = client.delete(
+        f"/v1/workspaces/{workspace_id}/environments/{environment_id}"
+    )
+
+    if response.status_code != 200:
+        raise FabricHTTPException(response)
+
+    print(
+        f"{icons.green_dot} The '{environment}' environment within the '{workspace}' workspace has been deleted."
+    )
+
+
+def publish_environment(environment: str, workspace: Optional[str] = None):
+    """
+    Publishes a Fabric environment.
+
+    Parameters
+    ----------
+    environment: str
+        Name 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.
+    """
+
+    # https://learn.microsoft.com/en-us/rest/api/fabric/environment/spark-libraries/publish-environment?tabs=HTTP
+
+    from sempy_labs._helper_functions import resolve_environment_id
+
+    (workspace, workspace_id) = resolve_workspace_name_and_id(workspace)
+    environment_id = resolve_environment_id(
+        environment=environment, workspace=workspace
+    )
+
+    client = fabric.FabricRestClient()
+    response = client.post(
+        f"/v1/workspaces/{workspace_id}/environments/{environment_id}/staging/publish"
+    )
+
+    lro(client, response)
+
+    print(
+        f"{icons.green_dot} The '{environment}' environment within the '{workspace}' workspace has been published."
+    )

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)

sempy_labs/_helper_functions.py

@@ -2,15 +2,14 @@ import sempy.fabric as fabric
 import re
 import json
 import base64
+import time
+from sempy.fabric.exceptions import FabricHTTPException
 import pandas as pd
 from functools import wraps
 import datetime
-import time
-from pyspark.sql import SparkSession
 from typing import Optional, Tuple, List
 from uuid import UUID
 import sempy_labs._icons as icons
-from sempy.fabric.exceptions import FabricHTTPException
 import urllib.parse
 from azure.core.credentials import TokenCredential, AccessToken
 
@@ -392,6 +391,7 @@ def save_as_delta_table(
     delta_table_name: str,
     write_mode: str,
     merge_schema: Optional[bool] = False,
+    schema: Optional[dict] = None,
     lakehouse: Optional[str] = None,
     workspace: Optional[str] = None,
 ):
@@ -408,6 +408,8 @@ def save_as_delta_table(
         The write mode for the save operation. Options: 'append', 'overwrite'.
     merge_schema : bool, default=False
         Merges the schemas of the dataframe to the delta table.
+    schema : dict, default=None
+        A dictionary showing the schema of the columns and their data types.
     lakehouse : str, default=None
         The Fabric lakehouse used by the Direct Lake semantic model.
         Defaults to None which resolves to the lakehouse attached to the notebook.
@@ -415,13 +417,22 @@ def save_as_delta_table(
         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
-    -------
-    UUID
-        The ID of the Power BI report.
     """
 
+    from pyspark.sql import SparkSession
+    from pyspark.sql.types import (
+        StringType,
+        IntegerType,
+        FloatType,
+        DateType,
+        StructType,
+        StructField,
+        BooleanType,
+        LongType,
+        DoubleType,
+        TimestampType,
+    )
+
     if workspace is None:
         workspace_id = fabric.get_workspace_id()
         workspace = fabric.resolve_workspace_name(workspace_id)
@@ -450,9 +461,32 @@ def save_as_delta_table(
         )
 
     dataframe.columns = dataframe.columns.str.replace(" ", "_")
-
     spark = SparkSession.builder.getOrCreate()
-    spark_df = spark.createDataFrame(dataframe)
+
+    type_mapping = {
+        "string": StringType(),
+        "str": StringType(),
+        "integer": IntegerType(),
+        "int": IntegerType(),
+        "float": FloatType(),
+        "date": DateType(),
+        "bool": BooleanType(),
+        "boolean": BooleanType(),
+        "long": LongType(),
+        "double": DoubleType(),
+        "timestamp": TimestampType(),
+    }
+
+    if schema is None:
+        spark_df = spark.createDataFrame(dataframe)
+    else:
+        schema_map = StructType(
+            [
+                StructField(column_name, type_mapping[data_type], True)
+                for column_name, data_type in schema.items()
+            ]
+        )
+        spark_df = spark.createDataFrame(dataframe, schema_map)
 
     filePath = create_abfss_path(
         lakehouse_id=lakehouse_id,
@@ -781,6 +815,37 @@ def resolve_capacity_name(capacity_id: Optional[UUID] = None) -> str:
     return dfC_filt["Display Name"].iloc[0]
 
 
+def resolve_capacity_id(capacity_name: Optional[str] = None) -> UUID:
+    """
+    Obtains the capacity Id for a given capacity name.
+
+    Parameters
+    ----------
+    capacity_name : str, default=None
+        The capacity name.
+        Defaults to None which resolves to the capacity id of the workspace of the attached lakehouse
+        or if no lakehouse attached, resolves to the capacity name of the workspace of the notebook.
+
+    Returns
+    -------
+    UUID
+        The capacity Id.
+    """
+
+    if capacity_name is None:
+        return get_capacity_id()
+
+    dfC = fabric.list_capacities()
+    dfC_filt = dfC[dfC["Display Name"] == capacity_name]
+
+    if len(dfC_filt) == 0:
+        raise ValueError(
+            f"{icons.red_dot} The '{capacity_name}' capacity does not exist."
+        )
+
+    return dfC_filt["Id"].iloc[0]
+
+
 def retry(sleep_time: int, timeout_error_message: str):
     def decorator(func):
         @wraps(func)
@@ -883,6 +948,7 @@ class FabricTokenCredential(TokenCredential):
     ) -> AccessToken:
 
         from notebookutils import mssparkutils
+
         token = mssparkutils.credentials.getToken(scopes)
         access_token = AccessToken(token, 0)
 
@@ -910,3 +976,78 @@ def resolve_warehouse_id(warehouse: str, workspace: Optional[str]):
     )
 
     return warehouse_id
+
+
+def get_language_codes(languages: str | List[str]):
+
+    if isinstance(languages, str):
+        languages = [languages]
+
+    for i, lang in enumerate(languages):
+        for k, v in icons.language_map.items():
+            if v == lang.capitalize():
+                languages[i] = k
+                break
+
+    return languages
+
+
+def get_azure_token_credentials(
+    key_vault_uri: str,
+    key_vault_tenant_id: str,
+    key_vault_client_id: str,
+    key_vault_client_secret: str,
+) -> Tuple[str, str, dict]:
+
+    from notebookutils import mssparkutils
+    from azure.identity import ClientSecretCredential
+
+    tenant_id = mssparkutils.credentials.getSecret(key_vault_uri, key_vault_tenant_id)
+    client_id = mssparkutils.credentials.getSecret(key_vault_uri, key_vault_client_id)
+    client_secret = mssparkutils.credentials.getSecret(
+        key_vault_uri, key_vault_client_secret
+    )
+
+    credential = ClientSecretCredential(
+        tenant_id=tenant_id, client_id=client_id, client_secret=client_secret
+    )
+
+    token = credential.get_token("https://management.azure.com/.default").token
+
+    headers = {
+        "Authorization": f"Bearer {token}",
+        "Content-Type": "application/json",
+    }
+
+    return token, credential, headers
+
+
+def convert_to_alphanumeric_lowercase(input_string):
+
+    cleaned_string = re.sub(r"[^a-zA-Z0-9]", "", input_string)
+    cleaned_string = cleaned_string.lower()
+
+    return cleaned_string
+
+
+def resolve_environment_id(environment: str, workspace: Optional[str] = None) -> UUID:
+    """
+    Obtains the environment Id for a given environment.
+
+    Parameters
+    ----------
+    environment: str
+        Name of the environment.
+    """
+    from sempy_labs._environments import list_environments
+
+    (workspace, workspace_id) = resolve_workspace_name_and_id(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]

sempy_labs/_icons.py

@@ -31,3 +31,65 @@ model_bpa_name = "ModelBPA"
 report_bpa_name = "ReportBPA"
 severity_mapping = {warning: "Warning", error: "Error", info: "Info"}
 special_characters = ['"', "/", '"', ":", "|", "<", ">", "*", "?", "'", "!"]
+
+language_map = {
+    "it-IT": "Italian",
+    "es-ES": "Spanish",
+    "he-IL": "Hebrew",
+    "pt-PT": "Portuguese",
+    "zh-CN": "Chinese",
+    "fr-FR": "French",
+    "da-DK": "Danish",
+    "cs-CZ": "Czech",
+    "de-DE": "German",
+    "el-GR": "Greek",
+    "fa-IR": "Persian",
+    "ga-IE": "Irish",
+    "hi-IN": "Hindi",
+    "hu-HU": "Hungarian",
+    "is-IS": "Icelandic",
+    "ja-JP": "Japanese",
+    "nl-NL": "Dutch",
+    "pl-PL": "Polish",
+    "pt-BR": "Portuguese",
+    "ru-RU": "Russian",
+    "te-IN": "Telugu",
+    "ta-IN": "Tamil",
+    "th-TH": "Thai",
+    "zu-ZA": "Zulu",
+    "am-ET": "Amharic",
+    "ar-AE": "Arabic",
+    "sv-SE": "Swedish",
+    "ko-KR": "Korean",
+    "id-ID": "Indonesian",
+    "mt-MT": "Maltese",
+    "ro-RO": "Romanian",
+    "sk-SK": "Slovak",
+    "sl-SL": "Slovenian",
+    "tr-TR": "Turkish",
+    "uk-UA": "Ukrainian",
+    "bg-BG": "Bulgarian",
+    "ca-ES": "Catalan",
+    "fi-FI": "Finnish",
+}
+workspace_roles = ["Admin", "Member", "Viewer", "Contributor"]
+principal_types = ["App", "Group", "None", "User"]
+azure_api_version = "2023-11-01"
+migrate_capacity_suffix = "fsku"
+sku_mapping = {
+    "A1": "F8",
+    "EM1": "F8",
+    "A2": "F16",
+    "EM2": "F16",
+    "A3": "F32",
+    "EM3": "F32",
+    "A4": "F64",
+    "P1": "F64",
+    "A5": "F128",
+    "P2": "F128",
+    "A6": "F256",
+    "P3": "F256",
+    "A7": "F512",
+    "P4": "F512",
+    "P5": "F1024",
+}