# -*- mode: conf; -*-
# Copyright 2002-2009 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:ca
LANGNAME:Catalan
CHARSET: utf-8

NEEDSSORT:true

LANGINFO: <p>Catalan includes several special tiles, "L·L", "NY" and
LANGINFO: "QU" in addition to Ç.  There are no "Y" or "Q" tiles,
LANGINFO: and all words containing either of these letters not in
LANGINFO: combination with a "N" or "U" will be excluded from the
LANGINFO: dictionary. </p>

LANGINFO: <p>"L" is legal by itself, as are words in which two "L"s
LANGINFO: appear side-by-side.  The "L·L" tile is used whenever any of
LANGINFO: these three strings appears in the wordlist you upload:
LANGINFO: "L-L", "L.L" or "L·L".  (And of course "l-l", "l.l" or
LANGINFO: "l·l".)</p>

LANGINFO: <p>In addition to the special multi-letter tiles discussed
LANGINFO: above, the following letters are allowed: A-J, L-V, X, Z and
LANGINFO: Ç.  Lowercase letters will be converted to uppercase, then
LANGINFO: words containing letters not listed here will be excluded.</p>

LANGINFO: <p>The file you upload should be encoded in UTF-8.</p>


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

LANGFILTER: | sed -e 's/[[:lower:]]*/\U&/'
LANGFILTER: | sed -e 's/L·L/1/g' -e 's/L\.L/1/g' -e 's/L-L/1/g'
LANGFILTER: | sed -e 's/NY/2/g' -e 's/QU/3/g'
LANGFILTER: | grep -x '[Ç1-3A-JL-VXZ\.]\{2,15\}'

# substitute in the octal control character values 
LANGFILTER: | tr '123' '\001\002\003'
LANGFILTER: | tr -s '\n' '\000'

D2DARGS: -r -term 0 -enc UTF-8


# High bit means "official".  Next 7 bits are an enum where
# Catalan==c.  Low byte is padding
XLOC_HEADER:0x8C00


<BEGIN_TILES>
{"_"}                      0    2
'A|a'                      1    12
'B|b'                      3    2
'C|c'                      2    3
'Ç|ç'                      10   1
'D|d'                      2    3
'E|e'                      1    13
'F|f'                      4    1
'G|g'                      3    2
'H|h'                      8    1
'I|i'                      1    8
'J|j'                      8    1
'L|l'                      1    4
{"L·L|L-L|ĿL|l·l|l-l|ŀl"}  10   1
'M|m'                      2    3
'N|n'                      1    6
{"NY|ny|Ny|nY"}            10   1
'O|o'                      1    5
'P|p'                      3    2
{"QU|qu|Qu|qU"}            8    1
'R|r'                      1    8
'S|s'                      1    8
'T|t'                      1    5
'U|u'                      1    4
'V|v'                      4    1
'X|x'                      10   1
'Z|z'                      8    1
<END_TILES>
#
# NOTES:
#------
#    (1) - Just for avoiding character set mistakes: in the "INT." section of the Palm 
#          screen keyboard, this letter is on the first line, at the very right of "ae".
#    (2) - This is another curious catalan double-letter: two "L" separated by a dot.
#    (3) - In catalan, the "Y" is only used for the double-letter "NY".
#    (4) - In catalan, the tile is not [Q], i [QU]; because it is not possible to
#          use a "Q" alone.
#    (5) - Blank tile.

