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'],
18 <h1>Character encoding</h1>
21 use Shiar_Sheet::FormatChar;
22 my $glyphs = Shiar_Sheet::FormatChar->new;
24 use Encode qw(decode resolve_alias);
25 # generate character table(s)
26 # (~16x faster than decoding in loop;
27 # substr strings is twice as fast as splitting to an array)
29 # default => [qw(unicode utf-8 iso-8859-1 cp437 -cp1252- --iso-8859-15- -koi8-f)],
30 default => [qw(unicode- utf-8 iso-8859-1 -cp1252- --iso-8859-15- cp437 -cp850)],
31 0 => [qw(cp437 cp863)],
32 1 => [qw(iso-8859-1 cp1252 MacRoman cp850)],
33 2 => [qw(iso-8859-2 cp1250 cp852 MacCentralEurRoman MacCroatian MacRumanian)],
34 5 => [qw(koi8-f iso-8859-5 cp1251 MacCyrillic cp855 cp866)],
35 7 => [qw(iso-8859-7 cp1253 MacGreek cp737 cp869)],
36 8 => [qw(iso-8859-8 cp1255 MacHebrew cp862)],
40 my %row = (offset => 0);
42 if ($input =~ s/^--//) {
43 $row{offset} = $endpoint > 160 ? 160 : 48;
45 elsif ($input =~ s/^-//) {
46 $row{offset} = $endpoint > 128 ? 128 : 32;
48 if ($input =~ s/-$//) {
49 $endpoint = $row{offset} ? $row{offset} < 160 ? 159 : 191 : 127;
52 if ($input =~ /^U([0-9a-f]+)(?:-([0-9a-f]+))?/) {
53 my $start = hex($1) << ($2 ? 4 : 8);
54 my $end = $2 ? hex($2) << 4 : $start + 240;
55 $row{table} = join '', map { chr } $start .. $end+15;
56 utf8::upgrade($row{table}); # prevent latin1 output
57 $row{set} = sprintf 'Unicode block U+%02Xxx', $start >> 8;
59 elsif ($input eq 'U') {
60 $row{table} = ' ' x 512;
61 $row{set} = 'Unicode planes';
62 $row{cell} = do 'charset-ucplanes.inc.pl';
64 elsif ($row{set} = resolve_alias($input)) {
65 if ($row{set} eq 'Internal') {
66 $row{table} = ' ' x ($endpoint < 255 ? 640 : 4096);
67 $row{set} = 'Unicode BMP';
68 $row{cell} = do 'charset-unicode.inc.pl';
70 elsif ($row{set} eq 'utf-8-strict') {
73 $row{cell} = do 'charset-utf8.inc.pl';
76 $row{table} = decode($row{set}, pack 'C*', $row{offset} .. $endpoint);
80 print "<p>Encoding $input unknown</p>\n";
87 } map { defined $ALIAS{$_} ? @{ $ALIAS{$_} } : $_ }
88 $ENV{PATH_INFO} =~ /\w/ ? split(m{[/+\s]}, $ENV{PATH_INFO}) : 'default';
89 my $NOCHAR = chr 0xFFFD;
91 for my $cp437 (grep {$request[$_]->{set} eq 'cp437'} 0 .. $#request) {
92 substr($request[$cp437]->{table}, 237, 1) = pack 'U*', 0x3D5; # phi sign
93 substr($request[$cp437]->{table}, 0, 32) = pack 'U*', map {hex} qw(
94 2007 263A 263B 2665 2666 2663 2660 2022 25D8 25CB 25D9 2642 2640 266A 266B 263C
95 25BA 25C4 2195 203C 00B6 00A7 25AC 21A8 2191 2193 2192 2190 221F 2194 25B2 25BC
99 my @nibble = (0..9, 'A'..'F');
100 for my $row (@request) {
101 printf '<div class="section"><table class="glyphs%s">', !$row->{cell} && ' charmap';
102 printf '<caption>%s</caption>', $row->{set};
104 for my $section (qw{thead}) {
105 print "<$section><tr><th>↱";
106 print '<th>', $_ for @nibble;
110 for my $msb (0 .. (length($row->{table}) || 256) - 1 >> 4) {
111 printf '<tr><th>%X', $msb + ($row->{offset} >> 4);
112 for my $lsb (0 .. $#nibble) {
114 print $row->{cell}->(($msb<<4) + $lsb);
118 my $glyph = substr $row->{table}, ($msb<<4) + $lsb, 1;
119 if ($glyph eq $NOCHAR) {
124 print "\n".$glyphs->glyph_cell($glyph);
128 print "</table></div>\n";
135 <table class="glyphs"><tr>
136 <td class="X Cc">control
137 <td class="X Zs"><span>whitespace</span>
138 <td class="X Mn">diacritic<table class="glyphs"><tr>
139 <td class="X Sk">letter
141 <td class="X Po">punctuation<table class="glyphs"><tr>
142 <td class="X Pf">quote
144 <td class="X So">symbol<table class="glyphs"><tr>
145 <td class="X Sm">math
146 <td class="X Sc">currency
148 <td class="X No">numeric
149 <td class="X Greek">greek<table class="glyphs"><tr>
150 <td class="X Latin">latin
151 <td class="X Cyrillic">cyrillic
153 <td class="X Aramaic">aramaic<table class="glyphs"><tr>
154 <td class="X Brahmic">brahmic
155 <td class="X Arabic">arabic
157 <td class="X Syllabic">syllabic<table class="glyphs"><tr>
158 <td class="X African">african
159 <td class="X Hiragana">japanese
160 <td class="X Han">cjk
161 <td class="X Bopomofo">chinese
163 <td class="X Alpha">alphabetic
166 <table class="glyphs"><tr>
167 <td class="X">unicode 5.0
168 <td class="X Xr">proposed
169 <td class="X Xd">deprecated
170 <td class="">unassigned
171 <td class="X Xi">invalid