Testing the performance of Python awk sed when reading a file at a specified location

#!/bin/env python

#coding: UTF8

‘‘‘

awk prints the specified number of rows

SED prints the specified number of lines

Python prints the specified position, a length string

Awk takes the longest, a long time

Sed awk time Half

Python time-consuming basic negligible

When you use a script to monitor log files, the location of the last exit is logged

Python is the most efficient.

‘‘‘

Import OS

From time Import time

From Os.path import GetSize

testfile= '/dev/shm/%s '% time ()

#生成文件总行数 10**8 approx. 800M 10**7 approx. 80M

Linesize=10**7

#提取文件中间行

Halfline=int (LINESIZE/2)

#文件大小一半

Halffilesize=0

#测试次数

num=10

#生成文件大小

Filesize=0

R=[]

Def create_testfile ():

F=open (testfile, ' W ')

For I in Xrange (linesize):

F.write (str (i) + ' \ n ')

F.close ()

def time1 (func):

T1=time ()

Func ()

T2=time ()

T=t2-t1

Print Func.func_name,t

R.append ("%s:\t\t%s"% (FUNC.FUNC_NAME,STR (t)))

Def awk ():

For I in range (num):

Os.system ("/bin/awk ' nr==%s {print $} '%s '% (halfline,testfile))

def sed ():

For I in range (num):

Os.system ("/bin/sed-n%sp%s"% (Halfline,testfile))

#os. System ("/bin/sed-n%sp%s|awk ' {print $} '"% (halfline,testfile))

def py ():

For I in range (num):

Fn=open (testfile)

#读取

Fn.seek (Halffilesize)

Print Fn.read (7)

Fn.close ()

Print "Create Test file!"

Create_testfile ()

Filesize=getsize (testfile)

Halffilesize=int (FILESIZE/2)

Time1 (awk)

TIME1 (SED)

Time1 (PY)

print "\ n"

Print "halffilesize:\t\t", halffilesize

Print "filesize:\t\t", FileSize

Os.system ('/bin/ls-lh%s '% testfile)

print "\ T"

For I in R:

Print I

Os.unlink (testfile)

Testing the performance of Python awk sed when reading a file at a specified location