CODEWITHSUNDEEP
python
ealeon
ealeon

Reputation: 12452

python: getting all possible alphabet up to given length

def permutations(iterable, r=None):
    # permutations('ABCD', 2) --> AB AC AD BA BC BD CA CB CD DA DB DC
    # permutations(range(3)) --> 012 021 102 120 201 210
    pool = tuple(iterable)
    n = len(pool)
    r = n if r is None else r
    if r > n:
        return
    indices = list(range(n))
    cycles = list(range(n, n-r, -1))
    yield tuple(pool[i] for i in indices[:r])
    while n:
        for i in reversed(range(r)):
            cycles[i] -= 1
            if cycles[i] == 0:
                indices[i:] = indices[i+1:] + indices[i:i+1]
                cycles[i] = n - i
            else:
                j = cycles[i]
                indices[i], indices[-j] = indices[-j], indices[i]
                yield tuple(pool[i] for i in indices[:r])
                break
        else:
            return

got = permutations(getAllTheLetters(),4)
cnt = 0
for i in got:
    cnt += 1
    print ''.join(i)

print cnt

The above doesnt give 'zzzz' or 'zzz'
I need something like below where it gives: a, b, c, d.. aa, ab, ac, .. aaa, aab...

but do_perm() is hard-coded to loop four times which i dont want to do. 

def getAllTheLetters(begin='a', end='z'):
    beginNum = ord(begin)
    endNum = ord(end)
    yield ''
    for number in xrange(beginNum, endNum+1):
        yield chr(number)

def do_perm(l):
    s = set()
    for a in getAllTheLetters():
        for b in getAllTheLetters():
            for c in getAllTheLetters():
                for d in getAllTheLetters():
                    to_add = "%s%s%s%s" % (a,b,c,d)
                    if to_add != "":
                        s.add(to_add)

    return s

got = do_perm(1)
cnt = 0
for i in sorted(got):
    cnt +=1
    print i
print cnt

Upvotes: 2

Views: 88

Answers (1)

thefourtheye
thefourtheye

Reputation: 239453

You can simply use itertools.product, like this

from itertools import product

def get_strings(letters, max_length):
    for i in range(1, max_length + 1):
        for value in product(letters, repeat=i):
            yield "".join(value)

And when you invoke it like this

print(list(get_strings("ab", 2)))

you will get

['a', 'b', 'aa', 'ab', 'ba', 'bb']

If you want to get all the values from a to z, you can invoke get_strings, like this

from string import ascii_lowercase
print(list(get_strings(ascii_lowercase, 4)))

Note: This will create a hell of a lot of strings, so your machine might stop responding. If you just want to iterate through the strings, use for loop with the get_strings like shown below and don't create a list.

for current_string in get_strings(ascii_lowercase, 4):
    # Process the current_string

Upvotes: 4

Related Questions