MonScoDocEssai/SuppressAccents.py

207 lines
5.7 KiB
Python

# -*- mode: python -*-
# -*- coding: utf-8 -*-
"""Suppression des accents d'une chaine
Source: http://wikipython.flibuste.net/moin.py/JouerAvecUnicode#head-1213938516c633958921591439c33d202244e2f4
"""
_reptable = {}
def _fill_reptable():
_corresp = [
(
u"A",
[0x00C0, 0x00C1, 0x00C2, 0x00C3, 0x00C4, 0x00C5, 0x0100, 0x0102, 0x0104],
),
(u"AE", [0x00C6]),
(
u"a",
[0x00E0, 0x00E1, 0x00E2, 0x00E3, 0x00E4, 0x00E5, 0x0101, 0x0103, 0x0105],
),
(u"ae", [0x00E6]),
(u"C", [0x00C7, 0x0106, 0x0108, 0x010A, 0x010C]),
(u"c", [0x00E7, 0x0107, 0x0109, 0x010B, 0x010D]),
(u"D", [0x00D0, 0x010E, 0x0110]),
(u"d", [0x00F0, 0x010F, 0x0111]),
(
u"E",
[0x00C8, 0x00C9, 0x00CA, 0x00CB, 0x0112, 0x0114, 0x0116, 0x0118, 0x011A],
),
(
u"e",
[
0x00E8,
0xE9,
0x00E9,
0x00EA,
0xEB,
0x00EB,
0x0113,
0x0115,
0x0117,
0x0119,
0x011B,
],
),
(u"G", [0x011C, 0x011E, 0x0120, 0x0122]),
(u"g", [0x011D, 0x011F, 0x0121, 0x0123]),
(u"H", [0x0124, 0x0126]),
(u"h", [0x0125, 0x0127]),
(
u"I",
[0x00CC, 0x00CD, 0x00CE, 0x00CF, 0x0128, 0x012A, 0x012C, 0x012E, 0x0130],
),
(
u"i",
[0x00EC, 0x00ED, 0x00EE, 0x00EF, 0x0129, 0x012B, 0x012D, 0x012F, 0x0131],
),
(u"IJ", [0x0132]),
(u"ij", [0x0133]),
(u"J", [0x0134]),
(u"j", [0x0135]),
(u"K", [0x0136]),
(u"k", [0x0137, 0x0138]),
(u"L", [0x0139, 0x013B, 0x013D, 0x013F, 0x0141]),
(u"l", [0x013A, 0x013C, 0x013E, 0x0140, 0x0142]),
(u"N", [0x00D1, 0x0143, 0x0145, 0x0147, 0x014A]),
(u"n", [0x00F1, 0x0144, 0x0146, 0x0148, 0x0149, 0x014B]),
(
u"O",
[0x00D2, 0x00D3, 0x00D4, 0x00D5, 0x00D6, 0x00D8, 0x014C, 0x014E, 0x0150],
),
(
u"o",
[0x00F2, 0x00F3, 0x00F4, 0x00F5, 0x00F6, 0x00F8, 0x014D, 0x014F, 0x0151],
),
(u"OE", [0x0152]),
(u"oe", [0x0153]),
(u"R", [0x0154, 0x0156, 0x0158]),
(u"r", [0x0155, 0x0157, 0x0159]),
(u"S", [0x015A, 0x015C, 0x015E, 0x0160]),
(u"s", [0x015B, 0x015D, 0x015F, 0x01610, 0x017F, 0x0218]),
(u"T", [0x0162, 0x0164, 0x0166]),
(u"t", [0x0163, 0x0165, 0x0167]),
(
u"U",
[
0x00D9,
0x00DA,
0x00DB,
0x00DC,
0x0168,
0x016A,
0x016C,
0x016E,
0x0170,
0x172,
],
),
(
u"u",
[
0x00F9,
0x00FA,
0x00FB,
0x00FC,
0x0169,
0x016B,
0x016D,
0x016F,
0x0171,
0xB5,
],
),
(u"W", [0x0174]),
(u"w", [0x0175]),
(u"Y", [0x00DD, 0x0176, 0x0178]),
(u"y", [0x00FD, 0x00FF, 0x0177]),
(u"Z", [0x0179, 0x017B, 0x017D]),
(u"z", [0x017A, 0x017C, 0x017E]),
(
u"",
[
0x80,
0x81,
0x82,
0x83,
0x84,
0x85,
0x86,
0x87,
0x88,
0x89,
0x8A,
0x8B,
0x8C,
0x8D,
0x8E,
0x8F,
0x90,
0x91,
0x92,
0x93,
0x94,
0x95,
0x96,
0x97,
0x98,
0x99,
0x9A,
0x9B,
0x9C,
0x9D,
0x9E,
0x9F,
],
), # misc controls
(u" ", [0x00A0]), # &nbsp
(u"!", [0xA1]), # ¡
(u"c", [0xA2]), # cent
(u"L", [0xA3]), # pound
(u"o", [0xA4]), # currency symbol
(u"Y", [0xA5]), # yen
(u"|", [0xA6]), # Broken Bar ¦
(u"S", [0xA7]), # section
(u"", [0xA8]), # diaeresis ¨
(u"", [0xA9]), # copyright
(u'"', [0xAB, 0xBA]), # &laquo;, &raquo; <<, >>
(u" ", [0xAC]), # Math Not Sign
(u"", [0xAD]), # DashPunctuation
(u"(r)", [0xAE]), # registred
(u"-", [0xAF]), # macron
(u"", [0xB0]), # degre
(u"+-", [0xB1]), # +-
(u"2", [0x00B2, 0xB2]), # deux exposant
(u"3", [0xB3]), # 3 exposant
(u".", [0xB7]), # &middot;,
(u"1/4", [0xBC]), # 1/4
(u"1/2", [0xBD]), # 1/2
(u"3/4", [0xBE]), # 3/4
(u"e", [0x20AC]), # euro
(u"--", [0x2013]), # EN DASH
(u"'", [0x2018, 0x2019, 0x201A]), # LEFT, RIGHT SINGLE QUOTATION MARK
(u" ", [0x2020]), # dagger
]
global _reptable
for repchar, codes in _corresp:
for code in codes:
_reptable[code] = repchar
_fill_reptable()
def suppression_diacritics(s):
"""Suppression des accents et autres marques.
@param s: le texte à nettoyer.
@type s: str ou unicode
@return: le texte nettoyé de ses marques diacritiques.
@rtype: unicode
"""
if isinstance(s, str):
s = unicode(s, "utf8", "replace")
return s.translate(_reptable)