# -*- 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 2 0 {"_"} 5 1 'A' 2 2 'Á' 2 3 'B' 3 2 'C' 1 4 'Č' 3 1 'D' 1 8 'Ď' 5 1 'E' 2 3 'É' 2 3 'Ě' 1 5 'F' 1 5 'G' 3 2 'H' 4 1 'I' 3 2 'Í' 2 2 'J' 3 1 'K' 3 1 'L' 3 2 'M' 5 1 'N' 1 6 'Ň' 6 1 'O' 1 7 'Ó' 3 1 'P' 3 1 'R' 2 4 'Ř' 4 1 'S' 2 4 'Š' 4 1 'T' 1 7 'Ť' 3 2 'U' 1 5 'Ú' 1 4 'Ů' 4 1 'V' 1 10 'X' 2 2 'Y' 2 4 'Ý' 2 2 'Z' 1 4 'Ž'