Flickr rev-canonical reverse engineering

baseconv.py

"""
Convert numbers from base 10 integers to base X strings and back again.

Sample usage:

>>> base20 = BaseConverter('0123456789abcdefghij')
>>> base20.from_decimal(1234)
'31e'
>>> base20.from_decimal('31e')
1234

Originally posted to http://www.djangosnippets.org/snippets/1431/ 
by Simon Willison

"""

class BaseConverter(object):
    decimal_digits = "0123456789"
    
    def __init__(self, digits):
        self.digits = digits
    
    def from_decimal(self, i):
        return self.convert(i, self.decimal_digits, self.digits)
    
    def to_decimal(self, s):
        return int(self.convert(s, self.digits, self.decimal_digits))
    
    def convert(number, fromdigits, todigits):
        # Based on http://code.activestate.com/recipes/111286/
        if str(number)[0] == '-':
            number = str(number)[1:]
            neg = 1
        else:
            neg = 0

        # make an integer out of the number
        x = 0
        for digit in str(number):
           x = x * len(fromdigits) + fromdigits.index(digit)
    
        # create the result in base 'len(todigits)'
        if x == 0:
            res = todigits[0]
        else:
            res = ""
            while x > 0:
                digit = x % len(todigits)
                res = todigits[digit] + res
                x = int(x / len(todigits))
            if neg:
                res = '-' + res
        return res
    convert = staticmethod(convert)

bin = BaseConverter('01')
hexconv = BaseConverter('0123456789ABCDEF')
base62 = BaseConverter(
    'ABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789abcdefghijklmnopqrstuvwxyz'
)

if __name__ == '__main__':
    nums = [-10 ** 10, 10 ** 10] + range(-100, 100)
    for convertor in [bin, hex, base62]:
        for i in nums:
            assert i == bin.to_decimal(bin.from_decimal(i)), '%s failed' % i
            

flickr-rev.py

#!/usr/bin/python

# trying to figure out the right base58 string for Flickr
# rev-canonical shortening from ID
# *nearly* there....

# yes, this should be written as a test really

import baseconv
# http://www.djangosnippets.org/snippets/1431/ - baseconv.py

base58 = baseconv.BaseConverter('123456789abcdefghijkmnopqrstuvwxyzABCDEFGHJKLMNPQRSTUVWXYZ')
# thank you kellan! http://www.flickr.com/groups/api/discuss/72157616713786392/

hashes = {3429289555: '6e3w38',
          3368: '215',
          74: '2h',
          75: '2i',
          94: '2C',
          88: '2w',
          195102: 'ZZQ',
          1253576: '7qDo',
          177: '44',
          193: '4k',
          195: '4n',
       }

for dec in hashes.keys():
  print dec,
  print base58.from_decimal(dec),
  print hashes[dec]

# results:
# 3429289555 6e31iZ 6e3w38 # <--- not right: overflow issue with integer?
# 1253576 7qDo 7qDo
# 195102 ZZQ ZZQ
# 3368 215 215
# 195 4n 4n
# 193 4k 4k
# 177 44 44
# 94 2C 2C
# 88 2w 2w
# 75 2i 2i
# 74 2h 2h