# -*- mode: conf; coding: utf-8; -*- # Copyright 2002,2007 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:ru LANGNAME:Russian CHARSET:windows-1251 # deal with DOS files LANGFILTER: tr -d '\r' # uppercase all LANGFILTER: | sed -e 's/[[:lower:]]*/\U&/' # LANGFILTER: | tr -s '\n' '\000' # note: don't turn off sorting! Can't do it with GNU 'sort' without # setting LANG D2DARGS: -r -term 10 LANGINFO:

Russian wordlists must be in utf-8: codepage. Lower-case LANGINFO: letters are converted to upper case and any words that LANGINFO: contain letters not listed below are removed.

# High bit means "official". Next 7 bits are an enum where # Russian==0x0F. Low byte is padding. XLOC_HEADER:0x8F00 'Ŕ' 1 8 'Á' 3 2 'Â' 1 4 'Ă' 3 2 'Ä' 2 2 'Ĺ' 1 7 'Ć' 4 1 'Ç' 3 1 'Č' 1 7 'É' 2 1 'Ę' 2 4 'Ë' 2 4 'Ě' 3 2 'Í' 1 4 'Î' 1 9 'Ď' 2 4 'Đ' 1 5 'Ń' 1 5 'Ň' 1 7 'Ó' 2 4 'Ô' 5 1 'Ő' 4 1 'Ö' 4 1 '×' 3 1 'Ř' 4 1 'Ů' 5 1 'Ú' 10 1 'Ű' 2 2 'Ü' 1 4 'Ý' 8 1 'Ţ' 5 1 'ß' 2 2 {"_"} 0 2 # should ignore all after the above