string-manipulation.py

#String Manipulation
orders = sc.textFile("/public/retail_db/orders")
s = orders.first()

#first character from a string
s[0]

#first 10 characters from a string
s[:10]

#get length of string
len(s)

#One way to get the date, but it will not work if the order id before first
#comma is more than one character or digit
s[2:12]

#split and extract date
s.split(",")
type(s.split(","))
#Get Date
s.split(",")[1]
#Get customer id
s.split(",")[2]

#type casting to integer
int(s.split(",")[0])

#type casting integer to string
print("printing " + str(1))

int(s.split(",")[1].split(" ")[0].replace("-", ""))