X-Git-Url: http://git.shiar.nl/sheet.git/blobdiff_plain/2d5b9e1f36bd86e3e7b862f40a9ed3e78325f45a..HEAD:/charset.plp

diff --git a/charset.plp b/charset.plp
index e9f097d..bbab1d6 100644
--- a/charset.plp
+++ b/charset.plp
@@ -5,7 +5,8 @@ my @tablist = split m{/+}, $Request || 'default';
 
 Html({
 	title => 'charset cheat sheet',
-	version => '1.1',
+	version => '1.3',
+	canonical => "/charset/$Request" . ($mode && '?compare'),
 	description => [
 		"Reference sheet with all glyphs in common character encoding tables,",
 		"and an overview of Unicode ranges and UTF-8 bytes.",
@@ -14,9 +15,9 @@ Html({
 		charset codepage unicode ascii utf8 latin glyph character encoding
 		reference common overview table
 	'],
-	stylesheet => [qw'light'],
+	(stylesheet => [qw'light']) x !$mode,
 	data => [qw(
-		charset-encoding.inc.pl
+		charset.inc.pl charset-encoding.inc.pl
 		charset-unicode.inc.pl charset-ucplanes.inc.pl charset-utf8.inc.pl
 	)],
 });
@@ -55,6 +56,7 @@ print join " •\n", (
 		dos      => 'DOS',
 		mac      => 'Apple',
 		ebcdic   => 'EBCDIC',
+		legacy   => 'legacy',
 		$tablist[0] eq 'default' ? () : ('' => 'common'),
 	],
 	[
@@ -78,8 +80,7 @@ use Shiar_Sheet::FormatChar;
 my $glyphs = Shiar_Sheet::FormatChar->new;
 my @request;
 
-my $charsets = do 'charset-encoding.inc.pl'
-	or Alert('Encoding metadata could not be read', $@ || $!);
+my $charsets = Data('charset');
 
 sub tabinput {
 	# generate character table(s)
@@ -97,6 +98,7 @@ sub tabinput {
 
 	state $visible = {'' => 1};  # all present tables
 	my %row = (offset => 0, cols => 16);
+	$row{$_} = $charset->{$_} for qw( note table );  # copy metadata
 
 	if (not defined $params) {
 		my @parents = @{ $charset->{inherit} || [] };
@@ -131,7 +133,7 @@ sub tabinput {
 				# extend earlier range
 				my $skip = int(($row{endpoint} || $row{startpoint}) / $row{cols});
 				for ($skip + 1 .. (hex($+{start}) / $row{cols}) - 1) {
-					$row{skip}->{ $_ * $row{cols} - $row{startpoint} }++;
+					$row{skip}->{ $_ * $row{cols} }++;
 				}
 			}
 			else {
@@ -153,7 +155,7 @@ sub tabinput {
 	if (defined $row{table} or defined $row{cell}) {
 		$row{set} //= $input;
 	}
-	elsif ($row{set} = Encode::resolve_alias($input)) {
+	elsif ($row{set} = Encode::resolve_alias($charset->{set} // $input)) {
 		$row{offset} = delete $row{startpoint};
 		if ($charset->{varchar}) {
 			# array of possibly multiple characters per code point
@@ -169,6 +171,7 @@ sub tabinput {
 
 		$row{endpoint} -= $row{offset};
 		$visible->{ascii}++;  # assume common base
+		$row{set} = $input if $charset->{set};  # base override
 	}
 	else {
 		Alert("Encoding <q>$input</q> unknown");
@@ -289,8 +292,8 @@ for my $row (@request) {
 
 	printf '<div class="section"><table class="glyphs%s">', !$row->{cell} && ' charmap';
 	my $title = $row->{set};
-	$title .= " <aside>(over $_)</aside>"
-		for $row->{parent} || ();
+	$title .= " <aside>(over $_)</aside>" for $row->{parent} || ();
+	$title .= " <aside>($_)</aside>" for $row->{note} || ();
 	printf '<caption>%s</caption>', $title;
 	print '<col>' x ($cols + 1);
 	for my $section (qw{thead}) {
@@ -301,13 +304,13 @@ for my $row (@request) {
 
 	print '<tbody>';
 	while ($offset <= $row->{endpoint} * $colsize) {
-		if ($row->{skip}->{$offset}) {
+		if ($row->{skip}->{$offset + $row->{offset}}) {
 			$offset += $cols * $colsize;
 			next;
 		}
 
 		print '<tr><th>';
-		if (defined $row->{skip}->{$offset}) {
+		if (defined $row->{skip}->{$offset + $row->{offset}}) {
 			print '⋮';
 		}
 		else {
@@ -340,15 +343,15 @@ for my $row (@request) {
 					$cp == ord $glyph ? 'l4' :
 					$row->{parent} && $glyph eq
 						Encode::decode($row->{parent}, pack 'C', $cp) ? 'l3' :
-					!$class ? undef :
+					!defined $cell ? undef :
 					$visible->{$glyph} ? 'l2' :
 					'l1'
 				);
 				$visible->{$glyph}++;
 			}
 
-			say sprintf $class ? '<td title="%s" class="X %s">%s' : '<td title="%s">',
-				$name, $class, $cell;
+			printf '<td title="%s"', $name;
+			say $class ? sprintf(' class="X %s">%s', $class, $cell) : '>';
 		}
 		continue {
 			$offset += $colsize;