为什么在某些情况下,Python 3中的连接似乎比Python 2中的连接慢？

影响最大的串联方法似乎是字节对象的连续串联,从O(n)到O(n?)操作.

我的分析代码大部分在这里：

#!/usr/bin/env python

from operator import concat

from sys import version, version_info

from timeit import timeit # Compatibility: ver >= 2.6

# ver = version.partition('

')[0].rstrip()

ver = '.'.join(str(v) for v in version_info[:3])

print(ver)

if version_info[0] == 2:

from StringIO import StringIO

else:

from io import StringIO

from functools import reduce

xrange = range

def build_plus():

output = ''

for _ in xrange(input_len):

output += 'a'

return output

def build_join():

return ''.join('a' for _ in xrange(input_len))

def build_bytes_plus():

output = b''

for _ in xrange(input_len):

output += b'a'

return output

def build_stringio():

output = StringIO()

for _ in xrange(input_len):

output.write('a')

return output.getvalue()

def build_reduce():

return reduce(concat, ('a' for _ in xrange(input_len)))

builds = {'str+': build_plus,

'join': build_join,

'reduce': build_reduce,

'bytes+': build_bytes_plus,

'StringIO': build_stringio}

if version_info[0] == 2:

import cStringIO

def build_cstringio():

output = cStringIO.StringIO()

for _ in xrange(input_len):

output.write('a')

return output.getvalue()

builds['cStringIO'] = build_cstringio

else:

from io import BytesIO

def build_bytesio():

output = BytesIO()

for _ in xrange(input_len):

output.write(b'a')

return output.getvalue()

builds['BytesIO'] = build_bytesio

resfile = open('times.csv', 'a')

size_range = 50 # Number of points over the size axis

min_order = 1.0 # 10^x byte input min

max_order = 5.0 # 10^x byte input max

for allow_gc in (False, True):

setup = 'gc.enable()' if allow_gc else 'pass'

for build_name, build_fun in builds.items():

# For a roughly constant confidence interval, aim for uniform sample density across the

# (logarithmic) input size axis.

for size_index in range(size_range+1):

input_len = int(10**((max_order-min_order)*size_index/size_range + min_order))

# Rather than repeating many measurements at one input size, perform one measurement

# per input size for a continuous range of input sizes and apply smoothing later.

dur = timeit(build_fun, setup, number=1)

resfile.write('"%s",%s,"%s",%d,%.6g

' % (ver, str(allow_gc).upper(), build_name,

input_len, dur))

我的R脚本中的一些图形如下所示：