# -*- 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 LANGNAME:Czech 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: | sed -e 's/[[:lower:]]*/\U&/' 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 #FACE VAL COUNT[15] {"_"} 0 2 'A' 1 5 'Á' 2 2 'B' 3 2 'C' 2 3 'Č' 4 1 'D' 1 3 'Ď' 8 1 'E' 1 5 'É' 3 2 'Ě' 3 2 'F' 5 1 'G' 5 1 'H' 2 3 'I' 1 4 'Í' 2 3 'J' 2 2 'K' 1 3 'L' 1 3 'M' 2 3 'N' 1 5 'Ň' 6 1 'O' 1 6 'Ó' 7 1 'P' 1 3 'R' 1 3 'Ř' 4 2 'S' 1 4 'Š' 4 2 'T' 1 4 'Ť' 7 1 'U' 2 3 'Ú' 5 1 'Ů' 4 1 'V' 1 4 'X' 10 1 'Y' 2 2 'Ý' 4 2 'Z' 2 2 'Ž' 4 1