X-Git-Url: http://git.shiar.nl/sheet.git/blobdiff_plain/ee28d695e83d760b1a0d88feefdd528b829f986e..3a76788894b92930175ec23149c0793c6b0b1100:/charset.plp diff --git a/charset.plp b/charset.plp index 7dc1aee..9a9586a 100644 --- a/charset.plp +++ b/charset.plp @@ -17,8 +17,54 @@ Html({ my @tablist = split m{/+}, $Request || 'default'; +use List::Util qw( first pairmap pairfirst pairs ); + :> -
+<: +if ($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), $href + ); +} + +print join " â¢\n", ( + map { + join " ·\n", pairmap { + optionlink($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, + ], + [ uc => 'Unicode' ], +); +:>. +
<: use POSIX qw( ceil ); @@ -32,6 +78,7 @@ sub tabinput { state $ALIAS = { default => [qw( unicode+0-639 utf-8 iso-8859-1 iso-8859-15 cp1252 cp437 cp850 )], + uc => [qw( U++ unicode+0-4095 unicode+4096-6319 unicode+6320-8191 )], us => [qw( cp437 cp863 gsm0338 AdobeStandardEncoding )], ebcdic => [qw( cp37 cp500 cp1047 posix-bc cp1026 cp875 )], iso => [map {"iso-8859-$_"} 1 .. 11, 13 .. 16], @@ -46,12 +93,15 @@ 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 )], @@ -76,14 +126,11 @@ sub tabinput { state $visible = {}; # all present tables my %row = (offset => 0, cols => 16); - my $endpoint = 255; 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'], @@ -129,8 +176,8 @@ sub tabinput { 'cp862' => ['cp437' => '128-159'], 'cp864' => ['MacArabic' => '128', 'iso-8859-6' => '128', 'cp437' => '128'], #TODO: compare form variants - 'koi8-u' => ['koi8-r' => 128], - 'koi8-f' => ['koi8-u' => 128], + 'koi8-u' => ['koi8-r' => '144-191'], + 'koi8-f' => ['koi8-u' => '144-191'], 'MacRomanian' => ['MacRoman' => '160-191+208-223'], 'MacRumanian' => ['MacRomanian' => '160-191+208-223', 'MacRoman' => '160-191+208-223'], @@ -164,16 +211,22 @@ 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} || (); + } + + if (length $params) { + # manual option to double table width + $row{cols} *= 2 if $params =~ s/[+]\z//; } - if (defined $params) { + if (length $params) { $params =~ m{ \A (?'; - { + if (defined $row->{skip}->{$offset}) { + print 'â®'; + } + else { if (my $rowmod = $offset % $rowdiv) { # offset in column units printf '+%X', $rowmod; |
---|