mdrakiburrahman

# Import widgets for Event Hub (i.e. topic) name

# Set default
dbutils.widgets.text("topic", "your--topic--name")
topic = dbutils.widgets.get("topic")

# Import required modules
from pyspark.sql import *
from pyspark.sql.functions import *
from pyspark.sql.types import *

mdrakiburrahman

### Azure Data Factory info
$SubscriptionName = "Azure Subscription Name"
$ResourceGroupName = "Resource Group Name containing Data Factory"
$DataFactoryName = "Data Factory Name"
$AzureSSISName = "SSIS IR Name that will appear in Portal"
$AzureSSISDescription = "E.g. Testing SSIS IR Deployment through PowerShell"
$AzureSSISLocation = "CanadaCentral"
$AzureSSISNodeSize = "Standard_D8_v3"
$AzureSSISNodeNumber = 4
$AzureSSISEdition = "Standard"

mdrakiburrahman

param(
 [string]
 $gatewayKey
)

# init log setting
$logPath = "$PWD\tracelog.log"
"Start to excute SHIRInstall.ps1. `n" | Out-File $logPath

function Now-Value()

mdrakiburrahman

import requests
import json
from termcolor import colored

def aadtoken(client_id, client_secret, client_tenant):
    url = "https://login.microsoftonline.com/{}/oauth2/token".format(client_tenant)
    payload='grant_type=client_credentials&client_id={}&client_secret={}&resource=https%3A%2F%2Fpurview.azure.net'.format(client_id, client_secret)
    response = requests.request("POST", url, data=payload)

    return json.loads(response.text)['access_token']

mdrakiburrahman

import requests
import json
from termcolor import colored

def aadtoken(client_id, client_secret, client_tenant):
    url = "https://login.microsoftonline.com/{}/oauth2/token".format(client_tenant)
    payload='grant_type=client_credentials&client_id={}&client_secret={}&resource=https%3A%2F%2Fpurview.azure.net'.format(client_id, client_secret)
    response = requests.request("POST", url, data=payload)

    return json.loads(response.text)['access_token']

mdrakiburrahman

import os
import requests
import json
import jmespath
import pandas as pd
from pprint import pprint

def azuread_auth(tenant_id: str, client_id: str, client_secret: str, resource_url: str):
    """
    Authenticates Service Principal to the provided Resource URL, and returns the OAuth Access Token

mdrakiburrahman

{
    "entities": [
        {
            "attributes": {
                "name": "aemigration.database.windows.net",
                "qualifiedName": "mssql://aemigration.database.windows.net"
            },
            "collectionId": "aia-purview-new",
            "status": "ACTIVE",
            "typeName": "azure_sql_server"

mdrakiburrahman

network:
  ethernets:
    eth0:
      dhcp4: true
      dhcp4-overrides:
        route-metric: 100
      dhcp6: false
    addresses: [172.20.0.0/21]
    nameservers:
      addresses: [172.20.0.4, 168.63.129.16]

mdrakiburrahman

// Kafka Topic ➡ Delta tables: `scene` via Spark Streaming
// `SOURCE`: Connect to Kafka topic as a streaming Dataframe: `raw_DF`

import org.apache.spark.sql.types._
import org.apache.spark.sql.functions._
import org.apache.spark.sql._
import org.apache.spark.sql.types.StructType
import org.apache.spark.sql.functions.from_json

// Pull from Key Vault for non-sandbox

mdrakiburrahman

URL="http://localhost:9200"
from=20
to=30
for i in `seq $from $to`
do
  # Delete index if older than i days
  DATE=`date -d "$dataset_date - $i days" +%Y.%m.%d`
  echo "Deleting day: $DATE"
  curl -XDELETE "$URL/logstash-$DATE" # Comment out to see what range is deleted
done