X-Git-Url: http://git.shiar.net/sheet.git/blobdiff_plain/77e386e3eac0e3bcfafd594eab707ef93eda789d..5ea095893fafdce2fa34e33cbc1d73ba1c65f167:/charset-ucplanes.inc.pl
diff --git a/charset-ucplanes.inc.pl b/charset-ucplanes.inc.pl
index ce57a94..fce05ff 100644
--- a/charset-ucplanes.inc.pl
+++ b/charset-ucplanes.inc.pl
@@ -1,77 +1,86 @@
use utf8;
-my %uniblock = (
- 0x000, '
ascii',
- 0x001, ' | latin',
-# 0x005, ' | spacing modifier',
- 0x005, ' | comb',
- 0x007, ' | grk',
- 0x008, ' | cyr',
- 0x00A, ' | arm',
- 0x00B, ' | aramaic',
- 0x011, ' | ',
- 0x012, ' | brahmic',
- 0x020, ' | mm',
- 0x021, ' | geor',
- 0x022, ' | jamo',
- 0x024, ' | ethiopic',
- 0x027, ' | aboriginal',
- 0x02D, ' | ger',
- 0x02E, ' | brahm',
- 0x030, ' | mon',
- 0x031, ' | can',
- 0x032, ' | brahmic',
- 0x03A, ' | extensions',
- 0x03E, ' | greek',
- 0x040, ' | ·â¦',
- 0x041, ' | misc',
- 0x044, ' | maths',
- 0x046, ' | technical',
- 0x049, ' | ()',
- 0x04A, ' | draw',
- 0x04C, ' | symbols',
- 0x050, ' | braille',
- 0x052, ' | â',
- 0x053, ' | math',
- 0x056, ' | misc',
- 0x058, ' | ancient',
- 0x05A, ' | ext',
- 0x05C, ' | ·+',
- 0x05D, ' | radicals',
- 0x060, ' | japanese',
- 0x062, ' | cjk+',
- 0x066, ' | compat',
- 0x068, ' | ',
- 0x070, ' | cjk ideographs A', #+2
- 0x09C, ' | cjk unified ideographs',
- 0x140, ' | yi',
- 0x149, ' | lisu',
- 0x14A, ' | vai',
- 0x14C, ' | cyr',
- 0x14D, ' | bam',
- 0x14E, ' | lat-D',
- 0x150, ' | brahmic',
- 0x158, ' | hangeul syllables',
- 0x160, ' | hangeul syllables',
- 0x1B0, ' | surrogates',
- 0x1C0, ' | private use',
- 0x1F0, ' | cjk compat',
- 0xFB0, ' | presentation',
- 0xFB5, ' | ',
- 0xFC0, ' | arabic presentation forms A',
- 0xFD0, ' | ',
- 0xFDD, ' | ?',
- 0xFDF, ' | ',
- 0xFE0, ' | var',
- 0xFE1, ' | ver',
- 0xFE2, ' | ½',
- 0xFE3, ' | comp',
- 0xFE5, ' | small',
- 0xFE7, ' | arabic presentation B',
- 0xFF0, ' | halfwidth & fullwidth forms',
- 0xFFF, ' | sp',
-);
-
-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', '·â¦'],
+ 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'],
+};
|