X-Git-Url: http://git.shiar.net/sheet.git/blobdiff_plain/a0ba9298856b2426c5c66b6d2f2b284d98cee594..ccf2f210912568cc5c5188a821de5a48368021a5:/charset.plp?ds=sidebyside diff --git a/charset.plp b/charset.plp index c9ef2b6..92b918f 100644 --- a/charset.plp +++ b/charset.plp @@ -1,185 +1,286 @@ -<: -use utf8; -use strict; -use warnings; -use open IO => ':utf8'; - -our $VERSION = '1.0'; +<(common.inc.plp)><: -$header{content_type} = 'text/html; charset=utf-8'; +Html({ + title => 'charset cheat sheet', + version => '1.0', + description => [ + "Reference sheet with all glyphs in common character encoding tables,", + "and an overview of Unicode ranges and UTF-8 bytes.", + ], + keywords => [qw' + charset codepage unicode ascii utf8 latin glyph character encoding + reference common overview table + '], + stylesheet => [qw'light'], + data => [qw'charset-unicode.inc.pl charset-utf8.inc.pl'], +}); -:> - +my @tablist = split /[^\w-]+/, $Request || 'default'; - -charset cheat sheet - - - - - +:>

Character encoding

<: -my $diinfo = do 'digraphs.inc.pl'; -my %di = map { $diinfo->{$_}->[0] => $_ } grep { ref $diinfo->{$_} } - keys %$diinfo; - -use Encode qw(decode); -# generate character table(s) -# (~16x faster than decoding in loop; -# substr strings is twice as fast as splitting to an array) -my @request = ('iso-8859-1', 'cp437'); -my @tables = map { decode($_, pack 'C*', 0..255) } @request; -my $NOCHAR = chr 0xFFFD; +use POSIX qw( ceil ); +use Shiar_Sheet::FormatChar; +my $glyphs = Shiar_Sheet::FormatChar->new; -for my $cp437 (grep {$request[$_] eq 'cp437'} 0 .. $#request) { - substr($tables[$cp437], 237, 1) = pack 'U*', 0x3D5; # phi sign - substr($tables[$cp437], 0, 32) = pack 'U*', map {hex} qw( - 2007 263A 263B 2665 2666 2663 2660 2022 25D8 25CB 25D9 2642 2640 266A 266B 263C - 25BA 25C4 2195 203C 00B6 00A7 25AC 21A8 2191 2193 2192 2190 221F 2194 25B2 25BC - ); -} +sub tabinput { + # generate character table(s) + my $input = shift or return; -sub quote { - local $_ = shift; - s/"/"/g; - s//>/g; - return $_; -} + state $ALIAS = { + default => [qw(unicode- utf-8 iso-8859-1 -cp1252-- --iso-8859-15-- cp437 -cp850)], + us => [qw( cp437 -cp863 AdobeStandardEncoding gsm0338-- )], + ebcdic => [qw( cp37 cp500 cp875 cp1026 cp1047 posix-bc )], + westeur => [qw( iso-8859-1 --iso-8859-15-- -cp1252-- --iso-8859-14 -cp850 -MacRoman -nextstep --hp-roman8 )], + centeur => [qw( iso-8859-2 --iso-8859-16 -cp1250 -cp852 -MacCentralEurRoman -MacCroatian -MacRomanian )], # MacRumanian only for DB + turkish => [qw( iso-8859-3 -iso-8859-9 -cp857 -cp1254 -MacTurkish )], + baltic => [qw( iso-8859-4 --iso-8859-13 -cp775 -cp1257 )], + nordic => [qw( iso-8859-10 -cp865 --cp861-- -MacIcelandic --MacSami )], + cyrillic => [qw( koi8-f -koi8-r- --koi8-u- -iso-8859-5 -cp1251 -MacCyrillic -cp855 -cp866 )], # MacUkrainian is broken + arabic => [qw( iso-8859-6 --cp1006 -cp864 -cp1256 MacArabic )], # MacFarsi same as MacArabic? + greek => [qw( iso-8859-7 -cp1253 -MacGreek -cp737 -cp869 )], + hebrew => [qw( iso-8859-8 -cp1255 -MacHebrew -cp862 )], + thai => [qw( iso-8859-11 -cp874-- -MacThai )], + vietnamese => [qw( viscii cp1258 MacVietnamese )], + symbol => [qw( symbol dingbats MacDingbats AdobeZdingbat AdobeSymbol )], + # iso-code shorthand + 1 => 'westeur', + 2 => 'centeur', + 3 => 'turkish', + 4 => 'baltic', + 5 => 'cyrillic', + 6 => 'arabic', + 7 => 'greek', + 8 => 'hebrew', + 9 => 'turkish', + 10 => 'nordic', + 11 => 'thai', + }; + if (my $follow = $ALIAS->{$input}) { + return map { tabinput($_) } ref $follow ? @{$follow} : $follow; + } -print "\n"; - :>
- - - +
+ +
control + whitespace + diacritic +
letter +
+
punctuation +
quote +
+
symbol +
math + currency +
+
numeric + greek +
latin + cyrillic +
+
aramaic +
brahmic + arabic +
+
syllabic +
african + japanese + cjk + chinese +
+
alphabetic +
+ + +
unicode 7.0 + proposed + deprecated + unassigned + invalid +
+
+