HCoop / bpt / emacs.git / blame
| Commit | Line | Data |
|---|---|---|
| 4ed46869 KH |
1 | /* Header for multilingual character handler. |
| 2 | Ver.1.0 | |
| 3 | ||
| 4 | Copyright (C) 1995 Free Software Foundation, Inc. | |
| 5 | Copyright (C) 1995 Electrotechnical Laboratory, JAPAN. | |
| 6 | ||
| 7 | This program is free software; you can redistribute it and/or modify | |
| 8 | it under the terms of the GNU General Public License as published by | |
| 9 | the Free Software Foundation; either version 2, or (at your option) | |
| 10 | any later version. | |
| 11 | ||
| 12 | This program is distributed in the hope that it will be useful, | |
| 13 | but WITHOUT ANY WARRANTY; without even the implied warranty of | |
| 14 | MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the | |
| 15 | GNU General Public License for more details. | |
| 16 | ||
| 17 | You should have received a copy of the GNU General Public License | |
| 18 | along with this program; if not, write to the Free Software | |
| 19 | Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. */ | |
| 20 | ||
| 21 | #ifndef _CHARSET_H | |
| 22 | #define _CHARSET_H | |
| 23 | ||
| 24 | /*** GENERAL NOTE on CHARACTER SET (CHARSET) *** | |
| 25 | ||
| 26 | A character set ("charset" hereafter) is a meaningful collection | |
| 27 | (i.e. language, culture, functionality, etc) of characters. Emacs | |
| 28 | handles multiple charsets at once. Each charset corresponds to one | |
| 29 | of ISO charsets (except for a special charset for composition | |
| 30 | characters). Emacs identifies a charset by a unique identification | |
| 31 | number, whereas ISO identifies a charset by a triplet of DIMENSION, | |
| 32 | CHARS and FINAL-CHAR. So, hereafter, just saying "charset" means an | |
| 33 | identification number (integer value). | |
| 34 | ||
| 35 | The value range of charset is 0x00, 0x80..0xFE. There are four | |
| 36 | kinds of charset depending on DIMENSION (1 or 2) and CHARS (94 or | |
| 37 | 96). For instance, a charset of DIMENSION2_CHARS94 contains 94x94 | |
| 38 | ||
| 39 | ||
| 40 | Within Emacs Lisp, a charset is treated as a symbol which has a | |
| 41 | property `charset'. The property value is a vector containing | |
| 42 | various information about the charset. For readability of C codes, | |
| 43 | we use the following convention on C variable names: | |
| 44 | charset_symbol: Emacs Lisp symbol of a charset | |
| 45 | charset_id: Emacs Lisp integer of an identification number of a charset | |
| 46 | charset: C integer of an identification number of a charset | |
| 47 | ||
| 48 | Each charset (except for ASCII) is assigned a base leading-code | |
| 49 | (range 0x80..0x9D). In addition, a charset of greater than 0xA0 | |
| 50 | (whose base leading-code is 0x9A..0x9D) is assigned an extended | |
| 51 | leading-code (range 0xA0..0xFE). In this case, each base | |
| 52 | leading-code specify the allowable range of extended leading-code as | |
| 53 | shown in the table below. A leading-code is used to represent a | |
| 54 | character in Emacs' buffer and string. | |
| 55 | ||
| 56 | We call a charset which has extended leading-code as "private | |
| 57 | charset" because those are mainly for a charset which is not | |
| 58 | registered by ISO. On the contrary, we call a charset which does | |
| 59 | not have extended leading-code as "official charset". | |
| 60 | ||
| 61 | --------------------------------------------------------------------------- | |
| 62 | charset dimension base leading-code extended leading-code | |
| 63 | --------------------------------------------------------------------------- | |
| 64 | 0x00 official dim1 -- none -- -- none -- | |
| 65 | (ASCII) | |
| 66 | 0x01..0x7F --never used-- | |
| 67 | 0x80 COMPOSITION same as charset -- none -- | |
| 68 | 0x81..0x8F official dim1 same as charset -- none -- | |
| 69 | 0x90..0x99 official dim2 same as charset -- none -- | |
| 70 | 0x9A..0x9F --never used-- | |
| 71 | 0xA0..0xDF private dim1 0x9A same as charset | |
| 72 | of 1-column width | |
| 73 | 0xE0..0xEF private dim1 0x9B same as charset | |
| 74 | of 2-column width | |
| 75 | 0xF0..0xF4 private dim2 0x9C same as charset | |
| 76 | of 1-column width | |
| 77 | 0xF5..0xFE private dim2 0x9D same as charset | |
| 78 | of 2-column width | |
| 79 | 0xFF --never used-- | |
| 80 | --------------------------------------------------------------------------- | |
| 81 | ||
| 82 | In the table, "COMPOSITION" means a charset for a composite | |
| 83 | character which is a character composed from several (up to 16) | |
| 84 | non-composite characters (components). Although a composite | |
| 85 | character can contain components of many charsets, a composite | |
| 86 | character itself belongs to the charset CHARSET-COMPOSITION. See | |
| 87 | the document "GENERAL NOTE on COMPOSITE CHARACTER" below for more | |
| 88 | detail. | |
| 89 | ||
| 90 | */ | |
| 91 | ||
| 92 | /* Definition of special leading-codes. */ | |
| 93 | /* Base leading-code. */ | |
| 94 | /* Special leading-code followed by components of a composite character. */ | |
| 95 | #define LEADING_CODE_COMPOSITION 0x80 | |
| 96 | /* Leading-code followed by extended leading-code. */ | |
| 97 | #define LEADING_CODE_PRIVATE_11 0x9A /* for private DIMENSION1 of 1-column */ | |
| 98 | #define LEADING_CODE_PRIVATE_12 0x9B /* for private DIMENSION1 of 2-column */ | |
| 99 | #define LEADING_CODE_PRIVATE_21 0x9C /* for private DIMENSION2 of 1-column */ | |
| 100 | #define LEADING_CODE_PRIVATE_22 0x9D /* for private DIMENSION2o f 2-column */ | |
| 101 | ||
| 102 | /* Extended leading-code. */ | |
| 103 | /* Start of each extended leading-codes. */ | |
| 104 | #define LEADING_CODE_EXT_11 0xA0 /* follows LEADING_CODE_PRIVATE_11 */ | |
| 105 | #define LEADING_CODE_EXT_12 0xE0 /* follows LEADING_CODE_PRIVATE_12 */ | |
| 106 | #define LEADING_CODE_EXT_21 0xF0 /* follows LEADING_CODE_PRIVATE_21 */ | |
| 107 | #define LEADING_CODE_EXT_22 0xF5 /* follows LEADING_CODE_PRIVATE_22 */ | |
| 108 | /* Maximum value of extended leading-codes. */ | |
| 109 | #define LEADING_CODE_EXT_MAX 0xFE | |
| 110 | ||
| 111 | /* Definition of minimum/maximum charset of each DIMENSION. */ | |
| 112 | #define MIN_CHARSET_OFFICIAL_DIMENSION1 0x81 | |
| 113 | #define MAX_CHARSET_OFFICIAL_DIMENSION1 0x8F | |
| 114 | #define MIN_CHARSET_OFFICIAL_DIMENSION2 0x90 | |
| 115 | #define MAX_CHARSET_OFFICIAL_DIMENSION2 0x99 | |
| 116 | #define MIN_CHARSET_PRIVATE_DIMENSION1 LEADING_CODE_EXT_11 | |
| 117 | #define MIN_CHARSET_PRIVATE_DIMENSION2 LEADING_CODE_EXT_21 | |
| 118 | ||
| 119 | /* Definition of special charsets. */ | |
| 120 | #define CHARSET_ASCII 0 | |
| 121 | #define CHARSET_COMPOSITION 0x80 | |
| 122 | ||
| 123 | extern int charset_ascii; /* ASCII */ | |
| 124 | extern int charset_composition; /* for a composite character */ | |
| 125 | extern int charset_latin_iso8859_1; /* ISO8859-1 (Latin-1) */ | |
| 126 | extern int charset_jisx0208_1978; /* JISX0208.1978 (Japanese Kanji old set) */ | |
| 127 | extern int charset_jisx0208; /* JISX0208.1983 (Japanese Kanji) */ | |
| 128 | extern int charset_katakana_jisx0201; /* JISX0201.Kana (Japanese Katakana) */ | |
| 129 | extern int charset_latin_jisx0201; /* JISX0201.Roman (Japanese Roman) */ | |
| 130 | extern int charset_big5_1; /* Big5 Level 1 (Chinese Traditional) */ | |
| 131 | extern int charset_big5_2; /* Big5 Level 2 (Chinese Traditional) */ | |
| 132 | ||
| 133 | /* Check if STR points the head of multi-byte form, i.e. *STR is an | |
| 134 | ASCII character or a base leading-code. */ | |
| 135 | #define CHAR_HEAD_P(str) ((unsigned char) *(str) < 0xA0) | |
| 136 | ||
| 137 | /*** GENERAL NOTE on CHARACTER REPRESENTATION *** | |
| 138 | ||
| 139 | At first, the term "character" or "char" is used for a multilingual | |
| 140 | character (of course, including ASCII character), not for a byte in | |
| 141 | computer memory. We use the term "code" or "byte" for the latter | |
| 142 | case. | |
| 143 | ||
| 144 | A character is identified by charset and one or two POSITION-CODEs. | |
| 145 | POSITION-CODE is the position of the character in the charset. A | |
| 146 | character of DIMENSION1 charset has one POSITION-CODE: POSITION-CODE-1. | |
| 147 | A character of DIMENSION2 charset has two POSITION-CODE: | |
| 148 | POSITION-CODE-1 and POSITION-CODE-2. The code range of | |
| 149 | POSITION-CODE is 0x20..0x7F. | |
| 150 | ||
| 151 | Emacs has two kinds of representation of a character: multi-byte | |
| 152 | form (for buffer and string) and single-word form (for character | |
| 153 | object in Emacs Lisp). The latter is called "character code" here | |
| 154 | after. Both representation encode the information of charset and | |
| 155 | POSITION-CODE but in a different way (for instance, MSB of | |
| 156 | POSITION-CODE is set in multi-byte form). | |
| 157 | ||
| 158 | For details of multi-byte form, see the section "2. Emacs internal | |
| 159 | format handlers" of `coding.c'. | |
| 160 | ||
| 161 | Emacs uses 19 bits for a character code. The bits are divided into | |
| 162 | 3 fields: FIELD1(5bits):FIELD2(7bits):FIELD3(7bits). | |
| 163 | ||
| 164 | A character code of DIMENSION1 character uses FIELD2 to hold charset | |
| 165 | and FIELD3 to hold POSITION-CODE-1. A character code of DIMENSION2 | |
| 166 | character uses FIELD1 to hold charset, FIELD2 and FIELD3 to hold | |
| 167 | POSITION-CODE-1 and POSITION-CODE-2 respectively. | |
| 168 | ||
| 169 | More precisely... | |
| 170 | ||
| 171 | FIELD2 of DIMENSION1 character (except for ASCII) is "charset - 0x70". | |
| 172 | This is to make all character codes except for ASCII greater than | |
| 173 | 256 (ASCII's FIELD2 is 0). So, the range of FIELD2 of DIMENSION1 | |
| 174 | character is 0 or 0x11..0x7F. | |
| 175 | ||
| 176 | FIELD1 of DIMENSION2 character is "charset - 0x8F" for official | |
| 177 | charset and "charset - 0xE0" for private charset. So, the range of | |
| 178 | FIELD1 of DIMENSION2 character is 0x01..0x1E. | |
| 179 | ||
| 180 | ----------------------------------------------------------------------- | |
| 181 | charset FIELD1 (5-bit) FIELD2 (7-bit) FIELD3 (7-bit) | |
| 182 | ----------------------------------------------------------------------- | |
| 183 | ASCII 0 0 POSITION-CODE-1 | |
| 184 | DIMENSION1 0 charset - 0x70 POSITION-CODE-1 | |
| 185 | DIMENSION2(o) charset - 0x8F POSITION-CODE-1 POSITION-CODE-2 | |
| 186 | DIMENSION2(p) charset - 0xE0 POSITION-CODE-1 POSITION-CODE-2 | |
| 187 | ----------------------------------------------------------------------- | |
| 188 | "(o)": official, "(p)": private | |
| 189 | ----------------------------------------------------------------------- | |
| 190 | ||
| 191 | */ | |
| 192 | ||
| 193 | /*** GENERAL NOTE on COMPOSITE CHARACTER *** | |
| 194 | ||
| 195 | A composite character is a character composed from several (up to | |
| 196 | 16) non-composite characters (components). Although each components | |
| 197 | can belong to any charset, a composite character itself belongs to | |
| 198 | the charset `charset-composition' and is assigned a special | |
| 199 | leading-code `LEADING_CODE_COMPOSITION' for multi-byte form. See | |
| 200 | the document "2. Emacs internal format handlers" in `coding.c' for | |
| 201 | more detail about multi-byte form. | |
| 202 | ||
| 203 | A character code of composite character has special format. In the | |
| 204 | above document, FIELD1 of a composite character is 0x1F. Each | |
| 205 | composite character is assigned a sequential number CMPCHAR-ID. | |
| 206 | FIELD2 and FIELD3 are combined to make 14bits field for holding | |
| 207 | CMPCHAR-ID, which means that Emacs can handle at most 2^14 (= 16384) | |
| 208 | composite characters at once. | |
| 209 | ||
| 210 | ----------------------------------------------------------------------- | |
| 211 | charset FIELD1 (5-bit) FIELD2&3 (14-bit) | |
| 212 | ----------------------------------------------------------------------- | |
| 213 | CHARSET-COMPOSITION 0x1F CMPCHAR-ID | |
| 214 | ----------------------------------------------------------------------- | |
| 215 | ||
| 216 | Emacs assigns CMPCHAR-ID to a composite character only when it | |
| 217 | requires the character code of the composite character (e.g. while | |
| 218 | displaying the composite character). | |
| 219 | ||
| 220 | */ | |
| 221 | ||
| 222 | /* Masks of each field of character code. */ | |
| 223 | #define CHAR_FIELD1_MASK (0x1F << 14) | |
| 224 | #define CHAR_FIELD2_MASK (0x7F << 7) | |
| 225 | #define CHAR_FIELD3_MASK 0x7F | |
| 226 | ||
| 227 | /* Macros to access each field of character C. */ | |
| 228 | #define CHAR_FIELD1(c) (((c) & CHAR_FIELD1_MASK) >> 14) | |
| 229 | #define CHAR_FIELD2(c) (((c) & CHAR_FIELD2_MASK) >> 7) | |
| 230 | #define CHAR_FIELD3(c) ((c) & CHAR_FIELD3_MASK) | |
| 231 | ||
| 232 | /* Minimum character code of character of each DIMENSION. */ | |
| 233 | #define MIN_CHAR_OFFICIAL_DIMENSION1 \ | |
| 234 | ((MIN_CHARSET_OFFICIAL_DIMENSION1 - 0x70) << 7) | |
| 235 | #define MIN_CHAR_PRIVATE_DIMENSION1 \ | |
| 236 | ((MIN_CHARSET_PRIVATE_DIMENSION1 - 0x70) << 7) | |
| 237 | #define MIN_CHAR_OFFICIAL_DIMENSION2 \ | |
| 238 | ((MIN_CHARSET_OFFICIAL_DIMENSION2 - 0x8F) << 14) | |
| 239 | #define MIN_CHAR_PRIVATE_DIMENSION2 \ | |
| 240 | ((MIN_CHARSET_PRIVATE_DIMENSION2 - 0xE0) << 14) | |
| 241 | #define MIN_CHAR_COMPOSITION \ | |
| 242 | (0x1F << 14) | |
| 243 | ||
| 244 | /* 1 if C is an ASCII character, else 0. */ | |
| 245 | #define SINGLE_BYTE_CHAR_P(c) ((c) < 0x100) | |
| 246 | /* 1 if C is an composite character, else 0. */ | |
| 247 | #define COMPOSITE_CHAR_P(c) ((c) >= MIN_CHAR_COMPOSITION) | |
| 248 | ||
| 249 | /* A char-table containing information of each character set. | |
| 250 | ||
| 251 | Unlike ordinary char-tables, this doesn't contain any nested table. | |
| 252 | Only the top level elements are used. Each element is a vector of | |
| 253 | the following information: | |
| 254 | CHARSET-ID, BYTES, DIMENSION, CHARS, WIDTH, DIRECTION, | |
| 255 | LEADING-CODE-BASE, LEADING-CODE-EXT, | |
| 256 | ISO-FINAL-CHAR, ISO-GRAPHIC-PLANE, | |
| 257 | REVERSE-CHARSET, SHORT-NAME, LONG-NAME, DESCRIPTION, | |
| 258 | PLIST. | |
| 259 | ||
| 260 | CHARSET-ID (integer) is the identification number of the charset. | |
| 261 | ||
| 262 | BYTE (integer) is the length of multi-byte form of a character in | |
| 263 | the charset: one of 1, 2, 3, and 4. | |
| 264 | ||
| 265 | DIMENSION (integer) is the number of bytes to represent a character: 1 or 2. | |
| 266 | ||
| 267 | CHARS (integer) is the number of characters in a dimension: 94 or 96. | |
| 268 | ||
| 269 | WIDTH (integer) is the number of columns a character in the charset | |
| 270 | occupies on the screen: one of 0, 1, and 2. | |
| 271 | ||
| 272 | DIRECTION (integer) is the rendering direction of characters in the | |
| 273 | charset when rendering. If 0, render from right to left, else | |
| 274 | render from left to right. | |
| 275 | ||
| 276 | LEADING-CODE-BASE (integer) is the base leading-code for the | |
| 277 | charset. | |
| 278 | ||
| 279 | LEADING-CODE-EXT (integer) is the extended leading-code for the | |
| 280 | charset. All charsets of less than 0xA0 has the value 0. | |
| 281 | ||
| 282 | ISO-FINAL-CHAR (character) is the final character of the | |
| 283 | corresponding ISO 2022 charset. | |
| 284 | ||
| 285 | ISO-GRAPHIC-PLANE (integer) is the graphic plane to be invoked | |
| 286 | while encoding to variants of ISO 2022 coding system, one of the | |
| 287 | following: 0/graphic-plane-left(GL), 1/graphic-plane-right(GR). | |
| 288 | ||
| 289 | REVERSE-CHARSET (integer) is the charset which differs only in | |
| 290 | LEFT-TO-RIGHT value from the charset. If there's no such a | |
| 291 | charset, the value is -1. | |
| 292 | ||
| 293 | SHORT-NAME (string) is the short name to refer to the charset. | |
| 294 | ||
| 295 | LONG-NAME (string) is the long name to refer to the charset. | |
| 296 | ||
| 297 | DESCRIPTION (string) is the description string of the charset. | |
| 298 | ||
| 299 | PLIST (property list) may contain any type of information a user | |
| 300 | want to put and get by functions `put-charset-property' and | |
| 301 | `get-charset-property' respectively. */ | |
| 302 | extern Lisp_Object Vcharset_table; | |
| 303 | ||
| 304 | /* Macros to access various information of CHARSET in Vcharset_table. | |
| 305 | We provide these macros for efficiency. No range check of CHARSET. */ | |
| 306 | ||
| 307 | /* Return entry of CHARSET (lisp integer) in Vcharset_table. */ | |
| 308 | #define CHARSET_TABLE_ENTRY(charset) \ | |
| 309 | XCHAR_TABLE (Vcharset_table)->contents[charset] | |
| 310 | ||
| 311 | /* Return information INFO-IDX of CHARSET. */ | |
| 312 | #define CHARSET_TABLE_INFO(charset, info_idx) \ | |
| 313 | XVECTOR (CHARSET_TABLE_ENTRY (charset))->contents[info_idx] | |
| 314 | ||
| 315 | #define CHARSET_ID_IDX (0) | |
| 316 | #define CHARSET_BYTES_IDX (1) | |
| 317 | #define CHARSET_DIMENSION_IDX (2) | |
| 318 | #define CHARSET_CHARS_IDX (3) | |
| 319 | #define CHARSET_WIDTH_IDX (4) | |
| 320 | #define CHARSET_DIRECTION_IDX (5) | |
| 321 | #define CHARSET_LEADING_CODE_BASE_IDX (6) | |
| 322 | #define CHARSET_LEADING_CODE_EXT_IDX (7) | |
| 323 | #define CHARSET_ISO_FINAL_CHAR_IDX (8) | |
| 324 | #define CHARSET_ISO_GRAPHIC_PLANE_IDX (9) | |
| 325 | #define CHARSET_REVERSE_CHARSET_IDX (10) | |
| 326 | #define CHARSET_SHORT_NAME_IDX (11) | |
| 327 | #define CHARSET_LONG_NAME_IDX (12) | |
| 328 | #define CHARSET_DESCRIPTION_IDX (13) | |
| 329 | #define CHARSET_PLIST_IDX (14) | |
| 330 | /* Size of a vector of each entry of Vcharset_table. */ | |
| 331 | #define CHARSET_MAX_IDX (15) | |
| 332 | ||
| 333 | /* And several more macros to be used frequently. */ | |
| 334 | #define CHARSET_BYTES(charset) \ | |
| 335 | XFASTINT (CHARSET_TABLE_INFO (charset, CHARSET_BYTES_IDX)) | |
| 336 | #define CHARSET_DIMENSION(charset) \ | |
| 337 | XFASTINT (CHARSET_TABLE_INFO (charset, CHARSET_DIMENSION_IDX)) | |
| 338 | #define CHARSET_CHARS(charset) \ | |
| 339 | XFASTINT (CHARSET_TABLE_INFO (charset, CHARSET_CHARS_IDX)) | |
| 340 | #define CHARSET_WIDTH(charset) \ | |
| 341 | XFASTINT (CHARSET_TABLE_INFO (charset, CHARSET_WIDTH_IDX)) | |
| 342 | #define CHARSET_DIRECTION(charset) \ | |
| 343 | XFASTINT (CHARSET_TABLE_INFO (charset, CHARSET_DIRECTION_IDX)) | |
| 344 | #define CHARSET_LEADING_CODE_BASE(charset) \ | |
| 345 | XFASTINT (CHARSET_TABLE_INFO (charset, CHARSET_LEADING_CODE_BASE_IDX)) | |
| 346 | #define CHARSET_LEADING_CODE_EXT(charset) \ | |
| 347 | XFASTINT (CHARSET_TABLE_INFO (charset, CHARSET_LEADING_CODE_EXT_IDX)) | |
| 348 | #define CHARSET_ISO_FINAL_CHAR(charset) \ | |
| 349 | XFASTINT (CHARSET_TABLE_INFO (charset, CHARSET_ISO_FINAL_CHAR_IDX)) | |
| 350 | #define CHARSET_ISO_GRAPHIC_PLANE(charset) \ | |
| 351 | XFASTINT (CHARSET_TABLE_INFO (charset, CHARSET_ISO_GRAPHIC_PLANE_IDX)) | |
| 352 | #define CHARSET_REVERSE_CHARSET(charset) \ | |
| 353 | XINT (CHARSET_TABLE_INFO (charset, CHARSET_REVERSE_CHARSET_IDX)) | |
| 354 | ||
| 355 | /* Macros to specify direction of a charset. */ | |
| 356 | #define CHARSET_DIRECTION_LEFT_TO_RIGHT 0 | |
| 357 | #define CHARSET_DIRECTION_RIGHT_TO_LEFT 1 | |
| 358 | ||
| 359 | /* A vector of charset symbol indexed by charset-id. This is used | |
| 360 | only for returning charset symbol from C functions. */ | |
| 361 | extern Lisp_Object Vcharset_symbol_table; | |
| 362 | ||
| 363 | /* Return symbol of CHARSET. */ | |
| 364 | #define CHARSET_SYMBOL(charset) \ | |
| 365 | XVECTOR (Vcharset_symbol_table)->contents[charset] | |
| 366 | ||
| 367 | /* 1 if CHARSET is valid, else 0. */ | |
| 368 | #define CHARSET_VALID_P(charset) \ | |
| 369 | ((charset) == 0 \ | |
| 370 | || ((charset) >= 0x80 && (charset) <= MAX_CHARSET_OFFICIAL_DIMENSION2) \ | |
| 371 | || ((charset) >= MIN_CHARSET_PRIVATE_DIMENSION1 && (charset) < MAX_CHARSET)) | |
| 372 | ||
| 373 | /* 1 if CHARSET is already defined, else 0. */ | |
| 374 | #define CHARSET_DEFINED_P(charset) \ | |
| 375 | (((charset) >= 0) && ((charset) < MAX_CHARSET) \ | |
| 376 | && !NILP (CHARSET_TABLE_ENTRY (charset))) | |
| 377 | ||
| 378 | /* Since the information CHARSET-BYTES and CHARSET-WIDTH of | |
| 379 | Vcharset_table can be retrieved only from the first byte of | |
| 380 | multi-byte form (an ASCII code or a base leading-code), we provide | |
| 381 | here tables to be used by macros BYTES_BY_CHAR_HEAD and | |
| 382 | WIDTH_BY_CHAR_HEAD for faster information retrieval. */ | |
| 383 | extern int bytes_by_char_head[256]; | |
| 384 | extern int width_by_char_head[256]; | |
| 385 | ||
| 386 | #define BYTES_BY_CHAR_HEAD(char_head) bytes_by_char_head[char_head] | |
| 387 | #define WIDTH_BY_CHAR_HEAD(char_head) width_by_char_head[char_head] | |
| 388 | ||
| 389 | /* Charset of the character C. */ | |
| 390 | #define CHAR_CHARSET(c) \ | |
| 391 | (SINGLE_BYTE_CHAR_P (c) \ | |
| 392 | ? CHARSET_ASCII \ | |
| 393 | : ((c) < MIN_CHAR_OFFICIAL_DIMENSION2 \ | |
| 394 | ? CHAR_FIELD2 (c) + 0x70 \ | |
| 395 | : ((c) < MIN_CHAR_PRIVATE_DIMENSION2 \ | |
| 396 | ? CHAR_FIELD1 (c) + 0x8F \ | |
| 397 | : ((c) < MIN_CHAR_COMPOSITION \ | |
| 398 | ? CHAR_FIELD1 (c) + 0xE0 \ | |
| 399 | : CHARSET_COMPOSITION)))) | |
| 400 | ||
| 401 | /* Return charset at the place pointed by P. */ | |
| 402 | #define CHARSET_AT(p) \ | |
| 403 | (*(p) < 0x80 \ | |
| 404 | ? CHARSET_ASCII \ | |
| 405 | : (*(p) == LEADING_CODE_COMPOSITION \ | |
| 406 | ? CHARSET_COMPOSITION \ | |
| 407 | : (*(p) < LEADING_CODE_PRIVATE_11 \ | |
| 408 | ? (int)*(p) \ | |
| 409 | : (*(p) <= LEADING_CODE_PRIVATE_22 \ | |
| 410 | ? (int)*((p) + 1) \ | |
| 411 | : -1)))) | |
| 412 | ||
| 413 | /* Same as `CHARSET_AT ()' but perhaps runs faster because of an | |
| 414 | additional argument C which is the code (byte) at P. */ | |
| 415 | #define FIRST_CHARSET_AT(p, c) \ | |
| 416 | ((c) < 0x80 \ | |
| 417 | ? CHARSET_ASCII \ | |
| 418 | : ((c) == LEADING_CODE_COMPOSITION \ | |
| 419 | ? CHARSET_COMPOSITION \ | |
| 420 | : ((c) < LEADING_CODE_PRIVATE_11 \ | |
| 421 | ? (int)(c) \ | |
| 422 | : ((c) <= LEADING_CODE_PRIVATE_22 \ | |
| 423 | ? (int)*((p) + 1) \ | |
| 424 | : -1)))) | |
| 425 | ||
| 426 | /* Check if two characters C1 and C2 belong to the same charset. | |
| 427 | Always return 0 for composite characters. */ | |
| 428 | #define SAME_CHARSET_P(c1, c2) \ | |
| 429 | (c1 < MIN_CHAR_COMPOSITION \ | |
| 430 | && (SINGLE_BYTE_CHAR_P (c1) \ | |
| 431 | ? SINGLE_BYTE_CHAR_P (c2) \ | |
| 432 | : (c1 < MIN_CHAR_OFFICIAL_DIMENSION2 \ | |
| 433 | ? (c1 & CHAR_FIELD2_MASK) == (c2 & CHAR_FIELD2_MASK) \ | |
| 434 | : (c1 & CHAR_FIELD1_MASK) == (c2 & CHAR_FIELD1_MASK)))) | |
| 435 | ||
| 436 | /* Return a non-ASCII character of which charset is CHARSET and | |
| 437 | position-codes are C1 and C2. DIMENSION1 character ignores C2. */ | |
| 438 | #define MAKE_NON_ASCII_CHAR(charset, c1, c2) \ | |
| 439 | ((charset) == CHARSET_COMPOSITION \ | |
| 440 | ? MAKE_COMPOSITE_CHAR (((c1) << 7) + (c2)) \ | |
| 441 | : (CHARSET_DIMENSION (charset) == 1 \ | |
| 442 | ? (((charset) - 0x70) << 7) | (c1) \ | |
| 443 | : ((charset) < MIN_CHARSET_PRIVATE_DIMENSION2 \ | |
| 444 | ? (((charset) - 0x8F) << 14) | ((c1) << 7) | (c2) \ | |
| 445 | : (((charset) - 0xE0) << 14) | ((c1) << 7) | (c2)))) | |
| 446 | ||
| 447 | /* Return a composite character of which CMPCHAR-ID is ID. */ | |
| 448 | #define MAKE_COMPOSITE_CHAR(id) (MIN_CHAR_COMPOSITION + (id)) | |
| 449 | ||
| 450 | /* Return CMPCHAR-ID of a composite character C. */ | |
| 451 | #define COMPOSITE_CHAR_ID(c) ((c) - MIN_CHAR_COMPOSITION) | |
| 452 | ||
| 453 | /* Return a character of which charset is CHARSET and position-codes | |
| 454 | are C1 and C2. DIMENSION1 character ignores C2. */ | |
| 455 | #define MAKE_CHAR(charset, c1, c2) \ | |
| 456 | ((charset) == CHARSET_ASCII \ | |
| 457 | ? (c1) \ | |
| 458 | : MAKE_NON_ASCII_CHAR ((charset), (c1) & 0x7F, (c2) & 0x7F)) | |
| 459 | ||
| 460 | /* The charset of non-ASCII character C is set to CHARSET, and the | |
| 461 | position-codes of C are set to C1 and C2. C2 of DIMENSION1 character | |
| 462 | is 0. */ | |
| 463 | #define SPLIT_NON_ASCII_CHAR(c, charset, c1, c2) \ | |
| 464 | ((c) < MIN_CHAR_OFFICIAL_DIMENSION2 \ | |
| 465 | ? (charset = CHAR_FIELD2 (c) + 0x70, \ | |
| 466 | c1 = CHAR_FIELD3 (c), \ | |
| 467 | c2 = 0) \ | |
| 468 | : (charset = ((c) < MIN_CHAR_COMPOSITION \ | |
| 469 | ? (CHAR_FIELD1 (c) \ | |
| 470 | + ((c) < MIN_CHAR_PRIVATE_DIMENSION2 ? 0x8F : 0xE0)) \ | |
| 471 | : CHARSET_COMPOSITION), \ | |
| 472 | c1 = CHAR_FIELD2 (c), \ | |
| 473 | c2 = CHAR_FIELD3 (c))) | |
| 474 | ||
| 475 | /* The charset of character C is set to CHARSET, and the | |
| 476 | position-codes of C are set to C1 and C2. C2 of DIMENSION1 character | |
| 477 | is 0. */ | |
| 478 | #define SPLIT_CHAR(c, charset, c1, c2) \ | |
| 479 | (SINGLE_BYTE_CHAR_P (c) \ | |
| 480 | ? charset = CHARSET_ASCII, c1 = (c), c2 = 0 \ | |
| 481 | : SPLIT_NON_ASCII_CHAR (c, charset, c1, c2)) | |
| 482 | ||
| 483 | /* The charset of the character at STR is set to CHARSET, and the | |
| 484 | position-codes are set to C1 and C2. C2 of DIMENSION1 character is 0. | |
| 485 | If the character is a composite character, the upper 7-bit and | |
| 486 | lower 7-bit of CMPCHAR-ID are set in C1 and C2 respectively. No | |
| 487 | range checking. */ | |
| 488 | #define SPLIT_STRING(str, len, charset, c1, c2) \ | |
| 489 | ((BYTES_BY_CHAR_HEAD ((unsigned char) *(str)) < 2 \ | |
| 490 | || BYTES_BY_CHAR_HEAD ((unsigned char) *(str)) > len \ | |
| 491 | || split_non_ascii_string (str, len, &charset, &c1, &c2, 0) < 0) \ | |
| 492 | ? c1 = *(str), charset = CHARSET_ASCII \ | |
| 493 | : charset) | |
| 494 | ||
| 495 | #define MAX_CHARSET 0xFF | |
| 496 | ||
| 497 | /* Mapping table from ISO2022's charset (specified by DIMENSION, | |
| 498 | CHARS, and FINAL_CHAR) to Emacs' charset. Should be accessed by | |
| 499 | macro ISO_CHARSET_TABLE (DIMENSION, CHARS, FINAL_CHAR). */ | |
| 500 | extern int iso_charset_table[2][2][128]; | |
| 501 | ||
| 502 | #define ISO_CHARSET_TABLE(dimension, chars, final_char) \ | |
| 503 | iso_charset_table[XINT (dimension) - 1][XINT (chars) > 94][XINT (final_char)] | |
| 504 | ||
| 505 | #define BASE_LEADING_CODE_P(c) (BYTES_BY_CHAR_HEAD ((unsigned char) (c)) > 1) | |
| 506 | ||
| 507 | /* The following two macros CHAR_STRING and STRING_CHAR are the main | |
| 508 | entry points to convert between Emacs two types of character | |
| 509 | representations: multi-byte form and single-word form (character | |
| 510 | code). */ | |
| 511 | ||
| 512 | /* Set STR a pointer to the multi-byte form of the character C. If C | |
| 513 | is not a composite character, the multi-byte form is set in WORKBUF | |
| 514 | and STR points WORKBUF. The caller should allocate at least 4-byte | |
| 515 | area at WORKBUF in advance. Returns the length of the multi-byte | |
| 516 | form. */ | |
| 517 | ||
| 518 | #define CHAR_STRING(c, workbuf, str) \ | |
| 519 | (SINGLE_BYTE_CHAR_P (c) \ | |
| 520 | ? *(str = workbuf) = (unsigned char)(c), 1 \ | |
| 521 | : non_ascii_char_to_string (c, workbuf, &str)) | |
| 522 | ||
| 523 | /* Return a character code of the character of which multi-byte form | |
| 524 | is at STR and the length is LEN. If STR doesn't contain valid | |
| 525 | multi-byte form, only the first byte in STR is returned. */ | |
| 526 | ||
| 527 | #define STRING_CHAR(str, len) \ | |
| 528 | ((BYTES_BY_CHAR_HEAD ((unsigned char) *(str)) == 1 \ | |
| 529 | || BYTES_BY_CHAR_HEAD ((unsigned char) *(str)) > (len)) \ | |
| 530 | ? (unsigned char) *(str) \ | |
| 531 | : string_to_non_ascii_char (str, len, 0)) | |
| 532 | ||
| 533 | /* This is like STRING_CHAR but the third arg ACTUAL_LEN is set to | |
| 534 | the length of the multi-byte form. Just to know the length, use | |
| 535 | MULTIBYTE_FORM_LENGTH. */ | |
| 536 | ||
| 537 | #define STRING_CHAR_AND_LENGTH(str, len, actual_len) \ | |
| 538 | ((BYTES_BY_CHAR_HEAD ((unsigned char) *(str)) == 1 \ | |
| 539 | || BYTES_BY_CHAR_HEAD ((unsigned char) *(str)) > (len)) \ | |
| 540 | ? (actual_len = 1), (unsigned char) *(str) \ | |
| 541 | : string_to_non_ascii_char (str, len, &actual_len)) | |
| 542 | ||
| 543 | /* Return the length of the multi-byte form at string STR of length LEN. */ | |
| 544 | ||
| 545 | #define MULTIBYTE_FORM_LENGTH(str, len) \ | |
| 546 | ((BYTES_BY_CHAR_HEAD (*(unsigned char *)(str)) == 1 \ | |
| 547 | || BYTES_BY_CHAR_HEAD (*(unsigned char *)(str)) > (len)) \ | |
| 548 | ? 1 \ | |
| 549 | : multibyte_form_length (str, len)) | |
| 550 | ||
| 551 | /* Set C a (possibly multibyte) character at P. P points into a | |
| 552 | string which is the virtual concatenation of STR1 (which ends at | |
| 553 | END1) or STR2 (which ends at END2). */ | |
| 554 | ||
| 555 | #define GET_CHAR_AFTER_2(c, p, str1, end1, str2, end2) \ | |
| 556 | do { \ | |
| 557 | const char *dtemp = (p) == (end1) ? (str2) : (p); \ | |
| 558 | const char *dlimit = ((p) >= (str1) && (p) < (end1)) ? (end1) : (end2); \ | |
| 559 | c = STRING_CHAR (dtemp, dlimit - dtemp); \ | |
| 560 | } while (0) | |
| 561 | ||
| 562 | /* Set C a (possibly multibyte) character before P. P points into a | |
| 563 | string which is the virtual concatenation of STR1 (which ends at | |
| 564 | END1) or STR2 (which ends at END2). */ | |
| 565 | ||
| 566 | #define GET_CHAR_BEFORE_2(c, p, str1, end1, str2, end2) \ | |
| 567 | do { \ | |
| 568 | const char *dtemp = (p); \ | |
| 569 | const char *dlimit = ((p) > (str2) && (p) <= (end2)) ? (str2) : (str1); \ | |
| 570 | while (dtemp-- > dlimit && (unsigned char) *dtemp >= 0xA0); \ | |
| 571 | c = STRING_CHAR (dtemp, p - dtemp); \ | |
| 572 | } while (0) | |
| 573 | ||
| 574 | #ifdef emacs | |
| 575 | ||
| 576 | /* Increase the buffer point POS of the current buffer to the next | |
| 577 | character boundary. This macro relies on the fact that *GPT_ADDR | |
| 578 | and *Z_ADDR are always accessible and the values are '\0'. No | |
| 579 | range checking of POS. */ | |
| 580 | #define INC_POS(pos) \ | |
| 581 | do { \ | |
| 582 | unsigned char *p = POS_ADDR (pos) + 1; \ | |
| 583 | pos++; \ | |
| 584 | while (!CHAR_HEAD_P (p)) p++, pos++; \ | |
| 585 | } while (0) | |
| 586 | ||
| 587 | /* Decrease the buffer point POS of the current buffer to the previous | |
| 588 | character boundary. No range checking of POS. */ | |
| 589 | #define DEC_POS(pos) \ | |
| 590 | do { \ | |
| 591 | unsigned char *p, *p_min; \ | |
| 592 | if (--pos < GPT) \ | |
| 593 | p = BEG_ADDR + pos - 1, p_min = BEG_ADDR; \ | |
| 594 | else \ | |
| 595 | p = BEG_ADDR + GAP_SIZE + pos - 1, p_min = GAP_END_ADDR; \ | |
| 596 | while (p > p_min && !CHAR_HEAD_P (p)) p--, pos--; \ | |
| 597 | } while (0) | |
| 598 | ||
| 599 | #endif /* emacs */ | |
| 600 | ||
| 601 | /* Maximum counts of components in one composite character. */ | |
| 602 | #define MAX_COMPONENT_COUNT 16 | |
| 603 | ||
| 604 | /* Structure to hold information of a composite character. */ | |
| 605 | struct cmpchar_info { | |
| 606 | /* Byte length of the composite character. */ | |
| 607 | int len; | |
| 608 | ||
| 609 | /* Multi-byte form of the composite character. */ | |
| 610 | unsigned char *data; | |
| 611 | ||
| 612 | /* Length of glyph codes. */ | |
| 613 | int glyph_len; | |
| 614 | ||
| 615 | /* Width of the overall glyph of the composite character. */ | |
| 616 | int width; | |
| 617 | ||
| 618 | /* Pointer to an array of glyph codes of the composite character. | |
| 619 | This actually contains only character code, no face. */ | |
| 620 | GLYPH *glyph; | |
| 621 | ||
| 622 | /* Pointer to an array of composition rules. The value has the form: | |
| 623 | (0xA0 + ((GLOBAL-REF-POINT << 2) | NEW-REF-POINT)) | |
| 624 | where each XXX-REF-POINT is 0..8. */ | |
| 625 | unsigned char *cmp_rule; | |
| 626 | ||
| 627 | /* Pointer to an array of x-axis offset of left edge of glyphs | |
| 628 | relative to the left of of glyph[0] except for the first element | |
| 629 | which is the absolute offset from the left edge of overall glyph. | |
| 630 | The actual pixel offset should be calculated by multiplying each | |
| 631 | frame's one column width by this value: | |
| 632 | (i.e. FONT_WIDTH (f->output_data.x->font) * col_offset[N]). */ | |
| 633 | float *col_offset; | |
| 634 | ||
| 635 | /* Work slot used by `dumpglyphs' (xterm.c). */ | |
| 636 | int face_work; | |
| 637 | }; | |
| 638 | ||
| 639 | /* Table of pointers to the structure `cmpchar_info' indexed by | |
| 640 | CMPCHAR-ID. */ | |
| 641 | extern struct cmpchar_info **cmpchar_table; | |
| 642 | /* Number of the current composite characters. */ | |
| 643 | extern int n_cmpchars; | |
| 644 | ||
| 645 | /* This is the maximum length of multi-byte form. */ | |
| 646 | #define MAX_LENGTH_OF_MULTI_BYTE_FORM (MAX_COMPONENT_COUNT * 6) | |
| 647 | ||
| 648 | #endif /* _CHARSET_H */ | |
| 649 |