X-Git-Url: http://git.shiar.nl/sheet.git/blobdiff_plain/bb412b576d883e11a4ec09d01c34a933d894af6c..cc3aea5b110f944ce10a22cdea96a0b3f6da15c9:/charset.plp diff --git a/charset.plp b/charset.plp index f546f2d..15183cf 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'; +<(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'], +}); -:> - - - -charset cheat sheet - - - - - +:>

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 1024; + $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 +101,48 @@ 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 "\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 +
+
+