mirror of
https://gitlab.freedesktop.org/uchardet/uchardet.git
synced 2025-12-06 16:56:40 +08:00
19737886fe
The alphabet was not complete and thus confidence was a bit too low. For instance the VISCII test case's confidence bumped from 0.643401 to 0.696346 and the UTF-8 test case bumped from 0.863777 to 0.99. Only the Windows-1258 test case is slightly worse from 0.532846 to 0.532098. But the overwhole recognition gain is obvious anyway.
65 lines
2.7 KiB
Python
65 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 ##
|
|
|
|
name = 'Vietnamese'
|
|
code = 'vi'
|
|
# It actually uses ASCII, but not all of it.
|
|
use_ascii = False
|
|
# From Wikipedia:
|
|
# For systems that lack support for Unicode, dozens of 8-bit Vietnamese code
|
|
# pages are available.[1] The most common are VISCII (TCVN 5712:1993), VPS, and
|
|
# Windows-1258.[3] Where ASCII is required, such as when ensuring readability in
|
|
# plain text e-mail, Vietnamese letters are often encoded according to Vietnamese
|
|
# Quoted-Readable (VIQR) or VSCII Mnemonic (VSCII-MNEM),[4] though usage of either
|
|
# variable-width scheme has declined dramatically following the adoption of
|
|
# Unicode on the World Wide Web.
|
|
charsets = ['WINDOWS-1258', 'VISCII']
|
|
|
|
## Optional Properties ##
|
|
|
|
alphabet = 'aăâàằầảẳẩãẵẫáắấạặậbcdđeèềêẻểẽễéếẹệghiìỉĩíịklmnoôơòồờỏổởõỗỡóốớọộợpqrstuưùừủửũữúứụựvxyỳỷỹýỵ'
|
|
start_pages = ['Chữ_Quốc_ngữ']
|
|
wikipedia_code = code
|
|
case_mapping = True
|