Computes the 10 most frequent token from stdin or a couple of files.

wordcount.py

import re
import fileinput
from collections import Counter

token_ptn = re.compile("[^\w]+")
word_count = Counter()

for line in fileinput.input():
    for token in token_ptn.split(line):
        if token != "":
            word_count[token] += 1

for (k,v) in word_count.most_common(10):
    print k, v