sequence matcher

x.py

from collections import defaultdict
from functools import partial
from pprint import pprint


match = {
    'abc': {
            '123':1,
            '234':2,
            '333':3,
            '4444':4,
            '55555':5,
            },
    
    'def': {
            '123':1,
            '234':2,
            '333':3,
            '4444':4,
            },
    'hiumpp': {
            '123':1,
            '234':2,
            '333':3,
            '4444':4,
            '55555':5,
            },
    }

def find_slice_sizes(match):
    ''' take a match dictionary and find out what different slice sizes
    we need to match to
    '''

    # first we make a set of all the lengths.  Set's automatically dedup
    generic_sizes = set([len(i) for i in match])
    # but sets do not maintain order, so we sort and force into a list
    generic_sizes = list(sorted(generic_sizes))
    

    # now we do the same thing for each specific
    specific_sizes = defaultdict(set)
    for generic, specifics in match.items():
        for specific in specifics:
            specific_sizes[generic].add(len(specific))

    # and here we force the sets into sorted lists
    
    specific_sizes = {k: list(sorted(v)) for k,v in
                          specific_sizes.items()}
    
    return generic_sizes, specific_sizes

def check_sequences(match, generic_sizes, specific_sizes, a, b):
    for generic_boundary in generic_sizes:
        g_seq = a[:generic_boundary]
        print(g_seq)
        if g_seq not in match:
            print('miss')
            continue
        print('hit')
        for specific_boundary in specific_sizes[g_seq]:
            s_seq = b[:specific_boundary]
            print('\ts_seq: {}'.format(s_seq))
            if s_seq not in match[g_seq]:
                print('\tmiss')
                continue
            print('\thit')
            return match[g_seq][s_seq]
            
# use better variable names than me, but you can see what I am doing here
g,s = find_slice_sizes(match)
pprint(g)
pprint(s)

# partial freezes a function so that you can fix the first n operators
# here we freeze check_sequences, with match, generic_sizes, and
# specific_sizes frozen
check = partial(check_sequences, match, g, s)

#now we can run check_sequences, with match, generic_sizes, and specific_sizes
# already frozen in place with partial

print(check('hiumppabcdefg', '33355555'))