It counts the amount of occurrences of words in a file and sorts those words. This script accepts a file as first parameter or it use the stdin if no arguments are given.

word_count.py

#!/usr/bin/python
# -*- coding: iso-8859-1 -*-
__version__ = "$Revision: 0.5 $"
__author__ = "Pierrick Terrettaz"
__date__ = "2006-12-09"

import sys
import time
import re

if __name__ == "__main__":
    start = time.time()
    try:
        f = open(sys.argv[1])
    except:
        f = sys.stdin
    d = {}
    lsum = 0
    vocabulary = 0
    for line in f:
        lsum += 1
        if line[-1] == '\n':
            line = line[:-1]
        
        for word in re.split('\s', line):
            if word != '':
                word = word.lower()
                if not d.has_key(word):
                    d[word] = 1
                    vocabulary += 1
                else:
                    d[word] = d[word] + 1
    f.close()
    rev_items = [(v, k) for k, v in d.items()]
    rev_items.sort()
    wsum = sum(d.values())
    for v, k in rev_items:
        ratio = float(v) / wsum * 100
        print "%s (%.2f%%): %s" % (v, ratio, k)
    print "lines: %s" % lsum
    print "words: %s" % wsum
    print "vocabulary: %s" % vocabulary
    print "script ended in : %d secondes" % (time.time() - start)