Find similar strings

stringsimilars.py

def similar(a, b):
    from difflib import SequenceMatcher
    return SequenceMatcher(None, a, b).ratio()


def list_match(key, mylist):
    mylist = list(set(mylist))      # Get unique values to speed processing
    top_score = -1
    top_name = ""
    for this_name in mylist:
        this_score = similar(key, this_name)
        if this_score > top_score:
            top_score = this_score
            top_name = this_name
    return (top_name, top_score)
    

# .. Where filelist contains a list of keys
# .. and people_without_photos contains the list of possible matches
       for orphan in filelist:
            best_name, best_score = list_match(orphan, people_without_photos)
            print("\t\t" + orphan + "   " + "\t\t Did you mean this?: " + unicode(best_name).encode("utf-8") + "  (" + str(int(round(100*best_score))) + "% match)")