4 title => 'charset cheat sheet',
7 "Reference sheet with all glyphs in common character encoding tables,",
8 "and an overview of Unicode ranges and UTF-8 bytes.",
11 charset codepage unicode ascii utf8 latin glyph character encoding
12 reference common overview table
14 stylesheet => [qw'light'],
15 data => [qw'charset-unicode.inc.pl charset-utf8.inc.pl'],
19 <h1>Character encoding</h1>
22 use Shiar_Sheet::FormatChar;
23 my $glyphs = Shiar_Sheet::FormatChar->new;
25 use Encode qw(decode resolve_alias);
26 # generate character table(s)
27 # (~16x faster than decoding in loop;
28 # substr strings is twice as fast as splitting to an array)
30 # default => [qw(unicode utf-8 iso-8859-1 cp437 -cp1252- --iso-8859-15- -koi8-f)],
31 default => [qw(unicode- utf-8 iso-8859-1 -cp1252- --iso-8859-15- cp437 -cp850)],
32 0 => [qw(cp437 cp863)],
33 1 => [qw(iso-8859-1 cp1252 MacRoman cp850)],
34 2 => [qw(iso-8859-2 cp1250 cp852 MacCentralEurRoman MacCroatian MacRumanian)],
35 5 => [qw(koi8-f iso-8859-5 cp1251 MacCyrillic cp855 cp866)],
36 7 => [qw(iso-8859-7 cp1253 MacGreek cp737 cp869)],
37 8 => [qw(iso-8859-8 cp1255 MacHebrew cp862)],
41 my %row = (offset => 0);
43 if ($input =~ s/^--//) {
44 $row{offset} = $endpoint > 160 ? 160 : 48;
46 elsif ($input =~ s/^-//) {
47 $row{offset} = $endpoint > 128 ? 128 : 32;
49 if ($input =~ s/-$//) {
50 $endpoint = $row{offset} ? $row{offset} < 160 ? 159 : 191 : 127;
53 if ($input =~ /^U([0-9a-f]+)(?:-([0-9a-f]+))?/) {
54 my $start = hex($1) << ($2 ? 4 : 8);
55 my $end = $2 ? hex($2) << 4 : $start + 240;
56 $row{table} = join '', map { chr } $start .. $end+15;
57 utf8::upgrade($row{table}); # prevent latin1 output
58 $row{set} = sprintf 'Unicode block U+%02Xxx', $start >> 8;
60 elsif ($input eq 'U') {
61 $row{table} = ' ' x 512;
62 $row{set} = 'Unicode planes';
63 $row{cell} = do 'charset-ucplanes.inc.pl';
65 elsif ($row{set} = resolve_alias($input)) {
66 if ($row{set} eq 'Internal') {
67 $row{table} = ' ' x ($endpoint < 255 ? 640 : 4096);
68 $row{set} = 'Unicode BMP';
69 $row{cell} = do 'charset-unicode.inc.pl';
71 elsif ($row{set} eq 'utf-8-strict') {
74 $row{cell} = do 'charset-utf8.inc.pl';
77 $row{table} = decode($row{set}, pack 'C*', $row{offset} .. $endpoint);
81 print "<p>Encoding $input unknown</p>\n";
88 } map { defined $ALIAS{$_} ? @{ $ALIAS{$_} } : $_ }
89 $ENV{PATH_INFO} =~ /\w/ ? split(m{[/+\s]}, $ENV{PATH_INFO}) : 'default';
90 my $NOCHAR = chr 0xFFFD;
92 for my $cp437 (grep {$request[$_]->{set} eq 'cp437'} 0 .. $#request) {
93 substr($request[$cp437]->{table}, 237, 1) = pack 'U*', 0x3D5; # phi sign
94 substr($request[$cp437]->{table}, 0, 32) = pack 'U*', map {hex} qw(
95 2007 263A 263B 2665 2666 2663 2660 2022 25D8 25CB 25D9 2642 2640 266A 266B 263C
96 25BA 25C4 2195 203C 00B6 00A7 25AC 21A8 2191 2193 2192 2190 221F 2194 25B2 25BC
100 my @nibble = (0..9, 'A'..'F');
101 for my $row (@request) {
102 printf '<div class="section"><table class="glyphs%s">', !$row->{cell} && ' charmap';
103 printf '<caption>%s</caption>', $row->{set};
105 for my $section (qw{thead}) {
106 print "<$section><tr><th>↱";
107 print '<th>', $_ for @nibble;
111 for my $msb (0 .. (length($row->{table}) || 256) - 1 >> 4) {
112 printf '<tr><th>%X', $msb + ($row->{offset} >> 4);
113 for my $lsb (0 .. $#nibble) {
115 print $row->{cell}->(($msb<<4) + $lsb);
119 my $glyph = substr $row->{table}, ($msb<<4) + $lsb, 1;
120 if ($glyph eq $NOCHAR) {
125 print "\n".$glyphs->glyph_cell($glyph);
129 print "</table></div>\n";
136 <table class="glyphs"><tr>
137 <td class="X Cc">control
138 <td class="X Zs"><span>whitespace</span>
139 <td class="X Mn">diacritic<table class="glyphs"><tr>
140 <td class="X Sk">letter
142 <td class="X Po">punctuation<table class="glyphs"><tr>
143 <td class="X Pf">quote
145 <td class="X So">symbol<table class="glyphs"><tr>
146 <td class="X Sm">math
147 <td class="X Sc">currency
149 <td class="X No">numeric
150 <td class="X Greek">greek<table class="glyphs"><tr>
151 <td class="X Latin">latin
152 <td class="X Cyrillic">cyrillic
154 <td class="X Aramaic">aramaic<table class="glyphs"><tr>
155 <td class="X Brahmic">brahmic
156 <td class="X Arabic">arabic
158 <td class="X Syllabic">syllabic<table class="glyphs"><tr>
159 <td class="X African">african
160 <td class="X Hiragana">japanese
161 <td class="X Han">cjk
162 <td class="X Bopomofo">chinese
164 <td class="X Alpha">alphabetic
167 <table class="glyphs"><tr>
168 <td class="X">unicode 7.0
169 <td class="X Xr">proposed
170 <td class="X Xd">deprecated
171 <td class="">unassigned
172 <td class="X Xi">invalid