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'],
18 my @tablist = split /[^\w-]+/, $Request || 'default';
21 <h1>Character encoding</h1>
25 use Shiar_Sheet::FormatChar;
26 my $glyphs = Shiar_Sheet::FormatChar->new;
29 # generate character table(s)
30 my $input = shift or return;
33 default => [qw( unicode+0-192 utf-8 iso-8859-1 cp1252+128-159 iso-8859-15+160-191 cp437 cp850+128 )],
34 us => [qw( cp437 cp863+128 AdobeStandardEncoding gsm0338+0-127 )],
35 ebcdic => [qw( cp37 cp500 cp875 cp1026 cp1047 posix-bc )],
36 westeur => [qw( iso-8859-1 iso-8859-15+160-191 cp1252+128-159 iso-8859-14+160 cp850+128 MacRoman+128 nextstep+128 hp-roman8+160 )],
37 centeur => [qw( iso-8859-2 iso-8859-16+160 cp1250+128 cp852+128 MacCentralEurRoman+128 MacCroatian+128 MacRomanian+128 )], # MacRumanian only for DB
38 turkish => [qw( iso-8859-3 iso-8859-9+128 cp857+128 cp1254+128 MacTurkish+128 )],
39 baltic => [qw( iso-8859-4 iso-8859-13+160 cp775+128 cp1257+128 )],
40 nordic => [qw( iso-8859-10 cp865+128 cp861+160-191 MacIcelandic+128 MacSami+160 )],
41 cyrillic => [qw( koi8-f koi8-r+128-192 koi8-u+160-192 iso-8859-5+128 cp1251+128 MacCyrillic+128 cp855+128 cp866+128 )], # MacUkrainian is broken
42 arabic => [qw( iso-8859-6 cp1006+160 cp864+128 cp1256+128 MacArabic )], # MacFarsi same as MacArabic?
43 greek => [qw( iso-8859-7 cp1253+128 MacGreek+128 cp737+128 cp869+128 )],
44 hebrew => [qw( iso-8859-8 cp1255+128 MacHebrew+128 cp862+128 )],
45 thai => [qw( iso-8859-11 cp874+128-159 MacThai+128 )],
46 vietnamese => [qw( viscii cp1258 MacVietnamese )],
47 symbol => [qw( symbol dingbats MacDingbats AdobeZdingbat AdobeSymbol )],
61 if (my $follow = $ALIAS->{$input}) {
62 return map { tabinput($_) } ref $follow ? @{$follow} : $follow;
65 my %row = (offset => 0, cols => 16);
67 my $params = $input =~ s/[+](.*)\z// ? $1 : undef;
69 if (defined $params and $params =~ m/^ (\d+) (-\d+)? /x) {
71 $endpoint = -$2 if $2;
74 $row{setnote} = 'over cp437' if $input eq 'cp850';
75 $row{setnote} = 'over iso-8859-1' if $input =~ /^iso-8859-|^cp125/;
78 if ($input =~ /^U([0-9a-f]+)(?:-([0-9a-f]+))?/) {
79 my $start = hex($1) << ($2 ? 4 : 8);
80 my $end = $2 ? hex($2) << 4 : $start + 240;
81 $row{table} = join '', map { chr } $start .. $end+15;
82 utf8::upgrade($row{table}); # prevent latin1 output
83 $row{set} = sprintf 'Unicode block U+%02Xxx', $start >> 8;
85 elsif ($input eq 'U') {
86 $row{table} = ' ' x 1024;
87 $row{set} = 'Unicode planes';
88 $row{cell} = do 'charset-ucplanes.inc.pl'
89 or Alert('Table data could not be read', $@ || $!);
92 elsif ($row{set} = Encode::resolve_alias($input)) {
93 if ($row{set} eq 'Internal') {
94 $row{table} = ' ' x ($endpoint < 255 ? 640 : 8192);
95 $row{set} = 'Unicode BMP';
96 $row{cell} = do 'charset-unicode.inc.pl'
97 or Alert('Table data could not be read', $@ || $!);
99 elsif ($row{set} eq 'utf-8-strict') {
102 $row{cell} = do 'charset-utf8.inc.pl'
103 or Alert('Table data could not be read', $@ || $!);
106 $row{table} = Encode::decode($row{set}, pack 'C*', $row{offset} .. $endpoint);
107 # (~16x faster than decoding in loop;
108 # substr strings is twice as fast as splitting to an array)
110 if ($row{set} eq 'cp437') {
111 substr($row{table}, 237, 1) = pack 'U*', 0x3D5; # phi sign
112 substr($row{table}, 0, 32) = pack 'U*', map {hex} qw(
113 2007 263A 263B 2665 2666 2663 2660 2022
114 25D8 25CB 25D9 2642 2640 266A 266B 263C
115 25BA 25C4 2195 203C 00B6 00A7 25AC 21A8
116 2191 2193 2192 2190 221F 2194 25B2 25BC
122 Alert("Encoding <q>$input</q> unknown");
127 my @request = map { tabinput($_) } @tablist;
129 my $NOCHAR = chr 0xFFFD;
132 my ($info, $offset) = @_;
133 my $table = $info->{cell} or return;
134 my $def = $table->{$offset} or return;
135 my ($len, $class, $name, $title) = @{$def};
137 my $cols = $info->{cols};
138 my $colsize = $table->{colsize} || 1;
141 $name //= $len <= 2 ? 'res' : 'reserved';
143 if (my $part = $offset/$colsize % $cols) {
145 my $rest = $cols - $part; # remaining
146 $rest = $len if $len < $rest; #TODO: optimise
148 # continued on new row
149 my @next = ($len * $colsize, "$class joinu");
152 push @next, $name, $title;
157 # minority on next row
158 push @next, '"', $title || $name;
160 $table->{$offset + $colsize*$rest} //= \@next;
165 elsif (my $rows = int($len / $cols)) {
167 if ($len -= $rows * $cols) {
168 # partial row remains
169 $table->{$offset + $colsize*$rows * $cols} //= [$len*$colsize, "$class joinu", '', $title];
172 $attr .= sprintf ' rowspan=%d', $rows;
176 $attr .= sprintf ' colspan=%d', $len unless $len == 1;
177 $attr .= $1 if $class and $class =~ s/( \w+="[^"]*")//;
178 $attr .= sprintf ' class="%s"', $class if $class;
179 $attr .= sprintf ' title="%s"', EscapeHTML($title) if $title;
180 return "<td$attr>$name";
183 for my $row (@request) {
184 my $cols = $row->{cols};
185 my $colsize = $row->{cell} && $row->{cell}->{colsize} || 1;
186 my $coldigits = ceil(log($colsize * $cols) / log(16)); # uniform length of hexadecimal header
187 my $rowdiv = 16 ** $coldigits; # row divide for column digits
188 $rowdiv = 1 if $rowdiv != $cols * $colsize; # divide only if all columns are matched
190 my $endpoint = $offset + (length($row->{table}) || 256) * $colsize;
192 printf '<div class="section"><table class="glyphs%s">', !$row->{cell} && ' charmap';
193 my $title = $row->{set};
194 $title .= " <aside>($_)</aside>" for $row->{setnote} // ();
195 printf '<caption>%s</caption>', $title;
196 print '<col>' x ($cols + 1);
197 for my $section (qw{thead}) {
198 print "<$section><tr><th>", $rowdiv == 1 ? '+' : '↱';
199 printf '<th>%0*X', $coldigits, $_ * $colsize for 0 .. $cols - 1;
203 while ($offset < $endpoint - 1) {
206 if (my $rowmod = $offset % $rowdiv) {
207 # offset in column units
208 printf '<small>+%X</small>', $rowmod;
212 printf '%X', ($offset + $row->{offset}) / $rowdiv;
217 print range_cell($row, $offset);
221 my $glyph = substr $row->{table}, $offset, 1;
222 if ($glyph eq $NOCHAR) {
227 print "\n".$glyphs->glyph_cell($glyph);
234 say '</table></div>';
241 <table class="glyphs"><tr>
242 <td class="X Cc">control
243 <td class="X Zs"><span>whitespace</span>
244 <td class="X Mn">diacritic<table class="glyphs"><tr>
245 <td class="X Sk">letter
247 <td class="X Po">punctuation<table class="glyphs"><tr>
248 <td class="X Pf">quote
250 <td class="X So">symbol<table class="glyphs"><tr>
251 <td class="X Sm">math
252 <td class="X Sc">currency
254 <td class="X No">numeric
255 <td class="X Greek">greek<table class="glyphs"><tr>
256 <td class="X Latin">latin
257 <td class="X Cyrillic">cyrillic
259 <td class="X Aramaic">aramaic<table class="glyphs"><tr>
260 <td class="X Brahmic">brahmic
261 <td class="X Arabic">arabic
263 <td class="X Syllabic">syllabic<table class="glyphs"><tr>
264 <td class="X African">african
265 <td class="X Hiragana">japanese
266 <td class="X Han">cjk
267 <td class="X Bopomofo">chinese
269 <td class="X Alpha">alphabetic
272 <table class="glyphs"><tr>
273 <td class="X">unicode 7.0
274 <td class="X Xr">proposed
275 <td class="X Xd">deprecated
276 <td class="">unassigned
277 <td class="X Xi">invalid