# Copyright 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.
LANGCODE:pt_PT
CHARSET: utf-8
# deal with DOS files
LANGFILTER: tr -d '\r'
# uppercase all
LANGFILTER: | tr [a-zç] [A-ZÇ]
# no words not containing a vowel
LANGFILTER: | grep '[AEIOU]'
# none with illegal chars
LANGFILTER: | grep '^[A-JL-VXZÇ]\+$'
# 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: Portuguese uses the letter A-Z, excluding K, W and Y, and adds
LANGINFO: Ç. Words containing any other letters are dropped.
# High bit means "official". Next 7 bits are an enum where
# Portuguese==D. Low byte is padding
XLOC_HEADER:0x8D00
3 0 {"_"}
14 1 'A|a'
3 3 'B|b'
4 2 'C|c'
2 3 'Ç|ç'
5 2 'D|d'
11 1 'E|e'
2 4 'F|f'
2 4 'G|g'
2 4 'H|h'
10 1 'I|i'
2 5 'J|j'
5 2 'L|l'
6 1 'M|m'
4 3 'N|n'
10 1 'O|o'
4 2 'P|p'
1 6 'Q|q'
6 1 'R|r'
8 1 'S|s'
5 1 'T|t'
7 1 'U|u'
2 4 'V|v'
1 8 'X|x'
1 8 'Z|z'
# should ignore all after the above