#! /bin/sh

echo generating Unicode width data for newlib/libc/string/wcwidth.c

cd `dirname $0`
PATH="$PATH":.	# ensure access to uniset tool

#############################################################################
# checks and (with option -u) downloads

case "$1" in
-u)
	#WGET=wget -N -t 1 --timeout=55
	WGET=curl -R -O --connect-timeout 55
	WGET+=-z $@

	echo downloading uniset tool
	$WGET http://www.cl.cam.ac.uk/~mgk25/download/uniset.tar.gz
	gzip -dc uniset.tar.gz | tar xvf - uniset

	echo downloading data from unicode.org
	for data in UnicodeData.txt Blocks.txt EastAsianWidth.txt
	do	$WGET http://unicode.org/Public/UNIDATA/$data
	done
	;;
*)	echo checking package unicode-ucd
	grep unicode-ucd /etc/setup/installed.db || exit 9
	;;
esac

echo checking uniset tool
type uniset || exit 9

for data in UnicodeData.txt Blocks.txt EastAsianWidth.txt
do	test -r $data || ln -s /usr/share/unicode/ucd/$data . || exit 9
done

echo generating from Unicode version `sed -e 's,[^.0-9],,g' -e 1q Blocks.txt`
exit

#############################################################################
# table generation

echo generating combining characters table
uniset +cat=Me +cat=Mn +cat=Cf -00AD +1160-11FF +200B +D7B0-D7C6 +D7CB-D7FB c > combining.t

echo generating ambiguous width characters table
sh ./mkwidthA && uniset +WIDTH-A -cat=Me -cat=Mn -cat=Cf c > ambiguous.t

echo generating wide characters table
sh ./mkwide

#############################################################################
# end