X-Git-Url: http://git.shiar.nl/sheet.git/blobdiff_plain/6d8c2623e104ad13895ddbe7b23d52ba0d3f0853..8c3e7dc6481f4d61eca39c1250699302a329be56:/charset.plp

diff --git a/charset.plp b/charset.plp
index 557c66f..3bf294e 100644
--- a/charset.plp
+++ b/charset.plp
@@ -31,12 +31,12 @@ use Encode qw(decode resolve_alias);
 my %ALIAS = (
 #	default => [qw(unicode utf-8 iso-8859-1 cp437 -cp1252- --iso-8859-15- -koi8-f)],
 	default => [qw(unicode- utf-8 iso-8859-1 -cp1252- --iso-8859-15- cp437 -cp850)],
-	0 => [qw(cp437 cp863)],
-	1 => [qw(iso-8859-1 cp1252 MacRoman cp850)],
-	2 => [qw(iso-8859-2 cp1250 cp852 MacCentralEurRoman MacCroatian MacRumanian)],
-	5 => [qw(koi8-f iso-8859-5 cp1251 MacCyrillic cp855 cp866)],
-	7 => [qw(iso-8859-7 cp1253 MacGreek cp737 cp869)],
-	8 => [qw(iso-8859-8 cp1255 MacHebrew cp862)],
+	0 => [qw(cp437 -cp863)],
+	1 => [qw(iso-8859-1 -cp1252 -MacRoman -cp850)],
+	2 => [qw(iso-8859-2 -cp1250 -cp852 -MacCentralEurRoman -MacCroatian -MacRumanian)],
+	5 => [qw(koi8-f -iso-8859-5 -cp1251 -MacCyrillic -cp855 -cp866)],
+	7 => [qw(iso-8859-7 -cp1253 -MacGreek -cp737 -cp869)],
+	8 => [qw(iso-8859-8 -cp1255 -MacHebrew -cp862)],
 );
 my @request = map {
 	if (my $input = $_) {
@@ -51,6 +51,10 @@ my @request = map {
 		if ($input =~ s/-$//) {
 			$endpoint = $row{offset} ? $row{offset} < 160 ? 159 : 191 : 127;
 		}
+		if ($row{offset}) {
+			$row{setnote} = 'over cp437' if $input eq 'cp850';
+			$row{setnote} = 'over iso-8859-1' if $input =~ /^iso-8859-|^cp125/;
+		}
 
 		if ($input =~ /^U([0-9a-f]+)(?:-([0-9a-f]+))?/) {
 			my $start = hex($1) << ($2 ? 4 : 8);
@@ -62,7 +66,8 @@ my @request = map {
 		elsif ($input eq 'U') {
 			$row{table} = ' ' x 1024;
 			$row{set} = 'Unicode planes';
-			$row{cell} = do 'charset-ucplanes.inc.pl';
+			$row{cell} = do 'charset-ucplanes.inc.pl'
+				or printf "<p class=error>Table data could not be read: <em>%s</em>.</p>\n", $@ || $!;
 			@nibble = (map { $_.0, $_.8 } 0 .. 7);
 			$nibsize = 8;
 		}
@@ -70,21 +75,23 @@ my @request = map {
 			if ($row{set} eq 'Internal') {
 				$row{table} = ' ' x ($endpoint < 255 ? 640 : 8192);
 				$row{set} = 'Unicode BMP';
-				$row{cell} = do 'charset-unicode.inc.pl';
+				$row{cell} = do 'charset-unicode.inc.pl'
+					or printf "<p class=error>Table data could not be read: <em>%s</em>.</p>\n", $@ || $!;
 			}
 			elsif ($row{set} eq 'utf-8-strict') {
 				$row{table} = undef;
 				$row{set} = 'UTF-8';
-				$row{cell} = do 'charset-utf8.inc.pl';
+				$row{cell} = do 'charset-utf8.inc.pl'
+					or printf "<p class=error>Table data could not be read: <em>%s</em>.</p>\n", $@ || $!;
 			}
 			else {
 				$row{table} = decode($row{set}, pack 'C*', $row{offset} .. $endpoint);
 			}
 		}
 		else {
-			print "<p>Encoding $input unknown</p>\n";
+			say "<p class=error>Encoding <q>$input</q> unknown</p>";
 		}
-		\%row;
+		$row{set} ? \%row : ();
 	}
 	else {
 		();
@@ -116,7 +123,7 @@ sub range_cell {
 		$cols = $len if $len < $cols; #TODO: optimise
 		if ($len -= $cols) {
 			# continued on new row
-			$table->{$offset + $nibsize*$cols} = [$len*$nibsize, "$class joinu", $name, $title];
+			$table->{$offset + $nibsize*$cols} //= [$len*$nibsize, "$class joinu", $name, $title];
 			$name = '';
 			$class .= ' joind';
 		}
@@ -126,7 +133,7 @@ sub range_cell {
 		# multiple full rows
 		if ($len -= $rows << 4) {
 			# partial row remains
-			$table->{$offset + $nibsize*$rows * 16} = [$len*$nibsize, "$class joinu", '', $title];
+			$table->{$offset + $nibsize*$rows * 16} //= [$len*$nibsize, "$class joinu", '', $title];
 			$class .= ' joind';
 		}
 		$attr .= sprintf ' rowspan=%d', $rows;
@@ -142,7 +149,9 @@ sub range_cell {
 
 for my $row (@request) {
 	printf '<div class="section"><table class="glyphs%s">', !$row->{cell} && ' charmap';
-	printf '<caption>%s</caption>', $row->{set};
+	my $title = $row->{set};
+	$title .= " <aside>($_)</aside>" for $row->{setnote} // ();
+	printf '<caption>%s</caption>', $title;
 	print '<col>' x 17;
 	for my $section (qw{thead}) {
 		print "<$section><tr><th>↱";