#!/usr/bin/python
# -*- coding: UTF-8 -*-

"""Soundex algorithm - Version 2.0

Based on Soundex Algorithm of Mark Pilgrim (mark@diveintopython.org)
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 (mark@diveintopython.org)"
__version__ = "$Revision: 1.5 $"
__date__ = "$Date: 2004/05/11 19:11:21 $"
__copyright__ = "Copyright (c) 2004 Mark Pilgrim"
__license__ = "Python"
"""

__author__ = "Florent Carlier (florent.carlier@univ-lemans.fr)"
__version__ = "$Revision: 2.0 $"
__date__ = "$Date: 2005/05/05 $"

import string
import re

def soundex(source):
    "convert string to Soundex equivalent"
    
    # Soundex requirements:
    # source string must be at least 1 character
    if (not source):
        return "0000"

    # 0. Replace "-" and " " by ""
    source = source.replace('-','')
    source = source.replace(' ','')
    source = source.upper()

    # and must consist entirely of letters
    if (not source.isalpha()):
        return "0000"

    allChar = string.uppercase
    tradChar = "91239129922455912623919292"
    charToSoundex = string.maketrans(allChar, tradChar)

    # Soundex algorithm:
    # 1. make first character uppercase
    # 2. translate all other characters to Soundex digits
    digits = source[0] + source[1:].translate(charToSoundex)

    # 3. remove consecutive duplicates
    digits2 = digits[0]
    for d in digits[1:]:
          if digits2[-1] != d:
            digits2 += d

    # 4. remove all "9"s
    # 5. pad end with "0"s to 4 characters
    return (digits2.replace('9', '') + '000')[:4]

def soundex_fr(source):
    "convert string to Soundex equivalent with french relation"
    
    if (not source):
        return "0000"

    source = source.replace('-','')
    source = source.replace(' ','')
    # Remplacer caractere accentués
    source = source.replace('é','E')
    source = source.replace('è','E')
    source = source.replace('ë','E')
    source = source.replace('ê','E')
    source = source.replace('à','A')
    source = source.replace('ä','A')
    source = source.replace('ç','C')
    source = source.replace('î','I')
    source = source.replace('ï','I')
    source = source.replace('ô','O')
    source = source.replace('ö','O')
    source = source.replace('ù','U')
    source = source.replace('ü','U')
    source = source.replace('û','U')
    source = source.upper()

    if (not source.isalpha()):
        return "0000"

    allChar = string.uppercase
    tradChar = "01230970072455012683090908"
    charToSoundex = string.maketrans(allChar, tradChar)
    digits = source[0] + source[1:].translate(charToSoundex)

    digits2 = digits[0]
    for d in digits[1:]:
          if digits2[-1] != d:
            digits2 += d

    return (digits2.replace('0', '') + '000')[:4]

def diff_hamming(soundex1, soundex2):
    """ return the hamming different """
    return "0 : Identique"
    return "1 : Difference N1"
    return "2 : Difference N2"
    return "3 : Difference N3"
    return "4 : Dissemblable"

def soundex2(source):
    "convert string to Soundex equivalent"
    
    # Soundex requirements:
    # source string must be at least 1 character
    if (not source):
        return "0000"

    # 0. Replace "-" and " " by ""
    source = source.replace('-','')
    source = source.replace(' ','')
    source = source.upper()

    # and must consist entirely of letters
    if (not source.isalpha()):
        return "0000"

    # Etape : Remplacement groupes lettres par correspondance
    source = source.replace('GUI','KI')
    source = source.replace('GUE','KE')
    source = source.replace('GA' ,'KA')
    source = source.replace('GO' ,'KO')
    source = source.replace('GU' ,'K')
    source = source.replace('CA' ,'KA')
    source = source.replace('CO' ,'KO')
    source = source.replace('CU' ,'KU')
    source = source.replace('Q'  ,'K')
    source = source.replace('CC' ,'K')
    source = source.replace('CK' ,'K')

    # Etape : Remplcaement des voyelles
    VoyelleToA = string.maketrans("AEIOU", "AAAAA")
    source = source[0] + source[1:].translate(VoyelleToA)

    # Etape : Remplacement des Prefixe
    source = source[0:3].replace('MAC', 'MCC') + source[3:]
    source = source[0:3].replace('SCH', 'SSS') + source[3:]
    source = source[0:3].replace('ASA', 'AZA') + source[3:]
    source = source[0:2].replace('KN','NN') + source[2:]
    source = source[0:2].replace('PH','FF') + source[2:]
    source = source[0:2].replace('PF','FF') + source[2:]

    # Etape H -> '' sauf SH et CH
    source2 = re.sub(r'([^C|S])H', r'\1', source)

    # Etape Y -> '' sauf A
    source3 = re.sub(r'([^A])Y', r'\1', source2)

    # Etape : Suppression des terminaisons A, D, T, S
    source4 = re.sub(r'(.*)[A|D|T|S]$',r'\1', source3)

    # Etape : Suppression des A sauf En-tete
    source5 = source4[0] + source4[1:].replace('A','')

    # Remove consecutive duplicates
    source6 = source5[0]
    for d in source5[1:]:
          if source6[-1] != d:
             source6 += d
        
    return (source6+ '   ')[:4]