X-Git-Url: http://git.shiar.nl/sheet.git/blobdiff_plain/1436e579bd7ccf52d5e53d2db969eb74093df149..d5ddd90537e6910cf1b2fd1c6181b98b59d39bd0:/charset.plp diff --git a/charset.plp b/charset.plp index 51c391c..f26b7bd 100644 --- a/charset.plp +++ b/charset.plp @@ -17,8 +17,53 @@ Html({ my @tablist = split m{/+}, $Request || 'default'; +use List::Util qw( first pairmap pairfirst pairs ); + :> -

Character encoding

+

Character encodings

+ +

+<: +if ($tablist[0] eq 'default') { + say "Overview of Unicode allocation and common latin code pages."; + say "Compare alternate charsets:"; +} +else { + say "Charset comparison:"; +} + +sub optionlink { + my ($title, $href, $selected) = @_; + return sprintf( + $selected ? '%s' : '%s', + EscapeHTML($title), $href + ); +} + +print join " •\n", ( + map { + join " ·\n", pairmap { + optionlink($b || ucfirst $a, "/charset/$a?compare", $a eq $Request); + } @{$_} + } + [ + iso => 'ISO', + dos => 'DOS', + mac => 'Apple', + ebcdic => 'EBCDIC', + ], + [ + westeur => 'West', + centeur => 'Central', + norteur => 'North European', + turkish => 0, + greek => 0, + cyrillic => 0, + hebrew => 0, + ], +); +:>. +

<: use POSIX qw( ceil ); @@ -32,8 +77,8 @@ sub tabinput { state $ALIAS = { default => [qw( unicode+0-639 utf-8 iso-8859-1 iso-8859-15 cp1252 cp437 cp850 )], - us => [qw( cp437 cp863 AdobeStandardEncoding gsm0338 )], - ebcdic => [qw( cp37 cp500 cp875 cp1026 cp1047 posix-bc )], + us => [qw( cp437 cp863 gsm0338 AdobeStandardEncoding )], + ebcdic => [qw( cp37 cp500 cp1047 posix-bc cp1026 cp875 )], iso => [map {"iso-8859-$_"} 1 .. 11, 13 .. 16], dos => [qw( cp437 cp865 cp861 cp860 cp863 cp850 cp857 cp852 cp775 cp737 cp869 cp866 cp855 cp862 cp864 )], @@ -46,12 +91,15 @@ sub tabinput { westeur => [qw( iso-8859-1 iso-8859-15 cp1252 iso-8859-14 cp850 hp-roman8 nextstep MacRoman )], centeur => [qw( iso-8859-2 iso-8859-16 cp1250 cp852 MacRomanian MacCroatian MacCentralEurRoman )], # MacRumanian only for DB turkish => [qw( iso-8859-9 iso-8859-3 cp1254 cp857 MacTurkish )], + norteur => [qw( baltic nordic )], baltic => [qw( iso-8859-4 iso-8859-13 cp1257 cp775 )], nordic => [qw( iso-8859-10 cp865 cp861 MacIcelandic MacSami )], - cyrillic => [qw( koi8-r koi8-u koi8-f iso-8859-5 cp1251 MacCyrillic cp866 cp855 )], # MacUkrainian is broken - arabic => [qw( iso-8859-6 cp1256 MacArabic cp864 cp1006 MacFarsi )], - greek => [qw( iso-8859-7 cp1253 MacGreek cp737 cp869 )], - hebrew => [qw( iso-8859-8 cp1255 MacHebrew cp862 )], + cyrillic => [qw( koi8-r koi8-u koi8-f iso-8859-5 cp1251 MacCyrillic cp866 cp855 + U4 U2DE-2DF UA64-A69 U50-52 )], # MacUkrainian is broken + arabic => [qw( iso-8859-6 cp1256 MacArabic cp864 cp1006 MacFarsi + U6 U8A-8F+0-31+64 U75-77 )], + greek => [qw( iso-8859-7 cp1253 MacGreek cp737 cp869 U37-3F U1F )], + hebrew => [qw( iso-8859-8 cp1255 MacHebrew cp862 U59-5F )], thai => [qw( iso-8859-11 cp874 MacThai )], vietnamese => [qw( viscii cp1258 MacVietnamese )], symbol => [qw( symbol dingbats MacDingbats AdobeZdingbat AdobeSymbol )], @@ -80,10 +128,8 @@ sub tabinput { my $params = $input =~ s/[+](.*)\z// ? $1 : undef; if (not defined $params) { - use List::Util qw( first pairfirst pairs ); - state $INHERIT = { - 'cp437' => ['cp850' => 0], # ascii range overridden later + 'cp437' => ['cp850' => 0, 'ascii' => '0-31+128'], # ascii range overridden later 'gsm0338' => ['ascii' => '0-127'], 'iso-8859-2' => ['iso-8859-1' => '160'], @@ -144,6 +190,14 @@ sub tabinput { 'MacHebrew' => ['iso-8859-8' => '128', 'MacRoman' => '128-143+160'], # partial ascii 'MacArabic' => ['iso-8859-6' => '128', 'cp864' => '128', 'MacRoman' => '128'], #TODO: multiple parents 'MacFarsi' => ['MacArabic' => '176-191', 'MacRoman' => '128'], + + 'cp37' => ['posix-bc' => '0'], + 'posix-bc' => ['cp1047' => '64'], + 'cp500' => ['cp37' => '64-95+176-191'], + 'cp1047' => ['cp37' => '16-95+160-191'], #TODO: gap at 3/4 + 'cp1026' => ['cp37' => '64'], + 'cp875' => ['cp37' => '48'], + }; my @parents = @{ $INHERIT->{$input} || [] }; @@ -156,16 +210,21 @@ sub tabinput { } elsif (defined $visible->{ascii}) { $row{parent} = $parents[0]; - $params = $parents[1] || 128; + $params = $parents[1] // 128; $params = 128 if $params >= 128; # ascii offset at most } elsif (@parents) { $row{parent} = $parents[0]; + $params = $parents[1] if $parents[1] == 0; # apply ascii end } - $visible->{$_} //= 0 for $row{parent}; + $visible->{$_} //= 0 for $row{parent} || (); + } + else { + # manual option to double table width + $row{cols} *= 2 if $params =~ s/[+]\z//; } - if (defined $params) { + if (length $params) { $params =~ m{ \A (? \d+) (?: (?: [-] (? \d+) )? (?: [+] (? \d+) ) )? @@ -185,13 +244,14 @@ sub tabinput { } } - if ($input =~ /^U([0-9a-f]+)(?:-([0-9a-f]+))?/) { + if ($input =~ /^U([0-9a-fA-F]+)(?:-([0-9a-fA-F]+))?/) { my $start = hex($1) << ($2 ? 4 : 8); - my $end = $2 ? hex($2) << 4 : $start + 240; - $row{table} = join '', map { chr } $start .. $end+15; + my $end = $2 ? (hex($2) << 4) + $row{cols} - 1 : $start + 255; + $row{table} = join '', map { chr } $start .. $end; utf8::upgrade($row{table}); # prevent latin1 output - $row{endpoint} = $end + 14 - $start; + $row{endpoint} = $end - $start; $row{set} = sprintf 'Unicode block U+%02Xxx', $start >> 8; + $row{offset} = $start % 256; } elsif ($input eq 'U') { $row{set} = 'Unicode planes'; @@ -287,11 +347,22 @@ sub range_cell { } elsif (my $rows = int($len / $cols)) { # multiple full rows + my $rowsize = $colsize * $cols; if ($len -= $rows * $cols) { # partial row remains - $table->{$offset + $colsize*$rows * $cols} //= [$len*$colsize, "$class joinu", '', $title]; + $table->{$offset + $rowsize * $rows} //= [$len*$colsize, "$class joinu", '', $title]; $class .= ' joind'; } + + # coalesce multiple rows + while ($rows > 3) { + $info->{skip}->{$offset += $rowsize}++; + $rows--; + } + if ($rows > 2) { + $info->{skip}->{$offset += $rowsize} = 0; + } + $attr .= sprintf ' rowspan=%d', $rows; $len = $cols; } @@ -330,7 +401,10 @@ for my $row (@request) { } print ''; - { + if (defined $row->{skip}->{$offset}) { + print '⋮'; + } + else { if (my $rowmod = $offset % $rowdiv) { # offset in column units printf '+%X', $rowmod;