X-Git-Url: http://git.shiar.nl/sheet.git/blobdiff_plain/130c94fc7747fd586b677f48fbabd2ecf10297c5..b97ebd969b2e520d3e65509c0f892edacae70520:/charset.plp diff --git a/charset.plp b/charset.plp index 6577f4c..d3b27b5 100644 --- a/charset.plp +++ b/charset.plp @@ -2,7 +2,7 @@ Html({ title => 'charset cheat sheet', - version => 'v1.0', + version => '1.0', description => [ "Reference sheet with all glyphs in common character encoding tables,", "and an overview of Unicode ranges and UTF-8 bytes.", @@ -24,19 +24,18 @@ 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) # (~16x faster than decoding in loop; # substr strings is twice as fast as splitting to an array) my %ALIAS = ( # default => [qw(unicode utf-8 iso-8859-1 cp437 -cp1252- --iso-8859-15- -koi8-f)], default => [qw(unicode- utf-8 iso-8859-1 -cp1252- --iso-8859-15- cp437 -cp850)], - 0 => [qw(cp437 cp863)], - 1 => [qw(iso-8859-1 cp1252 MacRoman cp850)], - 2 => [qw(iso-8859-2 cp1250 cp852 MacCentralEurRoman MacCroatian MacRumanian)], - 5 => [qw(koi8-f iso-8859-5 cp1251 MacCyrillic cp855 cp866)], - 7 => [qw(iso-8859-7 cp1253 MacGreek cp737 cp869)], - 8 => [qw(iso-8859-8 cp1255 MacHebrew cp862)], + 0 => [qw(cp437 -cp863)], + 1 => [qw(iso-8859-1 -cp1252 -MacRoman -cp850)], + 2 => [qw(iso-8859-2 -cp1250 -cp852 -MacCentralEurRoman -MacCroatian -MacRumanian)], + 5 => [qw(koi8-f -iso-8859-5 -cp1251 -MacCyrillic -cp855 -cp866)], + 7 => [qw(iso-8859-7 -cp1253 -MacGreek -cp737 -cp869)], + 8 => [qw(iso-8859-8 -cp1255 -MacHebrew -cp862)], ); my @request = map { if (my $input = $_) { @@ -51,6 +50,10 @@ my @request = map { if ($input =~ s/-$//) { $endpoint = $row{offset} ? $row{offset} < 160 ? 159 : 191 : 127; } + if ($row{offset}) { + $row{setnote} = 'over cp437' if $input eq 'cp850'; + $row{setnote} = 'over iso-8859-1' if $input =~ /^iso-8859-|^cp125/; + } if ($input =~ /^U([0-9a-f]+)(?:-([0-9a-f]+))?/) { my $start = hex($1) << ($2 ? 4 : 8); @@ -60,37 +63,40 @@ 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 Alert('Table data could not be read', $@ || $!); @nibble = (map { $_.0, $_.8 } 0 .. 7); $nibsize = 8; } - elsif ($row{set} = resolve_alias($input)) { + elsif ($row{set} = Encode::resolve_alias($input)) { if ($row{set} eq 'Internal') { $row{table} = ' ' x ($endpoint < 255 ? 640 : 8192); $row{set} = 'Unicode BMP'; - $row{cell} = do 'charset-unicode.inc.pl'; + $row{cell} = do 'charset-unicode.inc.pl' + or Alert('Table data could not be read', $@ || $!); } elsif ($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 Alert('Table data could not be read', $@ || $!); } else { - $row{table} = decode($row{set}, pack 'C*', $row{offset} .. $endpoint); + $row{table} = Encode::decode($row{set}, pack 'C*', $row{offset} .. $endpoint); } } else { - print "

Encoding $input unknown

\n"; + Alert("Encoding $input unknown"); } - \%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) { @@ -101,9 +107,50 @@ for my $cp437 (grep {$request[$_]->{set} eq 'cp437'} 0 .. $#request) { ); } +sub range_cell { + my ($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; + } + + $attr .= sprintf ' colspan=%d', $len unless $len == 1; + $attr .= $1 if $class and $class =~ s/( \w+="[^"]*")//; + $attr .= sprintf ' class="%s"', $class if $class; + $attr .= sprintf ' title="%s"', EscapeHTML($title) if $title; + return "$name"; +} + for my $row (@request) { printf '
', !$row->{cell} && ' charmap'; - printf '', $row->{set}; + my $title = $row->{set}; + $title .= " " for $row->{setnote} // (); + printf '', $title; print '' x 17; for my $section (qw{thead}) { print "<$section>'; for my $msb (0 .. (length($row->{table}) || 256) - 1 >> 4) { - printf '
%s%s
↱"; @@ -112,11 +159,15 @@ 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 $row->{cell}->($val); + if (ref $row->{cell} eq 'CODE') { + print $row->{cell}->($val); + next; + } + print range_cell($row->{cell}, $val); next; } @@ -130,7 +181,7 @@ for my $row (@request) { } print "\n"; } - print "
\n"; + say ''; } :>