snippets / Remplace les caractères accentués par leurs équivalents

Language: Python - First posted by manatlan on 2007-10-3 18:33 (1 year, 1 month)
Link to the snippet: http://www.friendsnippets.org/snippet/35/

Exemple d'utilisation Accents.clean("mämé") == "mame"

snippet: view plain - save this
 1 class Accents:
 2     __reptable = {}
 3 
 4     __corresp = [
 5         (u"A",  [0x00C0,0x00C1,0x00C2,0x00C3,0x00C4,0x00C5,0x0100,0x0102,0x0104]),
 6         (u"AE", [0x00C6]),
 7         (u"a",  [0x00E0,0x00E1,0x00E2,0x00E3,0x00E4,0x00E5,0x0101,0x0103,0x0105]),
 8         (u"ae", [0x00E6]),
 9         (u"C",  [0x00C7,0x0106,0x0108,0x010A,0x010C]),
10         (u"c",  [0x00E7,0x0107,0x0109,0x010B,0x010D]),
11         (u"D",  [0x00D0,0x010E,0x0110]),
12         (u"d",  [0x00F0,0x010F,0x0111]),
13         (u"E",  [0x00C8,0x00C9,0x00CA,0x00CB,0x0112,0x0114,0x0116,0x0118,0x011A]),
14         (u"e",  [0x00E8,0x00E9,0x00EA,0x00EB,0x0113,0x0115,0x0117,0x0119,0x011B]),
15         (u"G",  [0x011C,0x011E,0x0120,0x0122]),
16         (u"g",  [0x011D,0x011F,0x0121,0x0123]),
17         (u"H",  [0x0124,0x0126]),
18         (u"h",  [0x0125,0x0127]),
19         (u"I",  [0x00CC,0x00CD,0x00CE,0x00CF,0x0128,0x012A,0x012C,0x012E,0x0130]),
20         (u"i",  [0x00EC,0x00ED,0x00EE,0x00EF,0x0129,0x012B,0x012D,0x012F,0x0131]),
21         (u"IJ", [0x0132]),
22         (u"ij", [0x0133]),
23         (u"J",  [0x0134]),
24         (u"j",  [0x0135]),
25         (u"K",  [0x0136]),
26         (u"k",  [0x0137,0x0138]),
27         (u"L",  [0x0139,0x013B,0x013D,0x013F,0x0141]),
28         (u"l",  [0x013A,0x013C,0x013E,0x0140,0x0142]),
29         (u"N",  [0x00D1,0x0143,0x0145,0x0147,0x014A]),
30         (u"n",  [0x00F1,0x0144,0x0146,0x0148,0x0149,0x014B]),
31         (u"O",  [0x00D2,0x00D3,0x00D4,0x00D5,0x00D6,0x00D8,0x014C,0x014E,0x0150]),
32         (u"o",  [0x00F2,0x00F3,0x00F4,0x00F5,0x00F6,0x00F8,0x014D,0x014F,0x0151]),
33         (u"OE", [0x0152]),
34         (u"oe", [0x0153]),
35         (u"R",  [0x0154,0x0156,0x0158]),
36         (u"r",  [0x0155,0x0157,0x0159]),
37         (u"S",  [0x015A,0x015C,0x015E,0x0160]),
38         (u"s",  [0x015B,0x015D,0x015F,0x01610,0x017F]),
39         (u"T",  [0x0162,0x0164,0x0166]),
40         (u"t",  [0x0163,0x0165,0x0167]),
41         (u"U",  [0x00D9,0x00DA,0x00DB,0x00DC,0x0168,0x016A,0x016C,0x016E,0x0170,0x172]),
42         (u"u",  [0x00F9,0x00FA,0x00FB,0x00FC,0x0169,0x016B,0x016D,0x016F,0x0171]),
43         (u"W",  [0x0174]),
44         (u"w",  [0x0175]),
45         (u"Y",  [0x00DD,0x0176,0x0178]),
46         (u"y",  [0x00FD,0x00FF,0x0177]),
47         (u"Z",  [0x0179,0x017B,0x017D]),
48         (u"z",  [0x017A,0x017C,0x017E])
49         ]
50     for __repchar,__codes in __corresp :
51         for __code in __codes :
52             __reptable[__code] = __repchar
53 
54     @staticmethod
55     def clean(s):
56         """ enleve les accents de 's' (unicode ou utf8), et renvoi de l'unicode
57             (marche pour maj et minuscules !!!)
58         """
59         if isinstance(s,str) :
60             s = unicode(s,"utf8","replace")
61         return s.translate(Accents.__reptable)
In order to post a comment, you should have a friendsnippet account. Please sign-in.

2 comments

  • haypo
    October 4th 2007 at 11:45

    Voir aussi mon snippet qui fait la même chose ;-)

  • asrenzo
    October 4th 2007 at 11:25
     1 # -*- coding: UTF-8 -*-
     2 # ***** BEGIN LICENSE BLOCK *****
     3 #
     4 #   Copyright 2007, laurent.rahuel@gmail.com
     5 #
     6 #   Licensed under the Apache License, Version 2.0 (the "License");
     7 #   you may not use this file except in compliance with the License.
     8 #   You may obtain a copy of the License at
     9 #
    10 #       http://www.apache.org/licenses/LICENSE-2.0
    11 #
    12 #   Unless required by applicable law or agreed to in writing, software
    13 #   distributed under the License is distributed on an "AS IS" BASIS,
    14 #   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
    15 #   See the License for the specific language governing permissions and
    16 #   limitations under the License.
    17 #
    18 # ***** END LICENSE BLOCK *****
    19 import unicodedata
    20 
    21 def clean_string(my_string, encoding = 'utf-8'):
    22     my_string = my_string.decode(encoding)
    23     strange_chars_dict = {u'Æ':u'AE', u'æ':u'ae', u'Œ':u'OE', u'œ':u'oe', u'ß':u'ss'}
    24     for strange_char in strange_chars_dict.keys():
    25         my_string = my_string.replace(strange_char, strange_chars_dict[strange_char])
    26     my_string = unicodedata.normalize('NFKD', my_string).encode('ascii','ignore').decode('ascii')
    27     return my_string.encode(encoding)
    28 
    29 
    30 print clean_string("aàeéèêiîïù")

    aaeeeeiiiu

Oct '07

  • Exemple d'utilisation Accents.clean("mämé") == "mame"

    manatlan

Nov '07
Mar '08
Sep '08

  • Replace strange charactes. Trocar caracteres estranhos por normais.

    alanjds

Common Tags


Related snippets


snippet History

Oct '07
Nov '07
Mar '08
Sep '08