#!/usr/bin/env python

from azure.identity import DefaultAzureCredential
from azure.mgmt.datafactory import DataFactoryManagementClient
from azure.mgmt.datafactory.models import DatasetResource
from azure.identity import DefaultAzureCredential
from azure.identity import ClientSecretCredential
import json

# Replace with your Azure subscription ID and resource group name
subscription_id = '<subid>'
credential = DefaultAzureCredential()
resource_group_name = "<myrg>"
data_factory_name = "<myadf>"

adf_client = DataFactoryManagementClient(credential, subscription_id)

# Define dataset properties
dataset_name = "test_dataset"
dataset = '{"properties": {"linkedServiceName": { "referenceName": "AzureSqlDatabase1","type": "LinkedServiceReference"},"type": "AzureSqlTable","folder": {"name": "azuresql_test"},"typeProperties": {"schema": "sales","table": "customers"}}}'
dataset = json.loads(dataset)
print(dataset)

# Create the dataset in the Data Factory
adf_client.datasets.create_or_update(resource_group_name, data_factory_name, dataset_name, dataset)
print("created dataset")

# Fetch the dataset schema
print("Fetch the dataset schema")
dataset = adf_client.datasets.get(resource_group_name, data_factory_name, dataset_name)
print('dataset', dataset)
schema = dataset.properties["typeProperties"]["schema"]

# Now you can use the 'schema' dictionary to get information about column names, data types, etc.
print(schema)