Python中的字符串操作

array.array :

>>> import array
>>> a = array.array('c', 'foo')
>>> a[1] = 'e'
>>> a
array('c', 'feo')
>>> a.tostring()
'feo'

mmap

>>> f = open('foo', 'r+')
>>> import mmap
>>> m = mmap.mmap(f.fileno(), 0)
>>> m[:]
'foo\n'
>>> m[1] = 'e'
>>> m[:]
'feo\n'
>>> exit()
% cat foo
feo

这是一个快速的基准测试脚本(对于非Unix操作系统,您需要用其他东西替换dd):

import os, time, array, mmap

def modify(s):
    for i in xrange(len(s)):
        s[i] = 'q'

def measure(func):
    start = time.time()
    func(open('foo', 'r+'))
    print func.func_name, time.time() - start

def do_split(f):
    l = list(f.read())
    modify(l)
    return ''.join(l)

def do_array(f):
    a = array.array('c', f.read())
    modify(a)
    return a.tostring()

def do_mmap(f):
    m = mmap.mmap(f.fileno(), 0)
    modify(m)

os.system('dd if=/dev/random of=foo bs=1m count=5')

measure(do_mmap)
measure(do_array)
measure(do_split)

我在几年前的笔记本电脑上得到的输出与我的直觉相符:

5+0 records in
5+0 records out
5242880 bytes transferred in 0.710966 secs (7374304 bytes/sec)
do_mmap 1.00865888596
do_array 1.09792494774
do_split 1.20163106918

cProfile

l = list(str)
l[i] = 'e'
str = ''.join(l)

尝试:

sl = list(s)
sl[i] = 'e'
s = ''.join(sl)