blob: c807ebdc81167eadd7aeda095e3018cf8985a6d6 (
plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
|
# vim:encoding=utf-8:fileencoding=utf-8
#
# odfrecode
#
# (c) 2007,2008 Guido Günther <agx@sigxcpu.org>
#
# This program is free software; you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation; either version 2 of the License, or
# (at your option) any later version.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with this program; if not, write to the Free Software
# Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
#
class Recoder(object):
"""
base class for all encoders
@classvar dst_encoding: encoding of the destination "column"
@classvar encoding: name of the encoding
To write a new encoder simply add a dictionary
>>> character_table = { "national_encoding_1": "utf8_1",
national_encoding_2": "utf8_2",
}
If you don't want to use utf8 as dictionary values for the destination
encoding specify dst_encoding.
"""
dst_encoding = 'utf-8'
encoding = None
def recode(self, character):
try:
char = unicode(self.character_table[character], self.dst_encoding)
except KeyError: # needs no remapping
char = character
return char
|