X-Git-Url: http://git.shiar.nl/sheet.git/blobdiff_plain/2a2ae5d0bf7f0f0d0cf2377702fdf6f8827740ae..130c94fc7747fd586b677f48fbabd2ecf10297c5:/charset.plp diff --git a/charset.plp b/charset.plp index 41af494..6577f4c 100644 --- a/charset.plp +++ b/charset.plp @@ -1,30 +1,28 @@ -<: -use utf8; -use strict; -use warnings; -use open IO => ':utf8'; - -our $VERSION = '1.0'; - -$header{content_type} = 'text/html; charset=utf-8'; - -:> - - - -charset cheat sheet - - - +<(common.inc.plp)><: + +Html({ + title => 'charset cheat sheet', + version => 'v1.0', + 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'], +}); - +:>

Character encoding

<: -my $diinfo = do 'digraphs.inc.pl'; -my %di = map { $diinfo->{$_}->[0] => $_ } grep { ref $diinfo->{$_} } - keys %$diinfo; +use Shiar_Sheet::FormatChar; +my $glyphs = Shiar_Sheet::FormatChar->new; +my @nibble = (0..9, 'A'..'F'); +my $nibsize = 1; use Encode qw(decode resolve_alias); # generate character table(s) @@ -53,9 +51,24 @@ my @request = map { if ($input =~ s/-$//) { $endpoint = $row{offset} ? $row{offset} < 160 ? 159 : 191 : 127; } - if ($row{set} = resolve_alias($input)) { + + if ($input =~ /^U([0-9a-f]+)(?:-([0-9a-f]+))?/) { + my $start = hex($1) << ($2 ? 4 : 8); + my $end = $2 ? hex($2) << 4 : $start + 240; + $row{table} = join '', map { chr } $start .. $end+15; + utf8::upgrade($row{table}); # prevent latin1 output + $row{set} = sprintf 'Unicode block U+%02Xxx', $start >> 8; + } + elsif ($input eq 'U') { + $row{table} = ' ' x 512; + $row{set} = 'Unicode planes'; + $row{cell} = do 'charset-ucplanes.inc.pl'; + @nibble = (map { $_.0, $_.8 } 0 .. 7); + $nibsize = 8; + } + elsif ($row{set} = resolve_alias($input)) { if ($row{set} eq 'Internal') { - $row{table} = ' ' x ($endpoint < 255 ? 640 : 4096); + $row{table} = ' ' x ($endpoint < 255 ? 640 : 8192); $row{set} = 'Unicode BMP'; $row{cell} = do 'charset-unicode.inc.pl'; } @@ -88,21 +101,10 @@ for my $cp437 (grep {$request[$_]->{set} eq 'cp437'} 0 .. $#request) { ); } -sub quote { - local $_ = shift; - s/"/"/g; - s//>/g; - return $_; -} - -print "

'; + printf '

', !$row->{cell} && ' charmap'; printf '', $row->{set}; - print ''; + print '' x 17; for my $section (qw{thead}) { print "<$section>

%s
â±"; print '	', $_ for @nibble; @@ -112,39 +114,25 @@ for my $row (@request) { for my $msb (0 .. (length($row->{table}) \|\| 256) - 1 >> 4) { printf '
%X', $msb + ($row->{offset} >> 4); for my $lsb (0 .. $#nibble) { + my $val = ( ($msb<<4) + $lsb ) * $nibsize; if ($row->{cell}) { - print $row->{cell}->(($msb<<4) + $lsb); + print $row->{cell}->($val); next; } - my $glyph = substr $row->{table}, ($msb<<4) + $lsb, 1; + my $glyph = substr $row->{table}, $val, 1; if ($glyph eq $NOCHAR) { print '	'; next; } - my $info = [ord $glyph]; - if (defined (my $mnem = $di{ord $glyph})) { - $info = $diinfo->{$mnem}; - } - my ($codepoint, $name, $prop, $script, $string) = @$info; - - $glyph = quote($string \|\| $glyph); - my $desc = sprintf 'U+%04X%s', $codepoint, $name && " ($name)"; - my @class = ('X', grep {$_} $prop, $script); - - $glyph = "$glyph" if $prop eq 'Zs'; - - printf "\n".'	%s', - join(' ', @class), quote($desc), $glyph; + print "\n".$glyphs->glyph_cell($glyph); } print "\n"; } - print "

\n"; + print "\n"; } -print "

\n"; - :>

@@ -181,7 +169,7 @@ print "\n"; -

unicode 5.0 +

unicode 7.0

proposed

deprecated

unassigned @@ -189,16 +177,3 @@ print "\n";

- - -