Convert Strings to Soundex Equivalents 0

 1"""Soundex algorithm
 2
 3This program is part of "Dive Into Python", a free Python book for
 4experienced programmers.  Visit http://diveintopython.org/ for the
 5latest version.
 6"""
 7
 8__author__ = "Mark Pilgrim (mark@diveintopython.org)"
 9__version__ = "$Revision: 1.5 $"
10__date__ = "$Date: 2004/05/11 19:11:21 $"
11__copyright__ = "Copyright (c) 2004 Mark Pilgrim"
12__license__ = "Python"
13
14import string
15
16allChar = string.uppercase + string.lowercase
17charToSoundex = string.maketrans(allChar, "91239129922455912623919292" * 2)
18
19def soundex(source):
20    "convert string to Soundex equivalent"
21
22    # Soundex requirements:
23    # source string must be at least 1 character
24    # and must consist entirely of letters
25    if (not source) or (not source.isalpha()):
26        return "0000"
27
28    # Soundex algorithm:
29    # 1. make first character uppercase
30    # 2. translate all other characters to Soundex digits
31    digits = source[0].upper() + source[1:].translate(charToSoundex)
32
33    # 3. remove consecutive duplicates
34    digits2 = digits[0]
35    for d in digits[1:]:
36        if digits2[-1] != d:
37            digits2 += d
38        
39    # 4. remove all "9"s
40    # 5. pad end with "0"s to 4 characters
41    return (digits2.replace('9', '') + '000')[:4]
42
43if __name__ == '__main__':
44    import sys
45    if sys.argv[1:]:
46        print soundex(sys.argv[1])
47    else:
48        from timeit import Timer
49        names = ('Woo', 'Pilgrim', 'Flingjingwaller')
50        for name in names:
51            statement = "soundex('%s')" % name
52            t = Timer(statement, "from __main__ import soundex")
53            print name.ljust(15), soundex(name), min(t.repeat())