# -*- mode: makefile; coding: iso-8859-1 -*-
# 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.

XWLANG=Top10000
LANGCODE=nl_NL
ENC = ISO-8859-1 

TARGET_TYPE ?= WINCE

include ../Makefile.langcommon

# top10000nl.txt is from
# http://wortschatz.uni-leipzig.de/Papers/top10000nl.txt.  It contains
# a lot of words that aren't legal so as an approximation I removed
# all that aren't found in the much larger
# Dutch__unofficial_alphabetical.dict.gz
SOURCEDICT ?= $(XWDICTPATH)/Dutch/top10000nl.txt.gz

# This is weird.  We're keeping umlaut letters even though they're not
# on tiles.  Do they get translated to non-umlaut equivalents or are
# they allowed to drop this way.  Need to confirm the tile set and conversion.

$(XWLANG)Main.dict.gz: $(SOURCEDICT) Makefile
	zcat $< | tr -d '\r' | \
		tr [a-z���] [A-Z���] | \
		LANG=$(LANGCODE):$(ENC) grep '^[A-Z]\+$$' | \
		LANG=$(LANGCODE):$(ENC) sort -u | \
		gzip -c > $@

# Everything but creating of the Main.dict file is inherited from the
# "parent" Makefile.langcommon in the parent directory.

clean: clean_common
	rm -f $(XWLANG)Main.dict.gz *.bin $(XWLANG)*.pdb $(XWLANG)*.seb

help:
	@echo 'make [SOURCEDICT=Dutch__unofficial_alphabetical.dict.gz]'