Python MR Mapper

mapper.py

#!/usr/bin/env python3.4

import sys

#input from STDIN
for line in sys.stdin:
    #remove all trailing and leading whitespaces
    line = line.strip()
    #split line into words
    words = line.split()
    #loop for all the words in the words list
    for word in words:
        #output to STDOUT, the word and its count
        #we give count = 1 to every word here
        #this output is input to reducer
        #trivially tab delimited!
        print( '{0}\t{1}'. format(word, 1))