Files
colibri/c/tok_unicode_o200k.h
Nicholas Beerbower 364b9741e2 tok: o200k pre-tokenizer support, auto-detected from tokenizer.json
Inkling ships an o200k-family tokenizer (case-aware Split regex, GPT-4o
lineage) rather than cl100k. tok_load now detects the family from the
pattern itself (\p{Lu} appears only in the o200k regex) so GLM behavior
is untouched, and encode dispatches to a new pretok_chunk_o200k that
replays the regex engine's backtracking order exactly: greedy optional
prefix, maximally-greedy uppercase run given back until the lowercase
run can match, contractions attached to letter runs, \p{N}{1,3}, and
the [\r\n/]* punctuation tail.

tok_unicode_o200k.h adds the two range tables the new classes need
(Lu+Lt and Lm+Lo+M), generated from Python unicodedata.

Validated against HF tokenizers on 357 adversarial strings (case
transitions, contractions, CJK, combining marks, emoji + modifiers,
zero-width chars, 300 mixed-charset fuzz cases): 357/357 identical.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-16 15:14:50 -04:00

229 lines
21 KiB
C

/* Unicode range tables for the o200k pre-tokenizer (Inkling, GPT-4o family).
* Generated from Python unicodedata (see tools/ in git history):
* uni_U = Lu + Lt (uppercase/titlecase letters)
* uni_X = Lm + Lo + M (caseless letters and combining marks; members of
* BOTH bracket classes in the o200k regex)
* Lookup via the same uni_in() binary search as tok_unicode.h. */
#ifndef TOK_UNICODE_O200K_H
#define TOK_UNICODE_O200K_H
#include <stdint.h>
static const uint32_t uni_U[][2] = {
{0x41,0x5A},{0xC0,0xD6},{0xD8,0xDE},{0x100,0x100},{0x102,0x102},{0x104,0x104},
{0x106,0x106},{0x108,0x108},{0x10A,0x10A},{0x10C,0x10C},{0x10E,0x10E},{0x110,0x110},
{0x112,0x112},{0x114,0x114},{0x116,0x116},{0x118,0x118},{0x11A,0x11A},{0x11C,0x11C},
{0x11E,0x11E},{0x120,0x120},{0x122,0x122},{0x124,0x124},{0x126,0x126},{0x128,0x128},
{0x12A,0x12A},{0x12C,0x12C},{0x12E,0x12E},{0x130,0x130},{0x132,0x132},{0x134,0x134},
{0x136,0x136},{0x139,0x139},{0x13B,0x13B},{0x13D,0x13D},{0x13F,0x13F},{0x141,0x141},
{0x143,0x143},{0x145,0x145},{0x147,0x147},{0x14A,0x14A},{0x14C,0x14C},{0x14E,0x14E},
{0x150,0x150},{0x152,0x152},{0x154,0x154},{0x156,0x156},{0x158,0x158},{0x15A,0x15A},
{0x15C,0x15C},{0x15E,0x15E},{0x160,0x160},{0x162,0x162},{0x164,0x164},{0x166,0x166},
{0x168,0x168},{0x16A,0x16A},{0x16C,0x16C},{0x16E,0x16E},{0x170,0x170},{0x172,0x172},
{0x174,0x174},{0x176,0x176},{0x178,0x179},{0x17B,0x17B},{0x17D,0x17D},{0x181,0x182},
{0x184,0x184},{0x186,0x187},{0x189,0x18B},{0x18E,0x191},{0x193,0x194},{0x196,0x198},
{0x19C,0x19D},{0x19F,0x1A0},{0x1A2,0x1A2},{0x1A4,0x1A4},{0x1A6,0x1A7},{0x1A9,0x1A9},
{0x1AC,0x1AC},{0x1AE,0x1AF},{0x1B1,0x1B3},{0x1B5,0x1B5},{0x1B7,0x1B8},{0x1BC,0x1BC},
{0x1C4,0x1C5},{0x1C7,0x1C8},{0x1CA,0x1CB},{0x1CD,0x1CD},{0x1CF,0x1CF},{0x1D1,0x1D1},
{0x1D3,0x1D3},{0x1D5,0x1D5},{0x1D7,0x1D7},{0x1D9,0x1D9},{0x1DB,0x1DB},{0x1DE,0x1DE},
{0x1E0,0x1E0},{0x1E2,0x1E2},{0x1E4,0x1E4},{0x1E6,0x1E6},{0x1E8,0x1E8},{0x1EA,0x1EA},
{0x1EC,0x1EC},{0x1EE,0x1EE},{0x1F1,0x1F2},{0x1F4,0x1F4},{0x1F6,0x1F8},{0x1FA,0x1FA},
{0x1FC,0x1FC},{0x1FE,0x1FE},{0x200,0x200},{0x202,0x202},{0x204,0x204},{0x206,0x206},
{0x208,0x208},{0x20A,0x20A},{0x20C,0x20C},{0x20E,0x20E},{0x210,0x210},{0x212,0x212},
{0x214,0x214},{0x216,0x216},{0x218,0x218},{0x21A,0x21A},{0x21C,0x21C},{0x21E,0x21E},
{0x220,0x220},{0x222,0x222},{0x224,0x224},{0x226,0x226},{0x228,0x228},{0x22A,0x22A},
{0x22C,0x22C},{0x22E,0x22E},{0x230,0x230},{0x232,0x232},{0x23A,0x23B},{0x23D,0x23E},
{0x241,0x241},{0x243,0x246},{0x248,0x248},{0x24A,0x24A},{0x24C,0x24C},{0x24E,0x24E},
{0x370,0x370},{0x372,0x372},{0x376,0x376},{0x37F,0x37F},{0x386,0x386},{0x388,0x38A},
{0x38C,0x38C},{0x38E,0x38F},{0x391,0x3A1},{0x3A3,0x3AB},{0x3CF,0x3CF},{0x3D2,0x3D4},
{0x3D8,0x3D8},{0x3DA,0x3DA},{0x3DC,0x3DC},{0x3DE,0x3DE},{0x3E0,0x3E0},{0x3E2,0x3E2},
{0x3E4,0x3E4},{0x3E6,0x3E6},{0x3E8,0x3E8},{0x3EA,0x3EA},{0x3EC,0x3EC},{0x3EE,0x3EE},
{0x3F4,0x3F4},{0x3F7,0x3F7},{0x3F9,0x3FA},{0x3FD,0x42F},{0x460,0x460},{0x462,0x462},
{0x464,0x464},{0x466,0x466},{0x468,0x468},{0x46A,0x46A},{0x46C,0x46C},{0x46E,0x46E},
{0x470,0x470},{0x472,0x472},{0x474,0x474},{0x476,0x476},{0x478,0x478},{0x47A,0x47A},
{0x47C,0x47C},{0x47E,0x47E},{0x480,0x480},{0x48A,0x48A},{0x48C,0x48C},{0x48E,0x48E},
{0x490,0x490},{0x492,0x492},{0x494,0x494},{0x496,0x496},{0x498,0x498},{0x49A,0x49A},
{0x49C,0x49C},{0x49E,0x49E},{0x4A0,0x4A0},{0x4A2,0x4A2},{0x4A4,0x4A4},{0x4A6,0x4A6},
{0x4A8,0x4A8},{0x4AA,0x4AA},{0x4AC,0x4AC},{0x4AE,0x4AE},{0x4B0,0x4B0},{0x4B2,0x4B2},
{0x4B4,0x4B4},{0x4B6,0x4B6},{0x4B8,0x4B8},{0x4BA,0x4BA},{0x4BC,0x4BC},{0x4BE,0x4BE},
{0x4C0,0x4C1},{0x4C3,0x4C3},{0x4C5,0x4C5},{0x4C7,0x4C7},{0x4C9,0x4C9},{0x4CB,0x4CB},
{0x4CD,0x4CD},{0x4D0,0x4D0},{0x4D2,0x4D2},{0x4D4,0x4D4},{0x4D6,0x4D6},{0x4D8,0x4D8},
{0x4DA,0x4DA},{0x4DC,0x4DC},{0x4DE,0x4DE},{0x4E0,0x4E0},{0x4E2,0x4E2},{0x4E4,0x4E4},
{0x4E6,0x4E6},{0x4E8,0x4E8},{0x4EA,0x4EA},{0x4EC,0x4EC},{0x4EE,0x4EE},{0x4F0,0x4F0},
{0x4F2,0x4F2},{0x4F4,0x4F4},{0x4F6,0x4F6},{0x4F8,0x4F8},{0x4FA,0x4FA},{0x4FC,0x4FC},
{0x4FE,0x4FE},{0x500,0x500},{0x502,0x502},{0x504,0x504},{0x506,0x506},{0x508,0x508},
{0x50A,0x50A},{0x50C,0x50C},{0x50E,0x50E},{0x510,0x510},{0x512,0x512},{0x514,0x514},
{0x516,0x516},{0x518,0x518},{0x51A,0x51A},{0x51C,0x51C},{0x51E,0x51E},{0x520,0x520},
{0x522,0x522},{0x524,0x524},{0x526,0x526},{0x528,0x528},{0x52A,0x52A},{0x52C,0x52C},
{0x52E,0x52E},{0x531,0x556},{0x10A0,0x10C5},{0x10C7,0x10C7},{0x10CD,0x10CD},{0x13A0,0x13F5},
{0x1C90,0x1CBA},{0x1CBD,0x1CBF},{0x1E00,0x1E00},{0x1E02,0x1E02},{0x1E04,0x1E04},{0x1E06,0x1E06},
{0x1E08,0x1E08},{0x1E0A,0x1E0A},{0x1E0C,0x1E0C},{0x1E0E,0x1E0E},{0x1E10,0x1E10},{0x1E12,0x1E12},
{0x1E14,0x1E14},{0x1E16,0x1E16},{0x1E18,0x1E18},{0x1E1A,0x1E1A},{0x1E1C,0x1E1C},{0x1E1E,0x1E1E},
{0x1E20,0x1E20},{0x1E22,0x1E22},{0x1E24,0x1E24},{0x1E26,0x1E26},{0x1E28,0x1E28},{0x1E2A,0x1E2A},
{0x1E2C,0x1E2C},{0x1E2E,0x1E2E},{0x1E30,0x1E30},{0x1E32,0x1E32},{0x1E34,0x1E34},{0x1E36,0x1E36},
{0x1E38,0x1E38},{0x1E3A,0x1E3A},{0x1E3C,0x1E3C},{0x1E3E,0x1E3E},{0x1E40,0x1E40},{0x1E42,0x1E42},
{0x1E44,0x1E44},{0x1E46,0x1E46},{0x1E48,0x1E48},{0x1E4A,0x1E4A},{0x1E4C,0x1E4C},{0x1E4E,0x1E4E},
{0x1E50,0x1E50},{0x1E52,0x1E52},{0x1E54,0x1E54},{0x1E56,0x1E56},{0x1E58,0x1E58},{0x1E5A,0x1E5A},
{0x1E5C,0x1E5C},{0x1E5E,0x1E5E},{0x1E60,0x1E60},{0x1E62,0x1E62},{0x1E64,0x1E64},{0x1E66,0x1E66},
{0x1E68,0x1E68},{0x1E6A,0x1E6A},{0x1E6C,0x1E6C},{0x1E6E,0x1E6E},{0x1E70,0x1E70},{0x1E72,0x1E72},
{0x1E74,0x1E74},{0x1E76,0x1E76},{0x1E78,0x1E78},{0x1E7A,0x1E7A},{0x1E7C,0x1E7C},{0x1E7E,0x1E7E},
{0x1E80,0x1E80},{0x1E82,0x1E82},{0x1E84,0x1E84},{0x1E86,0x1E86},{0x1E88,0x1E88},{0x1E8A,0x1E8A},
{0x1E8C,0x1E8C},{0x1E8E,0x1E8E},{0x1E90,0x1E90},{0x1E92,0x1E92},{0x1E94,0x1E94},{0x1E9E,0x1E9E},
{0x1EA0,0x1EA0},{0x1EA2,0x1EA2},{0x1EA4,0x1EA4},{0x1EA6,0x1EA6},{0x1EA8,0x1EA8},{0x1EAA,0x1EAA},
{0x1EAC,0x1EAC},{0x1EAE,0x1EAE},{0x1EB0,0x1EB0},{0x1EB2,0x1EB2},{0x1EB4,0x1EB4},{0x1EB6,0x1EB6},
{0x1EB8,0x1EB8},{0x1EBA,0x1EBA},{0x1EBC,0x1EBC},{0x1EBE,0x1EBE},{0x1EC0,0x1EC0},{0x1EC2,0x1EC2},
{0x1EC4,0x1EC4},{0x1EC6,0x1EC6},{0x1EC8,0x1EC8},{0x1ECA,0x1ECA},{0x1ECC,0x1ECC},{0x1ECE,0x1ECE},
{0x1ED0,0x1ED0},{0x1ED2,0x1ED2},{0x1ED4,0x1ED4},{0x1ED6,0x1ED6},{0x1ED8,0x1ED8},{0x1EDA,0x1EDA},
{0x1EDC,0x1EDC},{0x1EDE,0x1EDE},{0x1EE0,0x1EE0},{0x1EE2,0x1EE2},{0x1EE4,0x1EE4},{0x1EE6,0x1EE6},
{0x1EE8,0x1EE8},{0x1EEA,0x1EEA},{0x1EEC,0x1EEC},{0x1EEE,0x1EEE},{0x1EF0,0x1EF0},{0x1EF2,0x1EF2},
{0x1EF4,0x1EF4},{0x1EF6,0x1EF6},{0x1EF8,0x1EF8},{0x1EFA,0x1EFA},{0x1EFC,0x1EFC},{0x1EFE,0x1EFE},
{0x1F08,0x1F0F},{0x1F18,0x1F1D},{0x1F28,0x1F2F},{0x1F38,0x1F3F},{0x1F48,0x1F4D},{0x1F59,0x1F59},
{0x1F5B,0x1F5B},{0x1F5D,0x1F5D},{0x1F5F,0x1F5F},{0x1F68,0x1F6F},{0x1F88,0x1F8F},{0x1F98,0x1F9F},
{0x1FA8,0x1FAF},{0x1FB8,0x1FBC},{0x1FC8,0x1FCC},{0x1FD8,0x1FDB},{0x1FE8,0x1FEC},{0x1FF8,0x1FFC},
{0x2102,0x2102},{0x2107,0x2107},{0x210B,0x210D},{0x2110,0x2112},{0x2115,0x2115},{0x2119,0x211D},
{0x2124,0x2124},{0x2126,0x2126},{0x2128,0x2128},{0x212A,0x212D},{0x2130,0x2133},{0x213E,0x213F},
{0x2145,0x2145},{0x2183,0x2183},{0x2C00,0x2C2E},{0x2C60,0x2C60},{0x2C62,0x2C64},{0x2C67,0x2C67},
{0x2C69,0x2C69},{0x2C6B,0x2C6B},{0x2C6D,0x2C70},{0x2C72,0x2C72},{0x2C75,0x2C75},{0x2C7E,0x2C80},
{0x2C82,0x2C82},{0x2C84,0x2C84},{0x2C86,0x2C86},{0x2C88,0x2C88},{0x2C8A,0x2C8A},{0x2C8C,0x2C8C},
{0x2C8E,0x2C8E},{0x2C90,0x2C90},{0x2C92,0x2C92},{0x2C94,0x2C94},{0x2C96,0x2C96},{0x2C98,0x2C98},
{0x2C9A,0x2C9A},{0x2C9C,0x2C9C},{0x2C9E,0x2C9E},{0x2CA0,0x2CA0},{0x2CA2,0x2CA2},{0x2CA4,0x2CA4},
{0x2CA6,0x2CA6},{0x2CA8,0x2CA8},{0x2CAA,0x2CAA},{0x2CAC,0x2CAC},{0x2CAE,0x2CAE},{0x2CB0,0x2CB0},
{0x2CB2,0x2CB2},{0x2CB4,0x2CB4},{0x2CB6,0x2CB6},{0x2CB8,0x2CB8},{0x2CBA,0x2CBA},{0x2CBC,0x2CBC},
{0x2CBE,0x2CBE},{0x2CC0,0x2CC0},{0x2CC2,0x2CC2},{0x2CC4,0x2CC4},{0x2CC6,0x2CC6},{0x2CC8,0x2CC8},
{0x2CCA,0x2CCA},{0x2CCC,0x2CCC},{0x2CCE,0x2CCE},{0x2CD0,0x2CD0},{0x2CD2,0x2CD2},{0x2CD4,0x2CD4},
{0x2CD6,0x2CD6},{0x2CD8,0x2CD8},{0x2CDA,0x2CDA},{0x2CDC,0x2CDC},{0x2CDE,0x2CDE},{0x2CE0,0x2CE0},
{0x2CE2,0x2CE2},{0x2CEB,0x2CEB},{0x2CED,0x2CED},{0x2CF2,0x2CF2},{0xA640,0xA640},{0xA642,0xA642},
{0xA644,0xA644},{0xA646,0xA646},{0xA648,0xA648},{0xA64A,0xA64A},{0xA64C,0xA64C},{0xA64E,0xA64E},
{0xA650,0xA650},{0xA652,0xA652},{0xA654,0xA654},{0xA656,0xA656},{0xA658,0xA658},{0xA65A,0xA65A},
{0xA65C,0xA65C},{0xA65E,0xA65E},{0xA660,0xA660},{0xA662,0xA662},{0xA664,0xA664},{0xA666,0xA666},
{0xA668,0xA668},{0xA66A,0xA66A},{0xA66C,0xA66C},{0xA680,0xA680},{0xA682,0xA682},{0xA684,0xA684},
{0xA686,0xA686},{0xA688,0xA688},{0xA68A,0xA68A},{0xA68C,0xA68C},{0xA68E,0xA68E},{0xA690,0xA690},
{0xA692,0xA692},{0xA694,0xA694},{0xA696,0xA696},{0xA698,0xA698},{0xA69A,0xA69A},{0xA722,0xA722},
{0xA724,0xA724},{0xA726,0xA726},{0xA728,0xA728},{0xA72A,0xA72A},{0xA72C,0xA72C},{0xA72E,0xA72E},
{0xA732,0xA732},{0xA734,0xA734},{0xA736,0xA736},{0xA738,0xA738},{0xA73A,0xA73A},{0xA73C,0xA73C},
{0xA73E,0xA73E},{0xA740,0xA740},{0xA742,0xA742},{0xA744,0xA744},{0xA746,0xA746},{0xA748,0xA748},
{0xA74A,0xA74A},{0xA74C,0xA74C},{0xA74E,0xA74E},{0xA750,0xA750},{0xA752,0xA752},{0xA754,0xA754},
{0xA756,0xA756},{0xA758,0xA758},{0xA75A,0xA75A},{0xA75C,0xA75C},{0xA75E,0xA75E},{0xA760,0xA760},
{0xA762,0xA762},{0xA764,0xA764},{0xA766,0xA766},{0xA768,0xA768},{0xA76A,0xA76A},{0xA76C,0xA76C},
{0xA76E,0xA76E},{0xA779,0xA779},{0xA77B,0xA77B},{0xA77D,0xA77E},{0xA780,0xA780},{0xA782,0xA782},
{0xA784,0xA784},{0xA786,0xA786},{0xA78B,0xA78B},{0xA78D,0xA78D},{0xA790,0xA790},{0xA792,0xA792},
{0xA796,0xA796},{0xA798,0xA798},{0xA79A,0xA79A},{0xA79C,0xA79C},{0xA79E,0xA79E},{0xA7A0,0xA7A0},
{0xA7A2,0xA7A2},{0xA7A4,0xA7A4},{0xA7A6,0xA7A6},{0xA7A8,0xA7A8},{0xA7AA,0xA7AE},{0xA7B0,0xA7B4},
{0xA7B6,0xA7B6},{0xA7B8,0xA7B8},{0xA7BA,0xA7BA},{0xA7BC,0xA7BC},{0xA7BE,0xA7BE},{0xA7C2,0xA7C2},
{0xA7C4,0xA7C7},{0xA7C9,0xA7C9},{0xA7F5,0xA7F5},{0xFF21,0xFF3A},{0x10400,0x10427},{0x104B0,0x104D3},
{0x10C80,0x10CB2},{0x118A0,0x118BF},{0x16E40,0x16E5F},{0x1D400,0x1D419},{0x1D434,0x1D44D},{0x1D468,0x1D481},
{0x1D49C,0x1D49C},{0x1D49E,0x1D49F},{0x1D4A2,0x1D4A2},{0x1D4A5,0x1D4A6},{0x1D4A9,0x1D4AC},{0x1D4AE,0x1D4B5},
{0x1D4D0,0x1D4E9},{0x1D504,0x1D505},{0x1D507,0x1D50A},{0x1D50D,0x1D514},{0x1D516,0x1D51C},{0x1D538,0x1D539},
{0x1D53B,0x1D53E},{0x1D540,0x1D544},{0x1D546,0x1D546},{0x1D54A,0x1D550},{0x1D56C,0x1D585},{0x1D5A0,0x1D5B9},
{0x1D5D4,0x1D5ED},{0x1D608,0x1D621},{0x1D63C,0x1D655},{0x1D670,0x1D689},{0x1D6A8,0x1D6C0},{0x1D6E2,0x1D6FA},
{0x1D71C,0x1D734},{0x1D756,0x1D76E},{0x1D790,0x1D7A8},{0x1D7CA,0x1D7CA},{0x1E900,0x1E921},
};
static const int uni_U_n = 641;
static const uint32_t uni_X[][2] = {
{0xAA,0xAA},{0xBA,0xBA},{0x1BB,0x1BB},{0x1C0,0x1C3},{0x294,0x294},{0x2B0,0x2C1},
{0x2C6,0x2D1},{0x2E0,0x2E4},{0x2EC,0x2EC},{0x2EE,0x2EE},{0x300,0x36F},{0x374,0x374},
{0x37A,0x37A},{0x483,0x489},{0x559,0x559},{0x591,0x5BD},{0x5BF,0x5BF},{0x5C1,0x5C2},
{0x5C4,0x5C5},{0x5C7,0x5C7},{0x5D0,0x5EA},{0x5EF,0x5F2},{0x610,0x61A},{0x620,0x65F},
{0x66E,0x6D3},{0x6D5,0x6DC},{0x6DF,0x6E8},{0x6EA,0x6EF},{0x6FA,0x6FC},{0x6FF,0x6FF},
{0x710,0x74A},{0x74D,0x7B1},{0x7CA,0x7F5},{0x7FA,0x7FA},{0x7FD,0x7FD},{0x800,0x82D},
{0x840,0x85B},{0x860,0x86A},{0x8A0,0x8B4},{0x8B6,0x8C7},{0x8D3,0x8E1},{0x8E3,0x963},
{0x971,0x983},{0x985,0x98C},{0x98F,0x990},{0x993,0x9A8},{0x9AA,0x9B0},{0x9B2,0x9B2},
{0x9B6,0x9B9},{0x9BC,0x9C4},{0x9C7,0x9C8},{0x9CB,0x9CE},{0x9D7,0x9D7},{0x9DC,0x9DD},
{0x9DF,0x9E3},{0x9F0,0x9F1},{0x9FC,0x9FC},{0x9FE,0x9FE},{0xA01,0xA03},{0xA05,0xA0A},
{0xA0F,0xA10},{0xA13,0xA28},{0xA2A,0xA30},{0xA32,0xA33},{0xA35,0xA36},{0xA38,0xA39},
{0xA3C,0xA3C},{0xA3E,0xA42},{0xA47,0xA48},{0xA4B,0xA4D},{0xA51,0xA51},{0xA59,0xA5C},
{0xA5E,0xA5E},{0xA70,0xA75},{0xA81,0xA83},{0xA85,0xA8D},{0xA8F,0xA91},{0xA93,0xAA8},
{0xAAA,0xAB0},{0xAB2,0xAB3},{0xAB5,0xAB9},{0xABC,0xAC5},{0xAC7,0xAC9},{0xACB,0xACD},
{0xAD0,0xAD0},{0xAE0,0xAE3},{0xAF9,0xAFF},{0xB01,0xB03},{0xB05,0xB0C},{0xB0F,0xB10},
{0xB13,0xB28},{0xB2A,0xB30},{0xB32,0xB33},{0xB35,0xB39},{0xB3C,0xB44},{0xB47,0xB48},
{0xB4B,0xB4D},{0xB55,0xB57},{0xB5C,0xB5D},{0xB5F,0xB63},{0xB71,0xB71},{0xB82,0xB83},
{0xB85,0xB8A},{0xB8E,0xB90},{0xB92,0xB95},{0xB99,0xB9A},{0xB9C,0xB9C},{0xB9E,0xB9F},
{0xBA3,0xBA4},{0xBA8,0xBAA},{0xBAE,0xBB9},{0xBBE,0xBC2},{0xBC6,0xBC8},{0xBCA,0xBCD},
{0xBD0,0xBD0},{0xBD7,0xBD7},{0xC00,0xC0C},{0xC0E,0xC10},{0xC12,0xC28},{0xC2A,0xC39},
{0xC3D,0xC44},{0xC46,0xC48},{0xC4A,0xC4D},{0xC55,0xC56},{0xC58,0xC5A},{0xC60,0xC63},
{0xC80,0xC83},{0xC85,0xC8C},{0xC8E,0xC90},{0xC92,0xCA8},{0xCAA,0xCB3},{0xCB5,0xCB9},
{0xCBC,0xCC4},{0xCC6,0xCC8},{0xCCA,0xCCD},{0xCD5,0xCD6},{0xCDE,0xCDE},{0xCE0,0xCE3},
{0xCF1,0xCF2},{0xD00,0xD0C},{0xD0E,0xD10},{0xD12,0xD44},{0xD46,0xD48},{0xD4A,0xD4E},
{0xD54,0xD57},{0xD5F,0xD63},{0xD7A,0xD7F},{0xD81,0xD83},{0xD85,0xD96},{0xD9A,0xDB1},
{0xDB3,0xDBB},{0xDBD,0xDBD},{0xDC0,0xDC6},{0xDCA,0xDCA},{0xDCF,0xDD4},{0xDD6,0xDD6},
{0xDD8,0xDDF},{0xDF2,0xDF3},{0xE01,0xE3A},{0xE40,0xE4E},{0xE81,0xE82},{0xE84,0xE84},
{0xE86,0xE8A},{0xE8C,0xEA3},{0xEA5,0xEA5},{0xEA7,0xEBD},{0xEC0,0xEC4},{0xEC6,0xEC6},
{0xEC8,0xECD},{0xEDC,0xEDF},{0xF00,0xF00},{0xF18,0xF19},{0xF35,0xF35},{0xF37,0xF37},
{0xF39,0xF39},{0xF3E,0xF47},{0xF49,0xF6C},{0xF71,0xF84},{0xF86,0xF97},{0xF99,0xFBC},
{0xFC6,0xFC6},{0x1000,0x103F},{0x1050,0x108F},{0x109A,0x109D},{0x10FC,0x10FC},{0x1100,0x1248},
{0x124A,0x124D},{0x1250,0x1256},{0x1258,0x1258},{0x125A,0x125D},{0x1260,0x1288},{0x128A,0x128D},
{0x1290,0x12B0},{0x12B2,0x12B5},{0x12B8,0x12BE},{0x12C0,0x12C0},{0x12C2,0x12C5},{0x12C8,0x12D6},
{0x12D8,0x1310},{0x1312,0x1315},{0x1318,0x135A},{0x135D,0x135F},{0x1380,0x138F},{0x1401,0x166C},
{0x166F,0x167F},{0x1681,0x169A},{0x16A0,0x16EA},{0x16F1,0x16F8},{0x1700,0x170C},{0x170E,0x1714},
{0x1720,0x1734},{0x1740,0x1753},{0x1760,0x176C},{0x176E,0x1770},{0x1772,0x1773},{0x1780,0x17D3},
{0x17D7,0x17D7},{0x17DC,0x17DD},{0x180B,0x180D},{0x1820,0x1878},{0x1880,0x18AA},{0x18B0,0x18F5},
{0x1900,0x191E},{0x1920,0x192B},{0x1930,0x193B},{0x1950,0x196D},{0x1970,0x1974},{0x1980,0x19AB},
{0x19B0,0x19C9},{0x1A00,0x1A1B},{0x1A20,0x1A5E},{0x1A60,0x1A7C},{0x1A7F,0x1A7F},{0x1AA7,0x1AA7},
{0x1AB0,0x1AC0},{0x1B00,0x1B4B},{0x1B6B,0x1B73},{0x1B80,0x1BAF},{0x1BBA,0x1BF3},{0x1C00,0x1C37},
{0x1C4D,0x1C4F},{0x1C5A,0x1C7D},{0x1CD0,0x1CD2},{0x1CD4,0x1CFA},{0x1D2C,0x1D6A},{0x1D78,0x1D78},
{0x1D9B,0x1DF9},{0x1DFB,0x1DFF},{0x2071,0x2071},{0x207F,0x207F},{0x2090,0x209C},{0x20D0,0x20F0},
{0x2135,0x2138},{0x2C7C,0x2C7D},{0x2CEF,0x2CF1},{0x2D30,0x2D67},{0x2D6F,0x2D6F},{0x2D7F,0x2D96},
{0x2DA0,0x2DA6},{0x2DA8,0x2DAE},{0x2DB0,0x2DB6},{0x2DB8,0x2DBE},{0x2DC0,0x2DC6},{0x2DC8,0x2DCE},
{0x2DD0,0x2DD6},{0x2DD8,0x2DDE},{0x2DE0,0x2DFF},{0x2E2F,0x2E2F},{0x3005,0x3006},{0x302A,0x302F},
{0x3031,0x3035},{0x303B,0x303C},{0x3041,0x3096},{0x3099,0x309A},{0x309D,0x309F},{0x30A1,0x30FA},
{0x30FC,0x30FF},{0x3105,0x312F},{0x3131,0x318E},{0x31A0,0x31BF},{0x31F0,0x31FF},{0x3400,0x4DBF},
{0x4E00,0x9FFC},{0xA000,0xA48C},{0xA4D0,0xA4FD},{0xA500,0xA60C},{0xA610,0xA61F},{0xA62A,0xA62B},
{0xA66E,0xA672},{0xA674,0xA67D},{0xA67F,0xA67F},{0xA69C,0xA6E5},{0xA6F0,0xA6F1},{0xA717,0xA71F},
{0xA770,0xA770},{0xA788,0xA788},{0xA78F,0xA78F},{0xA7F7,0xA7F9},{0xA7FB,0xA827},{0xA82C,0xA82C},
{0xA840,0xA873},{0xA880,0xA8C5},{0xA8E0,0xA8F7},{0xA8FB,0xA8FB},{0xA8FD,0xA8FF},{0xA90A,0xA92D},
{0xA930,0xA953},{0xA960,0xA97C},{0xA980,0xA9C0},{0xA9CF,0xA9CF},{0xA9E0,0xA9EF},{0xA9FA,0xA9FE},
{0xAA00,0xAA36},{0xAA40,0xAA4D},{0xAA60,0xAA76},{0xAA7A,0xAAC2},{0xAADB,0xAADD},{0xAAE0,0xAAEF},
{0xAAF2,0xAAF6},{0xAB01,0xAB06},{0xAB09,0xAB0E},{0xAB11,0xAB16},{0xAB20,0xAB26},{0xAB28,0xAB2E},
{0xAB5C,0xAB5F},{0xAB69,0xAB69},{0xABC0,0xABEA},{0xABEC,0xABED},{0xAC00,0xD7A3},{0xD7B0,0xD7C6},
{0xD7CB,0xD7FB},{0xF900,0xFA6D},{0xFA70,0xFAD9},{0xFB1D,0xFB28},{0xFB2A,0xFB36},{0xFB38,0xFB3C},
{0xFB3E,0xFB3E},{0xFB40,0xFB41},{0xFB43,0xFB44},{0xFB46,0xFBB1},{0xFBD3,0xFD3D},{0xFD50,0xFD8F},
{0xFD92,0xFDC7},{0xFDF0,0xFDFB},{0xFE00,0xFE0F},{0xFE20,0xFE2F},{0xFE70,0xFE74},{0xFE76,0xFEFC},
{0xFF66,0xFFBE},{0xFFC2,0xFFC7},{0xFFCA,0xFFCF},{0xFFD2,0xFFD7},{0xFFDA,0xFFDC},{0x10000,0x1000B},
{0x1000D,0x10026},{0x10028,0x1003A},{0x1003C,0x1003D},{0x1003F,0x1004D},{0x10050,0x1005D},{0x10080,0x100FA},
{0x101FD,0x101FD},{0x10280,0x1029C},{0x102A0,0x102D0},{0x102E0,0x102E0},{0x10300,0x1031F},{0x1032D,0x10340},
{0x10342,0x10349},{0x10350,0x1037A},{0x10380,0x1039D},{0x103A0,0x103C3},{0x103C8,0x103CF},{0x10450,0x1049D},
{0x10500,0x10527},{0x10530,0x10563},{0x10600,0x10736},{0x10740,0x10755},{0x10760,0x10767},{0x10800,0x10805},
{0x10808,0x10808},{0x1080A,0x10835},{0x10837,0x10838},{0x1083C,0x1083C},{0x1083F,0x10855},{0x10860,0x10876},
{0x10880,0x1089E},{0x108E0,0x108F2},{0x108F4,0x108F5},{0x10900,0x10915},{0x10920,0x10939},{0x10980,0x109B7},
{0x109BE,0x109BF},{0x10A00,0x10A03},{0x10A05,0x10A06},{0x10A0C,0x10A13},{0x10A15,0x10A17},{0x10A19,0x10A35},
{0x10A38,0x10A3A},{0x10A3F,0x10A3F},{0x10A60,0x10A7C},{0x10A80,0x10A9C},{0x10AC0,0x10AC7},{0x10AC9,0x10AE6},
{0x10B00,0x10B35},{0x10B40,0x10B55},{0x10B60,0x10B72},{0x10B80,0x10B91},{0x10C00,0x10C48},{0x10D00,0x10D27},
{0x10E80,0x10EA9},{0x10EAB,0x10EAC},{0x10EB0,0x10EB1},{0x10F00,0x10F1C},{0x10F27,0x10F27},{0x10F30,0x10F50},
{0x10FB0,0x10FC4},{0x10FE0,0x10FF6},{0x11000,0x11046},{0x1107F,0x110BA},{0x110D0,0x110E8},{0x11100,0x11134},
{0x11144,0x11147},{0x11150,0x11173},{0x11176,0x11176},{0x11180,0x111C4},{0x111C9,0x111CC},{0x111CE,0x111CF},
{0x111DA,0x111DA},{0x111DC,0x111DC},{0x11200,0x11211},{0x11213,0x11237},{0x1123E,0x1123E},{0x11280,0x11286},
{0x11288,0x11288},{0x1128A,0x1128D},{0x1128F,0x1129D},{0x1129F,0x112A8},{0x112B0,0x112EA},{0x11300,0x11303},
{0x11305,0x1130C},{0x1130F,0x11310},{0x11313,0x11328},{0x1132A,0x11330},{0x11332,0x11333},{0x11335,0x11339},
{0x1133B,0x11344},{0x11347,0x11348},{0x1134B,0x1134D},{0x11350,0x11350},{0x11357,0x11357},{0x1135D,0x11363},
{0x11366,0x1136C},{0x11370,0x11374},{0x11400,0x1144A},{0x1145E,0x11461},{0x11480,0x114C5},{0x114C7,0x114C7},
{0x11580,0x115B5},{0x115B8,0x115C0},{0x115D8,0x115DD},{0x11600,0x11640},{0x11644,0x11644},{0x11680,0x116B8},
{0x11700,0x1171A},{0x1171D,0x1172B},{0x11800,0x1183A},{0x118FF,0x11906},{0x11909,0x11909},{0x1190C,0x11913},
{0x11915,0x11916},{0x11918,0x11935},{0x11937,0x11938},{0x1193B,0x11943},{0x119A0,0x119A7},{0x119AA,0x119D7},
{0x119DA,0x119E1},{0x119E3,0x119E4},{0x11A00,0x11A3E},{0x11A47,0x11A47},{0x11A50,0x11A99},{0x11A9D,0x11A9D},
{0x11AC0,0x11AF8},{0x11C00,0x11C08},{0x11C0A,0x11C36},{0x11C38,0x11C40},{0x11C72,0x11C8F},{0x11C92,0x11CA7},
{0x11CA9,0x11CB6},{0x11D00,0x11D06},{0x11D08,0x11D09},{0x11D0B,0x11D36},{0x11D3A,0x11D3A},{0x11D3C,0x11D3D},
{0x11D3F,0x11D47},{0x11D60,0x11D65},{0x11D67,0x11D68},{0x11D6A,0x11D8E},{0x11D90,0x11D91},{0x11D93,0x11D98},
{0x11EE0,0x11EF6},{0x11FB0,0x11FB0},{0x12000,0x12399},{0x12480,0x12543},{0x13000,0x1342E},{0x14400,0x14646},
{0x16800,0x16A38},{0x16A40,0x16A5E},{0x16AD0,0x16AED},{0x16AF0,0x16AF4},{0x16B00,0x16B36},{0x16B40,0x16B43},
{0x16B63,0x16B77},{0x16B7D,0x16B8F},{0x16F00,0x16F4A},{0x16F4F,0x16F87},{0x16F8F,0x16F9F},{0x16FE0,0x16FE1},
{0x16FE3,0x16FE4},{0x16FF0,0x16FF1},{0x17000,0x187F7},{0x18800,0x18CD5},{0x18D00,0x18D08},{0x1B000,0x1B11E},
{0x1B150,0x1B152},{0x1B164,0x1B167},{0x1B170,0x1B2FB},{0x1BC00,0x1BC6A},{0x1BC70,0x1BC7C},{0x1BC80,0x1BC88},
{0x1BC90,0x1BC99},{0x1BC9D,0x1BC9E},{0x1D165,0x1D169},{0x1D16D,0x1D172},{0x1D17B,0x1D182},{0x1D185,0x1D18B},
{0x1D1AA,0x1D1AD},{0x1D242,0x1D244},{0x1DA00,0x1DA36},{0x1DA3B,0x1DA6C},{0x1DA75,0x1DA75},{0x1DA84,0x1DA84},
{0x1DA9B,0x1DA9F},{0x1DAA1,0x1DAAF},{0x1E000,0x1E006},{0x1E008,0x1E018},{0x1E01B,0x1E021},{0x1E023,0x1E024},
{0x1E026,0x1E02A},{0x1E100,0x1E12C},{0x1E130,0x1E13D},{0x1E14E,0x1E14E},{0x1E2C0,0x1E2EF},{0x1E800,0x1E8C4},
{0x1E8D0,0x1E8D6},{0x1E944,0x1E94B},{0x1EE00,0x1EE03},{0x1EE05,0x1EE1F},{0x1EE21,0x1EE22},{0x1EE24,0x1EE24},
{0x1EE27,0x1EE27},{0x1EE29,0x1EE32},{0x1EE34,0x1EE37},{0x1EE39,0x1EE39},{0x1EE3B,0x1EE3B},{0x1EE42,0x1EE42},
{0x1EE47,0x1EE47},{0x1EE49,0x1EE49},{0x1EE4B,0x1EE4B},{0x1EE4D,0x1EE4F},{0x1EE51,0x1EE52},{0x1EE54,0x1EE54},
{0x1EE57,0x1EE57},{0x1EE59,0x1EE59},{0x1EE5B,0x1EE5B},{0x1EE5D,0x1EE5D},{0x1EE5F,0x1EE5F},{0x1EE61,0x1EE62},
{0x1EE64,0x1EE64},{0x1EE67,0x1EE6A},{0x1EE6C,0x1EE72},{0x1EE74,0x1EE77},{0x1EE79,0x1EE7C},{0x1EE7E,0x1EE7E},
{0x1EE80,0x1EE89},{0x1EE8B,0x1EE9B},{0x1EEA1,0x1EEA3},{0x1EEA5,0x1EEA9},{0x1EEAB,0x1EEBB},{0x20000,0x2A6DD},
{0x2A700,0x2B734},{0x2B740,0x2B81D},{0x2B820,0x2CEA1},{0x2CEB0,0x2EBE0},{0x2F800,0x2FA1D},{0x30000,0x3134A},
{0xE0100,0xE01EF},
};
static const int uni_X_n = 595;
static inline int is_U(uint32_t c){ return uni_in(uni_U,uni_U_n,c); }
static inline int is_X(uint32_t c){ return uni_in(uni_X,uni_X_n,c); }
#endif