charset: common cell formatting for unicode planes

Like unicode include, but support different nibble size.

diff --git a/charset-ucplanes.inc.pl b/charset-ucplanes.inc.pl
index fd01acbbd7301b6cd87006f00fb40fd6b114b675..fce05ffdffd8c4eeac540f5151dd80c024664990 100644 (file)
--- a/charset-ucplanes.inc.pl
+++ b/charset-ucplanes.inc.pl
@@ -1,98 +1,86 @@
 use utf8;
 use utf8;

-my %uniblock = (
-       0x0000, '<td colspan="1" class="X Po">ascii',
-       0x0008, '<td colspan="4" class="X L Latin">latin',
-#      0x0028, '<td colspan="5" class="X Sk">spacing modifier',
-       0x0028, '<td colspan="2" class="X Mn">comb',
-       0x0038, '<td colspan="1" class="X L Greek">grk',
-       0x0040, '<td colspan="2" class="X L Cyrillic">cyr',
-       0x0050, '<td colspan="1" class="X L Armenian">arm',
-       0x0058, '<td colspan="1" class="X L Aramaic">heb',
-       0x0060, '<td colspan="2" class="X L Arabic">arabic',
-       0x0070, '<td colspan="3" class="X L Aramaic">aram',
-       0x0080, '<td colspan="2" class="X L Aramaic">aramaic',
-       0x0090, '<td colspan="14" class="X L Brahmic">brahmic',
-       0x0100, '<td colspan="1" class="X L Brahmic">mm',
-       0x0108, '<td colspan="1" class="X L Aramaic">geor',
-       0x0110, '<td colspan="2" class="X L Hangul">jamo',
-       0x0120, '<td colspan="3" class="X L African">ethiopic',
-       0x0138, '<td colspan="6" class="X L Syllabic">aboriginal',
-       0x0168, '<td colspan="1" class="X L Alpha">ger',
-       0x0170, '<td colspan="2" class="X L Brahmic">brahm',
-       0x0180, '<td colspan="1" class="X L Aramaic">mon',
-       0x0188, '<td colspan="1" class="X L Syllabic">can',
-       0x0190, '<td colspan="8" class="X L Brahmic">brahmic',
-       0x01D0, '<td colspan="4" class="X L Latin">extensions',
-       0x01F0, '<td colspan="2" class="X L Greek">greek',
-       0x0200, '<td colspan="1" class="X Po">·…',
-       0x0208, '<td colspan="3" class="X So">symbols',
-       0x0220, '<td colspan="2" class="X Sm">maths',
-       0x0230, '<td colspan="3" class="X So">technical',
-       0x0248, '<td colspan="1" class="X Latin">()',
-       0x0250, '<td colspan="2" class="X So">draw',
-       0x0260, '<td colspan="4" class="X So">symbols',
-       0x0280, '<td colspan="2" class="X L Alpha">braille',
-       0x0290, '<td colspan="1" class="X So">arr',
-       0x0298, '<td colspan="3" class="X Sm">maths',
-       0x02B0, '<td colspan="2" class="X So">misc',
-       0x02C0, '<td colspan="2" class="X L Greek">ancient',
-       0x02D0, '<td colspan="2" class="X L Alpha">ext',
-       0x02E0, '<td colspan="1" class="X Po">·+',
-       0x02E8, '<td colspan="3" class="X L Han">radicals',
-       0x0300, '<td colspan="2" class="X L Katakana">japanese',
-       0x0310, '<td colspan="4" class="X L Han">cjk+',
-       0x0330, '<td colspan="2" class="X Xd L Han">compat',
-       0x0340, '<td colspan="8" class="X L Han" style="border-bottom:none">',
-       0x0380, '<td colspan="16" rowspan="2" class="X L Han" style="border-top:none">cjk ideographs A', #+2
-       0x04E0, '<td colspan="16" rowspan="11" class="X L Han">cjk unified ideographs',
-       0x0A00, '<td colspan="9" class="X L Syllabic">yi',
-       0x0A48, '<td colspan="1" class="X L Latin">lisu',
-       0x0A50, '<td colspan="2" class="X L Syllabic">vai',
-       0x0A60, '<td colspan="1" class="X L Cyrillic">cyr',
-       0x0A68, '<td colspan="1" class="X L Syllabic">bam',
-       0x0A70, '<td colspan="2" class="X L Latin">lat-D',
-       0x0A80, '<td colspan="6" class="X L Brahmic">brahmic',
-       0x0AB0, '<td colspan="2" class="X L Alpha">ext',
-       0x0AC0, '<td colspan="8" class="X L Hangul" style="border-bottom:none">',
-       0x0B00, '<td colspan="16" rowspan="5" class="X L Hangul" style="border-top:none">hangeul syllables',
-       0x0D80, '<td colspan="16" class="X Cs">surrogates',
-       0x0E00, '<td colspan="16" rowspan="3" class="X Co" style="border-bottom:none">private use',
-       0x0F80, '<td colspan="2" class="X Co" style="border-top:none">',
-       0x0F90, '<td colspan="4" class="X L Han">cjk compat',
-       0x0FB0, '<td colspan="8" class="X L Arabic">presentation',
-       0x0FF0, '<td colspan="2" class="X L Latin">width',
-
-       0x1000, '<td colspan="2" class="X L Syllabic">linear B',
-       0x1010, '<td colspan="2" class="X No">a num',
-       0x1020, '<td colspan="8" class="X L Alpha">ltr',
-       0x1060, '<td colspan="3" class="X L Syllabic">linear A',
-       0x1078, '<td colspan="1" class="X L Alpha">ltr',
-       0x1080, '<td colspan="16" class="X L Aramaic">rtl',
-       0x1100, '<td colspan="16" rowspan="2" class="X L Brahmic">brahmic',
-       0x1200, '<td colspan="16" rowspan="2" class="X L Syllabic">cuneiform',
-       0x1300, '<td colspan="16" rowspan="2" class="X L Syllabic">egyptian hieroglyphs',
-       0x1400, '<td colspan="16" rowspan="4" class="X L Syllabic">other large scripts',
-       0x1600, '<td colspan="16" rowspan="2" class="X L Alpha">recent',
-       0x1700, '<td colspan="16" rowspan="8" class="X L Han">east asian',
-       0x1B40, '<td colspan="2" class="">res',
-       0x1B50, '<td colspan="14" class="X L Syllabic">proto-elamite',
-       0x1BC0, '<td colspan="8" class="X L Alpha">shorthands',
-       0x1BE0, '<td colspan="8" class="" style="border-bottom:none">',
-       0x1C00, '<td colspan="16" rowspan="2" class="" style="border-top:none">other large scripts',
-       0x1D00, '<td colspan="8" class="X So">notational systems',
-       0x1D40, '<td colspan="8" class="X L Latin">mathematical', # Sm
-       0x1D80, '<td colspan="8" class="X L Alpha">sutton signs',
-       0x1DC0, '<td colspan="8" class="">notational',
-       0x1E00, '<td colspan="16" class="X L Alpha">ltr',
-       0x1E80, '<td colspan="16" class="X L Alpha">rtl',
-       0x1F00, '<td colspan="2" class="X So">game',
-       0x1F10, '<td colspan="4" class="X L So">enclosed',
-       0x1F30, '<td colspan="12" class="X So">pictographic',
-       0x1F80, '<td colspan="2" class="X So">arrows',
-       0x1F90, '<td colspan="14" class="">unassigned',
-);
-
-sub {
-       return defined $uniblock{$_[0]} ? $uniblock{$_[0]} : ();
-}
-
++{
+       0x0000 => [0x008, 'X Po',               'ascii'],
+       0x0008 => [0x020, 'X L Latin',          'latin'],
+       0x0028 => [0x010, 'X Mn',               'comb'], # also spacing Sk
+       0x0038 => [0x008, 'X L Greek',          'grk'],
+       0x0040 => [0x010, 'X L Cyrillic',       'cyr'],
+       0x0050 => [0x008, 'X L Armenian',       'arm'],
+       0x0058 => [0x008, 'X L Aramaic',        'heb'],
+       0x0060 => [0x010, 'X L Arabic',         'arabic'],
+       0x0070 => [0x010, 'X L Aramaic',        'aram'],
+       0x0080 => [0x010, 'X L Aramaic',        'aramaic'],
+       0x0090 => [0x070, 'X L Brahmic',        'brahmic'],
+       0x0100 => [0x008, 'X L Brahmic',        'mm'],
+       0x0108 => [0x008, 'X L Aramaic',        'geor'],
+       0x0110 => [0x010, 'X L Hangul',         'jamo'],
+       0x0120 => [0x018, 'X L African',        'ethiopic'],
+       0x0138 => [0x030, 'X L Syllabic',       'aboriginal'],
+       0x0168 => [0x008, 'X L Alpha',          'ger'],
+       0x0170 => [0x010, 'X L Brahmic',        'brahm'],
+       0x0180 => [0x008, 'X L Aramaic',        'mon'],
+       0x0188 => [0x008, 'X L Syllabic',       'can'],
+       0x0190 => [0x040, 'X L Brahmic',        'brahmic'],
+       0x01D0 => [0x020, 'X L Latin',          'extensions'],
+       0x01F0 => [0x010, 'X L Greek',          'greek'],
+       0x0200 => [0x008, 'X Po',               '·…'],
+       0x0208 => [0x018, 'X So',               'symbols'],
+       0x0220 => [0x010, 'X Sm',               'maths'],
+       0x0230 => [0x018, 'X So',               'technical'],
+       0x0248 => [0x008, 'X Latin',            '()'],
+       0x0250 => [0x010, 'X So',               'draw'],
+       0x0260 => [0x020, 'X So',               'symbols'],
+       0x0280 => [0x010, 'X L Alpha',          'braille'],
+       0x0290 => [0x008, 'X So',               'arr'],
+       0x0298 => [0x018, 'X Sm',               'maths'],
+       0x02B0 => [0x010, 'X So',               'misc'],
+       0x02C0 => [0x010, 'X L Greek',          'ancient'],
+       0x02D0 => [0x010, 'X L Alpha',          'ext'],
+       0x02E0 => [0x008, 'X Po',               '·+'],
+       0x02E8 => [0x018, 'X L Han',            'radicals'],
+       0x0300 => [0x010, 'X L Katakana',       'japanese'],
+       0x0310 => [0x020, 'X L Han',            'cjk+'],
+       0x0330 => [0x010, 'X Xd L Han',         'compat'],
+       0x0340 => [0x1A0, 'X L Han',            'cjk ideographs A'],
+       0x04E0 => [0x520, 'X L Han',            'cjk unified ideographs'],
+       0x0A00 => [0x048, 'X L Syllabic',       'yi'],
+       0x0A48 => [0x008, 'X L Latin',          'lisu'],
+       0x0A50 => [0x010, 'X L Syllabic',       'vai'],
+       0x0A60 => [0x008, 'X L Cyrillic',       'cyr'],
+       0x0A68 => [0x008, 'X L Syllabic',       'bam'],
+       0x0A70 => [0x010, 'X L Latin',          'lat-D'],
+       0x0A80 => [0x030, 'X L Brahmic',        'brahmic'],
+       0x0AB0 => [0x010, 'X L Alpha',          'ext'],
+       0x0AC0 => [0x2C0, 'X L Hangul',         'hangeul syllables'],
+       0x0D80 => [0x080, 'X Cs',               'surrogates'],
+       0x0E00 => [0x190, 'X Co',               'private use'],
+       0x0F90 => [0x020, 'X L Han',            'cjk compat'],
+       0x0FB0 => [0x040, 'X L Arabic',         'presentation'],
+       0x0FF0 => [0x010, 'X L Latin',          'width'],
+       0x1000 => [0x010, 'X L Syllabic',       'linear B'],
+       0x1010 => [0x010, 'X No',               'a num'],
+       0x1020 => [0x040, 'X L Alpha',          'ltr'],
+       0x1060 => [0x018, 'X L Syllabic',       'linear A'],
+       0x1078 => [0x008, 'X L Alpha',          'ltr'],
+       0x1080 => [0x080, 'X L Aramaic',        'rtl'],
+       0x1100 => [0x100, 'X L Brahmic',        'brahmic'],
+       0x1200 => [0x100, 'X L Syllabic',       'cuneiform'],
+       0x1300 => [0x100, 'X L Syllabic',       'egyptian hieroglyphs'],
+       0x1400 => [0x200, 'X L Syllabic',       'other large scripts'],
+       0x1600 => [0x100, 'X L Alpha',          'recent'],
+       0x1700 => [0x450, 'X L Han',            'east asian'],
+       0x1B50 => [0x070, 'X L Syllabic',       'proto-elamite'],
+       0x1BC0 => [0x040, 'X L Alpha',          'shorthands'],
+       0x1C00 => [0x100, '',                   'other large scripts'],
+       0x1D00 => [0x040, 'X So',               'notational systems'],
+       0x1D40 => [0x040, 'X L Latin',          'mathematical'], # Sm
+       0x1D80 => [0x040, 'X L Alpha',          'sutton signs'],
+       0x1DC0 => [0x040, '',                   'notational'],
+       0x1E00 => [0x080, 'X L Alpha',          'ltr'],
+       0x1E80 => [0x080, 'X L Alpha',          'rtl'],
+       0x1F00 => [0x010, 'X So',               'game'],
+       0x1F10 => [0x020, 'X L So',             'enclosed'],
+       0x1F30 => [0x050, 'X So',               'pictographic'],
+       0x1F80 => [0x010, 'X So',               'arrows'],
+       0x1F90 => [0x070, '',                   'unassigned'],
+};

diff --git a/charset.plp b/charset.plp
index e55e771f2acd2a78196d0cb41db45db4b060a2c1..15183cfb479eae12889f06cfd41d5512b3be4c62 100644 (file)
--- a/charset.plp
+++ b/charset.plp
@@ -107,15 +107,16 @@ sub range_cell {
        my ($len, $class, $name, $title) = @{$def};
 
        my $attr = '';
        my ($len, $class, $name, $title) = @{$def};
 
        my $attr = '';

+       $len /= $nibsize;

        $name //= $len <= 2 ? 'res' : 'reserved';
 
        $name //= $len <= 2 ? 'res' : 'reserved';
 

-       if (my $part = $offset % 16) {
+       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
                # continued row
                my $cols = 16 - $part;  # remaining
                $cols = $len if $len < $cols; #TODO: optimise
                if ($len -= $cols) {
                        # continued on new row

-                       $table->{$offset + $cols} = [$len, "$class joinu", $name, $title];
+                       $table->{$offset + $nibsize*$cols} = [$len*$nibsize, "$class joinu", $name, $title];

                        $name = '';
                        $class .= ' joind';
                }
                        $name = '';
                        $class .= ' joind';
                }


@@ -125,7 +126,7 @@ sub range_cell {
                # multiple full rows
                if ($len -= $rows << 4) {
                        # partial row remains
                # multiple full rows
                if ($len -= $rows << 4) {
                        # partial row remains

-                       $table->{$offset + $rows * 16} = [$len, "$class joinu", '', $title];
+                       $table->{$offset + $nibsize*$rows * 16} = [$len*$nibsize, "$class joinu", '', $title];

                        $class .= ' joind';
                }
                $attr .= sprintf ' rowspan=%d', $rows;
                        $class .= ' joind';
                }
                $attr .= sprintf ' rowspan=%d', $rows;


@@ -149,7 +150,7 @@ for my $row (@request) {
        }
        print '<tbody>';
        for my $msb (0 .. (length($row->{table}) || 256) - 1 >> 4) {
        }
        print '<tbody>';
        for my $msb (0 .. (length($row->{table}) || 256) - 1 >> 4) {

-               printf '<tr><th>%X', $msb + ($row->{offset} >> 4);
+               printf '<tr><th>%X', ($msb + ($row->{offset} >> 4)) * $nibsize;

                for my $lsb (0 .. $#nibble) {
                        my $val = ( ($msb<<4) + $lsb ) * $nibsize;
                        if ($row->{cell}) {
                for my $lsb (0 .. $#nibble) {
                        my $val = ( ($msb<<4) + $lsb ) * $nibsize;
                        if ($row->{cell}) {