| 1 | /* Header for multibyte character handler. |
| 2 | Copyright (C) 1995, 1997, 1998 Electrotechnical Laboratory, JAPAN. |
| 3 | Licensed to the Free Software Foundation. |
| 4 | Copyright (C) 2003, 2004, 2005, 2006, 2007, 2008, 2009, 2010 |
| 5 | National Institute of Advanced Industrial Science and Technology (AIST) |
| 6 | Registration Number H13PRO009 |
| 7 | |
| 8 | This file is part of GNU Emacs. |
| 9 | |
| 10 | GNU Emacs is free software: you can redistribute it and/or modify |
| 11 | it under the terms of the GNU General Public License as published by |
| 12 | the Free Software Foundation, either version 3 of the License, or |
| 13 | (at your option) any later version. |
| 14 | |
| 15 | GNU Emacs is distributed in the hope that it will be useful, |
| 16 | but WITHOUT ANY WARRANTY; without even the implied warranty of |
| 17 | MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the |
| 18 | GNU General Public License for more details. |
| 19 | |
| 20 | You should have received a copy of the GNU General Public License |
| 21 | along with GNU Emacs. If not, see <http://www.gnu.org/licenses/>. */ |
| 22 | |
| 23 | #ifndef EMACS_CHARACTER_H |
| 24 | #define EMACS_CHARACTER_H |
| 25 | |
| 26 | /* character code 1st byte byte sequence |
| 27 | -------------- -------- ------------- |
| 28 | 0-7F 00..7F 0xxxxxxx |
| 29 | 80-7FF C2..DF 110xxxxx 10xxxxxx |
| 30 | 800-FFFF E0..EF 1110xxxx 10xxxxxx 10xxxxxx |
| 31 | 10000-1FFFFF F0..F7 11110xxx 10xxxxxx 10xxxxxx 10xxxxxx |
| 32 | 200000-3FFF7F F8 11111000 1000xxxx 10xxxxxx 10xxxxxx 10xxxxxx |
| 33 | 3FFF80-3FFFFF C0..C1 1100000x 10xxxxxx (for eight-bit-char) |
| 34 | 400000-... invalid |
| 35 | |
| 36 | invalid 1st byte 80..BF 10xxxxxx |
| 37 | F9..FF 11111xxx (xxx != 000) |
| 38 | */ |
| 39 | |
| 40 | /* Maximum character code ((1 << CHARACTERBITS) - 1). */ |
| 41 | #define MAX_CHAR 0x3FFFFF |
| 42 | |
| 43 | /* Maximum Unicode character code. */ |
| 44 | #define MAX_UNICODE_CHAR 0x10FFFF |
| 45 | |
| 46 | /* Maximum N-byte character codes. */ |
| 47 | #define MAX_1_BYTE_CHAR 0x7F |
| 48 | #define MAX_2_BYTE_CHAR 0x7FF |
| 49 | #define MAX_3_BYTE_CHAR 0xFFFF |
| 50 | #define MAX_4_BYTE_CHAR 0x1FFFFF |
| 51 | #define MAX_5_BYTE_CHAR 0x3FFF7F |
| 52 | |
| 53 | /* Minimum leading code of multibyte characters. */ |
| 54 | #define MIN_MULTIBYTE_LEADING_CODE 0xC0 |
| 55 | /* Maximum leading code of multibyte characters. */ |
| 56 | #define MAX_MULTIBYTE_LEADING_CODE 0xF8 |
| 57 | |
| 58 | /* Nonzero iff C is a character that corresponds to a raw 8-bit |
| 59 | byte. */ |
| 60 | #define CHAR_BYTE8_P(c) ((c) > MAX_5_BYTE_CHAR) |
| 61 | |
| 62 | /* Return the character code for raw 8-bit byte BYTE. */ |
| 63 | #define BYTE8_TO_CHAR(byte) ((byte) + 0x3FFF00) |
| 64 | |
| 65 | #define UNIBYTE_TO_CHAR(byte) \ |
| 66 | (ASCII_BYTE_P (byte) ? (byte) : BYTE8_TO_CHAR (byte)) |
| 67 | |
| 68 | /* Return the raw 8-bit byte for character C. */ |
| 69 | #define CHAR_TO_BYTE8(c) \ |
| 70 | (CHAR_BYTE8_P (c) \ |
| 71 | ? (c) - 0x3FFF00 \ |
| 72 | : multibyte_char_to_unibyte (c, Qnil)) |
| 73 | |
| 74 | /* Return the raw 8-bit byte for character C, |
| 75 | or -1 if C doesn't correspond to a byte. */ |
| 76 | #define CHAR_TO_BYTE_SAFE(c) \ |
| 77 | (CHAR_BYTE8_P (c) \ |
| 78 | ? (c) - 0x3FFF00 \ |
| 79 | : multibyte_char_to_unibyte_safe (c)) |
| 80 | |
| 81 | /* Nonzero iff BYTE is the 1st byte of a multibyte form of a character |
| 82 | that corresponds to a raw 8-bit byte. */ |
| 83 | #define CHAR_BYTE8_HEAD_P(byte) ((byte) == 0xC0 || (byte) == 0xC1) |
| 84 | |
| 85 | /* If C is not ASCII, make it unibyte. */ |
| 86 | #define MAKE_CHAR_UNIBYTE(c) \ |
| 87 | do { \ |
| 88 | if (! ASCII_CHAR_P (c)) \ |
| 89 | c = CHAR_TO_BYTE8 (c); \ |
| 90 | } while (0) |
| 91 | |
| 92 | |
| 93 | /* If C is not ASCII, make it multibyte. Assumes C < 256. */ |
| 94 | #define MAKE_CHAR_MULTIBYTE(c) \ |
| 95 | (eassert ((c) >= 0 && (c) < 256), (c) = UNIBYTE_TO_CHAR (c)) |
| 96 | |
| 97 | /* This is the maximum byte length of multibyte form. */ |
| 98 | #define MAX_MULTIBYTE_LENGTH 5 |
| 99 | |
| 100 | /* Return a Lisp character whose character code is C. Assumes C is |
| 101 | a valid character code. */ |
| 102 | #define make_char(c) make_number (c) |
| 103 | |
| 104 | /* Nonzero iff C is an ASCII byte. */ |
| 105 | #define ASCII_BYTE_P(c) ((unsigned) (c) < 0x80) |
| 106 | |
| 107 | /* Nonzero iff X is a character. */ |
| 108 | #define CHARACTERP(x) (NATNUMP (x) && XFASTINT (x) <= MAX_CHAR) |
| 109 | |
| 110 | /* Nonzero iff C is valid as a character code. GENERICP is not used. */ |
| 111 | #define CHAR_VALID_P(c, genericp) ((unsigned) (c) <= MAX_CHAR) |
| 112 | |
| 113 | /* Check if Lisp object X is a character or not. */ |
| 114 | #define CHECK_CHARACTER(x) \ |
| 115 | CHECK_TYPE (CHARACTERP (x), Qcharacterp, x) |
| 116 | |
| 117 | #define CHECK_CHARACTER_CAR(x) \ |
| 118 | do { \ |
| 119 | Lisp_Object tmp = XCAR (x); \ |
| 120 | CHECK_CHARACTER (tmp); \ |
| 121 | XSETCAR ((x), tmp); \ |
| 122 | } while (0) |
| 123 | |
| 124 | #define CHECK_CHARACTER_CDR(x) \ |
| 125 | do { \ |
| 126 | Lisp_Object tmp = XCDR (x); \ |
| 127 | CHECK_CHARACTER (tmp); \ |
| 128 | XSETCDR ((x), tmp); \ |
| 129 | } while (0) |
| 130 | |
| 131 | /* Nonzero iff C is an ASCII character. */ |
| 132 | #define ASCII_CHAR_P(c) ((unsigned) (c) < 0x80) |
| 133 | |
| 134 | /* Nonzero iff C is a character of code less than 0x100. */ |
| 135 | #define SINGLE_BYTE_CHAR_P(c) ((unsigned) (c) < 0x100) |
| 136 | |
| 137 | /* Nonzero if character C has a printable glyph. */ |
| 138 | #define CHAR_PRINTABLE_P(c) \ |
| 139 | (((c) >= 32 && (c) < 127) \ |
| 140 | || ! NILP (CHAR_TABLE_REF (Vprintable_chars, (c)))) |
| 141 | |
| 142 | /* Return byte length of multibyte form for character C. */ |
| 143 | #define CHAR_BYTES(c) \ |
| 144 | ( (c) <= MAX_1_BYTE_CHAR ? 1 \ |
| 145 | : (c) <= MAX_2_BYTE_CHAR ? 2 \ |
| 146 | : (c) <= MAX_3_BYTE_CHAR ? 3 \ |
| 147 | : (c) <= MAX_4_BYTE_CHAR ? 4 \ |
| 148 | : (c) <= MAX_5_BYTE_CHAR ? 5 \ |
| 149 | : 2) |
| 150 | |
| 151 | |
| 152 | /* Return the leading code of multibyte form of C. */ |
| 153 | #define CHAR_LEADING_CODE(c) \ |
| 154 | ((c) <= MAX_1_BYTE_CHAR ? c \ |
| 155 | : (c) <= MAX_2_BYTE_CHAR ? (0xC0 | ((c) >> 6)) \ |
| 156 | : (c) <= MAX_3_BYTE_CHAR ? (0xE0 | ((c) >> 12)) \ |
| 157 | : (c) <= MAX_4_BYTE_CHAR ? (0xF0 | ((c) >> 18)) \ |
| 158 | : (c) <= MAX_5_BYTE_CHAR ? 0xF8 \ |
| 159 | : (0xC0 | (((c) >> 6) & 0x01))) |
| 160 | |
| 161 | |
| 162 | /* Store multibyte form of the character C in P. The caller should |
| 163 | allocate at least MAX_MULTIBYTE_LENGTH bytes area at P in advance. |
| 164 | Returns the length of the multibyte form. */ |
| 165 | |
| 166 | #define CHAR_STRING(c, p) \ |
| 167 | ((unsigned) (c) <= MAX_1_BYTE_CHAR \ |
| 168 | ? ((p)[0] = (c), \ |
| 169 | 1) \ |
| 170 | : (unsigned) (c) <= MAX_2_BYTE_CHAR \ |
| 171 | ? ((p)[0] = (0xC0 | ((c) >> 6)), \ |
| 172 | (p)[1] = (0x80 | ((c) & 0x3F)), \ |
| 173 | 2) \ |
| 174 | : (unsigned) (c) <= MAX_3_BYTE_CHAR \ |
| 175 | ? ((p)[0] = (0xE0 | ((c) >> 12)), \ |
| 176 | (p)[1] = (0x80 | (((c) >> 6) & 0x3F)), \ |
| 177 | (p)[2] = (0x80 | ((c) & 0x3F)), \ |
| 178 | 3) \ |
| 179 | : char_string ((unsigned) c, p)) |
| 180 | |
| 181 | /* Store multibyte form of byte B in P. The caller should allocate at |
| 182 | least MAX_MULTIBYTE_LENGTH bytes area at P in advance. Returns the |
| 183 | length of the multibyte form. */ |
| 184 | |
| 185 | #define BYTE8_STRING(b, p) \ |
| 186 | ((p)[0] = (0xC0 | (((b) >> 6) & 0x01)), \ |
| 187 | (p)[1] = (0x80 | ((b) & 0x3F)), \ |
| 188 | 2) |
| 189 | |
| 190 | |
| 191 | /* Store multibyte form of the character C in P and advance P to the |
| 192 | end of the multibyte form. The caller should allocate at least |
| 193 | MAX_MULTIBYTE_LENGTH bytes area at P in advance. */ |
| 194 | |
| 195 | #define CHAR_STRING_ADVANCE(c, p) \ |
| 196 | do { \ |
| 197 | if ((c) <= MAX_1_BYTE_CHAR) \ |
| 198 | *(p)++ = (c); \ |
| 199 | else if ((c) <= MAX_2_BYTE_CHAR) \ |
| 200 | *(p)++ = (0xC0 | ((c) >> 6)), \ |
| 201 | *(p)++ = (0x80 | ((c) & 0x3F)); \ |
| 202 | else if ((c) <= MAX_3_BYTE_CHAR) \ |
| 203 | *(p)++ = (0xE0 | ((c) >> 12)), \ |
| 204 | *(p)++ = (0x80 | (((c) >> 6) & 0x3F)), \ |
| 205 | *(p)++ = (0x80 | ((c) & 0x3F)); \ |
| 206 | else \ |
| 207 | (p) += char_string ((c), (p)); \ |
| 208 | } while (0) |
| 209 | |
| 210 | |
| 211 | /* Nonzero iff BYTE starts a non-ASCII character in a multibyte |
| 212 | form. */ |
| 213 | #define LEADING_CODE_P(byte) (((byte) & 0xC0) == 0xC0) |
| 214 | |
| 215 | /* Nonzero iff BYTE is a trailing code of a non-ASCII character in a |
| 216 | multibyte form. */ |
| 217 | #define TRAILING_CODE_P(byte) (((byte) & 0xC0) == 0x80) |
| 218 | |
| 219 | /* Nonzero iff BYTE starts a character in a multibyte form. |
| 220 | This is equivalent to: |
| 221 | (ASCII_BYTE_P (byte) || LEADING_CODE_P (byte)) */ |
| 222 | #define CHAR_HEAD_P(byte) (((byte) & 0xC0) != 0x80) |
| 223 | |
| 224 | /* Kept for backward compatibility. This macro will be removed in the |
| 225 | future. */ |
| 226 | #define BASE_LEADING_CODE_P LEADING_CODE_P |
| 227 | |
| 228 | /* How many bytes a character that starts with BYTE occupies in a |
| 229 | multibyte form. */ |
| 230 | #define BYTES_BY_CHAR_HEAD(byte) \ |
| 231 | (!((byte) & 0x80) ? 1 \ |
| 232 | : !((byte) & 0x20) ? 2 \ |
| 233 | : !((byte) & 0x10) ? 3 \ |
| 234 | : !((byte) & 0x08) ? 4 \ |
| 235 | : 5) |
| 236 | |
| 237 | |
| 238 | /* Return the length of the multi-byte form at string STR of length |
| 239 | LEN while assuming that STR points a valid multi-byte form. As |
| 240 | this macro isn't necessary anymore, all callers will be changed to |
| 241 | use BYTES_BY_CHAR_HEAD directly in the future. */ |
| 242 | |
| 243 | #define MULTIBYTE_FORM_LENGTH(str, len) \ |
| 244 | BYTES_BY_CHAR_HEAD (*(str)) |
| 245 | |
| 246 | /* Parse multibyte string STR of length LENGTH and set BYTES to the |
| 247 | byte length of a character at STR while assuming that STR points a |
| 248 | valid multibyte form. As this macro isn't necessary anymore, all |
| 249 | callers will be changed to use BYTES_BY_CHAR_HEAD directly in the |
| 250 | future. */ |
| 251 | |
| 252 | #define PARSE_MULTIBYTE_SEQ(str, length, bytes) \ |
| 253 | (bytes) = BYTES_BY_CHAR_HEAD (*(str)) |
| 254 | |
| 255 | /* The byte length of multibyte form at unibyte string P ending at |
| 256 | PEND. If STR doesn't point to a valid multibyte form, return 0. */ |
| 257 | |
| 258 | #define MULTIBYTE_LENGTH(p, pend) \ |
| 259 | (p >= pend ? 0 \ |
| 260 | : !((p)[0] & 0x80) ? 1 \ |
| 261 | : ((p + 1 >= pend) || (((p)[1] & 0xC0) != 0x80)) ? 0 \ |
| 262 | : ((p)[0] & 0xE0) == 0xC0 ? 2 \ |
| 263 | : ((p + 2 >= pend) || (((p)[2] & 0xC0) != 0x80)) ? 0 \ |
| 264 | : ((p)[0] & 0xF0) == 0xE0 ? 3 \ |
| 265 | : ((p + 3 >= pend) || (((p)[3] & 0xC0) != 0x80)) ? 0 \ |
| 266 | : ((p)[0] & 0xF8) == 0xF0 ? 4 \ |
| 267 | : ((p + 4 >= pend) || (((p)[4] & 0xC0) != 0x80)) ? 0 \ |
| 268 | : (p)[0] == 0xF8 && ((p)[1] & 0xF0) == 0x80 ? 5 \ |
| 269 | : 0) |
| 270 | |
| 271 | |
| 272 | /* Like MULTIBYTE_LENGTH, but don't check the ending address. */ |
| 273 | |
| 274 | #define MULTIBYTE_LENGTH_NO_CHECK(p) \ |
| 275 | (!((p)[0] & 0x80) ? 1 \ |
| 276 | : ((p)[1] & 0xC0) != 0x80 ? 0 \ |
| 277 | : ((p)[0] & 0xE0) == 0xC0 ? 2 \ |
| 278 | : ((p)[2] & 0xC0) != 0x80 ? 0 \ |
| 279 | : ((p)[0] & 0xF0) == 0xE0 ? 3 \ |
| 280 | : ((p)[3] & 0xC0) != 0x80 ? 0 \ |
| 281 | : ((p)[0] & 0xF8) == 0xF0 ? 4 \ |
| 282 | : ((p)[4] & 0xC0) != 0x80 ? 0 \ |
| 283 | : (p)[0] == 0xF8 && ((p)[1] & 0xF0) == 0x80 ? 5 \ |
| 284 | : 0) |
| 285 | |
| 286 | /* If P is before LIMIT, advance P to the next character boundary. |
| 287 | Assumes that P is already at a character boundary of the same |
| 288 | mulitbyte form whose end address is LIMIT. */ |
| 289 | |
| 290 | #define NEXT_CHAR_BOUNDARY(p, limit) \ |
| 291 | do { \ |
| 292 | if ((p) < (limit)) \ |
| 293 | (p) += BYTES_BY_CHAR_HEAD (*(p)); \ |
| 294 | } while (0) |
| 295 | |
| 296 | |
| 297 | /* If P is after LIMIT, advance P to the previous character boundary. |
| 298 | Assumes that P is already at a character boundary of the same |
| 299 | mulitbyte form whose beginning address is LIMIT. */ |
| 300 | |
| 301 | #define PREV_CHAR_BOUNDARY(p, limit) \ |
| 302 | do { \ |
| 303 | if ((p) > (limit)) \ |
| 304 | { \ |
| 305 | const unsigned char *p0 = (p); \ |
| 306 | do { \ |
| 307 | p0--; \ |
| 308 | } while (p0 >= limit && ! CHAR_HEAD_P (*p0)); \ |
| 309 | (p) = (BYTES_BY_CHAR_HEAD (*p0) == (p) - p0) ? p0 : (p) - 1; \ |
| 310 | } \ |
| 311 | } while (0) |
| 312 | |
| 313 | /* Return the character code of character whose multibyte form is at |
| 314 | P. */ |
| 315 | |
| 316 | #define STRING_CHAR(p) \ |
| 317 | (!((p)[0] & 0x80) \ |
| 318 | ? (p)[0] \ |
| 319 | : ! ((p)[0] & 0x20) \ |
| 320 | ? (((((p)[0] & 0x1F) << 6) \ |
| 321 | | ((p)[1] & 0x3F)) \ |
| 322 | + (((unsigned char) (p)[0]) < 0xC2 ? 0x3FFF80 : 0)) \ |
| 323 | : ! ((p)[0] & 0x10) \ |
| 324 | ? ((((p)[0] & 0x0F) << 12) \ |
| 325 | | (((p)[1] & 0x3F) << 6) \ |
| 326 | | ((p)[2] & 0x3F)) \ |
| 327 | : string_char ((p), NULL, NULL)) |
| 328 | |
| 329 | |
| 330 | /* Like STRING_CHAR, but set ACTUAL_LEN to the length of multibyte |
| 331 | form. */ |
| 332 | |
| 333 | #define STRING_CHAR_AND_LENGTH(p, actual_len) \ |
| 334 | (!((p)[0] & 0x80) \ |
| 335 | ? ((actual_len) = 1, (p)[0]) \ |
| 336 | : ! ((p)[0] & 0x20) \ |
| 337 | ? ((actual_len) = 2, \ |
| 338 | (((((p)[0] & 0x1F) << 6) \ |
| 339 | | ((p)[1] & 0x3F)) \ |
| 340 | + (((unsigned char) (p)[0]) < 0xC2 ? 0x3FFF80 : 0))) \ |
| 341 | : ! ((p)[0] & 0x10) \ |
| 342 | ? ((actual_len) = 3, \ |
| 343 | ((((p)[0] & 0x0F) << 12) \ |
| 344 | | (((p)[1] & 0x3F) << 6) \ |
| 345 | | ((p)[2] & 0x3F))) \ |
| 346 | : string_char ((p), NULL, &actual_len)) |
| 347 | |
| 348 | |
| 349 | /* Like STRING_CHAR, but advance P to the end of multibyte form. */ |
| 350 | |
| 351 | #define STRING_CHAR_ADVANCE(p) \ |
| 352 | (!((p)[0] & 0x80) \ |
| 353 | ? *(p)++ \ |
| 354 | : ! ((p)[0] & 0x20) \ |
| 355 | ? ((p) += 2, \ |
| 356 | ((((p)[-2] & 0x1F) << 6) \ |
| 357 | | ((p)[-1] & 0x3F) \ |
| 358 | | ((unsigned char) ((p)[-2]) < 0xC2 ? 0x3FFF80 : 0))) \ |
| 359 | : ! ((p)[0] & 0x10) \ |
| 360 | ? ((p) += 3, \ |
| 361 | ((((p)[-3] & 0x0F) << 12) \ |
| 362 | | (((p)[-2] & 0x3F) << 6) \ |
| 363 | | ((p)[-1] & 0x3F))) \ |
| 364 | : string_char ((p), &(p), NULL)) |
| 365 | |
| 366 | |
| 367 | /* Fetch the "next" character from Lisp string STRING at byte position |
| 368 | BYTEIDX, character position CHARIDX. Store it into OUTPUT. |
| 369 | |
| 370 | All the args must be side-effect-free. |
| 371 | BYTEIDX and CHARIDX must be lvalues; |
| 372 | we increment them past the character fetched. */ |
| 373 | |
| 374 | #define FETCH_STRING_CHAR_ADVANCE(OUTPUT, STRING, CHARIDX, BYTEIDX) \ |
| 375 | do \ |
| 376 | { \ |
| 377 | CHARIDX++; \ |
| 378 | if (STRING_MULTIBYTE (STRING)) \ |
| 379 | { \ |
| 380 | unsigned char *ptr = &SDATA (STRING)[BYTEIDX]; \ |
| 381 | int len; \ |
| 382 | \ |
| 383 | OUTPUT = STRING_CHAR_AND_LENGTH (ptr, len); \ |
| 384 | BYTEIDX += len; \ |
| 385 | } \ |
| 386 | else \ |
| 387 | { \ |
| 388 | OUTPUT = SREF (STRING, BYTEIDX); \ |
| 389 | BYTEIDX++; \ |
| 390 | } \ |
| 391 | } \ |
| 392 | while (0) |
| 393 | |
| 394 | /* Like FETCH_STRING_CHAR_ADVANCE, but return a multibyte character |
| 395 | even if STRING is unibyte. */ |
| 396 | |
| 397 | #define FETCH_STRING_CHAR_AS_MULTIBYTE_ADVANCE(OUTPUT, STRING, CHARIDX, BYTEIDX) \ |
| 398 | do \ |
| 399 | { \ |
| 400 | CHARIDX++; \ |
| 401 | if (STRING_MULTIBYTE (STRING)) \ |
| 402 | { \ |
| 403 | unsigned char *ptr = &SDATA (STRING)[BYTEIDX]; \ |
| 404 | int len; \ |
| 405 | \ |
| 406 | OUTPUT = STRING_CHAR_AND_LENGTH (ptr, len); \ |
| 407 | BYTEIDX += len; \ |
| 408 | } \ |
| 409 | else \ |
| 410 | { \ |
| 411 | OUTPUT = SREF (STRING, BYTEIDX); \ |
| 412 | BYTEIDX++; \ |
| 413 | MAKE_CHAR_MULTIBYTE (OUTPUT); \ |
| 414 | } \ |
| 415 | } \ |
| 416 | while (0) |
| 417 | |
| 418 | |
| 419 | /* Like FETCH_STRING_CHAR_ADVANCE, but assumes STRING is multibyte. */ |
| 420 | |
| 421 | #define FETCH_STRING_CHAR_ADVANCE_NO_CHECK(OUTPUT, STRING, CHARIDX, BYTEIDX) \ |
| 422 | do \ |
| 423 | { \ |
| 424 | unsigned char *ptr = &SDATA (STRING)[BYTEIDX]; \ |
| 425 | int len; \ |
| 426 | \ |
| 427 | OUTPUT = STRING_CHAR_AND_LENGTH (ptr, len); \ |
| 428 | BYTEIDX += len; \ |
| 429 | CHARIDX++; \ |
| 430 | } \ |
| 431 | while (0) |
| 432 | |
| 433 | |
| 434 | /* Like FETCH_STRING_CHAR_ADVANCE, but fetch character from the current |
| 435 | buffer. */ |
| 436 | |
| 437 | #define FETCH_CHAR_ADVANCE(OUTPUT, CHARIDX, BYTEIDX) \ |
| 438 | do \ |
| 439 | { \ |
| 440 | CHARIDX++; \ |
| 441 | if (!NILP (current_buffer->enable_multibyte_characters)) \ |
| 442 | { \ |
| 443 | unsigned char *ptr = BYTE_POS_ADDR (BYTEIDX); \ |
| 444 | int len; \ |
| 445 | \ |
| 446 | OUTPUT= STRING_CHAR_AND_LENGTH (ptr, len); \ |
| 447 | BYTEIDX += len; \ |
| 448 | } \ |
| 449 | else \ |
| 450 | { \ |
| 451 | OUTPUT = *(BYTE_POS_ADDR (BYTEIDX)); \ |
| 452 | BYTEIDX++; \ |
| 453 | } \ |
| 454 | } \ |
| 455 | while (0) |
| 456 | |
| 457 | |
| 458 | /* Like FETCH_CHAR_ADVANCE, but assumes the current buffer is multibyte. */ |
| 459 | |
| 460 | #define FETCH_CHAR_ADVANCE_NO_CHECK(OUTPUT, CHARIDX, BYTEIDX) \ |
| 461 | do \ |
| 462 | { \ |
| 463 | unsigned char *ptr = BYTE_POS_ADDR (BYTEIDX); \ |
| 464 | int len; \ |
| 465 | \ |
| 466 | OUTPUT = STRING_CHAR_AND_LENGTH (ptr, len); \ |
| 467 | BYTEIDX += len; \ |
| 468 | CHARIDX++; \ |
| 469 | } \ |
| 470 | while (0) |
| 471 | |
| 472 | |
| 473 | /* Increment the buffer byte position POS_BYTE of the current buffer to |
| 474 | the next character boundary. No range checking of POS. */ |
| 475 | |
| 476 | #define INC_POS(pos_byte) \ |
| 477 | do { \ |
| 478 | unsigned char *p = BYTE_POS_ADDR (pos_byte); \ |
| 479 | pos_byte += BYTES_BY_CHAR_HEAD (*p); \ |
| 480 | } while (0) |
| 481 | |
| 482 | |
| 483 | /* Decrement the buffer byte position POS_BYTE of the current buffer to |
| 484 | the previous character boundary. No range checking of POS. */ |
| 485 | |
| 486 | #define DEC_POS(pos_byte) \ |
| 487 | do { \ |
| 488 | unsigned char *p; \ |
| 489 | \ |
| 490 | pos_byte--; \ |
| 491 | if (pos_byte < GPT_BYTE) \ |
| 492 | p = BEG_ADDR + pos_byte - BEG_BYTE; \ |
| 493 | else \ |
| 494 | p = BEG_ADDR + GAP_SIZE + pos_byte - BEG_BYTE;\ |
| 495 | while (!CHAR_HEAD_P (*p)) \ |
| 496 | { \ |
| 497 | p--; \ |
| 498 | pos_byte--; \ |
| 499 | } \ |
| 500 | } while (0) |
| 501 | |
| 502 | /* Increment both CHARPOS and BYTEPOS, each in the appropriate way. */ |
| 503 | |
| 504 | #define INC_BOTH(charpos, bytepos) \ |
| 505 | do \ |
| 506 | { \ |
| 507 | (charpos)++; \ |
| 508 | if (NILP (current_buffer->enable_multibyte_characters)) \ |
| 509 | (bytepos)++; \ |
| 510 | else \ |
| 511 | INC_POS ((bytepos)); \ |
| 512 | } \ |
| 513 | while (0) |
| 514 | |
| 515 | |
| 516 | /* Decrement both CHARPOS and BYTEPOS, each in the appropriate way. */ |
| 517 | |
| 518 | #define DEC_BOTH(charpos, bytepos) \ |
| 519 | do \ |
| 520 | { \ |
| 521 | (charpos)--; \ |
| 522 | if (NILP (current_buffer->enable_multibyte_characters)) \ |
| 523 | (bytepos)--; \ |
| 524 | else \ |
| 525 | DEC_POS ((bytepos)); \ |
| 526 | } \ |
| 527 | while (0) |
| 528 | |
| 529 | |
| 530 | /* Increment the buffer byte position POS_BYTE of the current buffer to |
| 531 | the next character boundary. This macro relies on the fact that |
| 532 | *GPT_ADDR and *Z_ADDR are always accessible and the values are |
| 533 | '\0'. No range checking of POS_BYTE. */ |
| 534 | |
| 535 | #define BUF_INC_POS(buf, pos_byte) \ |
| 536 | do { \ |
| 537 | unsigned char *p = BUF_BYTE_ADDRESS (buf, pos_byte); \ |
| 538 | pos_byte += BYTES_BY_CHAR_HEAD (*p); \ |
| 539 | } while (0) |
| 540 | |
| 541 | |
| 542 | /* Decrement the buffer byte position POS_BYTE of the current buffer to |
| 543 | the previous character boundary. No range checking of POS_BYTE. */ |
| 544 | |
| 545 | #define BUF_DEC_POS(buf, pos_byte) \ |
| 546 | do { \ |
| 547 | unsigned char *p; \ |
| 548 | pos_byte--; \ |
| 549 | if (pos_byte < BUF_GPT_BYTE (buf)) \ |
| 550 | p = BUF_BEG_ADDR (buf) + pos_byte - BEG_BYTE; \ |
| 551 | else \ |
| 552 | p = BUF_BEG_ADDR (buf) + BUF_GAP_SIZE (buf) + pos_byte - BEG_BYTE;\ |
| 553 | while (!CHAR_HEAD_P (*p)) \ |
| 554 | { \ |
| 555 | p--; \ |
| 556 | pos_byte--; \ |
| 557 | } \ |
| 558 | } while (0) |
| 559 | |
| 560 | |
| 561 | /* If C is a character to be unified with a Unicode character, return |
| 562 | the unified Unicode character. */ |
| 563 | |
| 564 | #define MAYBE_UNIFY_CHAR(c) \ |
| 565 | do { \ |
| 566 | if (c > MAX_UNICODE_CHAR && c <= MAX_5_BYTE_CHAR) \ |
| 567 | { \ |
| 568 | Lisp_Object val; \ |
| 569 | val = CHAR_TABLE_REF (Vchar_unify_table, c); \ |
| 570 | if (INTEGERP (val)) \ |
| 571 | c = XINT (val); \ |
| 572 | else if (! NILP (val)) \ |
| 573 | c = maybe_unify_char (c, val); \ |
| 574 | } \ |
| 575 | } while (0) |
| 576 | |
| 577 | |
| 578 | /* Return the width of ASCII character C. The width is measured by |
| 579 | how many columns C will occupy on the screen when displayed in the |
| 580 | current buffer. */ |
| 581 | |
| 582 | #define ASCII_CHAR_WIDTH(c) \ |
| 583 | (c < 0x20 \ |
| 584 | ? (c == '\t' \ |
| 585 | ? XFASTINT (current_buffer->tab_width) \ |
| 586 | : (c == '\n' ? 0 : (NILP (current_buffer->ctl_arrow) ? 4 : 2))) \ |
| 587 | : (c < 0x7f \ |
| 588 | ? 1 \ |
| 589 | : ((NILP (current_buffer->ctl_arrow) ? 4 : 2)))) |
| 590 | |
| 591 | /* Return the width of character C. The width is measured by how many |
| 592 | columns C will occupy on the screen when displayed in the current |
| 593 | buffer. */ |
| 594 | |
| 595 | #define CHAR_WIDTH(c) \ |
| 596 | (ASCII_CHAR_P (c) \ |
| 597 | ? ASCII_CHAR_WIDTH (c) \ |
| 598 | : XINT (CHAR_TABLE_REF (Vchar_width_table, c))) |
| 599 | |
| 600 | /* If C is a variation selector, return the index numnber of the |
| 601 | variation selector (1..256). Otherwise, return 0. */ |
| 602 | |
| 603 | #define CHAR_VARIATION_SELECTOR_P(c) \ |
| 604 | ((c) < 0xFE00 ? 0 \ |
| 605 | : (c) <= 0xFE0F ? (c) - 0xFE00 + 1 \ |
| 606 | : (c) < 0xE0100 ? 0 \ |
| 607 | : (c) <= 0xE01EF ? (c) - 0xE0100 + 17 \ |
| 608 | : 0) |
| 609 | |
| 610 | /* If C is a high surrogate, return 1. If C is a low surrogate, |
| 611 | return 0. Otherwise, return 0. */ |
| 612 | |
| 613 | #define CHAR_SURROGATE_PAIR_P(c) \ |
| 614 | ((c) < 0xD800 ? 0 \ |
| 615 | : (c) <= 0xDBFF ? 1 \ |
| 616 | : (c) <= 0xDFFF ? 2 \ |
| 617 | : 0) |
| 618 | |
| 619 | |
| 620 | extern int char_resolve_modifier_mask P_ ((int)); |
| 621 | extern int char_string P_ ((unsigned, unsigned char *)); |
| 622 | extern int string_char P_ ((const unsigned char *, |
| 623 | const unsigned char **, int *)); |
| 624 | |
| 625 | extern int translate_char P_ ((Lisp_Object, int c)); |
| 626 | extern int char_printable_p P_ ((int c)); |
| 627 | extern void parse_str_as_multibyte P_ ((const unsigned char *, int, int *, |
| 628 | int *)); |
| 629 | extern int parse_str_to_multibyte P_ ((unsigned char *, int)); |
| 630 | extern int str_as_multibyte P_ ((unsigned char *, int, int, int *)); |
| 631 | extern int str_to_multibyte P_ ((unsigned char *, int, int)); |
| 632 | extern int str_as_unibyte P_ ((unsigned char *, int)); |
| 633 | extern EMACS_INT str_to_unibyte P_ ((const unsigned char *, unsigned char *, |
| 634 | EMACS_INT, int)); |
| 635 | extern int strwidth P_ ((unsigned char *, int)); |
| 636 | extern int c_string_width P_ ((const unsigned char *, int, int, int *, int *)); |
| 637 | extern int lisp_string_width P_ ((Lisp_Object, int, int *, int *)); |
| 638 | |
| 639 | extern Lisp_Object Vprintable_chars; |
| 640 | |
| 641 | extern Lisp_Object Qcharacterp, Qauto_fill_chars; |
| 642 | extern Lisp_Object Vtranslation_table_vector; |
| 643 | extern Lisp_Object Vchar_width_table; |
| 644 | extern Lisp_Object Vchar_direction_table; |
| 645 | extern Lisp_Object Vchar_unify_table; |
| 646 | extern Lisp_Object Vunicode_category_table; |
| 647 | |
| 648 | extern Lisp_Object string_escape_byte8 P_ ((Lisp_Object)); |
| 649 | |
| 650 | /* Return a translation table of id number ID. */ |
| 651 | #define GET_TRANSLATION_TABLE(id) \ |
| 652 | (XCDR(XVECTOR(Vtranslation_table_vector)->contents[(id)])) |
| 653 | |
| 654 | /* A char-table for characters which may invoke auto-filling. */ |
| 655 | extern Lisp_Object Vauto_fill_chars; |
| 656 | |
| 657 | extern Lisp_Object Vchar_script_table; |
| 658 | extern Lisp_Object Vscript_representative_chars; |
| 659 | |
| 660 | /* Copy LEN bytes from FROM to TO. This macro should be used only |
| 661 | when a caller knows that LEN is short and the obvious copy loop is |
| 662 | faster than calling bcopy which has some overhead. Copying a |
| 663 | multibyte sequence of a character is the typical case. */ |
| 664 | |
| 665 | #define BCOPY_SHORT(from, to, len) \ |
| 666 | do { \ |
| 667 | int i = len; \ |
| 668 | unsigned char *from_p = from, *to_p = to; \ |
| 669 | while (i--) *to_p++ = *from_p++; \ |
| 670 | } while (0) |
| 671 | |
| 672 | #define DEFSYM(sym, name) \ |
| 673 | do { (sym) = intern_c_string ((name)); staticpro (&(sym)); } while (0) |
| 674 | |
| 675 | #endif /* EMACS_CHARACTER_H */ |
| 676 | |
| 677 | /* arch-tag: 4ef86004-2eff-4073-8cea-cfcbcf7188ac |
| 678 | (do not change this comment) */ |