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

LANGCODE:es
LANGNAME:Spanish
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: | sed -e 's/[[:lower:]]*/\U&/'
# remove words with illegal letters
LANGFILTER: | grep -x '[[A-JL-VX-ZÑ]\{2,15\}'
# 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>
{"_"}							0	2
'A|a'							1	12
'B|b'							3	2
'C|c'							3	4
{"CH|ch|Ch|cH",true,true}		5	1
'D|d'							2	5
'E|e'							1	12
'F|f'							4	1
'G|g'							2	2
'H|h'							4	2
'I|i'							1	6
'J|j'							8	1
'L|l'							1	4
{"LL|ll|Ll|lL",true,true}		8	1
'M|m'							3	2
'N|n'							1	5
'Ñ|ñ'							8	1
'O|o'							1	9
'P|p'							3	2
'Q|q'							5	1
'R|r'							1	5
{"RR|rr|Rr|rR",true,true}		8	1
'S|s'							1	6
'T|t'							1	4
'U|u'							1	5
'V|v'							4	1
'X|x'							8	1
'Y|y'							4	1
'Z|z'                       	10	1
<END_TILES>
# should ignore all after the <END> above