-<:
-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)><:
+
+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'],
+});
-<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>
-
-<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)],
+ 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 = $_) {
if ($input =~ s/-$//) {
$endpoint = $row{offset} ? $row{offset} < 160 ? 159 : 191 : 127;
}
- if ($row{set} = resolve_alias($input)) {
+ if ($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);
+ 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'
+ or Alert('Table data could not be read', $@ || $!);
+ @nibble = (map { $_.0, $_.8 } 0 .. 7);
+ $nibsize = 8;
+ }
+ elsif ($row{set} = Encode::resolve_alias($input)) {
if ($row{set} eq 'Internal') {
- $row{table} = ' 'x512;
+ $row{table} = ' ' x ($endpoint < 255 ? 640 : 8192);
$row{set} = 'Unicode BMP';
+ $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'
+ 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 $_;
-}
-
-sub printcell_unicode {
- my ($value) = @_;
- if ($value > 0x1FF) {
- print "\n".'<td class="X">?';
- }
- elsif ($value == 0) {
- print '<td colspan="2" class="X Cc">control';
- }
- elsif ($value == 2) {
- print '<td colspan="6" class="X Ll Latin">latin';
- }
- elsif ($value == 8) {
- print '<td colspan="2" class="X Cc">control';
- }
- elsif ($value == 10) {
- print '<td colspan="6" class="X Ll Latin">latin supplement';
- }
- elsif ($value == 0x10) {
- print '<td colspan="8" class="X Ll Latin">latin ext-A';
- }
- elsif ($value == 0x18) {
- print '<td colspan="8" class="X Ll Latin">latin ext-B';
- }
- elsif ($value == 0x20) {
- print '<td colspan="5" class="X Ll Latin">latin ext-B';
- }
- elsif ($value == 0x25) {
- print '<td colspan="6" class="X Ll Latin">IPA';
- }
- elsif ($value == 0x2B) {
- print '<td colspan="5" class="X Sk">spacing modifier';
- }
- elsif ($value == 0x30) {
- print '<td colspan="8" class="X Mn">diacritics';
- }
- elsif ($value == 0x38) {
- print '<td colspan="8" class="X Ll Greek">greek';
- }
- elsif ($value == 0x40) {
- print '<td colspan="16" class="X Ll Cyrillic">cyrillic';
- }
- elsif ($value == 0x50) {
- print '<td colspan="3" class="X Ll Cyrillic">cyrillic+';
- }
- elsif ($value == 0x53) {
- print '<td colspan="5" class="X Ll Armenian">armenian';
- }
- elsif ($value == 0x58) {
- print '<td colspan="8" class="X Ll Hebrew">hebrew';
- }
- elsif ($value == 0x60) {
- print '<td colspan="16" class="X Ll Arabic">arabic';
- }
- elsif ($value == 0x70) {
- print '<td colspan="5" class="X Ll Aramaic">syriac';
- }
- elsif ($value == 0x75) {
- print '<td colspan="3" class="X Ll Arabic">arabic+';
- }
- elsif ($value == 0x78) {
- print '<td colspan="4" class="X Ll African">thaana';
- }
- elsif ($value == 0x7C) {
- print '<td colspan="4" class="X Ll African">nko';
- }
- elsif ($value == 0x80) {
- print '<td colspan="4" class="X di-rare">samaritan';
- }
- elsif ($value == 0x84) {
- print '<td colspan="2" class="X di-rare Ll Aramaic">manda';
- }
- elsif ($value == 0x86) {
- print '<td colspan="12" class="di-invalid">reserved';
- }
- elsif ($value == 0x90) {
- print '<td colspan="8" class="X Ll Brahmic">devanagari';
- }
- elsif ($value == 0x98) {
- print '<td colspan="8" class="X Ll Brahmic">bengali';
- }
- elsif ($value == 0xA0) {
- print '<td colspan="8" class="X Ll Brahmic">gurmukhi';
- }
- elsif ($value == 0xA8) {
- print '<td colspan="8" class="X Ll Brahmic">gujarati';
- }
- elsif ($value == 0xB0) {
- print '<td colspan="8" class="X Ll Brahmic">oriya';
- }
- elsif ($value == 0xB8) {
- print '<td colspan="8" class="X Ll Brahmic">tamil';
- }
- elsif ($value == 0xC0) {
- print '<td colspan="8" class="X Ll Brahmic">telugu';
- }
- elsif ($value == 0xC8) {
- print '<td colspan="8" class="X Ll Brahmic">kannada';
- }
- elsif ($value == 0xD0) {
- print '<td colspan="8" class="X Ll Brahmic">malayalam';
- }
- elsif ($value == 0xD8) {
- print '<td colspan="8" class="X Ll Brahmic">sinhala';
- }
- elsif ($value == 0xE0) {
- print '<td colspan="8" class="X Ll Brahmic Khmer">thai';
- }
- elsif ($value == 0xE8) {
- print '<td colspan="8" class="X Ll Brahmic Khmer">lao';
- }
- elsif ($value == 0xF0) {
- print '<td colspan="16" class="X Ll Brahmic">tibetan';
- }
- elsif ($value == 0x100) {
- print '<td colspan="10" class="X Ll Brahmic">myanmar';
- }
- elsif ($value == 0x10A) {
- print '<td colspan="6" class="X Ll Aramaic">georgian';
- }
- elsif ($value == 0x110) {
- print '<td colspan="16" class="X Ll Hangul">hangeul jamo';
- }
- elsif ($value == 0x120) {
- print '<td colspan="16" class="X Ll African">ethiopic';
- }
- elsif ($value == 0x130) {
- print '<td colspan="8" class="X Ll African">ethiopic';
- }
- elsif ($value == 0x138) {
- print '<td colspan="2" class="X Ll African">eth+';
- }
- elsif ($value == 0x13A) {
- print '<td colspan="6" class="X Ll X">cherokee';
- }
- elsif ($value == 0x140) {
- print '<td colspan="16" rowspan="2" class="X Ll Syllabic">unified canadian aboriginal syllabics';
- }
- elsif ($value == 0x160) {
- print '<td colspan="8" class="X Ll Syllabic">unified canadian syllabics';
- }
- elsif ($value == 0x168) {
- print '<td colspan="2" class="X Ll X">ogham';
- }
- elsif ($value == 0x16A) {
- print '<td colspan="6" class="X Ll X">runic';
- }
- elsif ($value == 0x170) {
- print '<td colspan="2" class="X Ll Brahmic">tagalog';
- }
- elsif ($value == 0x172) {
- print '<td colspan="2" class="X Ll Brahmic">hanun';
- }
- elsif ($value == 0x174) {
- print '<td colspan="2" class="X Ll Brahmic">buhid';
- }
- elsif ($value == 0x176) {
- print '<td colspan="2" class="X Ll Brahmic" title="tagbanwa">tagb';
- }
- elsif ($value == 0x178) {
- print '<td colspan="8" class="X Ll Brahmic Khmer">khmer';
- }
- elsif ($value == 0x180) {
- print '<td colspan="11" class="X Ll Aramaic">mongolian';
- }
- elsif ($value == 0x18B) {
- print '<td colspan="5" class="X Ll Syllabic di-rare">canadian+';
- }
- elsif ($value == 0x190) {
- print '<td colspan="5" class="X Ll Brahmic">limbu';
- }
- elsif ($value == 0x195) {
- print '<td colspan="4" class="X Ll Brahmic">tai le';
- }
- elsif ($value == 0x198) {
- print '<td colspan="6" class="X Ll Brahmic">new tai lue';
- }
- elsif ($value == 0x19E) {
- print '<td colspan="2" class="X Ll Brahmic Khmer" title="khmer symbols">km';
- }
- elsif ($value == 0x1A0) {
- print '<td colspan="2" class="X Ll Brahmic">lontara';
- }
- elsif ($value == 0x1A2) {
- print '<td colspan="9" class="X Ll Brahmic di-rare">tai tham';
- }
- elsif ($value == 0x1AB) {
- print '<td colspan="5" class="di-invalid">reserved';
- }
- elsif ($value == 0x1B0) {
- print '<td colspan="8" class="X Ll ">balinese';
- }
- elsif ($value == 0x1B8) {
- print '<td colspan="4" class="X Ll ">sundanese';
- }
- elsif ($value == 0x1BC) {
- print '<td colspan="4" class="X Ll di-rare">batak';
- }
- elsif ($value == 0x1C0) {
- print '<td colspan="5" class="X Ll ">lepcha';
- }
- elsif ($value == 0x1C5) {
- print '<td colspan="3" class="X Ll ">ol chiki';
- }
- elsif ($value == 0x1C8) {
- print '<td colspan="5" class="di-invalid">reserved';
- }
- elsif ($value == 0x1CD) {
- print '<td colspan="3" class="X Ll di-rare">vedic';
- }
- elsif ($value == 0x1D0) {
- print '<td colspan="8" class="X Ll Latin">phonetic';
- }
- elsif ($value == 0x1D8) {
- print '<td colspan="4" class="X Ll Latin">phonetic+';
- }
- elsif ($value == 0x1DC) {
- print '<td colspan="4" class="X Mn">combining';
- }
- elsif ($value == 0x1E0) {
- print '<td colspan="16" class="X Ll Latin">latin extended additional';
- }
- elsif ($value == 0x1F0) {
- print '<td colspan="16" class="X Ll Greek">greek+';
+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;
+ $len = 16;
}
-}
-sub printcell_utf8 {
- my ($value) = @_;
- if ($value <= 0x7F) {
- print '<td rowspan="8" colspan="16" class="X di-a"',
- ' title="U+0000 – U+007F">Single byte ASCII'
- if $value == 0;
- }
- elsif ($value <= 0xBF) {
- print '<td rowspan="4" colspan="16" class="X di-d"',
- '>Multi-byte continuation'
- if $value == 0x80;
- }
- elsif ($value <= 0xC1) {
- print '<td colspan="2" class="X di-b" style="border-right:none; border-bottom:none"',
- ' title="U+0000 – U+007F">(Overl.)'
- if $value == 0xC0;
- }
- elsif ($value <= 0xDF) {
- print '<td rowspan="2" colspan="14" class="X di-prop" style="border-left:none"',
- ' title="U+0080 – U+03FF">2-byte sequence start'
- if $value == 0xC2;
- print '<td rowspan="1" colspan="16" class="X di-prop" style="border-top:none"',
- ' title="U+0400 – U+07FF">'
- if $value == 0xD0;
- }
- elsif ($value <= 0xEF) {
- print '<td colspan="16" class="X di-prop"',
- ' title="U+0800 – U+FFFF">3-byte sequence start'
- if $value == 0xE0;
- }
- elsif ($value <= 0xF4) {
- print '<td colspan="5" class="X di-prop" style="border-right:none"',
- ' title="U+1·0000 – U+10·FFFF">4-byte sequence'
- if $value == 0xF0;
- }
- elsif ($value <= 0xF7) {
- print '<td colspan="3" class="X di-b" style="border-left:none"',
- ' title="U+11·0000 – U+1FF·FFFF">(Overflow)'
- if $value == 0xF5;
- }
- elsif ($value <= 0xFB) {
- print '<td colspan="4" class="X di-b"',
- ' title="U+200·0000 – U+3FFF·FFFF">5-byte'
- if $value == 0xF8;
- }
- elsif ($value <= 0xFD) {
- print '<td colspan="2" class="X di-b"',
- ' title="U+4000·0000 – 7FFFF·FFFF">6-byte'
- if $value == 0xFC;
- }
- elsif ($value <= 0xFF) {
- print '<td colspan="2" class="di-invalid">Invalid'
- if $value == 0xFE;
- }
- else {
- print "\n".'<td class="X">?';
- }
+ $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";
}
-print "<ul>\n";
-
-my @nibble = (0..9, 'A'..'F');
for my $row (@request) {
- print '<li><table class="glyphs">';
- printf '<caption>%s</caption>', $row->{set};
- print '<col>';
+ printf '<div class="section"><table class="glyphs%s">', !$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 '<th>', $_ for @nibble;
}
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 .. $#nibble) {
- if ($row->{set} eq 'UTF-8') {
- printcell_utf8(($msb<<4) + $lsb);
- next;
- }
- elsif ($row->{set} eq 'Unicode BMP') {
- printcell_unicode(($msb<<4) + $lsb);
+ my $val = ( ($msb<<4) + $lsb ) * $nibsize;
+ if ($row->{cell}) {
+ 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};
- }
- 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($glyph);
}
print "\n";
}
- print "</table>\n";
+ say '</table></div>';
}
-print "</ul>\n";
-
:>
<hr>
-<p class="footer">
- <a href="http://sheet.shiar.nl/" rel="home">sheet.shiar.nl</a>/charset
- <a href="git://git.shiar.nl/sheet" rel="vcs-git" title="Git repository"><:= "v$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>