# -*- coding: utf-8; mode: conf; -*- # Copyright 2002-2008 by Eric House (xwords@eehouse.org). All rights reserved. # # 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. LANGCODE:cs_CZ CHARSET:utf-8 # deal with DOS files LANGFILTER: tr -d '\r' # tr seems to work on systems that don't know the Czech locale, but # grep does not. So don't use grep, e.g. to eliminate words # containing letters not in our alphabet. Instead, pass the -r flag # via D2DARGS so they're dropped. LANGFILTER: | tr [aábcčdďeéěfghiíjklmnňoóprřsštťuúůvxyýzž] [AÁBCČDĎEÉĚFGHIÍJKLMNŇOÓPRŘSŠTŤUÚŮVXYÝZŽ] LANGFILTER: | sort -u # presence of high-ascii means we must not pass -nosort D2DARGS: -r -term 0 -enc UTF-8 #D2DARGS: -term 10 -r -enc UTF-8 LANGINFO:
This BYOD language works on Czech wordlists encoded in LANGINFO: UTF-8 and produces dictionaries that should work on LANGINFO: Unicode-aware systems.
# High bit means "official". Next 7 bits are an enum where # Czech-ISO8859-2==0x11. Low byte is padding. XLOC_HEADER:0x9100 #COUNT VAL FACE