X-Git-Url: http://git.shiar.net/sheet.git/blobdiff_plain/c4a7214bce24b26fbe98d2708eb3c6ad7a5f5c2e..80a615f8414664e34d48d6ffc1263943ae6fbf73:/charset-ucplanes.inc.pl
diff --git a/charset-ucplanes.inc.pl b/charset-ucplanes.inc.pl
index 42c1762..fd01acb 100644
--- a/charset-ucplanes.inc.pl
+++ b/charset-ucplanes.inc.pl
@@ -1,73 +1,95 @@
+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',
+ 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, ' | ·â¦',
+ 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 {
|