Countword

#!/usr/bin/python

import sys
list = []
current_word = None
count_pool = []
sum = 0
file1 = 'd:/share/1business.seg.txt'
file = open(file1, 'r', encoding='UTF-8')
for line in file:
        ss = line.strip().split(' ')
        for s in ss:
                if s.strip() != "":
                        #print "%s\t%s" % (s, 1)
                        y = [s, 1]
                        list.append(y)
out_data = sorted(list, key=lambda x: x[0])
for line in out_data:
        word = line[0]
        val = line[1]

        if current_word == None:
                current_word = word

        if current_word != word:
                for count in count_pool:
                        sum += count
                print("%s\t%s" % (current_word, sum))
                current_word = word
                count_pool = []
                sum = 0
        count_pool.append(int(val))

for count in count_pool:
        sum += count
print("%s\t%s" % (current_word, str(sum)))