-<:
-use utf8;
-use strict;
-use warnings;
-use open IO => ':utf8';
-
-our $VERSION = '1.0';
-
-$header{content_type} = 'text/html; charset=utf-8';
-
-:><!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN"
- "http://www.w3.org/TR/html4/loose.dtd">
-<html>
-
-<head>
-<title>charset cheat sheet</title>
-<meta http-equiv="content-type" content="utf-8">
-<link rel="stylesheet" type="text/css" media="all" href="/base.css">
-</head>
+<(common.inc.plp)><:
+
+Html({
+ title => 'charset cheat sheet',
+ version => 'v1.0',
+ 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'],
+});
-<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 $nibsize = 1;
use Encode qw(decode resolve_alias);
# generate character table(s)
if ($input =~ s/-$//) {
$endpoint = $row{offset} ? $row{offset} < 160 ? 159 : 191 : 127;
}
- if ($row{set} = resolve_alias($input)) {
+
+ if ($input =~ /^U([0-9a-f]+)(?:-([0-9a-f]+))?/) {
+ my $start = hex($1) << ($2 ? 4 : 8);
+ my $end = $2 ? hex($2) << 4 : $start + 240;
+ $row{table} = join '', map { chr } $start .. $end+15;
+ utf8::upgrade($row{table}); # prevent latin1 output
+ $row{set} = sprintf 'Unicode block U+%02Xxx', $start >> 8;
+ }
+ elsif ($input eq 'U') {
+ $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';
}
);
}
-sub quote {
- local $_ = shift;
- s/"/"/g;
- s/</</g;
- s/>/>/g;
- return $_;
-}
-
-print "<ul>\n";
-
-my @nibble = (0..9, 'A'..'F');
for my $row (@request) {
- print '<li><table class="glyphs">';
+ printf '<div class="section"><table class="glyphs%s">', !$row->{cell} && ' charmap';
printf '<caption>%s</caption>', $row->{set};
- print '<col>';
+ print '<col>' x 17;
for my $section (qw{thead}) {
print "<$section><tr><th>↱";
print '<th>', $_ for @nibble;
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);
+ print $row->{cell}->($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};
- }
- 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($glyph);
}
print "\n";
}
- print "</table>\n";
+ print "</table></div>\n";
}
-print "</ul>\n";
-
:>
<hr>
-<p class="footer">
- <a href="http://sheet.shiar.nl/" rel="home">sheet.shiar.nl</a>/charset
- <a href="git://git.shiar.nl/sheet" rel="vcs-git" title="Git repository"><:= "v$VERSION" :></a>
- created by <a href="http://shiar.nl/" rel="author">Shiar</a> •
- <a title="Licensed under the GNU Affero General Public License, version 3" rel="copyright"
- href="http://www.fsf.org/licensing/licenses/agpl-3.0.html">AGPLv3</a> •
- last update <:
- use Time::Format qw(time_format);
- print time_format('yyyy-mm-dd', (stat $ENV{SCRIPT_FILENAME})[9]);
- :>
-</p>
+<div class="legend">
+ <table class="glyphs"><tr>
+ <td class="X Cc">control
+ <td class="X Zs"><span>whitespace</span>
+ <td class="X Mn">diacritic<table class="glyphs"><tr>
+ <td class="X Sk">letter
+ </table>
+ <td class="X Po">punctuation<table class="glyphs"><tr>
+ <td class="X Pf">quote
+ </table>
+ <td class="X So">symbol<table class="glyphs"><tr>
+ <td class="X Sm">math
+ <td class="X Sc">currency
+ </table>
+ <td class="X No">numeric
+ <td class="X Greek">greek<table class="glyphs"><tr>
+ <td class="X Latin">latin
+ <td class="X Cyrillic">cyrillic
+ </table>
+ <td class="X Aramaic">aramaic<table class="glyphs"><tr>
+ <td class="X Brahmic">brahmic
+ <td class="X Arabic">arabic
+ </table>
+ <td class="X Syllabic">syllabic<table class="glyphs"><tr>
+ <td class="X African">african
+ <td class="X Hiragana">japanese
+ <td class="X Han">cjk
+ <td class="X Bopomofo">chinese
+ </table>
+ <td class="X Alpha">alphabetic
+ </table>
+
+ <table class="glyphs"><tr>
+ <td class="X">unicode 7.0
+ <td class="X Xr">proposed
+ <td class="X Xd">deprecated
+ <td class="">unassigned
+ <td class="X Xi">invalid
+ </table>
+</div>
-</html>