better_wc_mapper

#!/usr/bin/env python

import sys
import string

def read_input(file):
    printable = set(string.printable)

    for line in file:
        line = filter(lambda x: x in printable, line)
        line = line.strip()
        yield line.lower().split()

def main(separator='\t'):
    ascii_letters = set(string.ascii_letters)
    data = read_input(sys.stdin)
    for words in data:
        for word in words:
            word = filter(lambda x: x in ascii_letters, word)
            word = str.strip(word)

            if len(word) == 1:
                continue

            print '%s\t%s' % (word, 1)

if __name__ == "__main__":
    main()