统计文件中单词的个数---Shell及python版

#!/bin/bash
if [ $# -ne 1 ];then
echo "Usage:basename $0 filename"
exit 1
fi


filename=$1
egrep -o "[a-zA-Z]+" $filename |
awk ‘{count[$0]++}
END{printf "%-14s %s\n","Word","Count"
for(i in count)printf "%-14s %s\n",i,count[i]|"sort -nrk 2"}‘

[root@localhost shellcookbook]# sh word_freq.sh item.txt 
Word           Count
Tennis         2
Sports         2
Racket         2
Printer        2
Office         2
Laser          2
Video          1
Refrigerator   1
Player         1
MP             1
HD             1
Camcorder      1
Audio          1
Appliance      1

#!/usr/bin/env python
import sys,re

if len(sys.argv[0:]) != 2:
    print "Usage:%s file" % sys.argv[0]
    sys.exit(0)

try:
    filename=sys.argv[1]
    with open(filename) as f:
        data=f.read()
except IOError:
    print "Please check %s is Exised!" % filename
    exit(0)
except Exception,e:
    print e
    sys.exit()

patten=r‘[a-zA-Z]+‘
words=re.findall(patten,data)
#print sorted([(i,words.count(i)) for i in set(words)],cmp=lambda x,y:cmp(x[1],y[1]),reverse=True)
wordcounts=sorted([(i,words.count(i)) for i in set(words)],key=lambda x:x[1],reverse=True)
print "%-14s %s" % ("Word","Counts")
for word,counts in wordcounts:
    print "%-14s %s" % (word,counts)

# time sh word_freq.sh item.txt 

real    0m0.007s
user    0m0.003s
sys     0m0.005s

time python word_freq_py.py item.txt 

real    0m0.035s
user    0m0.031s
sys     0m0.004s