xwords/xwords4/dawg/Spanish/info.txt

# -*- mode: conf; coding: utf-8; -*-
# Copyright 2002-2006 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.

# no way can unix sort handle the control chars I'm adding to text
# below

NEEDSSORT:true
CHARSET: utf-8

# MSDos LF chars go bye-bye
LANGFILTER: tr -d '\r'

# convert accented vowels
LANGFILTER: | tr '\207\216\222\227\234\237\226' 'aeiouu\321'
# uppercase
LANGFILTER: | tr [a-zñ] [A-ZÑ]
# remove words with illegal letters
LANGFILTER: | grep '^[[A-JL-VX-ZÑ]*$'
# substitute pairs (can't figure out how to use octal values)
LANGFILTER: | sed 's/CH/1/g'
LANGFILTER: | sed 's/LL/2/g'
LANGFILTER: | sed 's/RR/3/g'
# substitute in the octal control character values
LANGFILTER: | tr '123' '\001\002\003'
# now add nulls as terminators
LANGFILTER: | tr -s '\n' '\000'
LANGFILTER: | sort -u -z

D2DARGS: -r -term 0

LANGINFO: <p>Spanish words include all letters in the English alphabet
LANGINFO: except "K" and "W", and with "Ñ" added. Since there are no
LANGINFO: tiles for accented vowels, these are replaced by the
LANGINFO: unaccented forms.</p>


LANGINFO: <p>In addition, there are three special two-letter tiles
LANGINFO: "CH", "LL" and "RR".  The rules say that the corresponding
LANGINFO: two single tiles may not be used where a two-letter tile is
LANGINFO: possible (e.g. if a word contains "CH" you must use the "CH"
LANGINFO: tile rather than a "C" tile followed by an "H" tile.  Thus
LANGINFO: we remove all of these pairs from your wordlist and replace
LANGINFO: them with the appropriate two-letter "letter". </p>


LANGCODE:es_ES

# I think dealing with "specials" goes like this.  In the {} pairs
# below, if the first string is followed by other strings (one or two)
# they are assumed to be filenames.  The filenames will need to be
# found, and converted into binary files appropriate for the platform
# by rules given somewhere -- here?  No, since they're the same for
# all platforms.  Just put 'em in the byod.cgi file for now.

# It'll be assumed that the first name is for the "small" bitmap, and
# the second for the "large". It's ok for a file not to exist; it'll
# just be ignored.  In the unlikely case that you wanted to specify
# the large but not the small this is what you'd need to do.

# High bit means "official".  Next 7 bits are an enum where
# Spanish==6.  Low byte is padding
XLOC_HEADER:0x8600

<BEGIN_TILES>
2			0	{"_"}
12			1	'A|a'
2			3	'B|b'
4			3	'C|c'
1			5	{"CH|ch|Ch|cH",true,true}
5			2	'D|d'
12			1	'E|e'
1			4	'F|f'
2			2	'G|g'
2			4	'H|h'
6			1	'I|i'
1			8	'J|j'
4			1	'L|l'
1			8	{"LL|ll|Ll|lL", true, true}
2			3	'M|m'
5			1	'N|n'
1			8	'Ñ|ñ'
9			1	'O|o'
2			3	'P|p'
1			5	'Q|q'
5			1	'R|r'
1			8	{"RR|rr|Rr|rR",true,true}
6			1	'S|s'
4			1	'T|t'
5			1	'U|u'
1			4	'V|v'
1			8	'X|x'
1			4	'Y|y'
1			10	'Z|z'
<END_TILES>
# should ignore all after the <END> above