soundex2a.py

Dive Into Python,Some Example Sources.

"""Soundex algorithm

This program is part of "Dive Into Python", a free Python book for
experienced programmers.  Visit http://diveintopython.org/ for the
latest version.
"""

__author__ = "Mark Pilgrim ([e-mail])"
__version__ = "$Revision: 1.3 $"
__date__ = "$Date: 2004/05/11 19:11:21 $"
__copyright__ = "Copyright (c) 2004 Mark Pilgrim"
__license__ = "Python"

import string, re

charToSoundex = {"A": "9",
                 "B": "1",
                 "C": "2",
                 "D": "3",
                 "E": "9",
                 "F": "1",
                 "G": "2",
                 "H": "9",
                 "I": "9",
                 "J": "2",
                 "K": "2",
                 "L": "4",
                 "M": "5",
                 "N": "5",
                 "O": "9",
                 "P": "1",
                 "Q": "2",
                 "R": "6",
                 "S": "2",
                 "T": "3",
                 "U": "9",
                 "V": "1",
                 "W": "9",
                 "X": "2",
                 "Y": "9",
                 "Z": "2"}

def soundex(source):
    "convert string to Soundex equivalent"

    # Soundex requirements:
    # source string must be at least 1 character
    # and must consist entirely of letters
    if (not source) or (not source.isalpha()):
        return "0000"

    # Soundex algorithm:
    # 1. make first character uppercase
    # 2. translate all other characters to Soundex digits
    source = source.upper()
    digits = source[0] + "".join(map(lambda c: charToSoundex[c], source[1:]))

    # 3. remove consecutive duplicates
    digits2 = digits[0]
    for d in digits[1:]:
        if digits2[-1] != d:
            digits2 += d
        
    # 4. remove all "9"s
    digits3 = re.sub('9', '', digits2)
    
    # 5. pad end with "0"s to 4 characters
    while len(digits3) < 4:
        digits3 += "0"
        
    # 6. return first 4 characters
    return digits3[:4]

if __name__ == '__main__':
    from timeit import Timer
    names = ('Woo', 'Pilgrim', 'Flingjingwaller')
    for name in names:
        statement = "soundex('%s')" % name
        t = Timer(statement, "from __main__ import soundex")
        print name.ljust(15), soundex(name), min(t.repeat())