#!/bin/sh
#See http://www.unicode.org/reports/tr44/
#
#Me Enclosing_Mark  an enclosing combining mark
#Mn Nonspacing_Mark a nonspacing combining mark (zero advance width)
#Cf Format          a format control character
#
setglobal UNICODEWIDTH_H = '../unicode_width.h'
if ! test -d unicode {
	mkdir unicode
} &&
shell { cd unicode &&
	if ! test -f UnicodeData.txt {
		wget http://www.unicode.org/Public/UCD/latest/ucd/UnicodeData.txt
	} &&
	if ! test -f EastAsianWidth.txt {
		wget http://www.unicode.org/Public/UCD/latest/ucd/EastAsianWidth.txt
	} &&
	if ! test -d uniset {
		git clone https://github.com/depp/uniset.git
	} &&
	shell {
		cd uniset &&
		if ! test -x uniset {
			autoreconf -i &&
			./configure --enable-warnings=-Werror CFLAGS='-O0 -ggdb'
		} &&
		make
	} &&
	setglobal UNICODE_DIR = '.' && export UNICODE_DIR &&
	cat >$UNICODEWIDTH_H << """
static const struct interval zero_width[] = {
$[uniset/uniset --32 cat:Me,Mn,Cf + U+1160..U+11FF - U+00AD |
  grep -v plane]
};
static const struct interval double_width[] = {
$[uniset/uniset --32 eaw:F,W]
};
"""
}