use utf8;
my %uniblock = (
0x0000, '
ascii',
0x0008, ' | latin',
# 0x0028, ' | spacing modifier',
0x0028, ' | comb',
0x0038, ' | grk',
0x0040, ' | cyr',
0x0050, ' | arm',
0x0058, ' | heb',
0x0060, ' | arabic',
0x0070, ' | aram',
0x0080, ' | aramaic',
0x0090, ' | brahmic',
0x0100, ' | mm',
0x0108, ' | geor',
0x0110, ' | jamo',
0x0120, ' | ethiopic',
0x0138, ' | aboriginal',
0x0168, ' | ger',
0x0170, ' | brahm',
0x0180, ' | mon',
0x0188, ' | can',
0x0190, ' | brahmic',
0x01D0, ' | extensions',
0x01F0, ' | greek',
0x0200, ' | ·…',
0x0208, ' | symbols',
0x0220, ' | maths',
0x0230, ' | technical',
0x0248, ' | ()',
0x0250, ' | draw',
0x0260, ' | symbols',
0x0280, ' | braille',
0x0290, ' | arr',
0x0298, ' | maths',
0x02B0, ' | misc',
0x02C0, ' | ancient',
0x02D0, ' | ext',
0x02E0, ' | ·+',
0x02E8, ' | radicals',
0x0300, ' | japanese',
0x0310, ' | cjk+',
0x0330, ' | compat',
0x0340, ' | ',
0x0380, ' | cjk ideographs A', #+2
0x04E0, ' | cjk unified ideographs',
0x0A00, ' | yi',
0x0A48, ' | lisu',
0x0A50, ' | vai',
0x0A60, ' | cyr',
0x0A68, ' | bam',
0x0A70, ' | lat-D',
0x0A80, ' | brahmic',
0x0AB0, ' | ext',
0x0AC0, ' | ',
0x0B00, ' | hangeul syllables',
0x0D80, ' | surrogates',
0x0E00, ' | private use',
0x0F80, ' | ',
0x0F90, ' | cjk compat',
0x0FB0, ' | presentation',
0x0FF0, ' | width',
0x1000, ' | linear B',
0x1010, ' | a num',
0x1020, ' | ltr',
0x1060, ' | linear A',
0x1078, ' | ltr',
0x1080, ' | rtl',
0x1100, ' | brahmic',
0x1200, ' | cuneiform',
0x1300, ' | egyptian hieroglyphs',
0x1400, ' | other large scripts',
0x1600, ' | recent',
0x1700, ' | east asian',
0x1B40, ' | res',
0x1B50, ' | proto-elamite',
0x1BC0, ' | shorthands',
0x1BE0, ' | ',
0x1C00, ' | other large scripts',
0x1D00, ' | notational systems',
0x1D40, ' | mathematical', # Sm
0x1D80, ' | sutton signs',
0x1DC0, ' | notational',
0x1E00, ' | ltr',
0x1E80, ' | rtl',
0x1F00, ' | game',
0x1F10, ' | enclosed',
0x1F30, ' | pictographic',
0x1F80, ' | arrows',
0x1F90, ' | unassigned',
);
sub {
return defined $uniblock{$_[0]} ? $uniblock{$_[0]} : ();
}
|