X-Git-Url: http://git.shiar.nl/sheet.git/blobdiff_plain/f2e965b21a4be2aea69d887f619481e04f3ca58a..4e71d82512759ed7da92d213ac66d006dae456a1:/tools/convert-unicode.pl

diff --git a/tools/convert-unicode.pl b/tools/convert-unicode.pl
index 731210b..19fde5d 100755
--- a/tools/convert-unicode.pl
+++ b/tools/convert-unicode.pl
@@ -16,6 +16,29 @@ my %info = (
 );
 $info{chr $_} //= {} for 32 .. 126;
 
+eval {
+	my $tables = do 'unicode-table.inc.pl' or die $@ || $!;
+	for (values %$tables) {
+		for (values %$_) {
+			for (@$_) {
+				length $_ == 1 or next;  # ignore meta values
+				s/\\//;  # unescape
+				$info{$_} //= {};
+			}
+		}
+	}
+	1;
+} or warn "Failed reading unicode tables: $@";
+
+eval {
+	require HTML::Entities;
+	while (my ($char, $entity) = each %HTML::Entities::char2entity) {
+		$entity =~ /[a-zA-Z]/ or next;  # only actual aliases
+		$info{$char}->{html} = substr($entity, 1, -1);
+	}
+	1;
+} or warn "Failed importing html entities: $@";
+
 my %diinc = (
 	'digraphs.inc.pl' => 'u-di',
 );
@@ -39,7 +62,7 @@ for my $chr (keys %info) {
 			|| { block => '?', category => 'Xn', name => '', script => '' }
 	} or next;
 
-	$info->{$_} = $info{$chr}->{$_} for qw(di class string);
+	$info->{$_} = $info{$chr}->{$_} for qw(di html class string);
 
 	# categorise by unicode types and writing script
 	$info->{class}->{$_}++ for $info->{category};
@@ -76,7 +99,7 @@ say '+{';
 for my $cp (sort keys %info) {
 	$info{$cp}->{classstr} = join(' ', sort keys %{ $info{$cp}->{class} });
 	# convert info hashes into arrays of strings to output in display order
-	my $row = [ map { $info{$cp}->{$_} } qw/classstr name di string/ ];
+	my $row = [ map { $info{$cp}->{$_} } qw/classstr name di html string/ ];
 	# strip off trailing missing values (especially string may be unknown)
 	defined $row->[-1] ? last : pop @$row for 1 .. @$row;
 	# final line (assume safe within single quotes)