X-Git-Url: http://git.shiar.nl/sheet.git/blobdiff_plain/9b3b2b295e3ec1cd7970810050b3e11d00bfd2d0..42d8bbb170d20da856db097f3cec280e37578c31:/charset.plp diff --git a/charset.plp b/charset.plp index 16a49e9..c3477f1 100644 --- a/charset.plp +++ b/charset.plp @@ -31,18 +31,21 @@ sub tabinput { my $input = shift or return; state $ALIAS = { - default => [qw( unicode+0-192 utf-8 iso-8859-1 iso-8859-15 cp1252 cp437 cp850 )], + default => [qw( unicode+0-639 utf-8 iso-8859-1 iso-8859-15 cp1252 cp437 cp850 )], us => [qw( cp437 cp863 AdobeStandardEncoding gsm0338 )], ebcdic => [qw( cp37 cp500 cp875 cp1026 cp1047 posix-bc )], iso => [map {"iso-8859-$_"} 1 .. 11, 13 .. 16], - dos => [qw( cp437 cp863 cp850 cp860 cp852 cp855 cp866 cp864 cp1006 cp737 cp869 cp862 cp862 cp857 cp865 cp861 cp874 cp775 )], + dos => [qw( cp437 cp865 cp861 cp860 cp863 cp850 cp857 cp852 cp775 + cp737 cp869 cp866 cp855 cp862 cp864 )], + aix => [qw( cp1006 )], + win => [qw( cp1252 cp1250 cp1254 cp1257 cp1258 cp1253 cp1251 cp1255 cp1256 cp874 )], 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 )], baltic => [qw( iso-8859-4 iso-8859-13 cp1257 cp775 )], nordic => [qw( iso-8859-10 cp865 cp861 MacIcelandic MacSami )], - cyrillic => [qw( koi8-f koi8-r koi8-u iso-8859-5 cp1251 MacCyrillic cp855 cp866 )], # MacUkrainian is broken + cyrillic => [qw( koi8-r koi8-u koi8-f iso-8859-5 cp1251 MacCyrillic cp866 cp855 )], # MacUkrainian is broken arabic => [qw( iso-8859-6 cp1006 cp864 cp1256 MacArabic )], # MacFarsi same as MacArabic? greek => [qw( iso-8859-7 cp1253 MacGreek cp737 cp869 )], hebrew => [qw( iso-8859-8 cp1255 MacHebrew cp862 )], @@ -93,38 +96,63 @@ sub tabinput { 'iso-8859-14' => ['iso-8859-1' => '160'], 'iso-8859-15' => ['iso-8859-1' => '160-191'], 'iso-8859-16' => ['iso-8859-2' => '160'], + 'hp-roman8' => ['iso-8859-1' => '160'], 'cp1252' => ['iso-8859-1' => '128-159'], - 'cp1250' => ['iso-8859-2' => '128-191'], - 'cp1254' => ['iso-8859-9' => '128-159'], - 'cp1257' => ['iso-8859-13' => '128-'], + 'cp1250' => ['iso-8859-2' => '128-191', 'cp1252' => '128'], + 'cp1254' => ['iso-8859-9' => '128-159', 'cp1252' => '128'], + 'cp874' => ['iso-8859-11' => '128-159', 'cp1252' => '128'], # windows-874 actually cp1162 + 'cp1257' => ['iso-8859-13' => '128', 'cp1252' => '128'], + 'cp1251' => ['cp1252' => '128'], + 'cp1253' => ['cp1252' => '128'], + 'cp1255' => ['iso-8859-8' => '128-223', 'cp1252' => '128'], + 'cp1256' => ['cp1252' => '128'], + 'cp1258' => ['cp1252' => '128'], 'cp850' => ['cp437' => '144'], - 'cp865' => ['cp437' => '144-176'], + 'cp860' => ['cp437' => '128-175'], + 'cp861' => ['cp865' => '128-175'], + 'cp863' => ['cp437' => '128-175'], + 'cp865' => ['cp437' => '144-175'], 'cp852' => ['cp850' => '128', 'cp437' => '128'], 'cp857' => ['cp850' => '128-239', 'cp437' => '128'], 'cp775' => ['cp850' => '128'], # partial cp437 + 'cp866' => ['cp437' => '128'], + 'cp855' => ['cp437' => '128'], + 'cp1006' => ['cp437' => '128'], + 'cp737' => ['cp437' => '128'], + 'cp869' => ['cp437' => '128'], + 'cp862' => ['cp437' => '128'], + 'cp864' => ['cp437' => '128'], + + 'koi8-u' => ['koi8-r' => 128], + 'koi8-f' => ['koi8-u' => 128], 'MacRomanian' => ['MacRoman' => '160'], 'MacCroatian' => ['MacRoman' => '160'], 'MacCentralEurRoman' => ['MacRoman' => '128'], 'MacTurkish' => ['MacRoman' => '208-223'], # F5 is unassigned + 'MacCyrillic' => ['MacRoman' => '128'], + 'MacHebrew' => ['MacRoman' => '128'], }; my @parents = @{ $INHERIT->{$input} || [] }; - if (my ($parent, $part) = pairfirst { $visible->{$a} } @parents) { + if (my ($parent, $part) = pairfirst { defined $visible->{$a} } @parents) { $row{parent} = $parent; $params = $part; + $params = 128 unless $visible->{$parent} + or ($input eq 'MacCroatian' and defined $visible->{MacRomanian}); } - elsif ($visible->{ascii}) { - $row{parent} = $parents[0] || 'ascii'; + elsif (defined $visible->{ascii}) { + $row{parent} = $parents[0]; $params = $parents[1] || 128; $params = 128 if $params >= 128; # ascii offset at most } elsif (@parents) { $row{parent} = $parents[0]; } + $visible->{$_} //= 0 for $row{parent}; } if (defined $params and $params =~ m/^ (\d+) (-\d+)? /x) { @@ -137,34 +165,42 @@ sub tabinput { my $end = $2 ? hex($2) << 4 : $start + 240; $row{table} = join '', map { chr } $start .. $end+15; utf8::upgrade($row{table}); # prevent latin1 output - $row{len} = length $row{table}; + $row{endpoint} = $end + 14 - $start; $row{set} = sprintf 'Unicode block U+%02Xxx', $start >> 8; } elsif ($input eq 'U') { - $row{len} = 1024; $row{set} = 'Unicode planes'; $row{cell} = do 'charset-ucplanes.inc.pl' or Alert('Table data could not be read', $@ || $!); $row{cols} *= 2; + $row{endpoint} = 1023 * $row{cell}->{colsize}; } elsif ($row{set} = Encode::resolve_alias($input)) { if ($row{set} eq 'Internal') { - $row{len} = $endpoint < 255 ? 640 : 8192; $row{set} = 'Unicode BMP'; $row{cell} = do 'charset-unicode.inc.pl' or Alert('Table data could not be read', $@ || $!); + $row{endpoint} = ($endpoint || 8191) * $row{cell}->{colsize}; } elsif ($row{set} eq 'utf-8-strict') { - $row{len} = 256; $row{set} = 'UTF-8'; $row{cell} = do 'charset-utf8.inc.pl' or Alert('Table data could not be read', $@ || $!); + $row{endpoint} = 255; } else { - $row{len} = $endpoint - $row{offset}; - $row{table} = Encode::decode($row{set}, pack 'C*', $row{offset} .. $endpoint); - # (~16x faster than decoding in loop; - # substr strings is twice as fast as splitting to an array) + if ($row{set} eq 'MacHebrew') { + # array of possibly multiple characters per code point + $row{table} = [ + map { Encode::decode($row{set}, pack 'C*', $_) } $row{offset} .. $endpoint + ]; + } + else { + # ~16x faster than decoding in loop; + # substr strings is twice as fast as splitting to an array + $row{table} = Encode::decode($row{set}, pack 'C*', $row{offset} .. $endpoint); + } + $row{endpoint} = $endpoint - $row{offset}; if ($row{set} eq 'cp437' and !$row{offset}) { substr($row{table}, 237, 1) = pack 'U*', 0x3D5; # phi sign @@ -249,7 +285,6 @@ for my $row (@request) { my $rowdiv = 16 ** $coldigits; # row divide for column digits $rowdiv = 1 if $rowdiv != $cols * $colsize; # divide only if all columns are matched my $offset = 0; - my $endpoint = $offset + $row->{len} * $colsize; printf '
', !$row->{cell} && ' charmap'; my $title = $row->{set}; @@ -263,7 +298,7 @@ for my $row (@request) { print "\n"; } print ''; - while ($offset < $endpoint - 1) { + while ($offset < $row->{endpoint}) { print '
'; { if (my $rowmod = $offset % $rowdiv) { @@ -281,12 +316,27 @@ for my $row (@request) { next; } - my $glyph = substr $row->{table}, $offset, 1; + my $glyph = ref $row->{table} eq 'ARRAY' ? $row->{table}->[$offset] : + substr $row->{table}, $offset, 1; if ($glyph eq $NOCHAR) { print ''; next; } + if (exists $get{compare}) { + state $visible = {}; + my $cp = $offset + $row->{offset}; + printf '%2$s', + $cp == ord $glyph ? 'l4' : + $row->{parent} && $glyph eq + Encode::decode($row->{parent}, pack 'C', $cp) ? 'l3' : + $visible->{$glyph} ? 'l2' : + 'l1', + $glyphs->glyph_html($glyph); + $visible->{$glyph}++; + next; + } + print "\n".$glyphs->glyph_cell($glyph); } continue { @@ -301,7 +351,13 @@ for my $row (@request) {
- +
<: if (exists $get{compare}) { :> +
unicode + inherited + existing + original + unassigned +<: } else { :> control whitespace diacritic @@ -338,6 +394,6 @@ for my $row (@request) {
deprecated unassigned invalid -
+<: } :>