# words_compression.py

# words_compression.py

# note: the following algorithm is already in zlib

import zlib, base64

# todo: replace the following z string with scrabble words
z = '''
aardvark
aback
abaft
abandon
abandoned
abandoning
abandonment
abandons
abase
abased
abasement
abasements
abases
abash
abashed
abashes
abashing
abasing
abate
abated
abatement
abatements
abater
abates
abating
...
zone
zoned
zones
zoning
zoo
zoological
zoologically
zoom
zooms
zoos
'''

s = list('''~'!234567890_+`!@#$%^&*()-={}[]":;\|<>,.?/''')

z = '*'.join([x for x in z.splitlines() if x.islower()])

compressed = zlib.compress(z)
b64 = base64.encodestring(compressed)

print len(z),len(b64)

'''
r = []
x = []
c = ''
zzz = z
while zzz:
    char = zzz[0]
    zzz = zzz[1:]
    if char == '*':
        0
    elif c == '':
        c = char
    elif zzz.count(c+char):
        c += char
    else:
        if len(c) > 1 and c not in x:
            r += [((len(c)-1)*zzz.count(c),c)]
            r.sort(reverse=True)
            r=r[:20]
            x = [b for a,b in r]
            if c in x:
                print r
                print
        c = ''
'''

r = [(7346, 'ing'), (5411, 'es'), (4338, 'tion'), (4190, 'ed'), (4064, 'ng'), (3764, 're'), (3418, 'en'), (3400, 'ion'), (3380, 'ation'), (2816, 'ers'), (2696, 'nt'), (2692, 'at'), (2690, 'te'), (2492, 'ent'), (2482, 'ate'), (2475, 'ting'), (2408, 'ess'), (2377, 'in'), (2361, 'er'), (2334, 'al')]

for a,b in r: z=z.replace(b,s.pop(0))

compressed = zlib.compress(z)
b64 = base64.encodestring(compressed)

print len(z),len(b64)