xwords/xwords4/dawg/Danish/info.txt

# -*- mode: conf; coding: utf-8; -*-
# Copyright 2005 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:da
LANGNAME:Danish
CHARSET: utf-8

# deal with DOS files
LANGFILTER: tr -d '\r'
# uppercase all
LANGFILTER: | sed -e 's/[[:lower:]]*/\U&/'
# no words not containing a vowel
LANGFILTER: | grep '[AEIOUYÅÆØ]' 
# none with illegal chars
LANGFILTER: | grep -x '[A-PR-VX-ZÅÆØ]\{2,15\}'
# remove duplicates
LANGFILTER: | sort -u

# 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>Danish uses all English letters except Q and W.  There
LANGINFO: are three non-English letters: 'Å', 'Æ' and 'Ø'.  </p>

# High bit means "official".  Next 7 bits are an enum where
# Danish==9.  Low byte is padding
XLOC_HEADER:0x8900

<BEGIN_TILES>
{"_"}	 0		2
'A|a'	 1  	7  	
'Å|å'	 4      2
'Æ|æ'	 4 	    2
'B|b'	 3 	 	4
'C|c'	 8 	 	2
'D|d'	 2 	 	5
'E|e'	 1 	 	9
'F|f'	 3 	 	3
'G|g'	 3 	 	3
'H|h'	 4 	 	2
'I|i'	 3 	 	4
'J|j'	 4 	 	2
'K|k'	 3 	 	4
'L|l'	 2 	 	5
'M|m'	 3 	 	3
'N|n'	 1 	 	6
'O|o'	 2 	 	5
'Ø|ø'	 4 	    2
'P|p'	 4 	 	2
'R|r'	 1 	 	6
'S|s'	 2 	 	5
'T|t'	 2 	 	5
'U|u'	 3 	 	3
'V|v'	 3 	 	3
'X|x'	 8 	 	1
'Y|y'	 4 	 	2
'Z|z'    8 	 	1
<END_TILES>
# should ignore all after the <END_TILES> above
change tile info format in info.txt I'm moving toward allowing per-board-size counts with faces and values staying the same. So it makes more sense to have face and values be the first columns. 2022-04-04 08:12:29 +02:00			`# -- mode: conf; coding: utf-8; --`
update email address in header comments: no code change 2006-01-08 02:25:02 +01:00			`# Copyright 2005 by Eric House (xwords@eehouse.org). All rights reserved.`
first checkin for Danish 2005-06-11 17:32:09 +02:00			`#`
			`# 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.`

change tile info format in info.txt I'm moving toward allowing per-board-size counts with faces and values staying the same. So it makes more sense to have face and values be the first columns. 2022-04-04 08:12:29 +02:00			`LANGCODE:da`
			`LANGNAME:Danish`
fix: convert to utf8 and replace grep that didn't work (presuambly because ranges have different meanings in utf-8) with one that does. 2010-12-14 05:39:04 +01:00			`CHARSET: utf-8`
first checkin for Danish 2005-06-11 17:32:09 +02:00
			`# deal with DOS files`
Add support for Russian. So that Russian text can be processed on systems without setting LANG=ru_RU.CP1251, modify dict2dawg to skip duplicates and words outside of specified lengths. Modify all info.txt files for the new scheme (which includes change to byod.cgi not kept on sourceforge.) 2007-02-17 18:06:05 +01:00			`LANGFILTER: tr -d '\r'`
first checkin for Danish 2005-06-11 17:32:09 +02:00			`# uppercase all`
use sed instead of tr to uppercase -- everywhere Required for some unicode chars, but might as well use it everywhere to make copying easier. 2022-01-28 04:36:55 +01:00			`LANGFILTER: \| sed -e 's/[[:lower:]]*/\U&/'`
first checkin for Danish 2005-06-11 17:32:09 +02:00			`# no words not containing a vowel`
fix: convert to utf8 and replace grep that didn't work (presuambly because ranges have different meanings in utf-8) with one that does. 2010-12-14 05:39:04 +01:00			`LANGFILTER: \| grep '[AEIOUYÅÆØ]'`
first checkin for Danish 2005-06-11 17:32:09 +02:00			`# none with illegal chars`
limit word lengths to 2-15 dict2dawg crashes when given a 1-letter word. Easier to fix in the filtering that has to be there anyway. 2022-01-24 02:46:52 +01:00			`LANGFILTER: \| grep -x '[A-PR-VX-ZÅÆØ]\{2,15\}'`
add 'sort -u' to get rid of duplicates. All info files should have this.... 2006-04-30 17:15:28 +02:00			`# remove duplicates`
Add support for Russian. So that Russian text can be processed on systems without setting LANG=ru_RU.CP1251, modify dict2dawg to skip duplicates and words outside of specified lengths. Modify all info.txt files for the new scheme (which includes change to byod.cgi not kept on sourceforge.) 2007-02-17 18:06:05 +01:00			`LANGFILTER: \| sort -u`
first checkin for Danish 2005-06-11 17:32:09 +02:00
			`# 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.`

Add support for Russian. So that Russian text can be processed on systems without setting LANG=ru_RU.CP1251, modify dict2dawg to skip duplicates and words outside of specified lengths. Modify all info.txt files for the new scheme (which includes change to byod.cgi not kept on sourceforge.) 2007-02-17 18:06:05 +01:00			`D2DARGS: -r -term 10`
first checkin for Danish 2005-06-11 17:32:09 +02:00
add 'sort -u' to get rid of duplicates. All info files should have this.... 2006-04-30 17:15:28 +02:00			`LANGINFO: <p>Danish uses all English letters except Q and W. There`
fix: convert to utf8 and replace grep that didn't work (presuambly because ranges have different meanings in utf-8) with one that does. 2010-12-14 05:39:04 +01:00			`LANGINFO: are three non-English letters: 'Å', 'Æ' and 'Ø'. </p>`
first checkin for Danish 2005-06-11 17:32:09 +02:00
			`# High bit means "official". Next 7 bits are an enum where`
			`# Danish==9. Low byte is padding`
			`XLOC_HEADER:0x8900`

			`<BEGIN_TILES>`
change tile info format in info.txt I'm moving toward allowing per-board-size counts with faces and values staying the same. So it makes more sense to have face and values be the first columns. 2022-04-04 08:12:29 +02:00			`{"_"} 0 2`
			`'A\|a' 1 7`
			`'Å\|å' 4 2`
			`'Æ\|æ' 4 2`
			`'B\|b' 3 4`
			`'C\|c' 8 2`
			`'D\|d' 2 5`
			`'E\|e' 1 9`
			`'F\|f' 3 3`
			`'G\|g' 3 3`
			`'H\|h' 4 2`
			`'I\|i' 3 4`
			`'J\|j' 4 2`
			`'K\|k' 3 4`
			`'L\|l' 2 5`
			`'M\|m' 3 3`
			`'N\|n' 1 6`
			`'O\|o' 2 5`
			`'Ø\|ø' 4 2`
			`'P\|p' 4 2`
			`'R\|r' 1 6`
			`'S\|s' 2 5`
			`'T\|t' 2 5`
			`'U\|u' 3 3`
			`'V\|v' 3 3`
			`'X\|x' 8 1`
			`'Y\|y' 4 2`
			`'Z\|z' 8 1`
first checkin for Danish 2005-06-11 17:32:09 +02:00			`<END_TILES>`
			`# should ignore all after the <END_TILES> above`