5 use open IO => ':utf8';
9 $header{content_type} = 'text/html; charset=utf-8';
11 :><!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN"
12 "http://www.w3.org/TR/html4/loose.dtd">
16 <title>charset cheat sheet</title>
17 <meta http-equiv="content-type" content="utf-8">
18 <link rel="stylesheet" type="text/css" media="all" href="/base.css">
22 <h1>Character encoding</h1>
25 my $diinfo = do 'digraphs.inc.pl';
26 my %di = map { $diinfo->{$_}->[0] => $_ } grep { ref $diinfo->{$_} }
29 use Encode qw(decode resolve_alias);
30 # generate character table(s)
31 # (~16x faster than decoding in loop;
32 # substr strings is twice as fast as splitting to an array)
34 # default => [qw(unicode utf-8 iso-8859-1 cp437 -cp1252- --iso-8859-15- -koi8-f)],
35 default => [qw(unicode- utf-8 iso-8859-1 -cp1252- --iso-8859-15- cp437 -cp850)],
36 0 => [qw(cp437 cp863)],
37 1 => [qw(iso-8859-1 cp1252 MacRoman cp850)],
38 2 => [qw(iso-8859-2 cp1250 cp852 MacCentralEurRoman MacCroatian MacRumanian)],
39 5 => [qw(koi8-f iso-8859-5 cp1251 MacCyrillic cp855 cp866)],
40 7 => [qw(iso-8859-7 cp1253 MacGreek cp737 cp869)],
41 8 => [qw(iso-8859-8 cp1255 MacHebrew cp862)],
45 my %row = (offset => 0);
47 if ($input =~ s/^--//) {
48 $row{offset} = $endpoint > 160 ? 160 : 48;
50 elsif ($input =~ s/^-//) {
51 $row{offset} = $endpoint > 128 ? 128 : 32;
53 if ($input =~ s/-$//) {
54 $endpoint = $row{offset} ? $row{offset} < 160 ? 159 : 191 : 127;
56 if ($row{set} = resolve_alias($input)) {
57 if ($row{set} eq 'Internal') {
58 $row{table} = ' ' x ($endpoint < 255 ? 640 : 4096);
59 $row{set} = 'Unicode BMP';
60 $row{cell} = do 'charset-unicode.inc.pl';
62 elsif ($row{set} eq 'utf-8-strict') {
65 $row{cell} = do 'charset-utf8.inc.pl';
68 $row{table} = decode($row{set}, pack 'C*', $row{offset} .. $endpoint);
72 print "<p>Encoding $input unknown</p>\n";
79 } map { defined $ALIAS{$_} ? @{ $ALIAS{$_} } : $_ }
80 $ENV{PATH_INFO} =~ /\w/ ? split(m{[/+\s]}, $ENV{PATH_INFO}) : 'default';
81 my $NOCHAR = chr 0xFFFD;
83 for my $cp437 (grep {$request[$_]->{set} eq 'cp437'} 0 .. $#request) {
84 substr($request[$cp437]->{table}, 237, 1) = pack 'U*', 0x3D5; # phi sign
85 substr($request[$cp437]->{table}, 0, 32) = pack 'U*', map {hex} qw(
86 2007 263A 263B 2665 2666 2663 2660 2022 25D8 25CB 25D9 2642 2640 266A 266B 263C
87 25BA 25C4 2195 203C 00B6 00A7 25AC 21A8 2191 2193 2192 2190 221F 2194 25B2 25BC
101 my @nibble = (0..9, 'A'..'F');
102 for my $row (@request) {
103 print '<li><table class="glyphs">';
104 printf '<caption>%s</caption>', $row->{set};
106 for my $section (qw{thead}) {
107 print "<$section><tr><th>↱";
108 print '<th>', $_ for @nibble;
112 for my $msb (0 .. (length($row->{table}) || 256) - 1 >> 4) {
113 printf '<tr><th>%X', $msb + ($row->{offset} >> 4);
114 for my $lsb (0 .. $#nibble) {
116 print $row->{cell}->(($msb<<4) + $lsb);
120 my $glyph = substr $row->{table}, ($msb<<4) + $lsb, 1;
121 if ($glyph eq $NOCHAR) {
126 my $info = [ord $glyph];
127 if (defined (my $mnem = $di{ord $glyph})) {
128 $info = $diinfo->{$mnem};
130 my ($codepoint, $name, $prop, $script, $string) = @$info;
132 $glyph = quote($string || $glyph);
133 my $desc = sprintf 'U+%04X%s', $codepoint, $name && " ($name)";
134 my @class = ('X', grep {$_} $prop, $script);
136 $glyph = "<span>$glyph</span>" if $prop eq 'Zs';
138 printf "\n".'<td class="%s" title="%s">%s',
139 join(' ', @class), quote($desc), $glyph;
152 <table class="glyphs"><tr>
153 <td class="X Cc">control
154 <td class="X Zs"><span>whitespace</span>
155 <td class="X Mn">diacritic<table class="glyphs"><tr>
156 <td class="X Sk">letter
158 <td class="X Po">punctuation<table class="glyphs"><tr>
159 <td class="X Pf">quote
161 <td class="X So">symbol<table class="glyphs"><tr>
162 <td class="X Sm">math
163 <td class="X Sc">currency
165 <td class="X No">numeric
166 <td class="X Greek">greek<table class="glyphs"><tr>
167 <td class="X Latin">latin
168 <td class="X Cyrillic">cyrillic
170 <td class="X Aramaic">aramaic<table class="glyphs"><tr>
171 <td class="X Brahmic">brahmic
172 <td class="X Arabic">arabic
174 <td class="X Syllabic">syllabic<table class="glyphs"><tr>
175 <td class="X African">african
176 <td class="X Hiragana">japanese
177 <td class="X Han">cjk
178 <td class="X Bopomofo">chinese
180 <td class="X Alpha">alphabetic
183 <table class="glyphs"><tr>
184 <td class="X">unicode 5.0
185 <td class="X Xr">proposed
186 <td class="X Xd">deprecated
187 <td class="">unassigned
188 <td class="X Xi">invalid
193 <a href="http://sheet.shiar.nl/" rel="home">sheet.shiar.nl</a>/charset
194 <a href="git://git.shiar.nl/sheet" rel="vcs-git" title="Git repository"><:= "v$VERSION" :></a>
195 created by <a href="http://shiar.nl/" rel="author">Shiar</a> •
196 <a title="Licensed under the GNU Affero General Public License, version 3" rel="copyright"
197 href="http://www.fsf.org/licensing/licenses/agpl-3.0.html">AGPLv3</a> •
199 use Time::Format qw(time_format);
200 print time_format('yyyy-mm-dd', (stat $ENV{SCRIPT_FILENAME})[9]);