Html({
title => 'charset cheat sheet',
- version => 'v1.0',
+ version => '1.0',
description => [
"Reference sheet with all glyphs in common character encoding tables,",
"and an overview of Unicode ranges and UTF-8 bytes.",
reference common overview table
'],
stylesheet => [qw'light'],
+ data => [qw'charset-unicode.inc.pl charset-utf8.inc.pl'],
});
:>
<h1>Character encoding</h1>
<:
-my $diinfo = do 'digraphs.inc.pl';
-my %di = map { $diinfo->{$_}->[0] => $_ } grep { ref $diinfo->{$_} }
- keys %$diinfo;
+use Shiar_Sheet::FormatChar;
+my $glyphs = Shiar_Sheet::FormatChar->new;
+my @nibble = (0..9, 'A'..'F');
+my $nibsize = 1;
use Encode qw(decode resolve_alias);
# generate character table(s)
$row{set} = sprintf 'Unicode block U+%02Xxx', $start >> 8;
}
elsif ($input eq 'U') {
- $row{table} = ' ' x 512;
+ $row{table} = ' ' x 1024;
$row{set} = 'Unicode planes';
$row{cell} = do 'charset-ucplanes.inc.pl';
+ @nibble = (map { $_.0, $_.8 } 0 .. 7);
+ $nibsize = 8;
}
elsif ($row{set} = resolve_alias($input)) {
if ($row{set} eq 'Internal') {
- $row{table} = ' ' x ($endpoint < 255 ? 640 : 4096);
+ $row{table} = ' ' x ($endpoint < 255 ? 640 : 8192);
$row{set} = 'Unicode BMP';
$row{cell} = do 'charset-unicode.inc.pl';
}
);
}
-my @nibble = (0..9, 'A'..'F');
+sub range_cell {
+ my ($table, $offset) = @_;
+ my $def = $table->{$offset} or return;
+ my ($len, $class, $name, $title) = @{$def};
+
+ my $attr = '';
+ $name //= $len <= 2 ? 'res' : 'reserved';
+
+ if (my $part = $offset % 16) {
+ # continued row
+ my $cols = 16 - $part; # remaining
+ $cols = $len if $len < $cols; #TODO: optimise
+ if ($len -= $cols) {
+ # continued on new row
+ $table->{$offset + $cols} = [$len, "$class joinu", $name, $title];
+ $name = '';
+ $class .= ' joind';
+ }
+ $len = $cols;
+ }
+ elsif (my $rows = $len >> 4) {
+ # multiple full rows
+ if ($len -= $rows << 4) {
+ # partial row remains
+ $table->{$offset + $rows * 16} = [$len, "$class joinu", '', $title];
+ $class .= ' joind';
+ }
+ $attr .= sprintf ' rowspan=%d', $rows;
+ $len = 16;
+ }
+
+ $attr .= sprintf ' colspan=%d', $len unless $len == 1;
+ $attr .= sprintf ' class="%s"', $class if $class;
+ $attr .= sprintf ' title="%s"', EscapeHTML($title) if $title;
+ return "<td$attr>$name";
+}
+
for my $row (@request) {
- printf '<section><table class="glyphs%s">', !$row->{cell} && ' charmap';
+ printf '<div class="section"><table class="glyphs%s">', !$row->{cell} && ' charmap';
printf '<caption>%s</caption>', $row->{set};
print '<col>' x 17;
for my $section (qw{thead}) {
for my $msb (0 .. (length($row->{table}) || 256) - 1 >> 4) {
printf '<tr><th>%X', $msb + ($row->{offset} >> 4);
for my $lsb (0 .. $#nibble) {
+ my $val = ( ($msb<<4) + $lsb ) * $nibsize;
if ($row->{cell}) {
- print $row->{cell}->(($msb<<4) + $lsb);
+ if (ref $row->{cell} eq 'CODE') {
+ print $row->{cell}->($val);
+ next;
+ }
+ print range_cell($row->{cell}, $val);
next;
}
- my $glyph = substr $row->{table}, ($msb<<4) + $lsb, 1;
+ my $glyph = substr $row->{table}, $val, 1;
if ($glyph eq $NOCHAR) {
print '<td>';
next;
}
- my $info = [ord $glyph];
- if (defined (my $mnem = $di{ord $glyph})) {
- $info = $diinfo->{$mnem};
- }
- else {
- require Unicode::UCD;
- my $fullinfo = Unicode::UCD::charinfo(ord $glyph);
- $info = [@$fullinfo{qw/code name category script string/}] if $fullinfo;
- }
- my ($codepoint, $name, $prop, $script, $string) = @$info;
-
- $glyph = EscapeHTML($string || $glyph);
- my $desc = sprintf 'U+%04X%s', $codepoint, $name && " ($name)";
- my @class = ('X', grep {$_} $prop, $script);
-
- $glyph = "<span>$glyph</span>" if $prop eq 'Zs';
-
- printf "\n".'<td class="%s" title="%s">%s',
- join(' ', @class), EscapeHTML($desc), $glyph;
+ print "\n".$glyphs->glyph_cell($glyph);
}
print "\n";
}
- print "</table></section>\n";
+ print "</table></div>\n";
}
:>
</table>
<table class="glyphs"><tr>
- <td class="X">unicode 5.0
+ <td class="X">unicode 7.0
<td class="X Xr">proposed
<td class="X Xd">deprecated
<td class="">unassigned