"""
n-gram of a string by characters (not by words)

takes all args as input unless the first two args are numbers which are in
order, then it assume these are min and max length. Default min max is 2 - 60
"""


def ngram(inp='', mn=2, mx=60):
    """
    Returns a list of all segments of input inp that range
    in length from mn to mx characters.

    List comprehension version of the below code runs faster than it:
        def ngram(inp='', mn=2, mx=60):
            out = []
            for i in range(0, len(inp) + 1 - mn):
                for j in range(i + mn, min(i + mx + 1, len(inp) + 1)):
                    out.append(inp[i:j])
            return out
    """
    return [
        inp[i:j]
        for i in range(0, len(inp) + 1 - mn)
        for j in range(i + mn, min(i + mx + 1, len(inp) + 1))
    ]


def main():
    from sys import argv
    mn = 2
    mx = 60
    if len(argv) < 2:
        return
    if len(argv) > 3:
        try:
            pmn = int(argv[1])
            pmx = int(argv[2])
            if pmn < pmx:
                mn = pmn
                mx = pmx
                argv.pop(0)
                argv.pop(0)
        except ValueError:
            pass
    res = ngram(inp=" ".join(argv[1:]), mn=mn, mx=mx)
    print(res)
    print('{} values.'.format(len(res)))
    print('{} unique values.'.format(len({k: 1 for k in res}.keys())))


if __name__ == '__main__':
    main()