# count words in a text and show the first ten items
# by decreasing frequency
 
# sample text for testing
 
import sys
import string
import re
file = open ("arb.txt", "r")
text = file.read ( )
file.close ( )
 
word_freq = {}
 
word_list = text.split()
 
for word in word_list:
    # word all lower case
    word = word.lower()
    # strip any trailing period or comma
    word = word.rstrip('.,/"-_;\[]()')
    # build the dictionary
    count = word_freq.get(word, 0)
    word_freq[word] = count + 1
 
# create a list of (freq, word) tuples
freq_list = [(freq, word) for word, freq in word_freq.items()]
 
# sort the list by the first element in each tuple (default)
freq_list.sort(reverse=True)
 
for n, tup in enumerate(freq_list):
    # print the first ten items
    if n < 10:
        freq, word = tup
        print freq, word