xwords/xwords4/dawg/German/info.txt
2023-03-10 10:30:56 -08:00

84 lines
2.5 KiB
Text

# -*- mode: conf; coding: utf-8; -*-
# Copyright 2002 - 2010 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:de
LANGNAME:German
CHARSET: utf-8
# deal with DOS files
LANGFILTER: tr -d '\r'
# substitute for sharfes-s
LANGFILTER: | sed -e 's/ß/SS/g'
# uppercase all
LANGFILTER: | sed -e 's/[[:lower:]]*/\U&/'
# no words not containing a vowel
# LANGFILTER: | grep '[AEIOUÄÖÜ]'
# none with illegal chars
LANGFILTER: | grep -x '[A-ZÄÖÜ]\{2,15\}'
# Until I can figure out how to force sort to use a locale's collation
# rules we can't trust sort in the filtering rules above and so must
# leave the sorting work to dict2dawg.pl.
D2DARGS: -r -term 10
LANGINFO: <p>German has the 26 English letters plus the three umlaut
LANGINFO: vowels. Scharfes-s is not a legal tile, but if present in
LANGINFO: the wordlist submitted it'll be converted to "SS" by our
LANGINFO: filtering rules. Additional filtering rules eliminate all
LANGINFO: words that don't contain at least one vowel and any that
LANGINFO: contain letters not found on tiles.</p>
# High bit means "official". Next 7 bits are an enum where
# German==3. Low byte is padding
XLOC_HEADER:0x8300
COUNT_SIZES: 15 21
<BEGIN_TILES>
{"_"} 0 2 4
'A|a' 1 5 10
'Ä|ä' 6 1 2
'B|b' 3 2 4
'C|c' 4 2 4
'D|d' 1 4 8
'E|e' 1 15 29
'F|f' 4 2 4
'G|g' 2 3 6
'H|h' 2 4 8
'I|i' 1 6 11
'J|j' 6 1 2
'K|k' 4 2 4
'L|l' 2 3 6
'M|m' 3 4 8
'N|n' 1 9 17
'O|o' 2 3 6
'Ö|ö' 8 1 2
'P|p' 4 1 2
'Q|q' 10 1 2
'R|r' 1 6 11
'S|s' 1 7 14
'T|t' 1 6 12
'U|u' 1 6 12
'Ü|ü' 6 1 2
'V|v' 6 1 2
'W|w' 3 1 2
'X|x' 8 1 2
'Y|y' 10 1 2
'Z|z' 3 1 2
<END_TILES>
# should ignore all after the <END_TILES> above