X-Git-Url: http://git.shiar.nl/sheet.git/blobdiff_plain/dae21a09b01baa118720670247a87c5cdc2591b8..024fef82307d7b421c8ec3ebee930b774427a745:/charset.plp?ds=sidebyside diff --git a/charset.plp b/charset.plp index e82c5cc..d3b27b5 100644 --- a/charset.plp +++ b/charset.plp @@ -1,44 +1,41 @@ -<: -use utf8; -use strict; -use warnings; -use open IO => ':utf8'; - -our $VERSION = 'v1.0'; - -$header{content_type} = 'text/html; charset=utf-8'; +<(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'], +}); -:> - - -
- -Encoding $input unknown
\n"; + Alert("Encoding$inputunknown"); } - \%row; + $row{set} ? \%row : (); } else { (); } } map { defined $ALIAS{$_} ? @{ $ALIAS{$_} } : $_ } - $ENV{PATH_INFO} =~ /\w/ ? split(m{[/+\s]}, $ENV{PATH_INFO}) : 'default'; + $Request =~ /\w/ ? split(m{[/+\s]}, $Request) : 'default'; my $NOCHAR = chr 0xFFFD; for my $cp437 (grep {$request[$_]->{set} eq 'cp437'} 0 .. $#request) { @@ -101,20 +107,50 @@ for my $cp437 (grep {$request[$_]->{set} eq 'cp437'} 0 .. $#request) { ); } -sub quote { - local $_ = shift; - s/"/"/g; - 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 "
â±"; @@ -123,46 +159,31 @@ 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}; - } - else { - require Unicode::UCD; - my $fullinfo = Unicode::UCD::charinfo(ord $glyph); - $info = [@$fullinfo{qw/code name category script string/}] if $fullinfo; - } - my ($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 " |
unicode 5.0 + | unicode 7.0 | proposed | deprecated | unassigned @@ -207,14 +228,3 @@ print "\n"; |