-<:
-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>
+<(common.inc.plp)><:
-<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>
+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'],
+});
-<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 $glyphs = Shiar_Sheet::FormatChar->new;
-use Encode qw(decode);
+use Encode qw(decode resolve_alias);
# generate character table(s)
# (~16x faster than decoding in loop;
# substr strings is twice as fast as splitting to an array)
-my @tables = map { decode($_, pack 'C*', 0..255) } 'iso-8859-1';
+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)],
+);
+my @request = map {
+ if (my $input = $_) {
+ my %row = (offset => 0);
+ my $endpoint = 255;
+ if ($input =~ s/^--//) {
+ $row{offset} = $endpoint > 160 ? 160 : 48;
+ }
+ elsif ($input =~ s/^-//) {
+ $row{offset} = $endpoint > 128 ? 128 : 32;
+ }
+ if ($input =~ s/-$//) {
+ $endpoint = $row{offset} ? $row{offset} < 160 ? 159 : 191 : 127;
+ }
+
+ if ($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 512;
+ $row{set} = 'Unicode planes';
+ $row{cell} = do 'charset-ucplanes.inc.pl';
+ }
+ elsif ($row{set} = resolve_alias($input)) {
+ if ($row{set} eq 'Internal') {
+ $row{table} = ' ' x ($endpoint < 255 ? 640 : 4096);
+ $row{set} = 'Unicode BMP';
+ $row{cell} = do 'charset-unicode.inc.pl';
+ }
+ elsif ($row{set} eq 'utf-8-strict') {
+ $row{table} = undef;
+ $row{set} = 'UTF-8';
+ $row{cell} = do 'charset-utf8.inc.pl';
+ }
+ else {
+ $row{table} = decode($row{set}, pack 'C*', $row{offset} .. $endpoint);
+ }
+ }
+ else {
+ print "<p>Encoding $input unknown</p>\n";
+ }
+ \%row;
+ }
+ else {
+ ();
+ }
+} map { defined $ALIAS{$_} ? @{ $ALIAS{$_} } : $_ }
+ $ENV{PATH_INFO} =~ /\w/ ? split(m{[/+\s]}, $ENV{PATH_INFO}) : 'default';
my $NOCHAR = chr 0xFFFD;
-sub quote {
- local $_ = shift;
- s/"/"/g;
- s/</</g;
- s/>/>/g;
- return $_;
+for my $cp437 (grep {$request[$_]->{set} eq 'cp437'} 0 .. $#request) {
+ substr($request[$cp437]->{table}, 237, 1) = pack 'U*', 0x3D5; # phi sign
+ substr($request[$cp437]->{table}, 0, 32) = pack 'U*', map {hex} qw(
+ 2007 263A 263B 2665 2666 2663 2660 2022 25D8 25CB 25D9 2642 2640 266A 266B 263C
+ 25BA 25C4 2195 203C 00B6 00A7 25AC 21A8 2191 2193 2192 2190 221F 2194 25B2 25BC
+ );
}
my @nibble = (0..9, 'A'..'F');
-for my $table (@tables) {
- print '<table class="glyphs"><col>';
- for my $section (qw{thead tfoot}) {
- print "<$section><tr><th>↳";
+for my $row (@request) {
+ printf '<div class="section"><table class="glyphs%s">', !$row->{cell} && ' charmap';
+ printf '<caption>%s</caption>', $row->{set};
+ print '<col>' x 17;
+ for my $section (qw{thead}) {
+ print "<$section><tr><th>↱";
print '<th>', $_ for @nibble;
- print "<th> \n";
+ print "\n";
}
print '<tbody>';
- for my $msb (0 .. $#nibble) {
- print '<tr><th>', $nibble[$msb];
+ for my $msb (0 .. (length($row->{table}) || 256) - 1 >> 4) {
+ printf '<tr><th>%X', $msb + ($row->{offset} >> 4);
for my $lsb (0 .. $#nibble) {
- my $glyph = substr $table, ($msb<<4) + $lsb, 1;
+ if ($row->{cell}) {
+ print $row->{cell}->(($msb<<4) + $lsb);
+ next;
+ }
+
+ my $glyph = substr $row->{table}, ($msb<<4) + $lsb, 1;
if ($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<th>", $nibble[$msb], "\n";
+ print "\n";
}
- print "</table>\n";
+ print "</table></div>\n";
}
+:>
+<hr>
+
+<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 5.0
+ <td class="X Xr">proposed
+ <td class="X Xd">deprecated
+ <td class="">unassigned
+ <td class="X Xi">invalid
+ </table>
+</div>
+