Coverage for src / charset_normalizer / constant.py: 98%

1from __future__ import annotations 

2 

3from codecs import BOM_UTF8, BOM_UTF16_BE, BOM_UTF16_LE, BOM_UTF32_BE, BOM_UTF32_LE 

4from encodings.aliases import aliases 

5from re import IGNORECASE 

6from re import compile as re_compile 

7 

8# Contain for each eligible encoding a list of/item bytes SIG/BOM 

9ENCODING_MARKS: dict[str, bytes | list[bytes]] = { 

10 "utf_8": BOM_UTF8, 

11 "utf_7": [ 

12 b"\x2b\x2f\x76\x38", 

13 b"\x2b\x2f\x76\x39", 

14 b"\x2b\x2f\x76\x2b", 

15 b"\x2b\x2f\x76\x2f", 

16 ], 

17 "gb18030": b"\x84\x31\x95\x33", 

18 "utf_32": [BOM_UTF32_BE, BOM_UTF32_LE], 

19 "utf_16": [BOM_UTF16_BE, BOM_UTF16_LE], 

20} 

21 

22TOO_SMALL_SEQUENCE: int = 32 

23TOO_BIG_SEQUENCE: int = int(10e6) 

24 

25UTF8_MAXIMAL_ALLOCATION: int = 1_112_064 

26 

27# Up-to-date Unicode ucd/17.0.0 

28UNICODE_RANGES_COMBINED: dict[str, range] = { 

29 "Control character": range(32), 

30 "Basic Latin": range(32, 128), 

31 "Latin-1 Supplement": range(128, 256), 

32 "Latin Extended-A": range(256, 384), 

33 "Latin Extended-B": range(384, 592), 

34 "IPA Extensions": range(592, 688), 

35 "Spacing Modifier Letters": range(688, 768), 

36 "Combining Diacritical Marks": range(768, 880), 

37 "Greek and Coptic": range(880, 1024), 

38 "Cyrillic": range(1024, 1280), 

39 "Cyrillic Supplement": range(1280, 1328), 

40 "Armenian": range(1328, 1424), 

41 "Hebrew": range(1424, 1536), 

42 "Arabic": range(1536, 1792), 

43 "Syriac": range(1792, 1872), 

44 "Arabic Supplement": range(1872, 1920), 

45 "Thaana": range(1920, 1984), 

46 "NKo": range(1984, 2048), 

47 "Samaritan": range(2048, 2112), 

48 "Mandaic": range(2112, 2144), 

49 "Syriac Supplement": range(2144, 2160), 

50 "Arabic Extended-B": range(2160, 2208), 

51 "Arabic Extended-A": range(2208, 2304), 

52 "Devanagari": range(2304, 2432), 

53 "Bengali": range(2432, 2560), 

54 "Gurmukhi": range(2560, 2688), 

55 "Gujarati": range(2688, 2816), 

56 "Oriya": range(2816, 2944), 

57 "Tamil": range(2944, 3072), 

58 "Telugu": range(3072, 3200), 

59 "Kannada": range(3200, 3328), 

60 "Malayalam": range(3328, 3456), 

61 "Sinhala": range(3456, 3584), 

62 "Thai": range(3584, 3712), 

63 "Lao": range(3712, 3840), 

64 "Tibetan": range(3840, 4096), 

65 "Myanmar": range(4096, 4256), 

66 "Georgian": range(4256, 4352), 

67 "Hangul Jamo": range(4352, 4608), 

68 "Ethiopic": range(4608, 4992), 

69 "Ethiopic Supplement": range(4992, 5024), 

70 "Cherokee": range(5024, 5120), 

71 "Unified Canadian Aboriginal Syllabics": range(5120, 5760), 

72 "Ogham": range(5760, 5792), 

73 "Runic": range(5792, 5888), 

74 "Tagalog": range(5888, 5920), 

75 "Hanunoo": range(5920, 5952), 

76 "Buhid": range(5952, 5984), 

77 "Tagbanwa": range(5984, 6016), 

78 "Khmer": range(6016, 6144), 

79 "Mongolian": range(6144, 6320), 

80 "Unified Canadian Aboriginal Syllabics Extended": range(6320, 6400), 

81 "Limbu": range(6400, 6480), 

82 "Tai Le": range(6480, 6528), 

83 "New Tai Lue": range(6528, 6624), 

84 "Khmer Symbols": range(6624, 6656), 

85 "Buginese": range(6656, 6688), 

86 "Tai Tham": range(6688, 6832), 

87 "Combining Diacritical Marks Extended": range(6832, 6912), 

88 "Balinese": range(6912, 7040), 

89 "Sundanese": range(7040, 7104), 

90 "Batak": range(7104, 7168), 

91 "Lepcha": range(7168, 7248), 

92 "Ol Chiki": range(7248, 7296), 

93 "Cyrillic Extended-C": range(7296, 7312), 

94 "Georgian Extended": range(7312, 7360), 

95 "Sundanese Supplement": range(7360, 7376), 

96 "Vedic Extensions": range(7376, 7424), 

97 "Phonetic Extensions": range(7424, 7552), 

98 "Phonetic Extensions Supplement": range(7552, 7616), 

99 "Combining Diacritical Marks Supplement": range(7616, 7680), 

100 "Latin Extended Additional": range(7680, 7936), 

101 "Greek Extended": range(7936, 8192), 

102 "General Punctuation": range(8192, 8304), 

103 "Superscripts and Subscripts": range(8304, 8352), 

104 "Currency Symbols": range(8352, 8400), 

105 "Combining Diacritical Marks for Symbols": range(8400, 8448), 

106 "Letterlike Symbols": range(8448, 8528), 

107 "Number Forms": range(8528, 8592), 

108 "Arrows": range(8592, 8704), 

109 "Mathematical Operators": range(8704, 8960), 

110 "Miscellaneous Technical": range(8960, 9216), 

111 "Control Pictures": range(9216, 9280), 

112 "Optical Character Recognition": range(9280, 9312), 

113 "Enclosed Alphanumerics": range(9312, 9472), 

114 "Box Drawing": range(9472, 9600), 

115 "Block Elements": range(9600, 9632), 

116 "Geometric Shapes": range(9632, 9728), 

117 "Miscellaneous Symbols": range(9728, 9984), 

118 "Dingbats": range(9984, 10176), 

119 "Miscellaneous Mathematical Symbols-A": range(10176, 10224), 

120 "Supplemental Arrows-A": range(10224, 10240), 

121 "Braille Patterns": range(10240, 10496), 

122 "Supplemental Arrows-B": range(10496, 10624), 

123 "Miscellaneous Mathematical Symbols-B": range(10624, 10752), 

124 "Supplemental Mathematical Operators": range(10752, 11008), 

125 "Miscellaneous Symbols and Arrows": range(11008, 11264), 

126 "Glagolitic": range(11264, 11360), 

127 "Latin Extended-C": range(11360, 11392), 

128 "Coptic": range(11392, 11520), 

129 "Georgian Supplement": range(11520, 11568), 

130 "Tifinagh": range(11568, 11648), 

131 "Ethiopic Extended": range(11648, 11744), 

132 "Cyrillic Extended-A": range(11744, 11776), 

133 "Supplemental Punctuation": range(11776, 11904), 

134 "CJK Radicals Supplement": range(11904, 12032), 

135 "Kangxi Radicals": range(12032, 12256), 

136 "Ideographic Description Characters": range(12272, 12288), 

137 "CJK Symbols and Punctuation": range(12288, 12352), 

138 "Hiragana": range(12352, 12448), 

139 "Katakana": range(12448, 12544), 

140 "Bopomofo": range(12544, 12592), 

141 "Hangul Compatibility Jamo": range(12592, 12688), 

142 "Kanbun": range(12688, 12704), 

143 "Bopomofo Extended": range(12704, 12736), 

144 "CJK Strokes": range(12736, 12784), 

145 "Katakana Phonetic Extensions": range(12784, 12800), 

146 "Enclosed CJK Letters and Months": range(12800, 13056), 

147 "CJK Compatibility": range(13056, 13312), 

148 "CJK Unified Ideographs Extension A": range(13312, 19904), 

149 "Yijing Hexagram Symbols": range(19904, 19968), 

150 "CJK Unified Ideographs": range(19968, 40960), 

151 "Yi Syllables": range(40960, 42128), 

152 "Yi Radicals": range(42128, 42192), 

153 "Lisu": range(42192, 42240), 

154 "Vai": range(42240, 42560), 

155 "Cyrillic Extended-B": range(42560, 42656), 

156 "Bamum": range(42656, 42752), 

157 "Modifier Tone Letters": range(42752, 42784), 

158 "Latin Extended-D": range(42784, 43008), 

159 "Syloti Nagri": range(43008, 43056), 

160 "Common Indic Number Forms": range(43056, 43072), 

161 "Phags-pa": range(43072, 43136), 

162 "Saurashtra": range(43136, 43232), 

163 "Devanagari Extended": range(43232, 43264), 

164 "Kayah Li": range(43264, 43312), 

165 "Rejang": range(43312, 43360), 

166 "Hangul Jamo Extended-A": range(43360, 43392), 

167 "Javanese": range(43392, 43488), 

168 "Myanmar Extended-B": range(43488, 43520), 

169 "Cham": range(43520, 43616), 

170 "Myanmar Extended-A": range(43616, 43648), 

171 "Tai Viet": range(43648, 43744), 

172 "Meetei Mayek Extensions": range(43744, 43776), 

173 "Ethiopic Extended-A": range(43776, 43824), 

174 "Latin Extended-E": range(43824, 43888), 

175 "Cherokee Supplement": range(43888, 43968), 

176 "Meetei Mayek": range(43968, 44032), 

177 "Hangul Syllables": range(44032, 55216), 

178 "Hangul Jamo Extended-B": range(55216, 55296), 

179 "High Surrogates": range(55296, 56192), 

180 "High Private Use Surrogates": range(56192, 56320), 

181 "Low Surrogates": range(56320, 57344), 

182 "Private Use Area": range(57344, 63744), 

183 "CJK Compatibility Ideographs": range(63744, 64256), 

184 "Alphabetic Presentation Forms": range(64256, 64336), 

185 "Arabic Presentation Forms-A": range(64336, 65024), 

186 "Variation Selectors": range(65024, 65040), 

187 "Vertical Forms": range(65040, 65056), 

188 "Combining Half Marks": range(65056, 65072), 

189 "CJK Compatibility Forms": range(65072, 65104), 

190 "Small Form Variants": range(65104, 65136), 

191 "Arabic Presentation Forms-B": range(65136, 65280), 

192 "Halfwidth and Fullwidth Forms": range(65280, 65520), 

193 "Specials": range(65520, 65536), 

194 "Linear B Syllabary": range(65536, 65664), 

195 "Linear B Ideograms": range(65664, 65792), 

196 "Aegean Numbers": range(65792, 65856), 

197 "Ancient Greek Numbers": range(65856, 65936), 

198 "Ancient Symbols": range(65936, 66000), 

199 "Phaistos Disc": range(66000, 66048), 

200 "Lycian": range(66176, 66208), 

201 "Carian": range(66208, 66272), 

202 "Coptic Epact Numbers": range(66272, 66304), 

203 "Old Italic": range(66304, 66352), 

204 "Gothic": range(66352, 66384), 

205 "Old Permic": range(66384, 66432), 

206 "Ugaritic": range(66432, 66464), 

207 "Old Persian": range(66464, 66528), 

208 "Deseret": range(66560, 66640), 

209 "Shavian": range(66640, 66688), 

210 "Osmanya": range(66688, 66736), 

211 "Osage": range(66736, 66816), 

212 "Elbasan": range(66816, 66864), 

213 "Caucasian Albanian": range(66864, 66928), 

214 "Vithkuqi": range(66928, 67008), 

215 "Todhri": range(67008, 67072), 

216 "Linear A": range(67072, 67456), 

217 "Latin Extended-F": range(67456, 67520), 

218 "Cypriot Syllabary": range(67584, 67648), 

219 "Imperial Aramaic": range(67648, 67680), 

220 "Palmyrene": range(67680, 67712), 

221 "Nabataean": range(67712, 67760), 

222 "Hatran": range(67808, 67840), 

223 "Phoenician": range(67840, 67872), 

224 "Lydian": range(67872, 67904), 

225 "Sidetic": range(67904, 67936), 

226 "Meroitic Hieroglyphs": range(67968, 68000), 

227 "Meroitic Cursive": range(68000, 68096), 

228 "Kharoshthi": range(68096, 68192), 

229 "Old South Arabian": range(68192, 68224), 

230 "Old North Arabian": range(68224, 68256), 

231 "Manichaean": range(68288, 68352), 

232 "Avestan": range(68352, 68416), 

233 "Inscriptional Parthian": range(68416, 68448), 

234 "Inscriptional Pahlavi": range(68448, 68480), 

235 "Psalter Pahlavi": range(68480, 68528), 

236 "Old Turkic": range(68608, 68688), 

237 "Old Hungarian": range(68736, 68864), 

238 "Hanifi Rohingya": range(68864, 68928), 

239 "Garay": range(68928, 69008), 

240 "Rumi Numeral Symbols": range(69216, 69248), 

241 "Yezidi": range(69248, 69312), 

242 "Arabic Extended-C": range(69312, 69376), 

243 "Old Sogdian": range(69376, 69424), 

244 "Sogdian": range(69424, 69488), 

245 "Old Uyghur": range(69488, 69552), 

246 "Chorasmian": range(69552, 69600), 

247 "Elymaic": range(69600, 69632), 

248 "Brahmi": range(69632, 69760), 

249 "Kaithi": range(69760, 69840), 

250 "Sora Sompeng": range(69840, 69888), 

251 "Chakma": range(69888, 69968), 

252 "Mahajani": range(69968, 70016), 

253 "Sharada": range(70016, 70112), 

254 "Sinhala Archaic Numbers": range(70112, 70144), 

255 "Khojki": range(70144, 70224), 

256 "Multani": range(70272, 70320), 

257 "Khudawadi": range(70320, 70400), 

258 "Grantha": range(70400, 70528), 

259 "Tulu-Tigalari": range(70528, 70656), 

260 "Newa": range(70656, 70784), 

261 "Tirhuta": range(70784, 70880), 

262 "Siddham": range(71040, 71168), 

263 "Modi": range(71168, 71264), 

264 "Mongolian Supplement": range(71264, 71296), 

265 "Takri": range(71296, 71376), 

266 "Myanmar Extended-C": range(71376, 71424), 

267 "Ahom": range(71424, 71504), 

268 "Dogra": range(71680, 71760), 

269 "Warang Citi": range(71840, 71936), 

270 "Dives Akuru": range(71936, 72032), 

271 "Nandinagari": range(72096, 72192), 

272 "Zanabazar Square": range(72192, 72272), 

273 "Soyombo": range(72272, 72368), 

274 "Unified Canadian Aboriginal Syllabics Extended-A": range(72368, 72384), 

275 "Pau Cin Hau": range(72384, 72448), 

276 "Devanagari Extended-A": range(72448, 72544), 

277 "Sharada Supplement": range(72544, 72576), 

278 "Sunuwar": range(72640, 72704), 

279 "Bhaiksuki": range(72704, 72816), 

280 "Marchen": range(72816, 72896), 

281 "Masaram Gondi": range(72960, 73056), 

282 "Gunjala Gondi": range(73056, 73136), 

283 "Tolong Siki": range(73136, 73200), 

284 "Makasar": range(73440, 73472), 

285 "Kawi": range(73472, 73568), 

286 "Lisu Supplement": range(73648, 73664), 

287 "Tamil Supplement": range(73664, 73728), 

288 "Cuneiform": range(73728, 74752), 

289 "Cuneiform Numbers and Punctuation": range(74752, 74880), 

290 "Early Dynastic Cuneiform": range(74880, 75088), 

291 "Cypro-Minoan": range(77712, 77824), 

292 "Egyptian Hieroglyphs": range(77824, 78896), 

293 "Egyptian Hieroglyph Format Controls": range(78896, 78944), 

294 "Egyptian Hieroglyphs Extended-A": range(78944, 82944), 

295 "Anatolian Hieroglyphs": range(82944, 83584), 

296 "Gurung Khema": range(90368, 90432), 

297 "Bamum Supplement": range(92160, 92736), 

298 "Mro": range(92736, 92784), 

299 "Tangsa": range(92784, 92880), 

300 "Bassa Vah": range(92880, 92928), 

301 "Pahawh Hmong": range(92928, 93072), 

302 "Kirat Rai": range(93504, 93568), 

303 "Medefaidrin": range(93760, 93856), 

304 "Beria Erfe": range(93856, 93920), 

305 "Miao": range(93952, 94112), 

306 "Ideographic Symbols and Punctuation": range(94176, 94208), 

307 "Tangut": range(94208, 100352), 

308 "Tangut Components": range(100352, 101120), 

309 "Khitan Small Script": range(101120, 101632), 

310 "Tangut Supplement": range(101632, 101760), 

311 "Tangut Components Supplement": range(101760, 101888), 

312 "Kana Extended-B": range(110576, 110592), 

313 "Kana Supplement": range(110592, 110848), 

314 "Kana Extended-A": range(110848, 110896), 

315 "Small Kana Extension": range(110896, 110960), 

316 "Nushu": range(110960, 111360), 

317 "Duployan": range(113664, 113824), 

318 "Shorthand Format Controls": range(113824, 113840), 

319 "Symbols for Legacy Computing Supplement": range(117760, 118464), 

320 "Miscellaneous Symbols Supplement": range(118464, 118528), 

321 "Znamenny Musical Notation": range(118528, 118736), 

322 "Byzantine Musical Symbols": range(118784, 119040), 

323 "Musical Symbols": range(119040, 119296), 

324 "Ancient Greek Musical Notation": range(119296, 119376), 

325 "Kaktovik Numerals": range(119488, 119520), 

326 "Mayan Numerals": range(119520, 119552), 

327 "Tai Xuan Jing Symbols": range(119552, 119648), 

328 "Counting Rod Numerals": range(119648, 119680), 

329 "Mathematical Alphanumeric Symbols": range(119808, 120832), 

330 "Sutton SignWriting": range(120832, 121520), 

331 "Latin Extended-G": range(122624, 122880), 

332 "Glagolitic Supplement": range(122880, 122928), 

333 "Cyrillic Extended-D": range(122928, 123024), 

334 "Nyiakeng Puachue Hmong": range(123136, 123216), 

335 "Toto": range(123536, 123584), 

336 "Wancho": range(123584, 123648), 

337 "Nag Mundari": range(124112, 124160), 

338 "Ol Onal": range(124368, 124416), 

339 "Tai Yo": range(124608, 124672), 

340 "Ethiopic Extended-B": range(124896, 124928), 

341 "Mende Kikakui": range(124928, 125152), 

342 "Adlam": range(125184, 125280), 

343 "Indic Siyaq Numbers": range(126064, 126144), 

344 "Ottoman Siyaq Numbers": range(126208, 126288), 

345 "Arabic Mathematical Alphabetic Symbols": range(126464, 126720), 

346 "Mahjong Tiles": range(126976, 127024), 

347 "Domino Tiles": range(127024, 127136), 

348 "Playing Cards": range(127136, 127232), 

349 "Enclosed Alphanumeric Supplement": range(127232, 127488), 

350 "Enclosed Ideographic Supplement": range(127488, 127744), 

351 "Miscellaneous Symbols and Pictographs": range(127744, 128512), 

352 "Emoticons": range(128512, 128592), 

353 "Ornamental Dingbats": range(128592, 128640), 

354 "Transport and Map Symbols": range(128640, 128768), 

355 "Alchemical Symbols": range(128768, 128896), 

356 "Geometric Shapes Extended": range(128896, 129024), 

357 "Supplemental Arrows-C": range(129024, 129280), 

358 "Supplemental Symbols and Pictographs": range(129280, 129536), 

359 "Chess Symbols": range(129536, 129648), 

360 "Symbols and Pictographs Extended-A": range(129648, 129792), 

361 "Symbols for Legacy Computing": range(129792, 130048), 

362 "CJK Unified Ideographs Extension B": range(131072, 173792), 

363 "CJK Unified Ideographs Extension C": range(173824, 177984), 

364 "CJK Unified Ideographs Extension D": range(177984, 178208), 

365 "CJK Unified Ideographs Extension E": range(178208, 183984), 

366 "CJK Unified Ideographs Extension F": range(183984, 191472), 

367 "CJK Unified Ideographs Extension I": range(191472, 192096), 

368 "CJK Compatibility Ideographs Supplement": range(194560, 195104), 

369 "CJK Unified Ideographs Extension G": range(196608, 201552), 

370 "CJK Unified Ideographs Extension H": range(201552, 205744), 

371 "CJK Unified Ideographs Extension J": range(205744, 210048), 

372 "Tags": range(917504, 917632), 

373 "Variation Selectors Supplement": range(917760, 918000), 

374 "Supplementary Private Use Area-A": range(983040, 1048576), 

375 "Supplementary Private Use Area-B": range(1048576, 1114112), 

376} 

377 

378# Canonical family for every Unicode range above. Keep this exhaustive and 

379# explicit: official block names are labels, not a grammar we should parse. 

380_RANGE_FAMILIES: dict[str, str] = { 

381 "Control character": "Control character", 

382 "Basic Latin": "Latin", 

383 "Latin-1 Supplement": "Latin", 

384 "Latin Extended-A": "Latin", 

385 "Latin Extended-B": "Latin", 

386 "IPA Extensions": "IPA", 

387 "Spacing Modifier Letters": "Spacing Modifier Letters", 

388 "Combining Diacritical Marks": "Combining", 

389 "Greek and Coptic": "Greek", 

390 "Cyrillic": "Cyrillic", 

391 "Cyrillic Supplement": "Cyrillic", 

392 "Armenian": "Armenian", 

393 "Hebrew": "Hebrew", 

394 "Arabic": "Arabic", 

395 "Syriac": "Syriac", 

396 "Arabic Supplement": "Arabic", 

397 "Thaana": "Thaana", 

398 "NKo": "NKo", 

399 "Samaritan": "Samaritan", 

400 "Mandaic": "Mandaic", 

401 "Syriac Supplement": "Syriac", 

402 "Arabic Extended-B": "Arabic", 

403 "Arabic Extended-A": "Arabic", 

404 "Devanagari": "Devanagari", 

405 "Bengali": "Bengali", 

406 "Gurmukhi": "Gurmukhi", 

407 "Gujarati": "Gujarati", 

408 "Oriya": "Oriya", 

409 "Tamil": "Tamil", 

410 "Telugu": "Telugu", 

411 "Kannada": "Kannada", 

412 "Malayalam": "Malayalam", 

413 "Sinhala": "Sinhala", 

414 "Thai": "Thai", 

415 "Lao": "Lao", 

416 "Tibetan": "Tibetan", 

417 "Myanmar": "Myanmar", 

418 "Georgian": "Georgian", 

419 "Hangul Jamo": "Hangul", 

420 "Ethiopic": "Ethiopic", 

421 "Ethiopic Supplement": "Ethiopic", 

422 "Cherokee": "Cherokee", 

423 "Unified Canadian Aboriginal Syllabics": "Unified Canadian Aboriginal Syllabics", 

424 "Ogham": "Ogham", 

425 "Runic": "Runic", 

426 "Tagalog": "Tagalog", 

427 "Hanunoo": "Hanunoo", 

428 "Buhid": "Buhid", 

429 "Tagbanwa": "Tagbanwa", 

430 "Khmer": "Khmer", 

431 "Mongolian": "Mongolian", 

432 "Unified Canadian Aboriginal Syllabics Extended": "Unified Canadian Aboriginal Syllabics", 

433 "Limbu": "Limbu", 

434 "Tai Le": "Tai Le", 

435 "New Tai Lue": "New Tai Lue", 

436 "Khmer Symbols": "Khmer", 

437 "Buginese": "Buginese", 

438 "Tai Tham": "Tai Tham", 

439 "Combining Diacritical Marks Extended": "Combining", 

440 "Balinese": "Balinese", 

441 "Sundanese": "Sundanese", 

442 "Batak": "Batak", 

443 "Lepcha": "Lepcha", 

444 "Ol Chiki": "Ol Chiki", 

445 "Cyrillic Extended-C": "Cyrillic", 

446 "Georgian Extended": "Georgian", 

447 "Sundanese Supplement": "Sundanese", 

448 "Vedic Extensions": "Vedic", 

449 "Phonetic Extensions": "Phonetic", 

450 "Phonetic Extensions Supplement": "Phonetic", 

451 "Combining Diacritical Marks Supplement": "Combining", 

452 "Latin Extended Additional": "Latin", 

453 "Greek Extended": "Greek", 

454 "General Punctuation": "Punctuation", 

455 "Superscripts and Subscripts": "Superscripts and Subscripts", 

456 "Currency Symbols": "Currency Symbols", 

457 "Combining Diacritical Marks for Symbols": "Combining", 

458 "Letterlike Symbols": "Letterlike Symbols", 

459 "Number Forms": "Number Forms", 

460 "Arrows": "Arrows", 

461 "Mathematical Operators": "Mathematical", 

462 "Miscellaneous Technical": "Miscellaneous Technical", 

463 "Control Pictures": "Control Pictures", 

464 "Optical Character Recognition": "Optical Character Recognition", 

465 "Enclosed Alphanumerics": "Enclosed Alphanumerics", 

466 "Box Drawing": "Box Drawing", 

467 "Block Elements": "Block Elements", 

468 "Geometric Shapes": "Geometric Shapes", 

469 "Miscellaneous Symbols": "Miscellaneous Symbols", 

470 "Dingbats": "Dingbats", 

471 "Miscellaneous Mathematical Symbols-A": "Mathematical", 

472 "Supplemental Arrows-A": "Arrows", 

473 "Braille Patterns": "Braille", 

474 "Supplemental Arrows-B": "Arrows", 

475 "Miscellaneous Mathematical Symbols-B": "Mathematical", 

476 "Supplemental Mathematical Operators": "Mathematical", 

477 "Miscellaneous Symbols and Arrows": "Miscellaneous Symbols and Arrows", 

478 "Glagolitic": "Glagolitic", 

479 "Latin Extended-C": "Latin", 

480 "Coptic": "Coptic", 

481 "Georgian Supplement": "Georgian", 

482 "Tifinagh": "Tifinagh", 

483 "Ethiopic Extended": "Ethiopic", 

484 "Cyrillic Extended-A": "Cyrillic", 

485 "Supplemental Punctuation": "Punctuation", 

486 "CJK Radicals Supplement": "CJK", 

487 "Kangxi Radicals": "CJK", 

488 "Ideographic Description Characters": "CJK", 

489 "CJK Symbols and Punctuation": "CJK", 

490 "Hiragana": "Hiragana", 

491 "Katakana": "Katakana", 

492 "Bopomofo": "Bopomofo", 

493 "Hangul Compatibility Jamo": "Hangul", 

494 "Kanbun": "Kanbun", 

495 "Bopomofo Extended": "Bopomofo", 

496 "CJK Strokes": "CJK", 

497 "Katakana Phonetic Extensions": "Katakana", 

498 "Enclosed CJK Letters and Months": "CJK", 

499 "CJK Compatibility": "CJK", 

500 "CJK Unified Ideographs Extension A": "CJK", 

501 "Yijing Hexagram Symbols": "Yijing Hexagram Symbols", 

502 "CJK Unified Ideographs": "CJK", 

503 "Yi Syllables": "Yi", 

504 "Yi Radicals": "Yi", 

505 "Lisu": "Lisu", 

506 "Vai": "Vai", 

507 "Cyrillic Extended-B": "Cyrillic", 

508 "Bamum": "Bamum", 

509 "Modifier Tone Letters": "Phonetic", 

510 "Latin Extended-D": "Latin", 

511 "Syloti Nagri": "Syloti Nagri", 

512 "Common Indic Number Forms": "Common Indic Number Forms", 

513 "Phags-pa": "Phags-pa", 

514 "Saurashtra": "Saurashtra", 

515 "Devanagari Extended": "Devanagari", 

516 "Kayah Li": "Kayah Li", 

517 "Rejang": "Rejang", 

518 "Hangul Jamo Extended-A": "Hangul", 

519 "Javanese": "Javanese", 

520 "Myanmar Extended-B": "Myanmar", 

521 "Cham": "Cham", 

522 "Myanmar Extended-A": "Myanmar", 

523 "Tai Viet": "Tai Viet", 

524 "Meetei Mayek Extensions": "Meetei Mayek", 

525 "Ethiopic Extended-A": "Ethiopic", 

526 "Latin Extended-E": "Latin", 

527 "Cherokee Supplement": "Cherokee", 

528 "Meetei Mayek": "Meetei Mayek", 

529 "Hangul Syllables": "Hangul", 

530 "Hangul Jamo Extended-B": "Hangul", 

531 "High Surrogates": "Surrogates", 

532 "High Private Use Surrogates": "Surrogates", 

533 "Low Surrogates": "Surrogates", 

534 "Private Use Area": "Private Use", 

535 "CJK Compatibility Ideographs": "CJK", 

536 "Alphabetic Presentation Forms": "Alphabetic Presentation Forms", 

537 "Arabic Presentation Forms-A": "Arabic", 

538 "Variation Selectors": "Variation Selectors", 

539 "Vertical Forms": "CJK", 

540 "Combining Half Marks": "Combining", 

541 "CJK Compatibility Forms": "CJK", 

542 "Small Form Variants": "CJK", 

543 "Arabic Presentation Forms-B": "Arabic", 

544 "Halfwidth and Fullwidth Forms": "Halfwidth and Fullwidth Forms", 

545 "Specials": "Specials", 

546 "Linear B Syllabary": "Linear B", 

547 "Linear B Ideograms": "Linear B", 

548 "Aegean Numbers": "Aegean Numbers", 

549 "Ancient Greek Numbers": "Greek", 

550 "Ancient Symbols": "Ancient Symbols", 

551 "Phaistos Disc": "Phaistos Disc", 

552 "Lycian": "Lycian", 

553 "Carian": "Carian", 

554 "Coptic Epact Numbers": "Coptic", 

555 "Old Italic": "Old Italic", 

556 "Gothic": "Gothic", 

557 "Old Permic": "Old Permic", 

558 "Ugaritic": "Ugaritic", 

559 "Old Persian": "Old Persian", 

560 "Deseret": "Deseret", 

561 "Shavian": "Shavian", 

562 "Osmanya": "Osmanya", 

563 "Osage": "Osage", 

564 "Elbasan": "Elbasan", 

565 "Caucasian Albanian": "Caucasian Albanian", 

566 "Vithkuqi": "Vithkuqi", 

567 "Todhri": "Todhri", 

568 "Linear A": "Linear A", 

569 "Latin Extended-F": "Latin", 

570 "Cypriot Syllabary": "Cypriot", 

571 "Imperial Aramaic": "Imperial Aramaic", 

572 "Palmyrene": "Palmyrene", 

573 "Nabataean": "Nabataean", 

574 "Hatran": "Hatran", 

575 "Phoenician": "Phoenician", 

576 "Lydian": "Lydian", 

577 "Sidetic": "Sidetic", 

578 "Meroitic Hieroglyphs": "Meroitic", 

579 "Meroitic Cursive": "Meroitic", 

580 "Kharoshthi": "Kharoshthi", 

581 "Old South Arabian": "Old South Arabian", 

582 "Old North Arabian": "Old North Arabian", 

583 "Manichaean": "Manichaean", 

584 "Avestan": "Avestan", 

585 "Inscriptional Parthian": "Parthian", 

586 "Inscriptional Pahlavi": "Pahlavi", 

587 "Psalter Pahlavi": "Pahlavi", 

588 "Old Turkic": "Old Turkic", 

589 "Old Hungarian": "Old Hungarian", 

590 "Hanifi Rohingya": "Hanifi Rohingya", 

591 "Garay": "Garay", 

592 "Rumi Numeral Symbols": "Arabic", 

593 "Yezidi": "Yezidi", 

594 "Arabic Extended-C": "Arabic", 

595 "Old Sogdian": "Sogdian", 

596 "Sogdian": "Sogdian", 

597 "Old Uyghur": "Old Uyghur", 

598 "Chorasmian": "Chorasmian", 

599 "Elymaic": "Elymaic", 

600 "Brahmi": "Brahmi", 

601 "Kaithi": "Kaithi", 

602 "Sora Sompeng": "Sora Sompeng", 

603 "Chakma": "Chakma", 

604 "Mahajani": "Mahajani", 

605 "Sharada": "Sharada", 

606 "Sinhala Archaic Numbers": "Sinhala", 

607 "Khojki": "Khojki", 

608 "Multani": "Multani", 

609 "Khudawadi": "Khudawadi", 

610 "Grantha": "Grantha", 

611 "Tulu-Tigalari": "Tulu-Tigalari", 

612 "Newa": "Newa", 

613 "Tirhuta": "Tirhuta", 

614 "Siddham": "Siddham", 

615 "Modi": "Modi", 

616 "Mongolian Supplement": "Mongolian", 

617 "Takri": "Takri", 

618 "Myanmar Extended-C": "Myanmar", 

619 "Ahom": "Ahom", 

620 "Dogra": "Dogra", 

621 "Warang Citi": "Warang Citi", 

622 "Dives Akuru": "Dives Akuru", 

623 "Nandinagari": "Nandinagari", 

624 "Zanabazar Square": "Zanabazar Square", 

625 "Soyombo": "Soyombo", 

626 "Unified Canadian Aboriginal Syllabics Extended-A": "Unified Canadian Aboriginal Syllabics", 

627 "Pau Cin Hau": "Pau Cin Hau", 

628 "Devanagari Extended-A": "Devanagari", 

629 "Sharada Supplement": "Sharada", 

630 "Sunuwar": "Sunuwar", 

631 "Bhaiksuki": "Bhaiksuki", 

632 "Marchen": "Marchen", 

633 "Masaram Gondi": "Masaram Gondi", 

634 "Gunjala Gondi": "Gunjala Gondi", 

635 "Tolong Siki": "Tolong Siki", 

636 "Makasar": "Makasar", 

637 "Kawi": "Kawi", 

638 "Lisu Supplement": "Lisu", 

639 "Tamil Supplement": "Tamil", 

640 "Cuneiform": "Cuneiform", 

641 "Cuneiform Numbers and Punctuation": "Cuneiform", 

642 "Early Dynastic Cuneiform": "Cuneiform", 

643 "Cypro-Minoan": "Cypro-Minoan", 

644 "Egyptian Hieroglyphs": "Egyptian Hieroglyphs", 

645 "Egyptian Hieroglyph Format Controls": "Egyptian Hieroglyphs", 

646 "Egyptian Hieroglyphs Extended-A": "Egyptian Hieroglyphs", 

647 "Anatolian Hieroglyphs": "Anatolian Hieroglyphs", 

648 "Gurung Khema": "Gurung Khema", 

649 "Bamum Supplement": "Bamum", 

650 "Mro": "Mro", 

651 "Tangsa": "Tangsa", 

652 "Bassa Vah": "Bassa Vah", 

653 "Pahawh Hmong": "Pahawh Hmong", 

654 "Kirat Rai": "Kirat Rai", 

655 "Medefaidrin": "Medefaidrin", 

656 "Beria Erfe": "Beria Erfe", 

657 "Miao": "Miao", 

658 "Ideographic Symbols and Punctuation": "CJK", 

659 "Tangut": "Tangut", 

660 "Tangut Components": "Tangut", 

661 "Khitan Small Script": "Khitan Small Script", 

662 "Tangut Supplement": "Tangut", 

663 "Tangut Components Supplement": "Tangut", 

664 "Kana Extended-B": "Kana", 

665 "Kana Supplement": "Kana", 

666 "Kana Extended-A": "Kana", 

667 "Small Kana Extension": "Kana", 

668 "Nushu": "Nushu", 

669 "Duployan": "Duployan", 

670 "Shorthand Format Controls": "Shorthand Format Controls", 

671 "Symbols for Legacy Computing Supplement": "Symbols for Legacy Computing", 

672 "Miscellaneous Symbols Supplement": "Miscellaneous Symbols", 

673 "Znamenny Musical Notation": "Znamenny Musical Notation", 

674 "Byzantine Musical Symbols": "Byzantine Musical Symbols", 

675 "Musical Symbols": "Musical Symbols", 

676 "Ancient Greek Musical Notation": "Greek", 

677 "Kaktovik Numerals": "Kaktovik Numerals", 

678 "Mayan Numerals": "Mayan Numerals", 

679 "Tai Xuan Jing Symbols": "Tai Xuan Jing Symbols", 

680 "Counting Rod Numerals": "Counting Rod Numerals", 

681 "Mathematical Alphanumeric Symbols": "Mathematical", 

682 "Sutton SignWriting": "Sutton SignWriting", 

683 "Latin Extended-G": "Latin", 

684 "Glagolitic Supplement": "Glagolitic", 

685 "Cyrillic Extended-D": "Cyrillic", 

686 "Nyiakeng Puachue Hmong": "Nyiakeng Puachue Hmong", 

687 "Toto": "Toto", 

688 "Wancho": "Wancho", 

689 "Nag Mundari": "Nag Mundari", 

690 "Ol Onal": "Ol Onal", 

691 "Tai Yo": "Tai Yo", 

692 "Ethiopic Extended-B": "Ethiopic", 

693 "Mende Kikakui": "Mende Kikakui", 

694 "Adlam": "Adlam", 

695 "Indic Siyaq Numbers": "Indic Siyaq Numbers", 

696 "Ottoman Siyaq Numbers": "Ottoman Siyaq Numbers", 

697 "Arabic Mathematical Alphabetic Symbols": "Arabic",