mirror of
https://gitlab.freedesktop.org/uchardet/uchardet.git
synced 2025-12-07 01:06:40 +08:00
76 lines
2.9 KiB
Python
76 lines
2.9 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 ##
|
|
|
|
name = 'Hindi'
|
|
aliases = [ 'Devanagari' ]
|
|
code = 'hi'
|
|
use_ascii = False
|
|
# ISCII is a collection of single byte encodings (10 variants).
|
|
# Unfortunately it looks like neither iconv nor python (probably based off
|
|
# iconv?) know any of the ISCII encodings. Therefore I cannot build any ISCII
|
|
# data, and as a consequence process it.
|
|
# See:
|
|
# http://stackoverflow.com/questions/27143365/unicode-to-iscii-conversion
|
|
# https://en.wikipedia.org/wiki/Indian_Script_Code_for_Information_Interchange
|
|
# Anyway according to Wikipedia, these encodings don't seem much used. UTF-8 is
|
|
# mostly used in India, it would appear.
|
|
#charsets = ['ISCII']
|
|
charsets = []
|
|
|
|
## Optional Properties ##
|
|
|
|
# Devanagari script, see:
|
|
# https://en.wikipedia.org/wiki/Devanagari
|
|
# 11 vowels and 33 consonants with independent and diacritic forms, etc.
|
|
# To keep it simple, I don't list the alphabet and leave statistics work
|
|
# its magics.
|
|
unicode_ranges = [(0x900, 0x97F), # Devanagari
|
|
(0xA8E0, 0xA8FF), # Devanagari Extended
|
|
(0x1CD0, 0x1CFF), # Vedic Extensions
|
|
]
|
|
|
|
start_pages = ['मुखपृष्ठ']
|
|
wikipedia_code = code
|
|
case_mapping = False
|