| 1 | // utf-8 utility string functions |
| 2 | // |
| 3 | // Copyright (c) 2019-2024 Dario Deledda. All rights reserved. |
| 4 | // Use of this source code is governed by an MIT license |
| 5 | // that can be found in the LICENSE file. |
| 6 | module utf8 |
| 7 | |
| 8 | // Utility functions |
| 9 | |
| 10 | // len return the length as number of unicode chars from a string |
| 11 | pub fn len(s string) int { |
| 12 | if s.len == 0 { |
| 13 | return 0 |
| 14 | } |
| 15 | |
| 16 | mut count := 0 |
| 17 | mut index := 0 |
| 18 | |
| 19 | for { |
| 20 | ch_len := utf8_char_len(s[index]) |
| 21 | index += ch_len |
| 22 | count++ |
| 23 | if index >= s.len { |
| 24 | break |
| 25 | } |
| 26 | } |
| 27 | return count |
| 28 | } |
| 29 | |
| 30 | // get_rune convert a UTF-8 unicode codepoint in string[index] into a UTF-32 encoded rune |
| 31 | pub fn get_rune(s string, index int) rune { |
| 32 | mut res := 0 |
| 33 | mut ch_len := 0 |
| 34 | if s.len > 0 { |
| 35 | ch_len = utf8_char_len(s[index]) |
| 36 | |
| 37 | if ch_len == 1 { |
| 38 | return u16(s[index]) |
| 39 | } |
| 40 | if ch_len > 1 && ch_len < 5 { |
| 41 | mut lword := 0 |
| 42 | for i := 0; i < ch_len; i++ { |
| 43 | lword = int(u32(lword) << 8 | u32(s[index + i])) |
| 44 | } |
| 45 | |
| 46 | // 2 byte utf-8 |
| 47 | // byte format: 110xxxxx 10xxxxxx |
| 48 | // |
| 49 | if ch_len == 2 { |
| 50 | res = (lword & 0x1f00) >> 2 | (lword & 0x3f) |
| 51 | } |
| 52 | // 3 byte utf-8 |
| 53 | // byte format: 1110xxxx 10xxxxxx 10xxxxxx |
| 54 | // |
| 55 | else if ch_len == 3 { |
| 56 | res = (lword & 0x0f0000) >> 4 | (lword & 0x3f00) >> 2 | (lword & 0x3f) |
| 57 | } |
| 58 | // 4 byte utf-8 |
| 59 | // byte format: 11110xxx 10xxxxxx 10xxxxxx 10xxxxxx |
| 60 | // |
| 61 | else if ch_len == 4 { |
| 62 | res = ((lword & 0x07000000) >> 6) | ((lword & 0x003f0000) >> 4) | ((lword & 0x00003F00) >> 2) | (lword & 0x0000003f) |
| 63 | } |
| 64 | } |
| 65 | } |
| 66 | return res |
| 67 | } |
| 68 | |
| 69 | // raw_index - get the raw unicode character from the UTF-8 string by the given index value as UTF-8 string. |
| 70 | // example: utf8.raw_index('我是V Lang', 1) => '是' |
| 71 | pub fn raw_index(s string, index int) string { |
| 72 | mut r := []rune{} |
| 73 | |
| 74 | for i := 0; i < s.len; i++ { |
| 75 | if r.len - 1 == index { |
| 76 | break |
| 77 | } |
| 78 | |
| 79 | b := s[i] |
| 80 | ch_len := int((u32(0xe5000000) >> ((b >> 3) & 0x1e)) & 3) |
| 81 | |
| 82 | r << if ch_len > 0 { |
| 83 | i += ch_len |
| 84 | rune(get_rune(s, i - ch_len)) |
| 85 | } else { |
| 86 | rune(b) |
| 87 | } |
| 88 | } |
| 89 | |
| 90 | return r[index].str() |
| 91 | } |
| 92 | |
| 93 | // reverse - returns a reversed string. |
| 94 | // example: utf8.reverse('你好世界hello world') => 'dlrow olleh界世好你'. |
| 95 | pub fn reverse(s string) string { |
| 96 | len_s := len(s) |
| 97 | if len_s == 0 || len_s == 1 { |
| 98 | return s.clone() |
| 99 | } |
| 100 | mut str_array := []string{} |
| 101 | for i in 0 .. len_s { |
| 102 | str_array << raw_index(s, i) |
| 103 | } |
| 104 | str_array = str_array.reverse() |
| 105 | return str_array.join('') |
| 106 | } |
| 107 | |
| 108 | // Conversion functions |
| 109 | |
| 110 | // to_upper return an uppercase string from a string |
| 111 | pub fn to_upper(s string) string { |
| 112 | return convert_case(s, true) |
| 113 | } |
| 114 | |
| 115 | // to_lower return an lowercase string from a string |
| 116 | pub fn to_lower(s string) string { |
| 117 | return convert_case(s, false) |
| 118 | } |
| 119 | |
| 120 | // Punctuation functions |
| 121 | // |
| 122 | // The "western" function search on a small table, that is quicker than |
| 123 | // the global unicode table search. **Use only for western chars**. |
| 124 | |
| 125 | // Western |
| 126 | |
| 127 | // is_punct return true if the string[index] byte is the start of a unicode western punctuation |
| 128 | pub fn is_punct(s string, index int) bool { |
| 129 | return is_rune_punct(get_rune(s, index)) |
| 130 | } |
| 131 | |
| 132 | // is_control return true if the rune is control code |
| 133 | pub fn is_control(r rune) bool { |
| 134 | // control codes are all below 0xff |
| 135 | if r > max_latin_1 { |
| 136 | return false |
| 137 | } |
| 138 | return props[u8(r)] == 1 |
| 139 | } |
| 140 | |
| 141 | // is_letter returns true if the rune is unicode letter or in unicode category L |
| 142 | pub fn is_letter(r rune) bool { |
| 143 | if (r >= `a` && r <= `z`) || (r >= `A` && r <= `Z`) { |
| 144 | return true |
| 145 | } else if r <= max_latin_1 { |
| 146 | return props[u8(r)] & p_l_mask != 0 |
| 147 | } |
| 148 | return is_excluding_latin(letter_table, r) |
| 149 | } |
| 150 | |
| 151 | // is_space returns true if the rune is character in unicode category Z with property white space or the following character set: |
| 152 | // ``` |
| 153 | // `\t`, `\n`, `\v`, `\f`, `\r`, ` `, 0x85 (NEL), 0xA0 (NBSP) |
| 154 | // ``` |
| 155 | pub fn is_space(r rune) bool { |
| 156 | if r <= max_latin_1 { |
| 157 | match r { |
| 158 | `\t`, `\n`, `\v`, `\f`, `\r`, ` `, 0x85, 0xA0 { |
| 159 | return true |
| 160 | } |
| 161 | else { |
| 162 | return false |
| 163 | } |
| 164 | } |
| 165 | } |
| 166 | return is_excluding_latin(white_space_table, r) |
| 167 | } |
| 168 | |
| 169 | // is_number returns true if the rune is unicode number or in unicode category N |
| 170 | pub fn is_number(r rune) bool { |
| 171 | if r <= max_latin_1 { |
| 172 | return props[u8(r)] & p_n != 0 |
| 173 | } |
| 174 | return is_excluding_latin(number_table, r) |
| 175 | } |
| 176 | |
| 177 | // is_rune_punct return true if the input unicode is a western unicode punctuation |
| 178 | pub fn is_rune_punct(r rune) bool { |
| 179 | return find_punct_in_table(r, unicode_punct_western) != rune(-1) |
| 180 | } |
| 181 | |
| 182 | // Global |
| 183 | |
| 184 | // is_global_punct return true if the string[index] byte of is the start of a global unicode punctuation |
| 185 | pub fn is_global_punct(s string, index int) bool { |
| 186 | return is_rune_global_punct(get_rune(s, index)) |
| 187 | } |
| 188 | |
| 189 | // is_rune_global_punct return true if the input unicode is a global unicode punctuation |
| 190 | pub fn is_rune_global_punct(r rune) bool { |
| 191 | return find_punct_in_table(r, unicode_punct) != rune(-1) |
| 192 | } |
| 193 | |
| 194 | // Private functions |
| 195 | |
| 196 | // utf8_to_lower raw utf-8 to_lower function |
| 197 | fn utf8_to_lower(in_cp int) int { |
| 198 | mut cp := in_cp |
| 199 | if (0x0041 <= cp && 0x005a >= cp) || (0x00c0 <= cp && 0x00d6 >= cp) |
| 200 | || (0x00d8 <= cp && 0x00de >= cp) || (0x0391 <= cp && 0x03a1 >= cp) |
| 201 | || (0x03a3 <= cp && 0x03ab >= cp) || (0x0410 <= cp && 0x042f >= cp) { |
| 202 | cp += 32 |
| 203 | } else if 0x0400 <= cp && 0x040f >= cp { |
| 204 | cp += 80 |
| 205 | } else if (0x0100 <= cp && 0x012f >= cp) || (0x0132 <= cp && 0x0137 >= cp) |
| 206 | || (0x014a <= cp && 0x0177 >= cp) || (0x0182 <= cp && 0x0185 >= cp) |
| 207 | || (0x01a0 <= cp && 0x01a5 >= cp) || (0x01de <= cp && 0x01ef >= cp) |
| 208 | || (0x01f8 <= cp && 0x021f >= cp) || (0x0222 <= cp && 0x0233 >= cp) |
| 209 | || (0x0246 <= cp && 0x024f >= cp) || (0x03d8 <= cp && 0x03ef >= cp) |
| 210 | || (0x0460 <= cp && 0x0481 >= cp) || (0x048a <= cp && 0x04ff >= cp) { |
| 211 | cp |= 0x1 |
| 212 | } else if (0x0139 <= cp && 0x0148 >= cp) || (0x0179 <= cp && 0x017e >= cp) |
| 213 | || (0x01af <= cp && 0x01b0 >= cp) || (0x01b3 <= cp && 0x01b6 >= cp) |
| 214 | || (0x01cd <= cp && 0x01dc >= cp) { |
| 215 | cp += 1 |
| 216 | cp &= ~0x1 |
| 217 | } else if (0x0531 <= cp && 0x0556 >= cp) || (0x10A0 <= cp && 0x10C5 >= cp) { |
| 218 | // ARMENIAN or GEORGIAN |
| 219 | cp += 0x30 |
| 220 | } else if ((0x1E00 <= cp && 0x1E94 >= cp) || (0x1EA0 <= cp && 0x1EF8 >= cp)) && cp & 1 == 0 { |
| 221 | // LATIN CAPITAL LETTER |
| 222 | cp += 1 |
| 223 | } else if 0x24B6 <= cp && 0x24CF >= cp { |
| 224 | // CIRCLED LATIN |
| 225 | cp += 0x1a |
| 226 | } else if 0xFF21 <= cp && 0xFF3A >= cp { |
| 227 | // FULLWIDTH LATIN CAPITAL |
| 228 | cp += 0x19 |
| 229 | } else if (0x1F08 <= cp && 0x1F0F >= cp) || (0x1F18 <= cp && 0x1F1D >= cp) |
| 230 | || (0x1F28 <= cp && 0x1F2F >= cp) || (0x1F38 <= cp && 0x1F3F >= cp) |
| 231 | || (0x1F48 <= cp && 0x1F4D >= cp) || (0x1F68 <= cp && 0x1F6F >= cp) |
| 232 | || (0x1F88 <= cp && 0x1F8F >= cp) || (0x1F98 <= cp && 0x1F9F >= cp) |
| 233 | || (0x1FA8 <= cp && 0x1FAF >= cp) { |
| 234 | // GREEK |
| 235 | cp -= 8 |
| 236 | } else { |
| 237 | match cp { |
| 238 | 0x0178 { cp = 0x00ff } |
| 239 | 0x0243 { cp = 0x0180 } |
| 240 | 0x018e { cp = 0x01dd } |
| 241 | 0x023d { cp = 0x019a } |
| 242 | 0x0220 { cp = 0x019e } |
| 243 | 0x01b7 { cp = 0x0292 } |
| 244 | 0x01c4 { cp = 0x01c6 } |
| 245 | 0x01c7 { cp = 0x01c9 } |
| 246 | 0x01ca { cp = 0x01cc } |
| 247 | 0x01f1 { cp = 0x01f3 } |
| 248 | 0x01f7 { cp = 0x01bf } |
| 249 | 0x0187 { cp = 0x0188 } |
| 250 | 0x018b { cp = 0x018c } |
| 251 | 0x0191 { cp = 0x0192 } |
| 252 | 0x0198 { cp = 0x0199 } |
| 253 | 0x01a7 { cp = 0x01a8 } |
| 254 | 0x01ac { cp = 0x01ad } |
| 255 | 0x01af { cp = 0x01b0 } |
| 256 | 0x01b8 { cp = 0x01b9 } |
| 257 | 0x01bc { cp = 0x01bd } |
| 258 | 0x01f4 { cp = 0x01f5 } |
| 259 | 0x023b { cp = 0x023c } |
| 260 | 0x0241 { cp = 0x0242 } |
| 261 | 0x03fd { cp = 0x037b } |
| 262 | 0x03fe { cp = 0x037c } |
| 263 | 0x03ff { cp = 0x037d } |
| 264 | 0x037f { cp = 0x03f3 } |
| 265 | 0x0386 { cp = 0x03ac } |
| 266 | 0x0388 { cp = 0x03ad } |
| 267 | 0x0389 { cp = 0x03ae } |
| 268 | 0x038a { cp = 0x03af } |
| 269 | 0x038c { cp = 0x03cc } |
| 270 | 0x038e { cp = 0x03cd } |
| 271 | 0x038f { cp = 0x03ce } |
| 272 | 0x0370 { cp = 0x0371 } |
| 273 | 0x0372 { cp = 0x0373 } |
| 274 | 0x0376 { cp = 0x0377 } |
| 275 | 0x03f4 { cp = 0x03b8 } |
| 276 | 0x03cf { cp = 0x03d7 } |
| 277 | 0x03f9 { cp = 0x03f2 } |
| 278 | 0x03f7 { cp = 0x03f8 } |
| 279 | 0x03fa { cp = 0x03fb } |
| 280 | // GREEK |
| 281 | 0x1F59 { cp = 0x1F51 } |
| 282 | 0x1F5B { cp = 0x1F53 } |
| 283 | 0x1F5D { cp = 0x1F55 } |
| 284 | 0x1F5F { cp = 0x1F57 } |
| 285 | 0x1FB8 { cp = 0x1FB0 } |
| 286 | 0x1FB9 { cp = 0x1FB1 } |
| 287 | 0x1FD8 { cp = 0x1FD0 } |
| 288 | 0x1FD9 { cp = 0x1FD1 } |
| 289 | 0x1FE8 { cp = 0x1FE0 } |
| 290 | 0x1FE9 { cp = 0x1FE1 } |
| 291 | else {} |
| 292 | } |
| 293 | } |
| 294 | |
| 295 | return cp |
| 296 | } |
| 297 | |
| 298 | // utf8_to_upper raw utf-8 to_upper function |
| 299 | fn utf8_to_upper(in_cp int) int { |
| 300 | mut cp := in_cp |
| 301 | if (0x0061 <= cp && 0x007a >= cp) || (0x00e0 <= cp && 0x00f6 >= cp) |
| 302 | || (0x00f8 <= cp && 0x00fe >= cp) || (0x03b1 <= cp && 0x03c1 >= cp) |
| 303 | || (0x03c3 <= cp && 0x03cb >= cp) || (0x0430 <= cp && 0x044f >= cp) { |
| 304 | cp -= 32 |
| 305 | } else if 0x0450 <= cp && 0x045f >= cp { |
| 306 | cp -= 80 |
| 307 | } else if (0x0100 <= cp && 0x012f >= cp) || (0x0132 <= cp && 0x0137 >= cp) |
| 308 | || (0x014a <= cp && 0x0177 >= cp) || (0x0182 <= cp && 0x0185 >= cp) |
| 309 | || (0x01a0 <= cp && 0x01a5 >= cp) || (0x01de <= cp && 0x01ef >= cp) |
| 310 | || (0x01f8 <= cp && 0x021f >= cp) || (0x0222 <= cp && 0x0233 >= cp) |
| 311 | || (0x0246 <= cp && 0x024f >= cp) || (0x03d8 <= cp && 0x03ef >= cp) |
| 312 | || (0x0460 <= cp && 0x0481 >= cp) || (0x048a <= cp && 0x04ff >= cp) { |
| 313 | cp &= ~0x1 |
| 314 | } else if (0x0139 <= cp && 0x0148 >= cp) || (0x0179 <= cp && 0x017e >= cp) |
| 315 | || (0x01af <= cp && 0x01b0 >= cp) || (0x01b3 <= cp && 0x01b6 >= cp) |
| 316 | || (0x01cd <= cp && 0x01dc >= cp) { |
| 317 | cp -= 1 |
| 318 | cp |= 0x1 |
| 319 | } else if (0x0561 <= cp && 0x0586 >= cp) || (0x10D0 <= cp && 0x10F5 >= cp) { |
| 320 | // ARMENIAN or GEORGIAN |
| 321 | cp -= 0x30 |
| 322 | } else if ((0x1E01 <= cp && 0x1E95 >= cp) || (0x1EA1 <= cp && 0x1EF9 >= cp)) && cp & 1 == 1 { |
| 323 | // LATIN CAPITAL LETTER |
| 324 | cp -= 1 |
| 325 | } else if 0x24D0 <= cp && 0x24E9 >= cp { |
| 326 | // CIRCLED LATIN |
| 327 | cp -= 0x1a |
| 328 | } else if 0xFF41 <= cp && 0xFF5A >= cp { |
| 329 | // FULLWIDTH LATIN CAPITAL |
| 330 | cp -= 0x19 |
| 331 | } else if (0x1F00 <= cp && 0x1F07 >= cp) || (0x1F10 <= cp && 0x1F15 >= cp) |
| 332 | || (0x1F20 <= cp && 0x1F27 >= cp) || (0x1F30 <= cp && 0x1F37 >= cp) |
| 333 | || (0x1F40 <= cp && 0x1F45 >= cp) || (0x1F60 <= cp && 0x1F67 >= cp) |
| 334 | || (0x1F80 <= cp && 0x1F87 >= cp) || (0x1F90 <= cp && 0x1F97 >= cp) |
| 335 | || (0x1FA0 <= cp && 0x1FA7 >= cp) { |
| 336 | // GREEK |
| 337 | cp += 8 |
| 338 | } else { |
| 339 | match cp { |
| 340 | 0x00ff { cp = 0x0178 } |
| 341 | 0x0180 { cp = 0x0243 } |
| 342 | 0x01dd { cp = 0x018e } |
| 343 | 0x019a { cp = 0x023d } |
| 344 | 0x019e { cp = 0x0220 } |
| 345 | 0x0292 { cp = 0x01b7 } |
| 346 | 0x01c6 { cp = 0x01c4 } |
| 347 | 0x01c9 { cp = 0x01c7 } |
| 348 | 0x01cc { cp = 0x01ca } |
| 349 | 0x01f3 { cp = 0x01f1 } |
| 350 | 0x01bf { cp = 0x01f7 } |
| 351 | 0x0188 { cp = 0x0187 } |
| 352 | 0x018c { cp = 0x018b } |
| 353 | 0x0192 { cp = 0x0191 } |
| 354 | 0x0199 { cp = 0x0198 } |
| 355 | 0x01a8 { cp = 0x01a7 } |
| 356 | 0x01ad { cp = 0x01ac } |
| 357 | 0x01b0 { cp = 0x01af } |
| 358 | 0x01b9 { cp = 0x01b8 } |
| 359 | 0x01bd { cp = 0x01bc } |
| 360 | 0x01f5 { cp = 0x01f4 } |
| 361 | 0x023c { cp = 0x023b } |
| 362 | 0x0242 { cp = 0x0241 } |
| 363 | 0x037b { cp = 0x03fd } |
| 364 | 0x037c { cp = 0x03fe } |
| 365 | 0x037d { cp = 0x03ff } |
| 366 | 0x03f3 { cp = 0x037f } |
| 367 | 0x03ac { cp = 0x0386 } |
| 368 | 0x03ad { cp = 0x0388 } |
| 369 | 0x03ae { cp = 0x0389 } |
| 370 | 0x03af { cp = 0x038a } |
| 371 | 0x03cc { cp = 0x038c } |
| 372 | 0x03cd { cp = 0x038e } |
| 373 | 0x03ce { cp = 0x038f } |
| 374 | 0x0371 { cp = 0x0370 } |
| 375 | 0x0373 { cp = 0x0372 } |
| 376 | 0x0377 { cp = 0x0376 } |
| 377 | 0x03d1 { cp = 0x0398 } |
| 378 | 0x03d7 { cp = 0x03cf } |
| 379 | 0x03f2 { cp = 0x03f9 } |
| 380 | 0x03f8 { cp = 0x03f7 } |
| 381 | 0x03fb { cp = 0x03fa } |
| 382 | // GREEK |
| 383 | 0x1F51 { cp = 0x1F59 } |
| 384 | 0x1F53 { cp = 0x1F5B } |
| 385 | 0x1F55 { cp = 0x1F5D } |
| 386 | 0x1F57 { cp = 0x1F5F } |
| 387 | 0x1FB0 { cp = 0x1FB8 } |
| 388 | 0x1FB1 { cp = 0x1FB9 } |
| 389 | 0x1FD0 { cp = 0x1FD8 } |
| 390 | 0x1FD1 { cp = 0x1FD9 } |
| 391 | 0x1FE0 { cp = 0x1FE8 } |
| 392 | 0x1FE1 { cp = 0x1FE9 } |
| 393 | else {} |
| 394 | } |
| 395 | } |
| 396 | |
| 397 | return cp |
| 398 | } |
| 399 | |
| 400 | // convert_case converts letter cases |
| 401 | // |
| 402 | // if upper_flag == true then convert lowercase ==> uppercase |
| 403 | // if upper_flag == false then convert uppercase ==> lowercase |
| 404 | @[direct_array_access] |
| 405 | fn convert_case(s string, upper_flag bool) string { |
| 406 | mut index := 0 |
| 407 | mut tab_char := 0 |
| 408 | mut str_res := unsafe { malloc_noscan(s.len + 1) } |
| 409 | |
| 410 | for { |
| 411 | ch_len := utf8_char_len(s[index]) |
| 412 | |
| 413 | if ch_len == 1 { |
| 414 | if upper_flag == true { |
| 415 | unsafe { |
| 416 | // Subtract 0x20 from ASCII lowercase to convert to uppercase. |
| 417 | c := s[index] |
| 418 | str_res[index] = if c >= 0x61 && c <= 0x7a { c & 0xdf } else { c } |
| 419 | } |
| 420 | } else { |
| 421 | unsafe { |
| 422 | // Add 0x20 to ASCII uppercase to convert to lowercase. |
| 423 | c := s[index] |
| 424 | str_res[index] = if c >= 0x41 && c <= 0x5a { c | 0x20 } else { c } |
| 425 | } |
| 426 | } |
| 427 | } else if ch_len > 1 && ch_len < 5 { |
| 428 | mut lword := 0 |
| 429 | |
| 430 | for i := 0; i < ch_len; i++ { |
| 431 | lword = int(u32(lword) << 8 | u32(s[index + i])) |
| 432 | } |
| 433 | |
| 434 | // println("#${index} (${lword})") |
| 435 | |
| 436 | mut res := 0 |
| 437 | |
| 438 | // 2 byte utf-8 |
| 439 | // byte format: 110xxxxx 10xxxxxx |
| 440 | // |
| 441 | if ch_len == 2 { |
| 442 | res = (lword & 0x1f00) >> 2 | (lword & 0x3f) |
| 443 | } |
| 444 | // 3 byte utf-8 |
| 445 | // byte format: 1110xxxx 10xxxxxx 10xxxxxx |
| 446 | // |
| 447 | else if ch_len == 3 { |
| 448 | res = (lword & 0x0f0000) >> 4 | (lword & 0x3f00) >> 2 | (lword & 0x3f) |
| 449 | } |
| 450 | // 4 byte utf-8 |
| 451 | // byte format: 11110xxx 10xxxxxx 10xxxxxx 10xxxxxx |
| 452 | // |
| 453 | else if ch_len == 4 { |
| 454 | res = ((lword & 0x07000000) >> 6) | ((lword & 0x003f0000) >> 4) | ((lword & 0x00003F00) >> 2) | (lword & 0x0000003f) |
| 455 | } |
| 456 | |
| 457 | // println("res: ${res.hex():8}") |
| 458 | |
| 459 | if upper_flag == false { |
| 460 | tab_char = utf8_to_lower(res) |
| 461 | } else { |
| 462 | tab_char = utf8_to_upper(res) |
| 463 | } |
| 464 | |
| 465 | if ch_len == 2 { |
| 466 | ch0 := u8((tab_char >> 6) & 0x1f) | 0xc0 // 110x xxxx |
| 467 | ch1 := u8((tab_char >> 0) & 0x3f) | 0x80 // 10xx xxxx |
| 468 | // C.printf("[%02x%02x] \n",ch0,ch1) |
| 469 | |
| 470 | unsafe { |
| 471 | str_res[index + 0] = ch0 |
| 472 | str_res[index + 1] = ch1 |
| 473 | } |
| 474 | ///*************************************************************** |
| 475 | // BUG: doesn't compile, workaround use shitf to right of 0 bit |
| 476 | ///*************************************************************** |
| 477 | // str_res[index + 1 ] = u8( tab_char & 0xbf ) // 1011 1111 |
| 478 | } else if ch_len == 3 { |
| 479 | ch0 := u8((tab_char >> 12) & 0x0f) | 0xe0 // 1110 xxxx |
| 480 | ch1 := u8((tab_char >> 6) & 0x3f) | 0x80 // 10xx xxxx |
| 481 | ch2 := u8((tab_char >> 0) & 0x3f) | 0x80 // 10xx xxxx |
| 482 | // C.printf("[%02x%02x%02x] \n",ch0,ch1,ch2) |
| 483 | |
| 484 | unsafe { |
| 485 | str_res[index + 0] = ch0 |
| 486 | str_res[index + 1] = ch1 |
| 487 | str_res[index + 2] = ch2 |
| 488 | } |
| 489 | } |
| 490 | // TODO: write if needed |
| 491 | else if ch_len == 4 { |
| 492 | // place holder!! |
| 493 | // at the present time simply copy the utf8 char |
| 494 | for i in 0 .. ch_len { |
| 495 | unsafe { |
| 496 | str_res[index + i] = s[index + i] |
| 497 | } |
| 498 | } |
| 499 | } |
| 500 | } else { |
| 501 | // other cases, just copy the string |
| 502 | for i in 0 .. ch_len { |
| 503 | unsafe { |
| 504 | str_res[index + i] = s[index + i] |
| 505 | } |
| 506 | } |
| 507 | } |
| 508 | |
| 509 | index += ch_len |
| 510 | |
| 511 | // we are done, exit the loop |
| 512 | if index >= s.len { |
| 513 | break |
| 514 | } |
| 515 | } |
| 516 | |
| 517 | // for c compatibility set the ending 0 |
| 518 | unsafe { |
| 519 | str_res[index] = 0 |
| 520 | return tos(str_res, s.len) |
| 521 | } |
| 522 | } |
| 523 | |
| 524 | // find_punct_in_table looks for valid punctuation in table |
| 525 | @[direct_array_access] |
| 526 | fn find_punct_in_table(in_code rune, in_table []rune) rune { |
| 527 | // uses simple binary search |
| 528 | |
| 529 | mut first_index := 0 |
| 530 | mut last_index := (in_table.len) |
| 531 | mut index := 0 |
| 532 | mut x := rune(0) |
| 533 | |
| 534 | for { |
| 535 | x = in_table[index] |
| 536 | // C.printf("(%d..%d) index:%d base[%08x]==>[%08x]\n",first_index,last_index,index,in_code,x) |
| 537 | |
| 538 | if x == in_code { |
| 539 | return index |
| 540 | } else if x > in_code { |
| 541 | last_index = index |
| 542 | } else { |
| 543 | first_index = index |
| 544 | } |
| 545 | |
| 546 | if (last_index - first_index) <= 1 { |
| 547 | break |
| 548 | } |
| 549 | index = (first_index + last_index) >> 1 |
| 550 | } |
| 551 | |
| 552 | return -1 |
| 553 | } |
| 554 | |
| 555 | // Unicode punctuation chars |
| 556 | // |
| 557 | // source: http://www.unicode.org/faq/punctuation_symbols.html |
| 558 | |
| 559 | // Western punctuation mark |
| 560 | // Character Name Browser Image |
| 561 | const unicode_punct_western = [ |
| 562 | rune(0x0021), // EXCLAMATION MARK ! |
| 563 | 0x0022, // QUOTATION MARK " |
| 564 | 0x0027, // APOSTROPHE ' |
| 565 | 0x002A, // ASTERISK * |
| 566 | 0x002C, // COMMA , |
| 567 | 0x002E, // FULL STOP . |
| 568 | 0x002F, // SOLIDUS / |
| 569 | 0x003A, // COLON : |
| 570 | 0x003B, // SEMICOLON ; |
| 571 | 0x003F, // QUESTION MARK ? |
| 572 | 0x00A1, // INVERTED EXCLAMATION MARK ¡ |
| 573 | 0x00A7, // SECTION SIGN § |
| 574 | 0x00B6, // PILCROW SIGN ¶ |
| 575 | 0x00B7, // MIDDLE DOT · |
| 576 | 0x00BF, // INVERTED QUESTION MARK ¿ |
| 577 | 0x037E, // GREEK QUESTION MARK ; |
| 578 | 0x0387, // GREEK ANO TELEIA · |
| 579 | 0x055A, // ARMENIAN APOSTROPHE ՚ |
| 580 | 0x055B, // ARMENIAN EMPHASIS MARK ՛ |
| 581 | 0x055C, // ARMENIAN EXCLAMATION MARK ՜ |
| 582 | 0x055D, // ARMENIAN COMMA ՝ |
| 583 | 0x055E, // ARMENIAN QUESTION MARK ՞ |
| 584 | 0x055F, // ARMENIAN ABBREVIATION MARK ՟ |
| 585 | 0x0589, // ARMENIAN FULL STOP ։ |
| 586 | 0x05C0, // HEBREW PUNCTUATION PASEQ ׀ |
| 587 | 0x05C3, // HEBREW PUNCTUATION SOF PASUQ ׃ |
| 588 | 0x05C6, // HEBREW PUNCTUATION NUN HAFUKHA ׆ |
| 589 | 0x05F3, // HEBREW PUNCTUATION GERESH ׳ |
| 590 | 0x05F4, // HEBREW PUNCTUATION GERSHAYIM ״ |
| 591 | ] |
| 592 | |
| 593 | // Unicode Characters in the 'Punctuation, Other' Category |
| 594 | // Character Name Browser Image |
| 595 | const unicode_punct = [ |
| 596 | rune(0x0021), // EXCLAMATION MARK ! |
| 597 | 0x0022, // QUOTATION MARK " |
| 598 | 0x0023, // NUMBER SIGN # |
| 599 | 0x0025, // PERCENT SIGN % |
| 600 | 0x0026, // AMPERSAND & |
| 601 | 0x0027, // APOSTROPHE ' |
| 602 | 0x002A, // ASTERISK * |
| 603 | 0x002C, // COMMA , |
| 604 | 0x002E, // FULL STOP . |
| 605 | 0x002F, // SOLIDUS / |
| 606 | 0x003A, // COLON : |
| 607 | 0x003B, // SEMICOLON ; |
| 608 | 0x003F, // QUESTION MARK ? |
| 609 | 0x0040, // COMMERCIAL AT @ |
| 610 | 0x005C, // REVERSE SOLIDUS \ |
| 611 | 0x00A1, // INVERTED EXCLAMATION MARK ¡ |
| 612 | 0x00A7, // SECTION SIGN § |
| 613 | 0x00B6, // PILCROW SIGN ¶ |
| 614 | 0x00B7, // MIDDLE DOT · |
| 615 | 0x00BF, // INVERTED QUESTION MARK ¿ |
| 616 | 0x037E, // GREEK QUESTION MARK ; |
| 617 | 0x0387, // GREEK ANO TELEIA · |
| 618 | 0x055A, // ARMENIAN APOSTROPHE ՚ |
| 619 | 0x055B, // ARMENIAN EMPHASIS MARK ՛ |
| 620 | 0x055C, // ARMENIAN EXCLAMATION MARK ՜ |
| 621 | 0x055D, // ARMENIAN COMMA ՝ |
| 622 | 0x055E, // ARMENIAN QUESTION MARK ՞ |
| 623 | 0x055F, // ARMENIAN ABBREVIATION MARK ՟ |
| 624 | 0x0589, // ARMENIAN FULL STOP ։ |
| 625 | 0x05C0, // HEBREW PUNCTUATION PASEQ ׀ |
| 626 | 0x05C3, // HEBREW PUNCTUATION SOF PASUQ ׃ |
| 627 | 0x05C6, // HEBREW PUNCTUATION NUN HAFUKHA ׆ |
| 628 | 0x05F3, // HEBREW PUNCTUATION GERESH ׳ |
| 629 | 0x05F4, // HEBREW PUNCTUATION GERSHAYIM ״ |
| 630 | 0x0609, // ARABIC-INDIC PER MILLE SIGN ؉ |
| 631 | 0x060A, // ARABIC-INDIC PER TEN THOUSAND SIGN ؊ |
| 632 | 0x060C, // ARABIC COMMA ، |
| 633 | 0x060D, // ARABIC DATE SEPARATOR ؍ |
| 634 | 0x061B, // ARABIC SEMICOLON ؛ |
| 635 | 0x061E, // ARABIC TRIPLE DOT PUNCTUATION MARK ؞ |
| 636 | 0x061F, // ARABIC QUESTION MARK ؟ |
| 637 | 0x066A, // ARABIC PERCENT SIGN ٪ |
| 638 | 0x066B, // ARABIC DECIMAL SEPARATOR ٫ |
| 639 | 0x066C, // ARABIC THOUSANDS SEPARATOR ٬ |
| 640 | 0x066D, // ARABIC FIVE POINTED STAR ٭ |
| 641 | 0x06D4, // ARABIC FULL STOP ۔ |
| 642 | 0x0700, // SYRIAC END OF PARAGRAPH ܀ |
| 643 | 0x0701, // SYRIAC SUPRALINEAR FULL STOP ܁ |
| 644 | 0x0702, // SYRIAC SUBLINEAR FULL STOP ܂ |
| 645 | 0x0703, // SYRIAC SUPRALINEAR COLON ܃ |
| 646 | 0x0704, // SYRIAC SUBLINEAR COLON ܄ |
| 647 | 0x0705, // SYRIAC HORIZONTAL COLON ܅ |
| 648 | 0x0706, // SYRIAC COLON SKEWED LEFT ܆ |
| 649 | 0x0707, // SYRIAC COLON SKEWED RIGHT ܇ |
| 650 | 0x0708, // SYRIAC SUPRALINEAR COLON SKEWED LEFT ܈ |
| 651 | 0x0709, // SYRIAC SUBLINEAR COLON SKEWED RIGHT ܉ |
| 652 | 0x070A, // SYRIAC CONTRACTION ܊ |
| 653 | 0x070B, // SYRIAC HARKLEAN OBELUS ܋ |
| 654 | 0x070C, // SYRIAC HARKLEAN METOBELUS ܌ |
| 655 | 0x070D, // SYRIAC HARKLEAN ASTERISCUS ܍ |
| 656 | 0x07F7, // NKO SYMBOL GBAKURUNEN ߷ |
| 657 | 0x07F8, // NKO COMMA ߸ |
| 658 | 0x07F9, // NKO EXCLAMATION MARK ߹ |
| 659 | 0x0830, // SAMARITAN PUNCTUATION NEQUDAA ࠰ |
| 660 | 0x0831, // SAMARITAN PUNCTUATION AFSAAQ ࠱ |
| 661 | 0x0832, // SAMARITAN PUNCTUATION ANGED ࠲ |
| 662 | 0x0833, // SAMARITAN PUNCTUATION BAU ࠳ |
| 663 | 0x0834, // SAMARITAN PUNCTUATION ATMAAU ࠴ |
| 664 | 0x0835, // SAMARITAN PUNCTUATION SHIYYAALAA ࠵ |
| 665 | 0x0836, // SAMARITAN ABBREVIATION MARK ࠶ |
| 666 | 0x0837, // SAMARITAN PUNCTUATION MELODIC QITSA ࠷ |
| 667 | 0x0838, // SAMARITAN PUNCTUATION ZIQAA ࠸ |
| 668 | 0x0839, // SAMARITAN PUNCTUATION QITSA ࠹ |
| 669 | 0x083A, // SAMARITAN PUNCTUATION ZAEF ࠺ |
| 670 | 0x083B, // SAMARITAN PUNCTUATION TURU ࠻ |
| 671 | 0x083C, // SAMARITAN PUNCTUATION ARKAANU ࠼ |
| 672 | 0x083D, // SAMARITAN PUNCTUATION SOF MASHFAAT ࠽ |
| 673 | 0x083E, // SAMARITAN PUNCTUATION ANNAAU ࠾ |
| 674 | 0x085E, // MANDAIC PUNCTUATION ࡞ |
| 675 | 0x0964, // DEVANAGARI DANDA । |
| 676 | 0x0965, // DEVANAGARI DOUBLE DANDA ॥ |
| 677 | 0x0970, // DEVANAGARI ABBREVIATION SIGN ॰ |
| 678 | 0x09FD, // BENGALI ABBREVIATION SIGN ৽ |
| 679 | 0x0A76, // GURMUKHI ABBREVIATION SIGN ੶ |
| 680 | 0x0AF0, // GUJARATI ABBREVIATION SIGN ૰ |
| 681 | 0x0C77, // TELUGU SIGN SIDDHAM ౷ |
| 682 | 0x0C84, // KANNADA SIGN SIDDHAM ಄ |
| 683 | 0x0DF4, // SINHALA PUNCTUATION KUNDDALIYA ෴ |
| 684 | 0x0E4F, // THAI CHARACTER FONGMAN ๏ |
| 685 | 0x0E5A, // THAI CHARACTER ANGKHANKHU ๚ |
| 686 | 0x0E5B, // THAI CHARACTER KHOMUT ๛ |
| 687 | 0x0F04, // TIBETAN MARK INITIAL YIG MGO MDUN MA ༄ |
| 688 | 0x0F05, // TIBETAN MARK CLOSING YIG MGO SGAB MA ༅ |
| 689 | 0x0F06, // TIBETAN MARK CARET YIG MGO PHUR SHAD MA ༆ |
| 690 | 0x0F07, // TIBETAN MARK YIG MGO TSHEG SHAD MA ༇ |
| 691 | 0x0F08, // TIBETAN MARK SBRUL SHAD ༈ |
| 692 | 0x0F09, // TIBETAN MARK BSKUR YIG MGO ༉ |
| 693 | 0x0F0A, // TIBETAN MARK BKA- SHOG YIG MGO ༊ |
| 694 | 0x0F0B, // TIBETAN MARK INTERSYLLABIC TSHEG ་ |
| 695 | 0x0F0C, // TIBETAN MARK DELIMITER TSHEG BSTAR ༌ |
| 696 | 0x0F0D, // TIBETAN MARK SHAD ། |
| 697 | 0x0F0E, // TIBETAN MARK NYIS SHAD ༎ |
| 698 | 0x0F0F, // TIBETAN MARK TSHEG SHAD ༏ |
| 699 | 0x0F10, // TIBETAN MARK NYIS TSHEG SHAD ༐ |
| 700 | 0x0F11, // TIBETAN MARK RIN CHEN SPUNGS SHAD ༑ |
| 701 | 0x0F12, // TIBETAN MARK RGYA GRAM SHAD ༒ |
| 702 | 0x0F14, // TIBETAN MARK GTER TSHEG ༔ |
| 703 | 0x0F85, // TIBETAN MARK PALUTA ྅ |
| 704 | 0x0FD0, // TIBETAN MARK BSKA- SHOG GI MGO RGYAN ࿐ |
| 705 | 0x0FD1, // TIBETAN MARK MNYAM YIG GI MGO RGYAN ࿑ |
| 706 | 0x0FD2, // TIBETAN MARK NYIS TSHEG ࿒ |
| 707 | 0x0FD3, // TIBETAN MARK INITIAL BRDA RNYING YIG MGO MDUN MA ࿓ |
| 708 | 0x0FD4, // TIBETAN MARK CLOSING BRDA RNYING YIG MGO SGAB MA ࿔ |
| 709 | 0x0FD9, // TIBETAN MARK LEADING MCHAN RTAGS ࿙ |
| 710 | 0x0FDA, // TIBETAN MARK TRAILING MCHAN RTAGS ࿚ |
| 711 | 0x104A, // MYANMAR SIGN LITTLE SECTION ၊ |
| 712 | 0x104B, // MYANMAR SIGN SECTION ။ |
| 713 | 0x104C, // MYANMAR SYMBOL LOCATIVE ၌ |
| 714 | 0x104D, // MYANMAR SYMBOL COMPLETED ၍ |
| 715 | 0x104E, // MYANMAR SYMBOL AFOREMENTIONED ၎ |
| 716 | 0x104F, // MYANMAR SYMBOL GENITIVE ၏ |
| 717 | 0x10FB, // GEORGIAN PARAGRAPH SEPARATOR ჻ |
| 718 | 0x1360, // ETHIOPIC SECTION MARK ፠ |
| 719 | 0x1361, // ETHIOPIC WORDSPACE ፡ |
| 720 | 0x1362, // ETHIOPIC FULL STOP ። |
| 721 | 0x1363, // ETHIOPIC COMMA ፣ |
| 722 | 0x1364, // ETHIOPIC SEMICOLON ፤ |
| 723 | 0x1365, // ETHIOPIC COLON ፥ |
| 724 | 0x1366, // ETHIOPIC PREFACE COLON ፦ |
| 725 | 0x1367, // ETHIOPIC QUESTION MARK ፧ |
| 726 | 0x1368, // ETHIOPIC PARAGRAPH SEPARATOR ፨ |
| 727 | 0x166E, // CANADIAN SYLLABICS FULL STOP ᙮ |
| 728 | 0x16EB, // RUNIC SINGLE PUNCTUATION ᛫ |
| 729 | 0x16EC, // RUNIC MULTIPLE PUNCTUATION ᛬ |
| 730 | 0x16ED, // RUNIC CROSS PUNCTUATION ᛭ |
| 731 | 0x1735, // PHILIPPINE SINGLE PUNCTUATION ᜵ |
| 732 | 0x1736, // PHILIPPINE DOUBLE PUNCTUATION ᜶ |
| 733 | 0x17D4, // KHMER SIGN KHAN ។ |
| 734 | 0x17D5, // KHMER SIGN BARIYOOSAN ៕ |
| 735 | 0x17D6, // KHMER SIGN CAMNUC PII KUUH ៖ |
| 736 | 0x17D8, // KHMER SIGN BEYYAL ៘ |
| 737 | 0x17D9, // KHMER SIGN PHNAEK MUAN ៙ |
| 738 | 0x17DA, // KHMER SIGN KOOMUUT ៚ |
| 739 | 0x1800, // MONGOLIAN BIRGA ᠀ |
| 740 | 0x1801, // MONGOLIAN ELLIPSIS ᠁ |
| 741 | 0x1802, // MONGOLIAN COMMA ᠂ |
| 742 | 0x1803, // MONGOLIAN FULL STOP ᠃ |
| 743 | 0x1804, // MONGOLIAN COLON ᠄ |
| 744 | 0x1805, // MONGOLIAN FOUR DOTS ᠅ |
| 745 | 0x1807, // MONGOLIAN SIBE SYLLABLE BOUNDARY MARKER ᠇ |
| 746 | 0x1808, // MONGOLIAN MANCHU COMMA ᠈ |
| 747 | 0x1809, // MONGOLIAN MANCHU FULL STOP ᠉ |
| 748 | 0x180A, // MONGOLIAN NIRUGU ᠊ |
| 749 | 0x1944, // LIMBU EXCLAMATION MARK ᥄ |
| 750 | 0x1945, // LIMBU QUESTION MARK ᥅ |
| 751 | 0x1A1E, // BUGINESE PALLAWA ᨞ |
| 752 | 0x1A1F, // BUGINESE END OF SECTION ᨟ |
| 753 | 0x1AA0, // TAI THAM SIGN WIANG ᪠ |
| 754 | 0x1AA1, // TAI THAM SIGN WIANGWAAK ᪡ |
| 755 | 0x1AA2, // TAI THAM SIGN SAWAN ᪢ |
| 756 | 0x1AA3, // TAI THAM SIGN KEOW ᪣ |
| 757 | 0x1AA4, // TAI THAM SIGN HOY ᪤ |
| 758 | 0x1AA5, // TAI THAM SIGN DOKMAI ᪥ |
| 759 | 0x1AA6, // TAI THAM SIGN REVERSED ROTATED RANA ᪦ |
| 760 | 0x1AA8, // TAI THAM SIGN KAAN ᪨ |
| 761 | 0x1AA9, // TAI THAM SIGN KAANKUU ᪩ |
| 762 | 0x1AAA, // TAI THAM SIGN SATKAAN ᪪ |
| 763 | 0x1AAB, // TAI THAM SIGN SATKAANKUU ᪫ |
| 764 | 0x1AAC, // TAI THAM SIGN HANG ᪬ |
| 765 | 0x1AAD, // TAI THAM SIGN CAANG ᪭ |
| 766 | 0x1B5A, // BALINESE PANTI ᭚ |
| 767 | 0x1B5B, // BALINESE PAMADA ᭛ |
| 768 | 0x1B5C, // BALINESE WINDU ᭜ |
| 769 | 0x1B5D, // BALINESE CARIK PAMUNGKAH ᭝ |
| 770 | 0x1B5E, // BALINESE CARIK SIKI ᭞ |
| 771 | 0x1B5F, // BALINESE CARIK PAREREN ᭟ |
| 772 | 0x1B60, // BALINESE PAMENENG ᭠ |
| 773 | 0x1BFC, // BATAK SYMBOL BINDU NA METEK ᯼ |
| 774 | 0x1BFD, // BATAK SYMBOL BINDU PINARBORAS ᯽ |
| 775 | 0x1BFE, // BATAK SYMBOL BINDU JUDUL ᯾ |
| 776 | 0x1BFF, // BATAK SYMBOL BINDU PANGOLAT ᯿ |
| 777 | 0x1C3B, // LEPCHA PUNCTUATION TA-ROL ᰻ |
| 778 | 0x1C3C, // LEPCHA PUNCTUATION NYET THYOOM TA-ROL ᰼ |
| 779 | 0x1C3D, // LEPCHA PUNCTUATION CER-WA ᰽ |
| 780 | 0x1C3E, // LEPCHA PUNCTUATION TSHOOK CER-WA ᰾ |
| 781 | 0x1C3F, // LEPCHA PUNCTUATION TSHOOK ᰿ |
| 782 | 0x1C7E, // OL CHIKI PUNCTUATION MUCAAD ᱾ |
| 783 | 0x1C7F, // OL CHIKI PUNCTUATION DOUBLE MUCAAD ᱿ |
| 784 | 0x1CC0, // SUNDANESE PUNCTUATION BINDU SURYA ᳀ |
| 785 | 0x1CC1, // SUNDANESE PUNCTUATION BINDU PANGLONG ᳁ |
| 786 | 0x1CC2, // SUNDANESE PUNCTUATION BINDU PURNAMA ᳂ |
| 787 | 0x1CC3, // SUNDANESE PUNCTUATION BINDU CAKRA ᳃ |
| 788 | 0x1CC4, // SUNDANESE PUNCTUATION BINDU LEU SATANGA ᳄ |
| 789 | 0x1CC5, // SUNDANESE PUNCTUATION BINDU KA SATANGA ᳅ |
| 790 | 0x1CC6, // SUNDANESE PUNCTUATION BINDU DA SATANGA ᳆ |
| 791 | 0x1CC7, // SUNDANESE PUNCTUATION BINDU BA SATANGA ᳇ |
| 792 | 0x1CD3, // VEDIC SIGN NIHSHVASA ᳓ |
| 793 | 0x2016, // DOUBLE VERTICAL LINE ‖ |
| 794 | 0x2017, // DOUBLE LOW LINE ‗ |
| 795 | 0x2020, // DAGGER † |
| 796 | 0x2021, // DOUBLE DAGGER ‡ |
| 797 | 0x2022, // BULLET • |
| 798 | 0x2023, // TRIANGULAR BULLET ‣ |
| 799 | 0x2024, // ONE DOT LEADER ․ |
| 800 | 0x2025, // TWO DOT LEADER ‥ |
| 801 | 0x2026, // HORIZONTAL ELLIPSIS … |
| 802 | 0x2027, // HYPHENATION POINT ‧ |
| 803 | 0x2030, // PER MILLE SIGN ‰ |
| 804 | 0x2031, // PER TEN THOUSAND SIGN ‱ |
| 805 | 0x2032, // PRIME ′ |
| 806 | 0x2033, // DOUBLE PRIME ″ |
| 807 | 0x2034, // TRIPLE PRIME ‴ |
| 808 | 0x2035, // REVERSED PRIME ‵ |
| 809 | 0x2036, // REVERSED DOUBLE PRIME ‶ |
| 810 | 0x2037, // REVERSED TRIPLE PRIME ‷ |
| 811 | 0x2038, // CARET ‸ |
| 812 | 0x203B, // REFERENCE MARK ※ |
| 813 | 0x203C, // DOUBLE EXCLAMATION MARK ‼ |
| 814 | 0x203D, // INTERROBANG ‽ |
| 815 | 0x203E, // OVERLINE ‾ |
| 816 | 0x2041, // CARET INSERTION POINT ⁁ |
| 817 | 0x2042, // ASTERISM ⁂ |
| 818 | 0x2043, // HYPHEN BULLET ⁃ |
| 819 | 0x2047, // DOUBLE QUESTION MARK ⁇ |
| 820 | 0x2048, // QUESTION EXCLAMATION MARK ⁈ |
| 821 | 0x2049, // EXCLAMATION QUESTION MARK ⁉ |
| 822 | 0x204A, // TIRONIAN SIGN ET ⁊ |
| 823 | 0x204B, // REVERSED PILCROW SIGN ⁋ |
| 824 | 0x204C, // BLACK LEFTWARDS BULLET ⁌ |
| 825 | 0x204D, // BLACK RIGHTWARDS BULLET ⁍ |
| 826 | 0x204E, // LOW ASTERISK ⁎ |
| 827 | 0x204F, // REVERSED SEMICOLON ⁏ |
| 828 | 0x2050, // CLOSE UP ⁐ |
| 829 | 0x2051, // TWO ASTERISKS ALIGNED VERTICALLY ⁑ |
| 830 | 0x2053, // SWUNG DASH ⁓ |
| 831 | 0x2055, // FLOWER PUNCTUATION MARK ⁕ |
| 832 | 0x2056, // THREE DOT PUNCTUATION ⁖ |
| 833 | 0x2057, // QUADRUPLE PRIME ⁗ |
| 834 | 0x2058, // FOUR DOT PUNCTUATION ⁘ |
| 835 | 0x2059, // FIVE DOT PUNCTUATION ⁙ |
| 836 | 0x205A, // TWO DOT PUNCTUATION ⁚ |
| 837 | 0x205B, // FOUR DOT MARK ⁛ |
| 838 | 0x205C, // DOTTED CROSS ⁜ |
| 839 | 0x205D, // TRICOLON ⁝ |
| 840 | 0x205E, // VERTICAL FOUR DOTS ⁞ |
| 841 | 0x2CF9, // COPTIC OLD NUBIAN FULL STOP ⳹ |
| 842 | 0x2CFA, // COPTIC OLD NUBIAN DIRECT QUESTION MARK ⳺ |
| 843 | 0x2CFB, // COPTIC OLD NUBIAN INDIRECT QUESTION MARK ⳻ |
| 844 | 0x2CFC, // COPTIC OLD NUBIAN VERSE DIVIDER ⳼ |
| 845 | 0x2CFE, // COPTIC FULL STOP ⳾ |
| 846 | 0x2CFF, // COPTIC MORPHOLOGICAL DIVIDER ⳿ |
| 847 | 0x2D70, // TIFINAGH SEPARATOR MARK ⵰ |
| 848 | 0x2E00, // RIGHT ANGLE SUBSTITUTION MARKER ⸀ |
| 849 | 0x2E01, // RIGHT ANGLE DOTTED SUBSTITUTION MARKER ⸁ |
| 850 | 0x2E06, // RAISED INTERPOLATION MARKER ⸆ |
| 851 | 0x2E07, // RAISED DOTTED INTERPOLATION MARKER ⸇ |
| 852 | 0x2E08, // DOTTED TRANSPOSITION MARKER ⸈ |
| 853 | 0x2E0B, // RAISED SQUARE ⸋ |
| 854 | 0x2E0E, // EDITORIAL CORONIS ⸎ |
| 855 | 0x2E0F, // PARAGRAPHOS ⸏ |
| 856 | 0x2E10, // FORKED PARAGRAPHOS ⸐ |
| 857 | 0x2E11, // REVERSED FORKED PARAGRAPHOS ⸑ |
| 858 | 0x2E12, // HYPODIASTOLE ⸒ |
| 859 | 0x2E13, // DOTTED OBELOS ⸓ |
| 860 | 0x2E14, // DOWNWARDS ANCORA ⸔ |
| 861 | 0x2E15, // UPWARDS ANCORA ⸕ |
| 862 | 0x2E16, // DOTTED RIGHT-POINTING ANGLE ⸖ |
| 863 | 0x2E18, // INVERTED INTERROBANG ⸘ |
| 864 | 0x2E19, // PALM BRANCH ⸙ |
| 865 | 0x2E1B, // TILDE WITH RING ABOVE ⸛ |
| 866 | 0x2E1E, // TILDE WITH DOT ABOVE ⸞ |
| 867 | 0x2E1F, // TILDE WITH DOT BELOW ⸟ |
| 868 | 0x2E2A, // TWO DOTS OVER ONE DOT PUNCTUATION ⸪ |
| 869 | 0x2E2B, // ONE DOT OVER TWO DOTS PUNCTUATION ⸫ |
| 870 | 0x2E2C, // SQUARED FOUR DOT PUNCTUATION ⸬ |
| 871 | 0x2E2D, // FIVE DOT MARK ⸭ |
| 872 | 0x2E2E, // REVERSED QUESTION MARK ⸮ |
| 873 | 0x2E30, // RING POINT ⸰ |
| 874 | 0x2E31, // WORD SEPARATOR MIDDLE DOT ⸱ |
| 875 | 0x2E32, // TURNED COMMA ⸲ |
| 876 | 0x2E33, // RAISED DOT ⸳ |
| 877 | 0x2E34, // RAISED COMMA ⸴ |
| 878 | 0x2E35, // TURNED SEMICOLON ⸵ |
| 879 | 0x2E36, // DAGGER WITH LEFT GUARD ⸶ |
| 880 | 0x2E37, // DAGGER WITH RIGHT GUARD ⸷ |
| 881 | 0x2E38, // TURNED DAGGER ⸸ |
| 882 | 0x2E39, // TOP HALF SECTION SIGN ⸹ |
| 883 | 0x2E3C, // STENOGRAPHIC FULL STOP ⸼ |
| 884 | 0x2E3D, // VERTICAL SIX DOTS ⸽ |
| 885 | 0x2E3E, // WIGGLY VERTICAL LINE ⸾ |
| 886 | 0x2E3F, // CAPITULUM ⸿ |
| 887 | 0x2E41, // REVERSED COMMA ⹁ |
| 888 | 0x2E43, // DASH WITH LEFT UPTURN ⹃ |
| 889 | 0x2E44, // DOUBLE SUSPENSION MARK ⹄ |
| 890 | 0x2E45, // INVERTED LOW KAVYKA ⹅ |
| 891 | 0x2E46, // INVERTED LOW KAVYKA WITH KAVYKA ABOVE ⹆ |
| 892 | 0x2E47, // LOW KAVYKA ⹇ |
| 893 | 0x2E48, // LOW KAVYKA WITH DOT ⹈ |
| 894 | 0x2E49, // DOUBLE STACKED COMMA ⹉ |
| 895 | 0x2E4A, // DOTTED SOLIDUS ⹊ |
| 896 | 0x2E4B, // TRIPLE DAGGER ⹋ |
| 897 | 0x2E4C, // MEDIEVAL COMMA ⹌ |
| 898 | 0x2E4D, // PARAGRAPHUS MARK ⹍ |
| 899 | 0x2E4E, // PUNCTUS ELEVATUS MARK ⹎ |
| 900 | 0x2E4F, // CORNISH VERSE DIVIDER ⹏ |
| 901 | 0x3001, // IDEOGRAPHIC COMMA 、 |
| 902 | 0x3002, // IDEOGRAPHIC FULL STOP 。 |
| 903 | 0x3003, // DITTO MARK 〃 |
| 904 | 0x303D, // PART ALTERNATION MARK 〽 |
| 905 | 0x30FB, // KATAKANA MIDDLE DOT ・ |
| 906 | 0xA4FE, // LISU PUNCTUATION COMMA ꓾ |
| 907 | 0xA4FF, // LISU PUNCTUATION FULL STOP ꓿ |
| 908 | 0xA60D, // VAI COMMA ꘍ |
| 909 | 0xA60E, // VAI FULL STOP ꘎ |
| 910 | 0xA60F, // VAI QUESTION MARK ꘏ |
| 911 | 0xA673, // SLAVONIC ASTERISK ꙳ |
| 912 | 0xA67E, // CYRILLIC KAVYKA ꙾ |
| 913 | 0xA6F2, // BAMUM NJAEMLI ꛲ |
| 914 | 0xA6F3, // BAMUM FULL STOP ꛳ |
| 915 | 0xA6F4, // BAMUM COLON ꛴ |
| 916 | 0xA6F5, // BAMUM COMMA ꛵ |
| 917 | 0xA6F6, // BAMUM SEMICOLON ꛶ |
| 918 | 0xA6F7, // BAMUM QUESTION MARK ꛷ |
| 919 | 0xA874, // PHAGS-PA SINGLE HEAD MARK ꡴ |
| 920 | 0xA875, // PHAGS-PA DOUBLE HEAD MARK ꡵ |
| 921 | 0xA876, // PHAGS-PA MARK SHAD ꡶ |
| 922 | 0xA877, // PHAGS-PA MARK DOUBLE SHAD ꡷ |
| 923 | 0xA8CE, // SAURASHTRA DANDA ꣎ |
| 924 | 0xA8CF, // SAURASHTRA DOUBLE DANDA ꣏ |
| 925 | 0xA8F8, // DEVANAGARI SIGN PUSHPIKA ꣸ |
| 926 | 0xA8F9, // DEVANAGARI GAP FILLER ꣹ |
| 927 | 0xA8FA, // DEVANAGARI CARET ꣺ |
| 928 | 0xA8FC, // DEVANAGARI SIGN SIDDHAM ꣼ |
| 929 | 0xA92E, // KAYAH LI SIGN CWI ꤮ |
| 930 | 0xA92F, // KAYAH LI SIGN SHYA ꤯ |
| 931 | 0xA95F, // REJANG SECTION MARK ꥟ |
| 932 | 0xA9C1, // JAVANESE LEFT RERENGGAN ꧁ |
| 933 | 0xA9C2, // JAVANESE RIGHT RERENGGAN ꧂ |
| 934 | 0xA9C3, // JAVANESE PADA ANDAP ꧃ |
| 935 | 0xA9C4, // JAVANESE PADA MADYA ꧄ |
| 936 | 0xA9C5, // JAVANESE PADA LUHUR ꧅ |
| 937 | 0xA9C6, // JAVANESE PADA WINDU ꧆ |
| 938 | 0xA9C7, // JAVANESE PADA PANGKAT ꧇ |
| 939 | 0xA9C8, // JAVANESE PADA LINGSA ꧈ |
| 940 | 0xA9C9, // JAVANESE PADA LUNGSI ꧉ |
| 941 | 0xA9CA, // JAVANESE PADA ADEG ꧊ |
| 942 | 0xA9CB, // JAVANESE PADA ADEG ADEG ꧋ |
| 943 | 0xA9CC, // JAVANESE PADA PISELEH ꧌ |
| 944 | 0xA9CD, // JAVANESE TURNED PADA PISELEH ꧍ |
| 945 | 0xA9DE, // JAVANESE PADA TIRTA TUMETES ꧞ |
| 946 | 0xA9DF, // JAVANESE PADA ISEN-ISEN ꧟ |
| 947 | 0xAA5C, // CHAM PUNCTUATION SPIRAL ꩜ |
| 948 | 0xAA5D, // CHAM PUNCTUATION DANDA ꩝ |
| 949 | 0xAA5E, // CHAM PUNCTUATION DOUBLE DANDA ꩞ |
| 950 | 0xAA5F, // CHAM PUNCTUATION TRIPLE DANDA ꩟ |
| 951 | 0xAADE, // TAI VIET SYMBOL HO HOI ꫞ |
| 952 | 0xAADF, // TAI VIET SYMBOL KOI KOI ꫟ |
| 953 | 0xAAF0, // MEETEI MAYEK CHEIKHAN ꫰ |
| 954 | 0xAAF1, // MEETEI MAYEK AHANG KHUDAM ꫱ |
| 955 | 0xABEB, // MEETEI MAYEK CHEIKHEI ꯫ |
| 956 | 0xFE10, // PRESENTATION FORM FOR VERTICAL COMMA ︐ |
| 957 | 0xFE11, // PRESENTATION FORM FOR VERTICAL IDEOGRAPHIC COMMA ︑ |
| 958 | 0xFE12, // PRESENTATION FORM FOR VERTICAL IDEOGRAPHIC FULL STOP ︒ |
| 959 | 0xFE13, // PRESENTATION FORM FOR VERTICAL COLON ︓ |
| 960 | 0xFE14, // PRESENTATION FORM FOR VERTICAL SEMICOLON ︔ |
| 961 | 0xFE15, // PRESENTATION FORM FOR VERTICAL EXCLAMATION MARK ︕ |
| 962 | 0xFE16, // PRESENTATION FORM FOR VERTICAL QUESTION MARK ︖ |
| 963 | 0xFE19, // PRESENTATION FORM FOR VERTICAL HORIZONTAL ELLIPSIS ︙ |
| 964 | 0xFE30, // PRESENTATION FORM FOR VERTICAL TWO DOT LEADER ︰ |
| 965 | 0xFE45, // SESAME DOT ﹅ |
| 966 | 0xFE46, // WHITE SESAME DOT ﹆ |
| 967 | 0xFE49, // DASHED OVERLINE ﹉ |
| 968 | 0xFE4A, // CENTRELINE OVERLINE ﹊ |
| 969 | 0xFE4B, // WAVY OVERLINE ﹋ |
| 970 | 0xFE4C, // DOUBLE WAVY OVERLINE ﹌ |
| 971 | 0xFE50, // SMALL COMMA ﹐ |
| 972 | 0xFE51, // SMALL IDEOGRAPHIC COMMA ﹑ |
| 973 | 0xFE52, // SMALL FULL STOP ﹒ |
| 974 | 0xFE54, // SMALL SEMICOLON ﹔ |
| 975 | 0xFE55, // SMALL COLON ﹕ |
| 976 | 0xFE56, // SMALL QUESTION MARK ﹖ |
| 977 | 0xFE57, // SMALL EXCLAMATION MARK ﹗ |
| 978 | 0xFE5F, // SMALL NUMBER SIGN ﹟ |
| 979 | 0xFE60, // SMALL AMPERSAND ﹠ |
| 980 | 0xFE61, // SMALL ASTERISK ﹡ |
| 981 | 0xFE68, // SMALL REVERSE SOLIDUS ﹨ |
| 982 | 0xFE6A, // SMALL PERCENT SIGN ﹪ |
| 983 | 0xFE6B, // SMALL COMMERCIAL AT ﹫ |
| 984 | 0xFF01, // FULLWIDTH EXCLAMATION MARK ！ |
| 985 | 0xFF02, // FULLWIDTH QUOTATION MARK ＂ |
| 986 | 0xFF03, // FULLWIDTH NUMBER SIGN ＃ |
| 987 | 0xFF05, // FULLWIDTH PERCENT SIGN ％ |
| 988 | 0xFF06, // FULLWIDTH AMPERSAND ＆ |
| 989 | 0xFF07, // FULLWIDTH APOSTROPHE ＇ |
| 990 | 0xFF0A, // FULLWIDTH ASTERISK ＊ |
| 991 | 0xFF0C, // FULLWIDTH COMMA ， |
| 992 | 0xFF0E, // FULLWIDTH FULL STOP ． |
| 993 | 0xFF0F, // FULLWIDTH SOLIDUS ／ |
| 994 | 0xFF1A, // FULLWIDTH COLON ： |
| 995 | 0xFF1B, // FULLWIDTH SEMICOLON ； |
| 996 | 0xFF1F, // FULLWIDTH QUESTION MARK ？ |
| 997 | 0xFF20, // FULLWIDTH COMMERCIAL AT ＠ |
| 998 | 0xFF3C, // FULLWIDTH REVERSE SOLIDUS ＼ |
| 999 | 0xFF61, // HALFWIDTH IDEOGRAPHIC FULL STOP ｡ |
| 1000 | 0xFF64, // HALFWIDTH IDEOGRAPHIC COMMA ､ |
| 1001 | 0xFF65, // HALFWIDTH KATAKANA MIDDLE DOT ･ |
| 1002 | 0x10100, // AEGEAN WORD SEPARATOR LINE 𐄀 |
| 1003 | 0x10101, // AEGEAN WORD SEPARATOR DOT 𐄁 |
| 1004 | 0x10102, // AEGEAN CHECK MARK 𐄂 |
| 1005 | 0x1039F, // UGARITIC WORD DIVIDER 𐎟 |
| 1006 | 0x103D0, // OLD PERSIAN WORD DIVIDER 𐏐 |
| 1007 | 0x1056F, // CAUCASIAN ALBANIAN CITATION MARK 𐕯 |
| 1008 | 0x10857, // IMPERIAL ARAMAIC SECTION SIGN 𐡗 |
| 1009 | 0x1091F, // PHOENICIAN WORD SEPARATOR 𐤟 |
| 1010 | 0x1093F, // LYDIAN TRIANGULAR MARK 𐤿 |
| 1011 | 0x10A50, // KHAROSHTHI PUNCTUATION DOT 𐩐 |
| 1012 | 0x10A51, // KHAROSHTHI PUNCTUATION SMALL CIRCLE 𐩑 |
| 1013 | 0x10A52, // KHAROSHTHI PUNCTUATION CIRCLE 𐩒 |
| 1014 | 0x10A53, // KHAROSHTHI PUNCTUATION CRESCENT BAR 𐩓 |
| 1015 | 0x10A54, // KHAROSHTHI PUNCTUATION MANGALAM 𐩔 |
| 1016 | 0x10A55, // KHAROSHTHI PUNCTUATION LOTUS 𐩕 |
| 1017 | 0x10A56, // KHAROSHTHI PUNCTUATION DANDA 𐩖 |
| 1018 | 0x10A57, // KHAROSHTHI PUNCTUATION DOUBLE DANDA 𐩗 |
| 1019 | 0x10A58, // KHAROSHTHI PUNCTUATION LINES 𐩘 |
| 1020 | 0x10A7F, // OLD SOUTH ARABIAN NUMERIC INDICATOR 𐩿 |
| 1021 | 0x10AF0, // MANICHAEAN PUNCTUATION STAR 𐫰 |
| 1022 | 0x10AF1, // MANICHAEAN PUNCTUATION FLEURON 𐫱 |
| 1023 | 0x10AF2, // MANICHAEAN PUNCTUATION DOUBLE DOT WITHIN DOT 𐫲 |
| 1024 | 0x10AF3, // MANICHAEAN PUNCTUATION DOT WITHIN DOT 𐫳 |
| 1025 | 0x10AF4, // MANICHAEAN PUNCTUATION DOT 𐫴 |
| 1026 | 0x10AF5, // MANICHAEAN PUNCTUATION TWO DOTS 𐫵 |
| 1027 | 0x10AF6, // MANICHAEAN PUNCTUATION LINE FILLER 𐫶 |
| 1028 | 0x10B39, // AVESTAN ABBREVIATION MARK 𐬹 |
| 1029 | 0x10B3A, // TINY TWO DOTS OVER ONE DOT PUNCTUATION 𐬺 |
| 1030 | 0x10B3B, // SMALL TWO DOTS OVER ONE DOT PUNCTUATION 𐬻 |
| 1031 | 0x10B3C, // LARGE TWO DOTS OVER ONE DOT PUNCTUATION 𐬼 |
| 1032 | 0x10B3D, // LARGE ONE DOT OVER TWO DOTS PUNCTUATION 𐬽 |
| 1033 | 0x10B3E, // LARGE TWO RINGS OVER ONE RING PUNCTUATION 𐬾 |
| 1034 | 0x10B3F, // LARGE ONE RING OVER TWO RINGS PUNCTUATION 𐬿 |
| 1035 | 0x10B99, // PSALTER PAHLAVI SECTION MARK 𐮙 |
| 1036 | 0x10B9A, // PSALTER PAHLAVI TURNED SECTION MARK 𐮚 |
| 1037 | 0x10B9B, // PSALTER PAHLAVI FOUR DOTS WITH CROSS 𐮛 |
| 1038 | 0x10B9C, // PSALTER PAHLAVI FOUR DOTS WITH DOT 𐮜 |
| 1039 | 0x10F55, // SOGDIAN PUNCTUATION TWO VERTICAL BARS 𐽕 |
| 1040 | 0x10F56, // SOGDIAN PUNCTUATION TWO VERTICAL BARS WITH DOTS 𐽖 |
| 1041 | 0x10F57, // SOGDIAN PUNCTUATION CIRCLE WITH DOT 𐽗 |
| 1042 | 0x10F58, // SOGDIAN PUNCTUATION TWO CIRCLES WITH DOTS 𐽘 |
| 1043 | 0x10F59, // SOGDIAN PUNCTUATION HALF CIRCLE WITH DOT 𐽙 |
| 1044 | 0x11047, // BRAHMI DANDA 𑁇 |
| 1045 | 0x11048, // BRAHMI DOUBLE DANDA 𑁈 |
| 1046 | 0x11049, // BRAHMI PUNCTUATION DOT 𑁉 |
| 1047 | 0x1104A, // BRAHMI PUNCTUATION DOUBLE DOT 𑁊 |
| 1048 | 0x1104B, // BRAHMI PUNCTUATION LINE 𑁋 |
| 1049 | 0x1104C, // BRAHMI PUNCTUATION CRESCENT BAR 𑁌 |
| 1050 | 0x1104D, // BRAHMI PUNCTUATION LOTUS 𑁍 |
| 1051 | 0x110BB, // KAITHI ABBREVIATION SIGN 𑂻 |
| 1052 | 0x110BC, // KAITHI ENUMERATION SIGN 𑂼 |
| 1053 | 0x110BE, // KAITHI SECTION MARK 𑂾 |
| 1054 | 0x110BF, // KAITHI DOUBLE SECTION MARK 𑂿 |
| 1055 | 0x110C0, // KAITHI DANDA 𑃀 |
| 1056 | 0x110C1, // KAITHI DOUBLE DANDA 𑃁 |
| 1057 | 0x11140, // CHAKMA SECTION MARK 𑅀 |
| 1058 | 0x11141, // CHAKMA DANDA 𑅁 |
| 1059 | 0x11142, // CHAKMA DOUBLE DANDA 𑅂 |
| 1060 | 0x11143, // CHAKMA QUESTION MARK 𑅃 |
| 1061 | 0x11174, // MAHAJANI ABBREVIATION SIGN 𑅴 |
| 1062 | 0x11175, // MAHAJANI SECTION MARK 𑅵 |
| 1063 | 0x111C5, // SHARADA DANDA 𑇅 |
| 1064 | 0x111C6, // SHARADA DOUBLE DANDA 𑇆 |
| 1065 | 0x111C7, // SHARADA ABBREVIATION SIGN 𑇇 |
| 1066 | 0x111C8, // SHARADA SEPARATOR 𑇈 |
| 1067 | 0x111CD, // SHARADA SUTRA MARK 𑇍 |
| 1068 | 0x111DB, // SHARADA SIGN SIDDHAM 𑇛 |
| 1069 | 0x111DD, // SHARADA CONTINUATION SIGN 𑇝 |
| 1070 | 0x111DE, // SHARADA SECTION MARK-1 𑇞 |
| 1071 | 0x111DF, // SHARADA SECTION MARK-2 𑇟 |
| 1072 | 0x11238, // KHOJKI DANDA 𑈸 |
| 1073 | 0x11239, // KHOJKI DOUBLE DANDA 𑈹 |
| 1074 | 0x1123A, // KHOJKI WORD SEPARATOR 𑈺 |
| 1075 | 0x1123B, // KHOJKI SECTION MARK 𑈻 |
| 1076 | 0x1123C, // KHOJKI DOUBLE SECTION MARK 𑈼 |
| 1077 | 0x1123D, // KHOJKI ABBREVIATION SIGN 𑈽 |
| 1078 | 0x112A9, // MULTANI SECTION MARK 𑊩 |
| 1079 | 0x1144B, // NEWA DANDA 𑑋 |
| 1080 | 0x1144C, // NEWA DOUBLE DANDA 𑑌 |
| 1081 | 0x1144D, // NEWA COMMA 𑑍 |
| 1082 | 0x1144E, // NEWA GAP FILLER 𑑎 |
| 1083 | 0x1144F, // NEWA ABBREVIATION SIGN 𑑏 |
| 1084 | 0x1145B, // NEWA PLACEHOLDER MARK 𑑛 |
| 1085 | 0x1145D, // NEWA INSERTION SIGN 𑑝 |
| 1086 | 0x114C6, // TIRHUTA ABBREVIATION SIGN 𑓆 |
| 1087 | 0x115C1, // SIDDHAM SIGN SIDDHAM 𑗁 |
| 1088 | 0x115C2, // SIDDHAM DANDA 𑗂 |
| 1089 | 0x115C3, // SIDDHAM DOUBLE DANDA 𑗃 |
| 1090 | 0x115C4, // SIDDHAM SEPARATOR DOT 𑗄 |
| 1091 | 0x115C5, // SIDDHAM SEPARATOR BAR 𑗅 |
| 1092 | 0x115C6, // SIDDHAM REPETITION MARK-1 𑗆 |
| 1093 | 0x115C7, // SIDDHAM REPETITION MARK-2 𑗇 |
| 1094 | 0x115C8, // SIDDHAM REPETITION MARK-3 𑗈 |
| 1095 | 0x115C9, // SIDDHAM END OF TEXT MARK 𑗉 |
| 1096 | 0x115CA, // SIDDHAM SECTION MARK WITH TRIDENT AND U-SHAPED ORNAMENTS 𑗊 |
| 1097 | 0x115CB, // SIDDHAM SECTION MARK WITH TRIDENT AND DOTTED CRESCENTS 𑗋 |
| 1098 | 0x115CC, // SIDDHAM SECTION MARK WITH RAYS AND DOTTED CRESCENTS 𑗌 |
| 1099 | 0x115CD, // SIDDHAM SECTION MARK WITH RAYS AND DOTTED DOUBLE CRESCENTS 𑗍 |
| 1100 | 0x115CE, // SIDDHAM SECTION MARK WITH RAYS AND DOTTED TRIPLE CRESCENTS 𑗎 |
| 1101 | 0x115CF, // SIDDHAM SECTION MARK DOUBLE RING 𑗏 |
| 1102 | 0x115D0, // SIDDHAM SECTION MARK DOUBLE RING WITH RAYS 𑗐 |
| 1103 | 0x115D1, // SIDDHAM SECTION MARK WITH DOUBLE CRESCENTS 𑗑 |
| 1104 | 0x115D2, // SIDDHAM SECTION MARK WITH TRIPLE CRESCENTS 𑗒 |
| 1105 | 0x115D3, // SIDDHAM SECTION MARK WITH QUADRUPLE CRESCENTS 𑗓 |
| 1106 | 0x115D4, // SIDDHAM SECTION MARK WITH SEPTUPLE CRESCENTS 𑗔 |
| 1107 | 0x115D5, // SIDDHAM SECTION MARK WITH CIRCLES AND RAYS 𑗕 |
| 1108 | 0x115D6, // SIDDHAM SECTION MARK WITH CIRCLES AND TWO ENCLOSURES 𑗖 |
| 1109 | 0x115D7, // SIDDHAM SECTION MARK WITH CIRCLES AND FOUR ENCLOSURES 𑗗 |
| 1110 | 0x11641, // MODI DANDA 𑙁 |
| 1111 | 0x11642, // MODI DOUBLE DANDA 𑙂 |
| 1112 | 0x11643, // MODI ABBREVIATION SIGN 𑙃 |
| 1113 | 0x11660, // MONGOLIAN BIRGA WITH ORNAMENT 𑙠 |
| 1114 | 0x11661, // MONGOLIAN ROTATED BIRGA 𑙡 |
| 1115 | 0x11662, // MONGOLIAN DOUBLE BIRGA WITH ORNAMENT 𑙢 |
| 1116 | 0x11663, // MONGOLIAN TRIPLE BIRGA WITH ORNAMENT 𑙣 |
| 1117 | 0x11664, // MONGOLIAN BIRGA WITH DOUBLE ORNAMENT 𑙤 |
| 1118 | 0x11665, // MONGOLIAN ROTATED BIRGA WITH ORNAMENT 𑙥 |
| 1119 | 0x11666, // MONGOLIAN ROTATED BIRGA WITH DOUBLE ORNAMENT 𑙦 |
| 1120 | 0x11667, // MONGOLIAN INVERTED BIRGA 𑙧 |
| 1121 | 0x11668, // MONGOLIAN INVERTED BIRGA WITH DOUBLE ORNAMENT 𑙨 |
| 1122 | 0x11669, // MONGOLIAN SWIRL BIRGA 𑙩 |
| 1123 | 0x1166A, // MONGOLIAN SWIRL BIRGA WITH ORNAMENT 𑙪 |
| 1124 | 0x1166B, // MONGOLIAN SWIRL BIRGA WITH DOUBLE ORNAMENT 𑙫 |
| 1125 | 0x1166C, // MONGOLIAN TURNED SWIRL BIRGA WITH DOUBLE ORNAMENT 𑙬 |
| 1126 | 0x1173C, // AHOM SIGN SMALL SECTION 𑜼 |
| 1127 | 0x1173D, // AHOM SIGN SECTION 𑜽 |
| 1128 | 0x1173E, // AHOM SIGN RULAI 𑜾 |
| 1129 | 0x1183B, // DOGRA ABBREVIATION SIGN 𑠻 |
| 1130 | 0x119E2, // NANDINAGARI SIGN SIDDHAM 𑧢 |
| 1131 | 0x11A3F, // ZANABAZAR SQUARE INITIAL HEAD MARK 𑨿 |
| 1132 | 0x11A40, // ZANABAZAR SQUARE CLOSING HEAD MARK 𑩀 |
| 1133 | 0x11A41, // ZANABAZAR SQUARE MARK TSHEG 𑩁 |
| 1134 | 0x11A42, // ZANABAZAR SQUARE MARK SHAD 𑩂 |
| 1135 | 0x11A43, // ZANABAZAR SQUARE MARK DOUBLE SHAD 𑩃 |
| 1136 | 0x11A44, // ZANABAZAR SQUARE MARK LONG TSHEG 𑩄 |
| 1137 | 0x11A45, // ZANABAZAR SQUARE INITIAL DOUBLE-LINED HEAD MARK 𑩅 |
| 1138 | 0x11A46, // ZANABAZAR SQUARE CLOSING DOUBLE-LINED HEAD MARK 𑩆 |
| 1139 | 0x11A9A, // SOYOMBO MARK TSHEG 𑪚 |
| 1140 | 0x11A9B, // SOYOMBO MARK SHAD 𑪛 |
| 1141 | 0x11A9C, // SOYOMBO MARK DOUBLE SHAD 𑪜 |
| 1142 | 0x11A9E, // SOYOMBO HEAD MARK WITH MOON AND SUN AND TRIPLE FLAME 𑪞 |
| 1143 | 0x11A9F, // SOYOMBO HEAD MARK WITH MOON AND SUN AND FLAME 𑪟 |
| 1144 | 0x11AA0, // SOYOMBO HEAD MARK WITH MOON AND SUN 𑪠 |
| 1145 | 0x11AA1, // SOYOMBO TERMINAL MARK-1 𑪡 |
| 1146 | 0x11AA2, // SOYOMBO TERMINAL MARK-2 𑪢 |
| 1147 | 0x11C41, // BHAIKSUKI DANDA 𑱁 |
| 1148 | 0x11C42, // BHAIKSUKI DOUBLE DANDA 𑱂 |
| 1149 | 0x11C43, // BHAIKSUKI WORD SEPARATOR 𑱃 |
| 1150 | 0x11C44, // BHAIKSUKI GAP FILLER-1 𑱄 |
| 1151 | 0x11C45, // BHAIKSUKI GAP FILLER-2 𑱅 |
| 1152 | 0x11C70, // MARCHEN HEAD MARK 𑱰 |
| 1153 | 0x11C71, // MARCHEN MARK SHAD 𑱱 |
| 1154 | 0x11EF7, // MAKASAR PASSIMBANG 𑻷 |
| 1155 | 0x11EF8, // MAKASAR END OF SECTION 𑻸 |
| 1156 | 0x11FFF, // TAMIL PUNCTUATION END OF TEXT 𑿿 |
| 1157 | 0x12470, // CUNEIFORM PUNCTUATION SIGN OLD ASSYRIAN WORD DIVIDER 𒑰 |
| 1158 | 0x12471, // CUNEIFORM PUNCTUATION SIGN VERTICAL COLON 𒑱 |
| 1159 | 0x12472, // CUNEIFORM PUNCTUATION SIGN DIAGONAL COLON 𒑲 |
| 1160 | 0x12473, // CUNEIFORM PUNCTUATION SIGN DIAGONAL TRICOLON 𒑳 |
| 1161 | 0x12474, // CUNEIFORM PUNCTUATION SIGN DIAGONAL QUADCOLON 𒑴 |
| 1162 | 0x16A6E, // MRO DANDA 𖩮 |
| 1163 | 0x16A6F, // MRO DOUBLE DANDA 𖩯 |
| 1164 | 0x16AF5, // BASSA VAH FULL STOP 𖫵 |
| 1165 | 0x16B37, // PAHAWH HMONG SIGN VOS THOM 𖬷 |
| 1166 | 0x16B38, // PAHAWH HMONG SIGN VOS TSHAB CEEB 𖬸 |
| 1167 | 0x16B39, // PAHAWH HMONG SIGN CIM CHEEM 𖬹 |
| 1168 | 0x16B3A, // PAHAWH HMONG SIGN VOS THIAB 𖬺 |
| 1169 | 0x16B3B, // PAHAWH HMONG SIGN VOS FEEM 𖬻 |
| 1170 | 0x16B44, // PAHAWH HMONG SIGN XAUS 𖭄 |
| 1171 | 0x16E97, // MEDEFAIDRIN COMMA 𖺗 |
| 1172 | 0x16E98, // MEDEFAIDRIN FULL STOP 𖺘 |
| 1173 | 0x16E99, // MEDEFAIDRIN SYMBOL AIVA 𖺙 |
| 1174 | 0x16E9A, // MEDEFAIDRIN EXCLAMATION OH 𖺚 |
| 1175 | 0x16FE2, // OLD CHINESE HOOK MARK 𖿢 |
| 1176 | 0x1BC9F, // DUPLOYAN PUNCTUATION CHINOOK FULL STOP 𛲟 |
| 1177 | 0x1DA87, // SIGNWRITING COMMA 𝪇 |
| 1178 | 0x1DA88, // SIGNWRITING FULL STOP 𝪈 |
| 1179 | 0x1DA89, // SIGNWRITING SEMICOLON 𝪉 |
| 1180 | 0x1DA8A, // SIGNWRITING COLON 𝪊 |
| 1181 | 0x1DA8B, // SIGNWRITING PARENTHESIS 𝪋 |
| 1182 | 0x1E95E, // ADLAM INITIAL EXCLAMATION MARK 𞥞 |
| 1183 | 0x1E95F, // ADLAM INITIAL QUESTION MARK |
| 1184 | ] |
| 1185 | |