X-Git-Url: http://git.shiar.nl/sheet.git/blobdiff_plain/efc30e581f90743618f1bbf44fe0bfae075549ef..2f6bd0f228e04949e561c9e5d7713a0baef77cd5:/charset.plp

diff --git a/charset.plp b/charset.plp
index 7ff3f42..ed495fe 100644
--- a/charset.plp
+++ b/charset.plp
@@ -1,5 +1,8 @@
 <(common.inc.plp)><:
 
+my $mode = exists $get{compare};
+my @tablist = split m{/+}, $Request || 'default';
+
 Html({
 	title => 'charset cheat sheet',
 	version => '1.0',
@@ -18,8 +21,6 @@ Html({
 	)],
 });
 
-my @tablist = split m{/+}, $Request || 'default';
-
 use List::Util qw( first pairmap pairfirst pairs );
 
 :>
@@ -76,67 +77,28 @@ use Shiar_Sheet::FormatChar;
 my $glyphs = Shiar_Sheet::FormatChar->new;
 my @request;
 
-my $INHERIT = do 'charset-encoding.inc.pl'
+my $charsets = do 'charset-encoding.inc.pl'
 	or Alert('Encoding metadata could not be read', $@ || $!);
 
 sub tabinput {
 	# generate character table(s)
 	my $input = shift or return;
+	my $params = $input =~ s/[+](.*)\z// ? $1 : undef;
+	my $charset = $charsets->{lc $input} || {};
 
-	state $ALIAS = {
-		default    => [qw( u+0-27F utf-8+realsize iso-8859-1 iso-8859-15 cp1252 cp437 cp850 )],
-		unicode    => [qw( uu+cols=32+realsize u+0-FFF u+1000-18AF u+18B0-1FFF )],
-		us         => [qw( cp437 cp863 gsm0338 AdobeStandardEncoding )],
-		ebcdic     => [qw( cp37 cp500 cp1047 posix-bc cp1026 cp875 )],
-		iso        => [map {"iso-8859-$_"} 1 .. 11, 13 .. 16],
-		dos        => [qw( cp437 cp865 cp861 cp860 cp863 cp850 cp857 cp852 cp775
-		                   cp737 cp869 cp866 cp855 cp862 cp864 )],
-		aix        => [qw( cp1006 )],
-		win        => [qw( cp1252 cp1250 cp1254 cp1257 cp1258 cp1253 cp1251 cp1255 cp1256 cp874 )],
-		mac        => [qw( MacRoman MacRomanian MacRumanian MacCroatian MacCentralEurRoman MacTurkish MacIcelandic MacSami
-		                   MacGreek MacCyrillic MacHebrew MacArabic MacFarsi MacThai )],
-
-		# languages
-		westeur    => [qw( iso-8859-1 iso-8859-15 cp1252 iso-8859-14 cp850 hp-roman8 nextstep MacRoman )],
-		centeur    => [qw( iso-8859-2 iso-8859-16 cp1250 cp852 MacRomanian MacCroatian MacCentralEurRoman )], # MacRumanian only for DB
-		turkish    => [qw( iso-8859-9 iso-8859-3 cp1254 cp857 MacTurkish )],
-		norteur    => [qw( baltic nordic )],
-		baltic     => [qw( iso-8859-4 iso-8859-13 cp1257 cp775 )],
-		nordic     => [qw( iso-8859-10 cp865 cp861 MacIcelandic MacSami )],
-		cyrillic   => [qw( koi8-r koi8-u koi8-f iso-8859-5 cp1251 MacCyrillic cp866 cp855
-		                   +400 +2DE0 +A640-A69F +500-52F )], # MacUkrainian is broken
-		arabic     => [qw( iso-8859-6 cp1256 MacArabic cp864 cp1006 MacFarsi
-		                   +600 +8A0-8BF+8E0 +750-77F )],
-		greek      => [qw( iso-8859-7 cp1253 MacGreek cp737 cp869  +370 +1F00 )],
-		hebrew     => [qw( iso-8859-8 cp1255 MacHebrew cp862  +590 )],
-		thai       => [qw( iso-8859-11 cp874 MacThai )],
-		vietnamese => [qw( viscii cp1258 MacVietnamese )],
-		symbols    => [qw( symbol dingbats MacDingbats wingdings wingdings2 wingdings3 webdings )],
-
-		# iso-code shorthand
-		1 => 'westeur',
-		2 => 'centeur',
-		3 => 'turkish',
-		4 => 'baltic',
-		5 => 'cyrillic',
-		6 => 'arabic',
-		7 => 'greek',
-		8 => 'hebrew',
-		9 => 'turkish',
-		10 => 'nordic',
-		11 => 'thai',
-	};
-	if (my $follow = $ALIAS->{$input}) {
-		tabinput($_) for ref $follow ? @{$follow} : $follow;
+	if (ref $charset ne 'HASH') {
+		$params and Alert("Parameters ignored for $input",
+			"Cannot apply <q>$params</q> to multiple charsets.",
+		);
+		tabinput($_) for ref $charset ? @{$charset} : $charset;
 		return;
 	}
 
 	state $visible = {'' => 1};  # all present tables
 	my %row = (offset => 0, cols => 16);
-	my $params = $input =~ s/[+](.*)\z// ? $1 : undef;
 
 	if (not defined $params) {
-		my @parents = @{ $INHERIT->{$input} || [] };
+		my @parents = @{ $charset->{inherit} || [] };
 
 		if (my ($parent, $part) = pairfirst { defined $visible->{$a} } @parents) {
 			$row{parent} = $parent;
@@ -181,50 +143,12 @@ sub tabinput {
 		}
 	}
 
-	if ($input =~ m{ \A (?:wing|web)dings \d* \z }ix) {
-		eval "require Encode::\u$input";
+	if ($charset->{setup}) {
+		eval { $charset->{setup}->(\%row) }
+			or Alert("Incomplete setup of $input", $@);
 	}
 
-	if ($input eq '') {
-		$row{offset} = delete $row{startpoint};
-		$row{set} = 'Unicode characters';
-		my $block = $row{offset} >> 8;
-		$row{endpoint} ||= ($block + 1 << 8) - 1;
-		$block == ($row{endpoint} >> 8) or undef $block;
-
-		$row{table} = join '', map { chr } $row{offset} .. $row{endpoint};
-		utf8::upgrade($row{table});  # prevent latin1 output
-
-		$row{endpoint} -= $row{offset};
-
-		if (defined $block) {
-			$row{set} = sprintf 'Unicode block U+%02Xxx', $block;
-			$row{offset} %= 0x100;
-		}
-	}
-	elsif (lc $input eq 'uu') {
-		$row{cell} = do 'charset-ucplanes.inc.pl'
-			or Alert('Table data could not be read', $@ || $!);
-		$row{endpoint} ||= 0x3FF;
-		$row{set} = 'Unicode planes';
-	}
-	elsif (lc $input eq 'u') {
-		$row{cell} = do 'charset-unicode.inc.pl'
-			or Alert('Table data could not be read', $@ || $!);
-
-		$row{endpoint} ||= 0x1FFF;
-		$row{set} = 'Unicode ' . (
-			$row{startpoint} <  0x1000 && $row{endpoint} < 0x1000 ? 'BMP' :
-			$row{startpoint} >= 0x1000 && $row{endpoint} < 0x2000 ? 'SMP' :
-			'allocations'
-		);
-	}
-	elsif ($input =~ m/^utf-*8$/i) {
-		$row{set} = 'UTF-8';
-		$row{cell} = do 'charset-utf8.inc.pl'
-			or Alert('Table data could not be read', $@ || $!);
-		$row{endpoint} = 0xFF;
-	}
+	if ($row{set}) {}
 	elsif ($row{set} = Encode::resolve_alias($input)) {
 		$row{offset} = delete $row{startpoint};
 		$row{endpoint} ||= 0xFF;
@@ -403,7 +327,7 @@ for my $row (@request) {
 			my ($cell, $name, $class) = $glyph eq $NOCHAR ? () :
 				$glyphs->glyph_html($glyph);
 
-			if (exists $get{compare}) {
+			if ($mode) {
 				state $visible = {};
 				$class = (
 					$cp == ord $glyph ? 'l4' :
@@ -430,7 +354,7 @@ for my $row (@request) {
 <hr>
 
 <div class="legend">
-	<table class="glyphs"><tr><: if (exists $get{compare}) { :>
+	<table class="glyphs"><tr><: if ($mode) { :>
 	<td class="X l4">unicode
 	<td class="X l3">inherited
 	<td class="X l2">existing