Created
July 9, 2011 21:30
-
-
Save mrestko/1073976 to your computer and use it in GitHub Desktop.
Soundex Encoder
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| from itertools import chain, repeat | |
| drops = 'aehiouwy' | |
| ones = 'bfpv' | |
| twos = 'cgjkqsxz' | |
| threes = 'dt' | |
| fours = 'l' | |
| fives = 'mn' | |
| sixes = 'r' | |
| alpha_list = [(ones, 1), (twos, 2), (threes, 3), (fours, 4), (fives, 5), (sixes, 6)] | |
| code = [zip(letter, repeat(code_number)) for letter, code_number in alpha_list] | |
| code_dict = dict(chain.from_iterable(code)) | |
| def soundex(name): | |
| first = name[0].upper() | |
| lowered = name[1:].lower() | |
| dupe_less = rm_dupes(lowered) | |
| dropped = drop(dupe_less) | |
| encoded = encode(dropped) | |
| return (first + encoded + '000')[:4] | |
| def encode(name): | |
| code_nums = [code_dict[c] for c in name] | |
| return ''.join(str(i) for i in code_nums) | |
| def rm_dupes(name): | |
| if len(name) < 2: | |
| return name | |
| elif name[0] == name[1]: | |
| return name[0] + rm_dupes(name[2:]) | |
| else: | |
| return name[0] + rm_dupes(name[1:]) | |
| def drop(name): | |
| return [c for c in name if c not in drops] | |
| if __name__ == "__main__": | |
| name = raw_input("Enter name:") | |
| print soundex(name) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment