> > But the performance of this is hopeless for very long strings!
> > Presumable because there's too much list reallocation? Can't Python
> > just optimise this by shuffling the start of the list forward?
Using generators here compares favorably with a smart while loop. They have
the advantage of separating the iteration from the processing, so you can
actually reuse gen_substring since it allows you to iterate over the
n-length substrings:
#! /usr/bin/env python
from __future__ import generators
from time import clock
def gen_substring(s, n):
i = 0
end = len(s)
while i <= end:
j = i + n
yield s[i:j]
i = j
def do_gen(s, n):
for sub in gen_substring(s, n):
sub.upper()
def do_while_simple(s, n):
while s:
sub = s[:n]
s = s[n:]
sub.upper()
def do_while_smarter(s, n):
i = 0
end = len(s)
while i <= end:
j = i + n
sub = s[i:j]
i = j
sub.upper()
def time_it(f, *args, **kwargs):
start = clock()
f(*args, **kwargs)
end = clock()
print "%s: %1.3f" % (f.func_name, end - start)
n = 4
size = 100000
s = 'a' * size
time_it(do_gen, s, n)
time_it(do_while_simple, s, n)
time_it(do_while_smarter, s, n)
-