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;
30 # generate character table(s)
31 my $input = shift or return;
34 default => [qw( unicode+0-192 utf-8 iso-8859-1 iso-8859-15 cp1252 cp437 cp850 )],
35 us => [qw( cp437 cp863 AdobeStandardEncoding gsm0338 )],
36 ebcdic => [qw( cp37 cp500 cp875 cp1026 cp1047 posix-bc )],
37 iso => [map {"iso-8859-$_"} 1 .. 11, 13 .. 16],
38 dos => [qw( cp437 cp863 cp850 cp860 cp852 cp855 cp866 cp864 cp1006 cp737 cp869 cp862 cp862 cp857 cp865 cp861 cp874 cp775 )],
40 westeur => [qw( iso-8859-1 iso-8859-15 cp1252 iso-8859-14 cp850 hp-roman8 nextstep MacRoman )],
41 centeur => [qw( iso-8859-2 iso-8859-16 cp1250 cp852 MacRomanian MacCroatian MacCentralEurRoman )], # MacRumanian only for DB
42 turkish => [qw( iso-8859-9 iso-8859-3 cp1254 cp857 MacTurkish )],
43 baltic => [qw( iso-8859-4 iso-8859-13 cp1257 cp775 )],
44 nordic => [qw( iso-8859-10 cp865 cp861 MacIcelandic MacSami )],
45 cyrillic => [qw( koi8-f koi8-r koi8-u iso-8859-5 cp1251 MacCyrillic cp855 cp866 )], # MacUkrainian is broken
46 arabic => [qw( iso-8859-6 cp1006 cp864 cp1256 MacArabic )], # MacFarsi same as MacArabic?
47 greek => [qw( iso-8859-7 cp1253 MacGreek cp737 cp869 )],
48 hebrew => [qw( iso-8859-8 cp1255 MacHebrew cp862 )],
49 thai => [qw( iso-8859-11 cp874 MacThai )],
50 vietnamese => [qw( viscii cp1258 MacVietnamese )],
51 symbol => [qw( symbol dingbats MacDingbats AdobeZdingbat AdobeSymbol )],
65 if (my $follow = $ALIAS->{$input}) {
66 tabinput($_) for ref $follow ? @{$follow} : $follow;
70 state $visible = {}; # all present tables
71 my %row = (offset => 0, cols => 16);
73 my $params = $input =~ s/[+](.*)\z// ? $1 : undef;
75 if (not defined $params) {
76 use List::Util qw( first pairfirst pairs );
79 'cp437' => ['cp850' => 0], # ascii range overridden later
80 'gsm0338' => ['ascii' => '0-127'],
82 'iso-8859-2' => ['iso-8859-1' => '160'],
83 'iso-8859-3' => ['iso-8859-1' => '160'],
84 'iso-8859-4' => ['iso-8859-2' => '160'],
85 'iso-8859-5' => ['iso-8859-1' => '160'],
86 'iso-8859-6' => ['iso-8859-1' => '160'],
87 'iso-8859-7' => ['iso-8859-1' => '160'],
88 'iso-8859-8' => ['iso-8859-1' => '160'],
89 'iso-8859-9' => ['iso-8859-1' => '208'],
90 'iso-8859-10' => ['iso-8859-4' => '160'],
91 'iso-8859-11' => ['iso-8859-1' => '160'],
92 'iso-8859-13' => ['iso-8859-4' => '160'],
93 'iso-8859-14' => ['iso-8859-1' => '160'],
94 'iso-8859-15' => ['iso-8859-1' => '160-191'],
95 'iso-8859-16' => ['iso-8859-2' => '160'],
97 'cp1252' => ['iso-8859-1' => '128-159'],
98 'cp1250' => ['iso-8859-2' => '128-191'],
99 'cp1254' => ['iso-8859-9' => '128-159'],
100 'cp1257' => ['iso-8859-13' => '128-'],
102 'cp850' => ['cp437' => '144'],
103 'cp865' => ['cp437' => '144-176'],
104 'cp852' => ['cp850' => '128', 'cp437' => '128'],
105 'cp857' => ['cp850' => '128-239', 'cp437' => '128'],
106 'cp775' => ['cp850' => '128'], # partial cp437
108 'MacRomanian' => ['MacRoman' => '160'],
109 'MacCroatian' => ['MacRoman' => '160'],
110 'MacCentralEurRoman' => ['MacRoman' => '128'],
111 'MacTurkish' => ['MacRoman' => '208-223'], # F5 is unassigned
114 my @parents = @{ $INHERIT->{$input} || [] };
116 if (my ($parent, $part) = pairfirst { $visible->{$a} } @parents) {
117 $row{parent} = $parent;
120 elsif ($visible->{ascii}) {
121 $row{parent} = $parents[0] || 'ascii';
122 $params = $parents[1] || 128;
123 $params = 128 if $params >= 128; # ascii offset at most
126 $row{parent} = $parents[0];
130 if (defined $params and $params =~ m/^ (\d+) (-\d+)? /x) {
132 $endpoint = -$2 if $2;
135 if ($input =~ /^U([0-9a-f]+)(?:-([0-9a-f]+))?/) {
136 my $start = hex($1) << ($2 ? 4 : 8);
137 my $end = $2 ? hex($2) << 4 : $start + 240;
138 $row{table} = join '', map { chr } $start .. $end+15;
139 utf8::upgrade($row{table}); # prevent latin1 output
140 $row{len} = length $row{table};
141 $row{set} = sprintf 'Unicode block U+%02Xxx', $start >> 8;
143 elsif ($input eq 'U') {
145 $row{set} = 'Unicode planes';
146 $row{cell} = do 'charset-ucplanes.inc.pl'
147 or Alert('Table data could not be read', $@ || $!);
150 elsif ($row{set} = Encode::resolve_alias($input)) {
151 if ($row{set} eq 'Internal') {
152 $row{len} = $endpoint < 255 ? 640 : 8192;
153 $row{set} = 'Unicode BMP';
154 $row{cell} = do 'charset-unicode.inc.pl'
155 or Alert('Table data could not be read', $@ || $!);
157 elsif ($row{set} eq 'utf-8-strict') {
160 $row{cell} = do 'charset-utf8.inc.pl'
161 or Alert('Table data could not be read', $@ || $!);
164 $row{len} = $endpoint - $row{offset};
165 $row{table} = Encode::decode($row{set}, pack 'C*', $row{offset} .. $endpoint);
166 # (~16x faster than decoding in loop;
167 # substr strings is twice as fast as splitting to an array)
169 if ($row{set} eq 'cp437' and !$row{offset}) {
170 substr($row{table}, 237, 1) = pack 'U*', 0x3D5; # phi sign
171 substr($row{table}, 0, 32) = pack 'U*', map {hex} qw(
172 2007 263A 263B 2665 2666 2663 2660 2022
173 25D8 25CB 25D9 2642 2640 266A 266B 263C
174 25BA 25C4 2195 203C 00B6 00A7 25AC 21A8
175 2191 2193 2192 2190 221F 2194 25B2 25BC
179 $visible->{ascii} = # assume common base
180 $visible->{ $row{set} } = 1;
184 Alert("Encoding <q>$input</q> unknown");
187 push @request, \%row;
189 tabinput($_) for @tablist;
191 my $NOCHAR = chr 0xFFFD;
194 my ($info, $offset) = @_;
195 my $table = $info->{cell} or return;
196 my $def = $table->{$offset} or return;
197 my ($len, $class, $name, $title) = @{$def};
199 my $cols = $info->{cols};
200 my $colsize = $table->{colsize} || 1;
203 $name //= $len <= 2 ? 'res' : 'reserved';
205 if (my $part = $offset/$colsize % $cols) {
207 my $rest = $cols - $part; # remaining
208 $rest = $len if $len < $rest; #TODO: optimise
210 # continued on new row
211 my @next = ($len * $colsize, "$class joinu");
214 push @next, $name, $title;
219 # minority on next row
220 push @next, '"', $title || $name;
222 $table->{$offset + $colsize*$rest} //= \@next;
227 elsif (my $rows = int($len / $cols)) {
229 if ($len -= $rows * $cols) {
230 # partial row remains
231 $table->{$offset + $colsize*$rows * $cols} //= [$len*$colsize, "$class joinu", '', $title];
234 $attr .= sprintf ' rowspan=%d', $rows;
238 $attr .= sprintf ' colspan=%d', $len unless $len == 1;
239 $attr .= $1 if $class and $class =~ s/( \w+="[^"]*")//;
240 $attr .= sprintf ' class="%s"', $class if $class;
241 $attr .= sprintf ' title="%s"', EscapeHTML($title) if $title;
242 return "<td$attr>$name";
245 for my $row (@request) {
246 my $cols = $row->{cols};
247 my $colsize = $row->{cell} && $row->{cell}->{colsize} || 1;
248 my $coldigits = ceil(log($colsize * $cols) / log(16)); # uniform length of hexadecimal header
249 my $rowdiv = 16 ** $coldigits; # row divide for column digits
250 $rowdiv = 1 if $rowdiv != $cols * $colsize; # divide only if all columns are matched
252 my $endpoint = $offset + $row->{len} * $colsize;
254 printf '<div class="section"><table class="glyphs%s">', !$row->{cell} && ' charmap';
255 my $title = $row->{set};
256 $title .= " <aside>(over $_)</aside>"
257 for grep { $_ ne 'iso-8859-1' } $row->{parent} // ();
258 printf '<caption>%s</caption>', $title;
259 print '<col>' x ($cols + 1);
260 for my $section (qw{thead}) {
261 print "<$section><tr><th>", $rowdiv == 1 ? '+' : '↱';
262 printf '<th>%0*X', $coldigits, $_ * $colsize for 0 .. $cols - 1;
266 while ($offset < $endpoint - 1) {
269 if (my $rowmod = $offset % $rowdiv) {
270 # offset in column units
271 printf '<small>+%X</small>', $rowmod;
275 printf '%X', ($offset + $row->{offset}) / $rowdiv;
280 print range_cell($row, $offset);
284 my $glyph = substr $row->{table}, $offset, 1;
285 if ($glyph eq $NOCHAR) {
290 print "\n".$glyphs->glyph_cell($glyph);
297 say '</table></div>';
304 <table class="glyphs"><tr>
305 <td class="X Cc">control
306 <td class="X Zs"><span>whitespace</span>
307 <td class="X Mn">diacritic<table class="glyphs"><tr>
308 <td class="X Sk">letter
310 <td class="X Po">punctuation<table class="glyphs"><tr>
311 <td class="X Pf">quote
313 <td class="X So">symbol<table class="glyphs"><tr>
314 <td class="X Sm">math
315 <td class="X Sc">currency
317 <td class="X No">numeric
318 <td class="X Greek">greek<table class="glyphs"><tr>
319 <td class="X Latin">latin
320 <td class="X Cyrillic">cyrillic
322 <td class="X Aramaic">aramaic<table class="glyphs"><tr>
323 <td class="X Brahmic">brahmic
324 <td class="X Arabic">arabic
326 <td class="X Syllabic">syllabic<table class="glyphs"><tr>
327 <td class="X African">african
328 <td class="X Hiragana">japanese
329 <td class="X Han">cjk
330 <td class="X Bopomofo">chinese
332 <td class="X Alpha">alphabetic
335 <table class="glyphs"><tr>
336 <td class="X">unicode 7.0
337 <td class="X Xr">proposed
338 <td class="X Xd">deprecated
339 <td class="">unassigned
340 <td class="X Xi">invalid