mydict = {"&y":"\033[0;30m",
"&c":"\033[0;31m",
"&b":"\033[0;32m",
"&Y":"\033[0;33m",
"&u":"\033[0;34m"}
mystr = "The &yquick &cbrown &bfox &Yjumps over the &ulazy dog"
for k, v in mydict.iteritems():
mystr = mystr.replace(k, v)
print mystr
The ←[0;30mquick ←[0;31mbrown ←[0;32mfox ←[0;33mjumps over the ←[0;34mlazy dog
I took the liberty of comparing a few solutions:
mydict = dict([('&' + chr(i), str(i)) for i in list(range(65, 91)) + list(range(97, 123))])
# random inserts between keys
from random import randint
rawstr="".join(mydict.keys())
mystr=""
for i in range(0, len(rawstr), 2):
mystr += chr(randint(65,91)) * randint(0,20) # insert between 0 and 20 chars
from time import time
# How many times to run each solution
rep = 10000
print 'Running %d times with string length %d and ' \
'random inserts of lengths 0-20' % (rep, len(mystr))
# My solution
t = time()
for x in range(rep):
for k, v in mydict.items():
mystr.replace(k, v)
#print(mystr)
print '%-30s' % 'Tor fixed & variable dict', time()-t
from re import sub, compile, escape
# Peter Hansen
t = time()
for x in range(rep):
sub(r'(&[a-zA-Z])', r'%(\1)s', mystr) % mydict
print '%-30s' % 'Peter fixed & variable dict', time()-t
# Claudiu
def multiple_replace(dict, text):
# Create a regular expression from the dictionary keys
regex = compile("(%s)" % "|".join(map(escape, dict.keys())))
# For each match, look-up corresponding value in dictionary
return regex.sub(lambda mo: dict[mo.string[mo.start():mo.end()]], text)
t = time()
for x in range(rep):
multiple_replace(mydict, mystr)
print '%-30s' % 'Claudio variable dict', time()-t
# Claudiu - Precompiled
regex = compile("(%s)" % "|".join(map(escape, mydict.keys())))
t = time()
for x in range(rep):
regex.sub(lambda mo: mydict[mo.string[mo.start():mo.end()]], mystr)
print '%-30s' % 'Claudio fixed dict', time()-t
# Andrew Y - variable dict
def mysubst(somestr, somedict):
subs = somestr.split("&")
return subs[0] + "".join(map(lambda arg: somedict["&" + arg[0:1]] + arg[1:], subs[1:]))
t = time()
for x in range(rep):
mysubst(mystr, mydict)
print '%-30s' % 'Andrew Y variable dict', time()-t
# Andrew Y - fixed
def repl(s):
return mydict["&"+s[0:1]] + s[1:]
t = time()
for x in range(rep):
subs = mystr.split("&")
res = subs[0] + "".join(map(repl, subs[1:]))
print '%-30s' % 'Andrew Y fixed dict', time()-t
Results in Python 2.6
Running 10000 times with string length 490 and random inserts of lengths 0-20
Tor fixed & variable dict 1.04699993134
Peter fixed & variable dict 0.218999862671
Claudio variable dict 2.48400020599
Claudio fixed dict 0.0940001010895
Andrew Y variable dict 0.0309998989105
Andrew Y fixed dict 0.0310001373291
Both claudiu’s and andrew’s solutions kept going into 0, so I had to increase it to 10 000 runs.
I ran it in Python 3 (because of unicode) with replacements of chars from 39 to 1024 (38 is ampersand, so I didn’t wanna include it). String length up to 10.000 including about 980 replacements with variable random inserts of length 0-20. The unicode values from 39 to 1024 causes characters of both 1 and 2 bytes length, which could affect some solutions.
mydict = dict([('&' + chr(i), str(i)) for i in range(39,1024)])
# random inserts between keys
from random import randint
rawstr="".join(mydict.keys())
mystr=""
for i in range(0, len(rawstr), 2):
mystr += chr(randint(65,91)) * randint(0,20) # insert between 0 and 20 chars
from time import time
# How many times to run each solution
rep = 10000
print('Running %d times with string length %d and ' \
'random inserts of lengths 0-20' % (rep, len(mystr)))
# Tor Valamo - too long
#t = time()
#for x in range(rep):
# for k, v in mydict.items():
# mystr.replace(k, v)
#print('%-30s' % 'Tor fixed & variable dict', time()-t)
from re import sub, compile, escape
# Peter Hansen
t = time()
for x in range(rep):
sub(r'(&[a-zA-Z])', r'%(\1)s', mystr) % mydict
print('%-30s' % 'Peter fixed & variable dict', time()-t)
# Peter 2
def dictsub(m):
return mydict[m.group()]
t = time()
for x in range(rep):
sub(r'(&[a-zA-Z])', dictsub, mystr)
print('%-30s' % 'Peter fixed dict', time()-t)
# Claudiu - too long
#def multiple_replace(dict, text):
# # Create a regular expression from the dictionary keys
# regex = compile("(%s)" % "|".join(map(escape, dict.keys())))
#
# # For each match, look-up corresponding value in dictionary
# return regex.sub(lambda mo: dict[mo.string[mo.start():mo.end()]], text)
#
#t = time()
#for x in range(rep):
# multiple_replace(mydict, mystr)
#print('%-30s' % 'Claudio variable dict', time()-t)
# Claudiu - Precompiled
regex = compile("(%s)" % "|".join(map(escape, mydict.keys())))
t = time()
for x in range(rep):
regex.sub(lambda mo: mydict[mo.string[mo.start():mo.end()]], mystr)
print('%-30s' % 'Claudio fixed dict', time()-t)
# Separate setup for Andrew and gnibbler optimized dict
mydict = dict((k[1], v) for k, v in mydict.items())
# Andrew Y - variable dict
def mysubst(somestr, somedict):
subs = somestr.split("&")
return subs[0] + "".join(map(lambda arg: somedict[arg[0:1]] + arg[1:], subs[1:]))
def mysubst2(somestr, somedict):
subs = somestr.split("&")
return subs[0].join(map(lambda arg: somedict[arg[0:1]] + arg[1:], subs[1:]))
t = time()
for x in range(rep):
mysubst(mystr, mydict)
print('%-30s' % 'Andrew Y variable dict', time()-t)
t = time()
for x in range(rep):
mysubst2(mystr, mydict)
print('%-30s' % 'Andrew Y variable dict 2', time()-t)
# Andrew Y - fixed
def repl(s):
return mydict[s[0:1]] + s[1:]
t = time()
for x in range(rep):
subs = mystr.split("&")
res = subs[0] + "".join(map(repl, subs[1:]))
print('%-30s' % 'Andrew Y fixed dict', time()-t)
# gnibbler
t = time()
for x in range(rep):
myparts = mystr.split("&")
myparts[1:]=[mydict[x[0]]+x[1:] for x in myparts[1:]]
"".join(myparts)
print('%-30s' % 'gnibbler fixed & variable dict', time()-t)
Results:
Running 10000 times with string length 9491 and random inserts of lengths 0-20
Tor fixed & variable dict 0.0 # disqualified 329 secs
Peter fixed & variable dict 2.07799983025
Peter fixed dict 1.53100013733
Claudio variable dict 0.0 # disqualified, 37 secs
Claudio fixed dict 1.5
Andrew Y variable dict 0.578000068665
Andrew Y variable dict 2 0.56299996376
Andrew Y fixed dict 0.56200003624
gnibbler fixed & variable dict 0.530999898911
(** Note that gnibbler’s code uses a different dict, where keys don’t have the ‘&’ included. Andrew’s code also uses this alternate dict, but it didn’t make much of a difference, maybe just 0.01x speedup.)