-<:
-use utf8;
-use strict;
-use warnings;
-use open IO => ':utf8';
-
-our $VERSION = 'v1.0';
-
-$header{content_type} = 'text/html; charset=utf-8';
+<(common.inc.plp)><:
+
+Html({
+ title => 'charset cheat sheet',
+ version => '1.0',
+ description => [
+ "Reference sheet with all glyphs in common character encoding tables,",
+ "and an overview of Unicode ranges and UTF-8 bytes.",
+ ],
+ keywords => [qw'
+ charset codepage unicode ascii utf8 latin glyph character encoding
+ reference common overview table
+ '],
+ stylesheet => [qw'light'],
+ data => [qw'charset-unicode.inc.pl charset-utf8.inc.pl'],
+});
-:><!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN"
- "http://www.w3.org/TR/html4/loose.dtd">
-<html>
-
-<head>
-<meta http-equiv="content-type" content="<:= $header{content_type} :>">
-<title>charset cheat sheet</title>
-<link rel="stylesheet" type="text/css" media="all" href="/base.css">
-</head>
-
-<body>
+:>
<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)
# (~16x faster than decoding in loop;
# substr strings is twice as fast as splitting to an array)
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 = $_) {
if ($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);
$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';
+ $row{cell} = do 'charset-ucplanes.inc.pl'
+ or Alert('Table data could not be read', $@ || $!);
+ @nibble = (map { $_.0, $_.8 } 0 .. 7);
+ $nibsize = 8;
}
- elsif ($row{set} = resolve_alias($input)) {
+ elsif ($row{set} = Encode::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';
+ $row{cell} = do 'charset-unicode.inc.pl'
+ or Alert('Table data could not be read', $@ || $!);
}
elsif ($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 Alert('Table data could not be read', $@ || $!);
}
else {
- $row{table} = decode($row{set}, pack 'C*', $row{offset} .. $endpoint);
+ $row{table} = Encode::decode($row{set}, pack 'C*', $row{offset} .. $endpoint);
}
}
else {
- print "<p>Encoding $input unknown</p>\n";
+ Alert("Encoding <q>$input</q> unknown");
}
- \%row;
+ $row{set} ? \%row : ();
}
else {
();
}
} map { defined $ALIAS{$_} ? @{ $ALIAS{$_} } : $_ }
- $ENV{PATH_INFO} =~ /\w/ ? split(m{[/+\s]}, $ENV{PATH_INFO}) : 'default';
+ $Request =~ /\w/ ? split(m{[/+\s]}, $Request) : 'default';
my $NOCHAR = chr 0xFFFD;
for my $cp437 (grep {$request[$_]->{set} eq 'cp437'} 0 .. $#request) {
);
}
-sub quote {
- local $_ = shift;
- s/"/"/g;
- s/</</g;
- s/>/>/g;
- return $_;
-}
+sub range_cell {
+ my ($table, $offset) = @_;
+ my $def = $table->{$offset} or return;
+ my ($len, $class, $name, $title) = @{$def};
+
+ my $attr = '';
+ $len /= $nibsize;
+ $name //= $len <= 2 ? 'res' : 'reserved';
+
+ if (my $part = $offset/$nibsize % 16) {
+ # continued row
+ my $cols = 16 - $part; # remaining
+ $cols = $len if $len < $cols; #TODO: optimise
+ if ($len -= $cols) {
+ # continued on new row
+ $table->{$offset + $nibsize*$cols} //= [$len*$nibsize, "$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 + $nibsize*$rows * 16} //= [$len*$nibsize, "$class joinu", '', $title];
+ $class .= ' joind';
+ }
+ $attr .= sprintf ' rowspan=%d', $rows;
+ $len = 16;
+ }
-print "<ul>\n";
+ $attr .= sprintf ' colspan=%d', $len unless $len == 1;
+ $attr .= $1 if $class and $class =~ s/( \w+="[^"]*")//;
+ $attr .= sprintf ' class="%s"', $class if $class;
+ $attr .= sprintf ' title="%s"', EscapeHTML($title) if $title;
+ return "<td$attr>$name";
+}
-my @nibble = (0..9, 'A'..'F');
for my $row (@request) {
- printf '<li><table class="glyphs%s">', !$row->{cell} && ' charmap';
- printf '<caption>%s</caption>', $row->{set};
+ printf '<div class="section"><table class="glyphs%s">', !$row->{cell} && ' charmap';
+ 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>↱";
}
print '<tbody>';
for my $msb (0 .. (length($row->{table}) || 256) - 1 >> 4) {
- printf '<tr><th>%X', $msb + ($row->{offset} >> 4);
+ printf '<tr><th>%X', ($msb + ($row->{offset} >> 4)) * $nibsize;
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;
-
- $glyph = quote($string || $glyph);
- my $desc = sprintf 'U+%04X%s', $codepoint, $name && " ($name)";
- my @class = ('X', grep {$_} $prop, $script);
-
- $glyph = "<span>$glyph</span>" if $prop eq 'Zs';
-
- printf "\n".'<td class="%s" title="%s">%s',
- join(' ', @class), quote($desc), $glyph;
+ print "\n".$glyphs->glyph_cell($glyph);
}
print "\n";
}
- print "</table>\n";
+ say '</table></div>';
}
-print "</ul>\n";
-
:>
<hr>
</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
</table>
</div>
-<p class="footer">
- <a href="/" rel="home">sheet.shiar.nl</a>/charset.<a href="/source/charset.plp"
- rel="code" title="Written in Perl">plp</a>
- <a href="http://git.shiar.nl/sheet.git/history/HEAD:/charset.plp"
- rel="vcs-git" title="Git repository"><:= $VERSION :></a>
- created by <a href="http://shiar.nl/" rel="author">Shiar</a> •
- <a href="http://www.fsf.org/licensing/licenses/agpl-3.0.html" rel="copyright"
- title="Licensed under the GNU Affero General Public License, version 3">AGPLv3</a>
-</p>
-
-</html>