mirror of
https://gitlab.freedesktop.org/uchardet/uchardet.git
synced 2025-12-06 16:56:40 +08:00
388777be51
Newly added IBM865 charset (for Norwegian) can also be used for Danish
By the way, I fixed `script/charsets/ibm865.py` as Danish uses the 'da'
ISO 639-1 code by the way, not 'dk' (which is sometimes used for other
codes for Denmark, such as ISO 3166 country code and internet TLD) but
not for the language itself.
For the test, adding some text from the top article of the day on the
Danish Wikipedia, which was about Jimi Hendrix. And that's cool! 🎸 ;-)
70 lines
2.7 KiB
Python
70 lines
2.7 KiB
Python
#!/bin/python3
|
|
# -*- coding: utf-8 -*-
|
|
|
|
# ##### BEGIN LICENSE BLOCK #####
|
|
# Version: MPL 1.1/GPL 2.0/LGPL 2.1
|
|
#
|
|
# The contents of this file are subject to the Mozilla Public License Version
|
|
# 1.1 (the "License"); you may not use this file except in compliance with
|
|
# the License. You may obtain a copy of the License at
|
|
# http://www.mozilla.org/MPL/
|
|
#
|
|
# Software distributed under the License is distributed on an "AS IS" basis,
|
|
# WITHOUT WARRANTY OF ANY KIND, either express or implied. See the License
|
|
# for the specific language governing rights and limitations under the
|
|
# License.
|
|
#
|
|
# The Original Code is Mozilla Universal charset detector code.
|
|
#
|
|
# The Initial Developer of the Original Code is
|
|
# Netscape Communications Corporation.
|
|
# Portions created by the Initial Developer are Copyright (C) 2001
|
|
# the Initial Developer. All Rights Reserved.
|
|
#
|
|
# Contributor(s):
|
|
# Jehan <jehan@girinstud.io>
|
|
#
|
|
# Alternatively, the contents of this file may be used under the terms of
|
|
# either the GNU General Public License Version 2 or later (the "GPL"), or
|
|
# the GNU Lesser General Public License Version 2.1 or later (the "LGPL"),
|
|
# in which case the provisions of the GPL or the LGPL are applicable instead
|
|
# of those above. If you wish to allow use of your version of this file only
|
|
# under the terms of either the GPL or the LGPL, and not to allow others to
|
|
# use your version of this file under the terms of the MPL, indicate your
|
|
# decision by deleting the provisions above and replace them with the notice
|
|
# and other provisions required by the GPL or the LGPL. If you do not delete
|
|
# the provisions above, a recipient may use your version of this file under
|
|
# the terms of any one of the MPL, the GPL or the LGPL.
|
|
#
|
|
# ##### END LICENSE BLOCK #####
|
|
|
|
import re
|
|
|
|
## Mandatory Properties ##
|
|
|
|
# The human name for the language, in English.
|
|
name = 'Danish'
|
|
# Use 2-letter ISO 639-1 if possible, 3-letter ISO code otherwise,
|
|
# or use another catalog as a last resort.
|
|
code = 'da'
|
|
# ASCII characters are also used in French.
|
|
use_ascii = True
|
|
# The charsets we want to support and create data for.
|
|
charsets = ['ISO-8859-15', 'ISO-8859-1', 'WINDOWS-1252', 'IBM865' ]
|
|
|
|
## Optional Properties ##
|
|
|
|
# Alphabet characters.
|
|
# If use_ascii=True, there is no need to add any ASCII characters.
|
|
# If case_mapping=True, there is no need to add several cases of a same
|
|
# character (provided Python algorithms know the right cases).
|
|
alphabet = 'æøå'
|
|
# The start page. Though optional, it is advised to choose one yourself.
|
|
start_pages = ['Forside']
|
|
# give possibility to select another code for the Wikipedia URL.
|
|
wikipedia_code = code
|
|
# 'a' and 'A' will be considered the same character, and so on.
|
|
# This uses Python algorithm to determine upper/lower-case of a given
|
|
# character.
|
|
case_mapping = True
|