xwords/xwords4/dawg/German/info.txt

82 lines
2.2 KiB
Text

# Copyright 2002 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_DE
# deal with DOS files
LANGFILTER: tr -d '\r'
# substitute for sharfes-s
LANGFILTER: | sed -e 's/ß/SS/g'
# uppercase all
LANGFILTER: | tr [a-zäöü] [A-ZÄÖÜ]
# no words not containing a vowel
LANGFILTER: | grep '[AEIOUÄÖÜ]'
# none with illegal chars
LANGFILTER: | grep '^[A-ZÄÖÜ]\+$'
# 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
<BEGIN_TILES>
2 0 {"_"}
5 1 'A'
# A mit umlaut
1 6 196
2 3 'B'
2 4 'C'
4 1 'D'
15 1 'E'
2 4 'F'
3 2 'G'
4 2 'H'
6 1 'I'
1 6 'J'
2 4 'K'
3 2 'L'
4 3 'M'
9 1 'N'
3 2 'O'
# O mit umlaut
1 8 214
1 4 'P'
1 10 'Q'
6 1 'R'
7 1 'S'
6 1 'T'
6 1 'U'
# U mit umlaut
1 6 220
1 6 'V'
1 3 'W'
1 8 'X'
1 10 'Y'
1 3 'Z'
<END_TILES>
# should ignore all after the <END_TILES> above