X-Git-Url: http://git.shiar.nl/sheet.git/blobdiff_plain/14e719f07fcb43c9a0ada3f9f9f018ff5a20a1cf..4aed151cd144c6c74f28d537c9d8f0285e72fec3:/charset.plp diff --git a/charset.plp b/charset.plp index a3e845d..734d227 100644 --- a/charset.plp +++ b/charset.plp @@ -1,30 +1,28 @@ -<: -use utf8; -use strict; -use warnings; -use open IO => ':utf8'; - -our $VERSION = 'v1.0'; - -$header{content_type} = 'text/html; charset=utf-8'; - -:> - - - - -charset cheat sheet - - +<(common.inc.plp)><: + +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'], +}); - +:>

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) @@ -62,20 +60,25 @@ my @request = map { $row{set} = sprintf 'Unicode block U+%02Xxx', $start >> 8; } elsif ($input eq 'U') { - $row{table} = ' ' x 512; + $row{table} = ' ' x 1024; $row{set} = 'Unicode planes'; - $row{cell} = do 'charset-ucplanes.inc.pl'; + $row{cell} = do 'charset-ucplanes.inc.pl' + or printf "

Table data could not be read: %s.

\n", $@ || $!; + @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'; + $row{cell} = do 'charset-unicode.inc.pl' + or printf "

Table data could not be read: %s.

\n", $@ || $!; } elsif ($row{set} eq 'utf-8-strict') { $row{table} = undef; $row{set} = 'UTF-8'; - $row{cell} = do 'charset-utf8.inc.pl'; + $row{cell} = do 'charset-utf8.inc.pl' + or printf "

Table data could not be read: %s.

\n", $@ || $!; } else { $row{table} = decode($row{set}, pack 'C*', $row{offset} .. $endpoint); @@ -101,21 +104,49 @@ for my $cp437 (grep {$request[$_]->{set} eq 'cp437'} 0 .. $#request) { ); } -sub quote { - local $_ = shift; - s/"/"/g; - s//>/g; - return $_; -} +sub range_cell { + my ($table, $offset) = @_; + my $def = $table->{$offset} or return; + my ($len, $class, $name, $title) = @{$def}; + + my $attr = ''; + $len /= $nibsize; + $name //= $len <= 2 ? 'res' : 'reserved'; + + if (my $part = $offset/$nibsize % 16) { + # continued row + my $cols = 16 - $part; # remaining + $cols = $len if $len < $cols; #TODO: optimise + if ($len -= $cols) { + # continued on new row + $table->{$offset + $nibsize*$cols} = [$len*$nibsize, "$class joinu", $name, $title]; + $name = ''; + $class .= ' joind'; + } + $len = $cols; + } + elsif (my $rows = $len >> 4) { + # multiple full rows + if ($len -= $rows << 4) { + # partial row remains + $table->{$offset + $nibsize*$rows * 16} = [$len*$nibsize, "$class joinu", '', $title]; + $class .= ' joind'; + } + $attr .= sprintf ' rowspan=%d', $rows; + $len = 16; + } -print "

$name"; +} -my @nibble = (0..9, 'A'..'F'); for my $row (@request) { - printf '

', !$row->{cell} && ' charmap'; + printf '

', !$row->{cell} && ' charmap'; printf '', $row->{set}; - print ''; + print '' x 17; for my $section (qw{thead}) { print "<$section>'; for my $msb (0 .. (length($row->{table}) || 256) - 1 >> 4) { - printf '

%s
â±"; print '	', $_ for @nibble; @@ -123,41 +154,31 @@ for my $row (@request) { } print '
%X', $msb + ($row->{offset} >> 4); + printf '
%X', ($msb + ($row->{offset} >> 4)) * $nibsize; for my $lsb (0 .. $#nibble) { + my $val = ( ($msb<<4) + $lsb ) * $nibsize; if ($row->{cell}) { - print $row->{cell}->(($msb<<4) + $lsb); + if (ref $row->{cell} eq 'CODE') { + print $row->{cell}->($val); + next; + } + print range_cell($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"; - :>

@@ -194,7 +215,7 @@ print "\n"; -

unicode 5.0 +

unicode 7.0

proposed

deprecated

unassigned @@ -202,12 +223,3 @@ print "\n";

- - -