| 1 | /* Header for coding system handler. |
| 2 | Copyright (C) 1995, 1997 Electrotechnical Laboratory, JAPAN. |
| 3 | Licensed to the Free Software Foundation. |
| 4 | |
| 5 | This file is part of GNU Emacs. |
| 6 | |
| 7 | GNU Emacs 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 | GNU Emacs 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 GNU Emacs; see the file COPYING. If not, write to |
| 19 | the Free Software Foundation, Inc., 59 Temple Place - Suite 330, |
| 20 | Boston, MA 02111-1307, USA. */ |
| 21 | |
| 22 | #ifndef EMACS_CODING_H |
| 23 | #define EMACS_CODING_H |
| 24 | |
| 25 | #include "ccl.h" |
| 26 | |
| 27 | /*** EMACS' INTERNAL FORMAT (emacs-mule) section ***/ |
| 28 | |
| 29 | /* All code (1-byte) of Emacs' internal format is classified into one |
| 30 | of the followings. See also `charset.h'. */ |
| 31 | enum emacs_code_class_type |
| 32 | { |
| 33 | EMACS_control_code, /* Control codes in the range |
| 34 | 0x00..0x1F and 0x7F except for the |
| 35 | following two codes. */ |
| 36 | EMACS_linefeed_code, /* 0x0A (linefeed) to denote |
| 37 | end-of-line. */ |
| 38 | EMACS_carriage_return_code, /* 0x0D (carriage-return) to be used |
| 39 | in selective display mode. */ |
| 40 | EMACS_ascii_code, /* ASCII characters. */ |
| 41 | EMACS_leading_code_2, /* Base leading code of official |
| 42 | TYPE9N character. */ |
| 43 | EMACS_leading_code_3, /* Base leading code of private TYPE9N |
| 44 | or official TYPE9Nx9N character. */ |
| 45 | EMACS_leading_code_4, /* Base leading code of private |
| 46 | TYPE9Nx9N character. */ |
| 47 | EMACS_invalid_code /* Invalid code, i.e. a base leading |
| 48 | code not yet assigned to any |
| 49 | charset, or a code of the range |
| 50 | 0xA0..0xFF. */ |
| 51 | }; |
| 52 | |
| 53 | extern enum emacs_code_class_type emacs_code_class[256]; |
| 54 | |
| 55 | /*** ISO2022 section ***/ |
| 56 | |
| 57 | /* Macros to define code of control characters for ISO2022's functions. */ |
| 58 | /* code */ /* function */ |
| 59 | #define ISO_CODE_LF 0x0A /* line-feed */ |
| 60 | #define ISO_CODE_CR 0x0D /* carriage-return */ |
| 61 | #define ISO_CODE_SO 0x0E /* shift-out */ |
| 62 | #define ISO_CODE_SI 0x0F /* shift-in */ |
| 63 | #define ISO_CODE_SS2_7 0x19 /* single-shift-2 for 7-bit code */ |
| 64 | #define ISO_CODE_ESC 0x1B /* escape */ |
| 65 | #define ISO_CODE_SS2 0x8E /* single-shift-2 */ |
| 66 | #define ISO_CODE_SS3 0x8F /* single-shift-3 */ |
| 67 | #define ISO_CODE_CSI 0x9B /* control-sequence-introduce */ |
| 68 | |
| 69 | /* All code (1-byte) of ISO2022 is classified into one of the |
| 70 | followings. */ |
| 71 | enum iso_code_class_type |
| 72 | { |
| 73 | ISO_control_0, /* Control codes in the range |
| 74 | 0x00..0x1F and 0x7F, except for the |
| 75 | following 5 codes. */ |
| 76 | ISO_carriage_return, /* ISO_CODE_CR (0x0D) */ |
| 77 | ISO_shift_out, /* ISO_CODE_SO (0x0E) */ |
| 78 | ISO_shift_in, /* ISO_CODE_SI (0x0F) */ |
| 79 | ISO_single_shift_2_7, /* ISO_CODE_SS2_7 (0x19) */ |
| 80 | ISO_escape, /* ISO_CODE_SO (0x1B) */ |
| 81 | ISO_control_1, /* Control codes in the range |
| 82 | 0x80..0x9F, except for the |
| 83 | following 3 codes. */ |
| 84 | ISO_single_shift_2, /* ISO_CODE_SS2 (0x8E) */ |
| 85 | ISO_single_shift_3, /* ISO_CODE_SS3 (0x8F) */ |
| 86 | ISO_control_sequence_introducer, /* ISO_CODE_CSI (0x9B) */ |
| 87 | ISO_0x20_or_0x7F, /* Codes of the values 0x20 or 0x7F. */ |
| 88 | ISO_graphic_plane_0, /* Graphic codes in the range 0x21..0x7E. */ |
| 89 | ISO_0xA0_or_0xFF, /* Codes of the values 0xA0 or 0xFF. */ |
| 90 | ISO_graphic_plane_1 /* Graphic codes in the range 0xA1..0xFE. */ |
| 91 | }; |
| 92 | |
| 93 | /** The macros CODING_FLAG_ISO_XXX defines a flag bit of the `flags' |
| 94 | element in the structure `coding_system'. This information is used |
| 95 | while encoding a text to ISO2022. **/ |
| 96 | |
| 97 | /* If set, produce short-form designation sequence (e.g. ESC $ A) |
| 98 | instead of long-form sequence (e.g. ESC $ ( A). */ |
| 99 | #define CODING_FLAG_ISO_SHORT_FORM 0x0001 |
| 100 | |
| 101 | /* If set, reset graphic planes and registers at end-of-line to the |
| 102 | initial state. */ |
| 103 | #define CODING_FLAG_ISO_RESET_AT_EOL 0x0002 |
| 104 | |
| 105 | /* If set, reset graphic planes and registers before any control |
| 106 | characters to the initial state. */ |
| 107 | #define CODING_FLAG_ISO_RESET_AT_CNTL 0x0004 |
| 108 | |
| 109 | /* If set, encode by 7-bit environment. */ |
| 110 | #define CODING_FLAG_ISO_SEVEN_BITS 0x0008 |
| 111 | |
| 112 | /* If set, use locking-shift function. */ |
| 113 | #define CODING_FLAG_ISO_LOCKING_SHIFT 0x0010 |
| 114 | |
| 115 | /* If set, use single-shift function. Overwrite |
| 116 | CODING_FLAG_ISO_LOCKING_SHIFT. */ |
| 117 | #define CODING_FLAG_ISO_SINGLE_SHIFT 0x0020 |
| 118 | |
| 119 | /* If set, designate JISX0201-Roman instead of ASCII. */ |
| 120 | #define CODING_FLAG_ISO_USE_ROMAN 0x0040 |
| 121 | |
| 122 | /* If set, designate JISX0208-1978 instead of JISX0208-1983. */ |
| 123 | #define CODING_FLAG_ISO_USE_OLDJIS 0x0080 |
| 124 | |
| 125 | /* If set, do not produce ISO6429's direction specifying sequence. */ |
| 126 | #define CODING_FLAG_ISO_NO_DIRECTION 0x0100 |
| 127 | |
| 128 | /* If set, assume designation states are reset at beginning of line on |
| 129 | output. */ |
| 130 | #define CODING_FLAG_ISO_INIT_AT_BOL 0x0200 |
| 131 | |
| 132 | /* If set, designation sequence should be placed at beginning of line |
| 133 | on output. */ |
| 134 | #define CODING_FLAG_ISO_DESIGNATE_AT_BOL 0x0400 |
| 135 | |
| 136 | /* If set, do not encode unsafe charactes on output. */ |
| 137 | #define CODING_FLAG_ISO_SAFE 0x0800 |
| 138 | |
| 139 | /* If set, extra latin codes (128..159) are accepted as a valid code |
| 140 | on input. */ |
| 141 | #define CODING_FLAG_ISO_LATIN_EXTRA 0x1000 |
| 142 | |
| 143 | /* If set, use designation escape sequence. */ |
| 144 | #define CODING_FLAG_ISO_DESIGNATION 0x10000 |
| 145 | |
| 146 | /* A character to be produced on output if encoding of the original |
| 147 | character is prohibited by CODING_FLAG_ISO_SAFE. */ |
| 148 | #define CODING_INHIBIT_CHARACTER_SUBSTITUTION 077 /* 077 == `?' */ |
| 149 | |
| 150 | /* Structure of the field `spec.iso2022' in the structure `coding_system'. */ |
| 151 | struct iso2022_spec |
| 152 | { |
| 153 | /* The current graphic register invoked to each graphic plane. */ |
| 154 | int current_invocation[2]; |
| 155 | |
| 156 | /* The current charset designated to each graphic register. */ |
| 157 | int current_designation[4]; |
| 158 | |
| 159 | /* A charset initially designated to each graphic register. */ |
| 160 | int initial_designation[4]; |
| 161 | |
| 162 | /* If not -1, it is a graphic register specified in an invalid |
| 163 | designation sequence. */ |
| 164 | int last_invalid_designation_register; |
| 165 | |
| 166 | /* A graphic register to which each charset should be designated. */ |
| 167 | unsigned char requested_designation[MAX_CHARSET + 1]; |
| 168 | |
| 169 | /* A revision number to be specified for each charset on encoding. |
| 170 | The value 255 means no revision number for the corresponding |
| 171 | charset. */ |
| 172 | unsigned char charset_revision_number[MAX_CHARSET + 1]; |
| 173 | |
| 174 | /* Set to 1 temporarily only when graphic register 2 or 3 is invoked |
| 175 | by single-shift while encoding. */ |
| 176 | int single_shifting; |
| 177 | |
| 178 | /* Set to 1 temporarily only when processing at beginning of line. */ |
| 179 | int bol; |
| 180 | }; |
| 181 | |
| 182 | /* Macros to access each field in the structure `spec.iso2022'. */ |
| 183 | #define CODING_SPEC_ISO_INVOCATION(coding, plane) \ |
| 184 | (coding)->spec.iso2022.current_invocation[plane] |
| 185 | #define CODING_SPEC_ISO_DESIGNATION(coding, reg) \ |
| 186 | (coding)->spec.iso2022.current_designation[reg] |
| 187 | #define CODING_SPEC_ISO_INITIAL_DESIGNATION(coding, reg) \ |
| 188 | (coding)->spec.iso2022.initial_designation[reg] |
| 189 | #define CODING_SPEC_ISO_REQUESTED_DESIGNATION(coding, charset) \ |
| 190 | (coding)->spec.iso2022.requested_designation[charset] |
| 191 | #define CODING_SPEC_ISO_REVISION_NUMBER(coding, charset) \ |
| 192 | (coding)->spec.iso2022.charset_revision_number[charset] |
| 193 | #define CODING_SPEC_ISO_SINGLE_SHIFTING(coding) \ |
| 194 | (coding)->spec.iso2022.single_shifting |
| 195 | #define CODING_SPEC_ISO_BOL(coding) \ |
| 196 | (coding)->spec.iso2022.bol |
| 197 | |
| 198 | /* A value which may appear in |
| 199 | coding->spec.iso2022.requested_designation indicating that the |
| 200 | corresponding charset does not request any graphic register to be |
| 201 | designated. */ |
| 202 | #define CODING_SPEC_ISO_NO_REQUESTED_DESIGNATION 4 |
| 203 | |
| 204 | /* Return a charset which is currently designated to the graphic plane |
| 205 | PLANE in the coding-system CODING. */ |
| 206 | #define CODING_SPEC_ISO_PLANE_CHARSET(coding, plane) \ |
| 207 | ((CODING_SPEC_ISO_INVOCATION (coding, plane) < 0) \ |
| 208 | ? -1 \ |
| 209 | : CODING_SPEC_ISO_DESIGNATION (coding, \ |
| 210 | CODING_SPEC_ISO_INVOCATION (coding, plane))) |
| 211 | |
| 212 | /*** BIG5 section ***/ |
| 213 | |
| 214 | /* Macros to denote each type of BIG5 coding system. */ |
| 215 | #define CODING_FLAG_BIG5_HKU 0x00 /* BIG5-HKU is one of variants of |
| 216 | BIG5 developed by Hong Kong |
| 217 | University. */ |
| 218 | #define CODING_FLAG_BIG5_ETEN 0x01 /* BIG5_ETen is one of variants |
| 219 | of BIG5 developed by the |
| 220 | company ETen in Taiwan. */ |
| 221 | |
| 222 | /*** GENERAL section ***/ |
| 223 | |
| 224 | /* Types of coding system. */ |
| 225 | enum coding_type |
| 226 | { |
| 227 | coding_type_no_conversion, /* A coding system which requires no |
| 228 | conversion for reading and writing |
| 229 | including end-of-line format. */ |
| 230 | coding_type_emacs_mule, /* A coding system used in Emacs' |
| 231 | buffer and string. Requires no |
| 232 | conversion for reading and writing |
| 233 | except for end-of-line format. */ |
| 234 | coding_type_undecided, /* A coding system which requires |
| 235 | automatic detection of a real |
| 236 | coding system. */ |
| 237 | coding_type_sjis, /* SJIS coding system for Japanese. */ |
| 238 | coding_type_iso2022, /* Any coding system of ISO2022 |
| 239 | variants. */ |
| 240 | coding_type_big5, /* BIG5 coding system for Chinese. */ |
| 241 | coding_type_ccl, /* The coding system of which decoder |
| 242 | and encoder are written in CCL. */ |
| 243 | coding_type_raw_text /* A coding system for a text |
| 244 | containing ramdom 8-bit code which |
| 245 | does not require code conversion |
| 246 | except for end-of-line format. */ |
| 247 | }; |
| 248 | |
| 249 | /* Formats of end-of-line. */ |
| 250 | #define CODING_EOL_LF 0 /* Line-feed only, same as Emacs' |
| 251 | internal format. */ |
| 252 | #define CODING_EOL_CRLF 1 /* Sequence of carriage-return and |
| 253 | line-feed. */ |
| 254 | #define CODING_EOL_CR 2 /* Carriage-return only. */ |
| 255 | #define CODING_EOL_UNDECIDED 3 /* This value is used to denote the |
| 256 | eol-type is not yet decided. */ |
| 257 | #define CODING_EOL_INCONSISTENT 4 /* This value is used to denote the |
| 258 | eol-type is not consistent |
| 259 | through the file. */ |
| 260 | |
| 261 | /* 1 iff composing. */ |
| 262 | #define COMPOSING_P(coding) ((int) coding->composing > (int) COMPOSITION_NO) |
| 263 | |
| 264 | #define COMPOSITION_DATA_SIZE 4080 |
| 265 | #define COMPOSITION_DATA_MAX_BUNCH_LENGTH (4 + MAX_COMPOSITION_COMPONENTS*2) |
| 266 | |
| 267 | /* Data structure to hold information about compositions of text that |
| 268 | is being decoded or encode. ISO 2022 base code conversion routines |
| 269 | handle special ESC sequences for composition specification. But, |
| 270 | they can't get/put such information directly from/to a buffer in |
| 271 | the deepest place. So, they store or retrieve the information |
| 272 | through this structure. |
| 273 | |
| 274 | The encoder stores the information in this structure when it meets |
| 275 | ESC sequences for composition while encoding codes, then, after all |
| 276 | text codes are encoded, puts `composition' properties on the text |
| 277 | by refering the structure. |
| 278 | |
| 279 | The decoder at first stores the information of a text to be |
| 280 | decoded, then, while decoding codes, generates ESC sequences for |
| 281 | composition at proper places by refering the structure. */ |
| 282 | |
| 283 | struct composition_data |
| 284 | { |
| 285 | /* The character position of the first character to be encoded or |
| 286 | decoded. START and END (see below) are relative to this |
| 287 | position. */ |
| 288 | int char_offset; |
| 289 | |
| 290 | /* The composition data. These elements are repeated for each |
| 291 | composition: |
| 292 | LENGTH START END METHOD [ COMPONENT ... ] |
| 293 | where, |
| 294 | LENGTH is the number of elements for this composition. |
| 295 | |
| 296 | START and END are starting and ending character positions of |
| 297 | the composition relative to `char_offset'. |
| 298 | |
| 299 | METHOD is one of `enum cmposing_status' specifying the way of |
| 300 | composition. |
| 301 | |
| 302 | COMPONENT is a character or an encoded composition rule. */ |
| 303 | int data[COMPOSITION_DATA_SIZE]; |
| 304 | |
| 305 | /* The number of elements in `data' currently used. */ |
| 306 | int used; |
| 307 | |
| 308 | /* Pointers to the previous and next structures. When `data' is |
| 309 | filled up, another structure is allocated and linked in `next'. |
| 310 | The new struture has backward link to this struture in `prev'. |
| 311 | The number of chaind structures depends on how many compositions |
| 312 | the text being encoded or decoded contains. */ |
| 313 | struct composition_data *prev, *next; |
| 314 | }; |
| 315 | |
| 316 | /* Macros used for the member `result' of the struct |
| 317 | coding_system. */ |
| 318 | #define CODING_FINISH_NORMAL 0 |
| 319 | #define CODING_FINISH_INSUFFICIENT_SRC 1 |
| 320 | #define CODING_FINISH_INSUFFICIENT_DST 2 |
| 321 | #define CODING_FINISH_INCONSISTENT_EOL 3 |
| 322 | #define CODING_FINISH_INSUFFICIENT_CMP 4 |
| 323 | #define CODING_FINISH_INTERRUPT 5 |
| 324 | |
| 325 | /* Macros used for the member `mode' of the struct coding_system. */ |
| 326 | |
| 327 | /* If set, recover the original CR or LF of the already decoded text |
| 328 | when the decoding routine encounters an inconsistent eol format. */ |
| 329 | #define CODING_MODE_INHIBIT_INCONSISTENT_EOL 0x01 |
| 330 | |
| 331 | /* If set, the decoding/encoding routines treat the current data as |
| 332 | the last block of the whole text to be converted, and do |
| 333 | appropriate fisishing job. */ |
| 334 | #define CODING_MODE_LAST_BLOCK 0x02 |
| 335 | |
| 336 | /* If set, it means that the current source text is in a buffer which |
| 337 | enables selective display. */ |
| 338 | #define CODING_MODE_SELECTIVE_DISPLAY 0x04 |
| 339 | |
| 340 | /* This flag is used by the decoding/encoding routines on the fly. If |
| 341 | set, it means that right-to-left text is being processed. */ |
| 342 | #define CODING_MODE_DIRECTION 0x08 |
| 343 | |
| 344 | struct coding_system |
| 345 | { |
| 346 | /* Type of the coding system. */ |
| 347 | enum coding_type type; |
| 348 | |
| 349 | /* Type of end-of-line format (LF, CRLF, or CR) of the coding system. */ |
| 350 | int eol_type; |
| 351 | |
| 352 | /* Flag bits of the coding system. The meaning of each bit is common |
| 353 | to all types of coding systems. */ |
| 354 | unsigned int common_flags; |
| 355 | |
| 356 | /* Flag bits of the coding system. The meaning of each bit depends |
| 357 | on the type of the coding system. */ |
| 358 | unsigned int flags; |
| 359 | |
| 360 | /* Mode bits of the coding system. See the comments of the macros |
| 361 | CODING_MODE_XXX. */ |
| 362 | unsigned int mode; |
| 363 | |
| 364 | /* The current status of composition handling. */ |
| 365 | int composing; |
| 366 | |
| 367 | /* 1 iff the next character is a composition rule. */ |
| 368 | int composition_rule_follows; |
| 369 | |
| 370 | /* Information of compositions are stored here on decoding and set |
| 371 | in advance on encoding. */ |
| 372 | struct composition_data *cmp_data; |
| 373 | |
| 374 | /* Index to cmp_data->data for the first element for the current |
| 375 | composition. */ |
| 376 | int cmp_data_start; |
| 377 | |
| 378 | /* Index to cmp_data->data for the current element for the current |
| 379 | composition. */ |
| 380 | int cmp_data_index; |
| 381 | |
| 382 | /* Detailed information specific to each type of coding system. */ |
| 383 | union spec |
| 384 | { |
| 385 | struct iso2022_spec iso2022; |
| 386 | struct ccl_spec ccl; /* Defined in ccl.h. */ |
| 387 | } spec; |
| 388 | |
| 389 | /* Index number of coding category of the coding system. */ |
| 390 | int category_idx; |
| 391 | |
| 392 | /* The following two members specify how characters 128..159 are |
| 393 | represented in source and destination text respectively. 1 means |
| 394 | they are represented by 2-byte sequence, 0 means they are |
| 395 | represented by 1-byte as is (see the comment in charset.h). */ |
| 396 | unsigned src_multibyte : 1; |
| 397 | unsigned dst_multibyte : 1; |
| 398 | |
| 399 | /* How may heading bytes we can skip for decoding. This is set to |
| 400 | -1 in setup_coding_system, and updated by detect_coding. So, |
| 401 | when this is equal to the byte length of the text being |
| 402 | converted, we can skip the actual conversion process. */ |
| 403 | int heading_ascii; |
| 404 | |
| 405 | /* The following members are set by encoding/decoding routine. */ |
| 406 | int produced, produced_char, consumed, consumed_char; |
| 407 | |
| 408 | /* Number of error source data found in a decoding routine. */ |
| 409 | int errors; |
| 410 | |
| 411 | /* Finish status of code conversion. It should be one of macros |
| 412 | CODING_FINISH_XXXX. */ |
| 413 | int result; |
| 414 | |
| 415 | /* The following members are all Lisp symbols. We don't have to |
| 416 | protect them from GC because the current garbage collection |
| 417 | doesn't relocate Lisp symbols. But, when it is changed, we must |
| 418 | find a way to protect them. */ |
| 419 | |
| 420 | /* Backward pointer to the Lisp symbol of the coding system. */ |
| 421 | Lisp_Object symbol; |
| 422 | |
| 423 | /* Lisp function (symbol) to be called after decoding to do |
| 424 | additional conversion, or nil. */ |
| 425 | Lisp_Object post_read_conversion; |
| 426 | |
| 427 | /* Lisp function (symbol) to be called before encoding to do |
| 428 | additional conversion, or nil. */ |
| 429 | Lisp_Object pre_write_conversion; |
| 430 | |
| 431 | /* Character translation tables to look up, or nil. */ |
| 432 | Lisp_Object translation_table_for_decode; |
| 433 | Lisp_Object translation_table_for_encode; |
| 434 | }; |
| 435 | |
| 436 | #define CODING_REQUIRE_FLUSHING_MASK 1 |
| 437 | #define CODING_REQUIRE_DECODING_MASK 2 |
| 438 | #define CODING_REQUIRE_ENCODING_MASK 4 |
| 439 | #define CODING_REQUIRE_DETECTION_MASK 8 |
| 440 | |
| 441 | /* Return 1 if the coding system CODING requires specific code to be |
| 442 | attached at the tail of converted text. */ |
| 443 | #define CODING_REQUIRE_FLUSHING(coding) \ |
| 444 | ((coding)->common_flags & CODING_REQUIRE_FLUSHING_MASK) |
| 445 | |
| 446 | /* Return 1 if the coding system CODING requires code conversion on |
| 447 | decoding. */ |
| 448 | #define CODING_REQUIRE_DECODING(coding) \ |
| 449 | ((coding)->dst_multibyte \ |
| 450 | || (coding)->common_flags & CODING_REQUIRE_DECODING_MASK) |
| 451 | |
| 452 | /* Return 1 if the coding system CODING requires code conversion on |
| 453 | encoding. */ |
| 454 | #define CODING_REQUIRE_ENCODING(coding) \ |
| 455 | ((coding)->src_multibyte \ |
| 456 | || (coding)->common_flags & CODING_REQUIRE_ENCODING_MASK) |
| 457 | |
| 458 | /* Return 1 if the coding system CODING requires some kind of code |
| 459 | detection. */ |
| 460 | #define CODING_REQUIRE_DETECTION(coding) \ |
| 461 | ((coding)->common_flags & CODING_REQUIRE_DETECTION_MASK) |
| 462 | |
| 463 | /* Return 1 if the coding system CODING requires code conversion on |
| 464 | decoding or some kind of code detection. */ |
| 465 | #define CODING_MAY_REQUIRE_DECODING(coding) \ |
| 466 | (CODING_REQUIRE_DECODING (coding) \ |
| 467 | || CODING_REQUIRE_DETECTION (coding)) |
| 468 | |
| 469 | /* Index for each coding category in `coding_category_table' */ |
| 470 | #define CODING_CATEGORY_IDX_EMACS_MULE 0 |
| 471 | #define CODING_CATEGORY_IDX_SJIS 1 |
| 472 | #define CODING_CATEGORY_IDX_ISO_7 2 |
| 473 | #define CODING_CATEGORY_IDX_ISO_7_TIGHT 3 |
| 474 | #define CODING_CATEGORY_IDX_ISO_8_1 4 |
| 475 | #define CODING_CATEGORY_IDX_ISO_8_2 5 |
| 476 | #define CODING_CATEGORY_IDX_ISO_7_ELSE 6 |
| 477 | #define CODING_CATEGORY_IDX_ISO_8_ELSE 7 |
| 478 | #define CODING_CATEGORY_IDX_CCL 8 |
| 479 | #define CODING_CATEGORY_IDX_BIG5 9 |
| 480 | #define CODING_CATEGORY_IDX_UTF_8 10 |
| 481 | #define CODING_CATEGORY_IDX_UTF_16_BE 11 |
| 482 | #define CODING_CATEGORY_IDX_UTF_16_LE 12 |
| 483 | #define CODING_CATEGORY_IDX_RAW_TEXT 13 |
| 484 | #define CODING_CATEGORY_IDX_BINARY 14 |
| 485 | #define CODING_CATEGORY_IDX_MAX 15 |
| 486 | |
| 487 | /* Definitions of flag bits returned by the function |
| 488 | detect_coding_mask (). */ |
| 489 | #define CODING_CATEGORY_MASK_EMACS_MULE (1 << CODING_CATEGORY_IDX_EMACS_MULE) |
| 490 | #define CODING_CATEGORY_MASK_SJIS (1 << CODING_CATEGORY_IDX_SJIS) |
| 491 | #define CODING_CATEGORY_MASK_ISO_7 (1 << CODING_CATEGORY_IDX_ISO_7) |
| 492 | #define CODING_CATEGORY_MASK_ISO_7_TIGHT (1 << CODING_CATEGORY_IDX_ISO_7_TIGHT) |
| 493 | #define CODING_CATEGORY_MASK_ISO_8_1 (1 << CODING_CATEGORY_IDX_ISO_8_1) |
| 494 | #define CODING_CATEGORY_MASK_ISO_8_2 (1 << CODING_CATEGORY_IDX_ISO_8_2) |
| 495 | #define CODING_CATEGORY_MASK_ISO_7_ELSE (1 << CODING_CATEGORY_IDX_ISO_7_ELSE) |
| 496 | #define CODING_CATEGORY_MASK_ISO_8_ELSE (1 << CODING_CATEGORY_IDX_ISO_8_ELSE) |
| 497 | #define CODING_CATEGORY_MASK_CCL (1 << CODING_CATEGORY_IDX_CCL) |
| 498 | #define CODING_CATEGORY_MASK_BIG5 (1 << CODING_CATEGORY_IDX_BIG5) |
| 499 | #define CODING_CATEGORY_MASK_UTF_8 (1 << CODING_CATEGORY_IDX_UTF_8) |
| 500 | #define CODING_CATEGORY_MASK_UTF_16_BE (1 << CODING_CATEGORY_IDX_UTF_16_BE) |
| 501 | #define CODING_CATEGORY_MASK_UTF_16_LE (1 << CODING_CATEGORY_IDX_UTF_16_LE) |
| 502 | #define CODING_CATEGORY_MASK_RAW_TEXT (1 << CODING_CATEGORY_IDX_RAW_TEXT) |
| 503 | #define CODING_CATEGORY_MASK_BINARY (1 << CODING_CATEGORY_IDX_BINARY) |
| 504 | |
| 505 | /* This value is returned if detect_coding_mask () find nothing other |
| 506 | than ASCII characters. */ |
| 507 | #define CODING_CATEGORY_MASK_ANY \ |
| 508 | ( CODING_CATEGORY_MASK_EMACS_MULE \ |
| 509 | | CODING_CATEGORY_MASK_SJIS \ |
| 510 | | CODING_CATEGORY_MASK_ISO_7 \ |
| 511 | | CODING_CATEGORY_MASK_ISO_7_TIGHT \ |
| 512 | | CODING_CATEGORY_MASK_ISO_8_1 \ |
| 513 | | CODING_CATEGORY_MASK_ISO_8_2 \ |
| 514 | | CODING_CATEGORY_MASK_ISO_7_ELSE \ |
| 515 | | CODING_CATEGORY_MASK_ISO_8_ELSE \ |
| 516 | | CODING_CATEGORY_MASK_CCL \ |
| 517 | | CODING_CATEGORY_MASK_BIG5 \ |
| 518 | | CODING_CATEGORY_MASK_UTF_8 \ |
| 519 | | CODING_CATEGORY_MASK_UTF_16_BE \ |
| 520 | | CODING_CATEGORY_MASK_UTF_16_LE) |
| 521 | |
| 522 | #define CODING_CATEGORY_MASK_ISO_7BIT \ |
| 523 | (CODING_CATEGORY_MASK_ISO_7 | CODING_CATEGORY_MASK_ISO_7_TIGHT) |
| 524 | |
| 525 | #define CODING_CATEGORY_MASK_ISO_8BIT \ |
| 526 | (CODING_CATEGORY_MASK_ISO_8_1 | CODING_CATEGORY_MASK_ISO_8_2) |
| 527 | |
| 528 | #define CODING_CATEGORY_MASK_ISO_SHIFT \ |
| 529 | (CODING_CATEGORY_MASK_ISO_7_ELSE | CODING_CATEGORY_MASK_ISO_8_ELSE) |
| 530 | |
| 531 | #define CODING_CATEGORY_MASK_ISO \ |
| 532 | ( CODING_CATEGORY_MASK_ISO_7BIT \ |
| 533 | | CODING_CATEGORY_MASK_ISO_SHIFT \ |
| 534 | | CODING_CATEGORY_MASK_ISO_8BIT) |
| 535 | |
| 536 | #define CODING_CATEGORY_MASK_UTF_16_BE_LE \ |
| 537 | (CODING_CATEGORY_MASK_UTF_16_BE | CODING_CATEGORY_MASK_UTF_16_LE) |
| 538 | |
| 539 | /* Macros to decode or encode a character of JISX0208 in SJIS. S1 and |
| 540 | S2 are the 1st and 2nd position-codes of JISX0208 in SJIS coding |
| 541 | system. C1 and C2 are the 1st and 2nd position codes of Emacs' |
| 542 | internal format. */ |
| 543 | |
| 544 | #define DECODE_SJIS(s1, s2, c1, c2) \ |
| 545 | do { \ |
| 546 | if (s2 >= 0x9F) \ |
| 547 | c1 = s1 * 2 - (s1 >= 0xE0 ? 0x160 : 0xE0), \ |
| 548 | c2 = s2 - 0x7E; \ |
| 549 | else \ |
| 550 | c1 = s1 * 2 - ((s1 >= 0xE0) ? 0x161 : 0xE1), \ |
| 551 | c2 = s2 - ((s2 >= 0x7F) ? 0x20 : 0x1F); \ |
| 552 | } while (0) |
| 553 | |
| 554 | #define ENCODE_SJIS(c1, c2, s1, s2) \ |
| 555 | do { \ |
| 556 | if (c1 & 1) \ |
| 557 | s1 = c1 / 2 + ((c1 < 0x5F) ? 0x71 : 0xB1), \ |
| 558 | s2 = c2 + ((c2 >= 0x60) ? 0x20 : 0x1F); \ |
| 559 | else \ |
| 560 | s1 = c1 / 2 + ((c1 < 0x5F) ? 0x70 : 0xB0), \ |
| 561 | s2 = c2 + 0x7E; \ |
| 562 | } while (0) |
| 563 | |
| 564 | /* Encode the file name NAME using the specified coding system |
| 565 | for file names, if any. */ |
| 566 | #define ENCODE_FILE(name) \ |
| 567 | (! NILP (Vfile_name_coding_system) \ |
| 568 | && XFASTINT (Vfile_name_coding_system) != 0 \ |
| 569 | ? code_convert_string_norecord (name, Vfile_name_coding_system, 1) \ |
| 570 | : (! NILP (Vdefault_file_name_coding_system) \ |
| 571 | && XFASTINT (Vdefault_file_name_coding_system) != 0 \ |
| 572 | ? code_convert_string_norecord (name, Vdefault_file_name_coding_system, 1) \ |
| 573 | : name)) |
| 574 | |
| 575 | /* Decode the file name NAME using the specified coding system |
| 576 | for file names, if any. */ |
| 577 | #define DECODE_FILE(name) \ |
| 578 | (! NILP (Vfile_name_coding_system) \ |
| 579 | && XFASTINT (Vfile_name_coding_system) != 0 \ |
| 580 | ? code_convert_string_norecord (name, Vfile_name_coding_system, 0) \ |
| 581 | : (! NILP (Vdefault_file_name_coding_system) \ |
| 582 | && XFASTINT (Vdefault_file_name_coding_system) != 0 \ |
| 583 | ? code_convert_string_norecord (name, Vdefault_file_name_coding_system, 0) \ |
| 584 | : name)) |
| 585 | |
| 586 | #ifdef WINDOWSNT |
| 587 | /* Encode the string STR using the specified coding system |
| 588 | for w32 system functions, if any. */ |
| 589 | #define ENCODE_SYSTEM(str) \ |
| 590 | (! NILP (Vw32_system_coding_system) \ |
| 591 | && XFASTINT (Vw32_system_coding_system) != 0 \ |
| 592 | ? code_convert_string_norecord (str, Vw32_system_coding_system, 1) \ |
| 593 | : str) |
| 594 | |
| 595 | /* Decode the string STR using the specified coding system |
| 596 | for w32 system functions, if any. */ |
| 597 | #define DECODE_SYSTEM(name) \ |
| 598 | (! NILP (Vw32_system_coding_system) \ |
| 599 | && XFASTINT (Vw32_system_coding_system) != 0 \ |
| 600 | ? code_convert_string_norecord (str, Vw32_system_coding_system, 0) \ |
| 601 | : str) |
| 602 | #endif |
| 603 | |
| 604 | /* Extern declarations. */ |
| 605 | extern int decode_coding P_ ((struct coding_system *, unsigned char *, |
| 606 | unsigned char *, int, int)); |
| 607 | extern int encode_coding P_ ((struct coding_system *, unsigned char *, |
| 608 | unsigned char *, int, int)); |
| 609 | extern void coding_save_composition P_ ((struct coding_system *, int, int, |
| 610 | Lisp_Object)); |
| 611 | extern void coding_free_composition_data P_ ((struct coding_system *)); |
| 612 | extern void coding_adjust_composition_offset P_ ((struct coding_system *, |
| 613 | int)); |
| 614 | extern void coding_allocate_composition_data P_ ((struct coding_system *, |
| 615 | int)); |
| 616 | extern void coding_restore_composition P_ ((struct coding_system *, |
| 617 | Lisp_Object)); |
| 618 | extern int code_convert_region P_ ((int, int, int, int, struct coding_system *, |
| 619 | int, int)); |
| 620 | extern int decoding_buffer_size P_ ((struct coding_system *, int)); |
| 621 | extern int encoding_buffer_size P_ ((struct coding_system *, int)); |
| 622 | extern void detect_coding P_ ((struct coding_system *, unsigned char *, int)); |
| 623 | extern void detect_eol P_ ((struct coding_system *, unsigned char *, int)); |
| 624 | extern int setup_coding_system P_ ((Lisp_Object, struct coding_system *)); |
| 625 | extern Lisp_Object code_convert_string P_ ((Lisp_Object, |
| 626 | struct coding_system *, int, int)); |
| 627 | extern Lisp_Object code_convert_string_norecord P_ ((Lisp_Object, Lisp_Object, |
| 628 | int)); |
| 629 | extern void setup_raw_text_coding_system P_ ((struct coding_system *)); |
| 630 | extern Lisp_Object encode_coding_string P_ ((Lisp_Object, |
| 631 | struct coding_system *, int)); |
| 632 | extern Lisp_Object decode_coding_string P_ ((Lisp_Object, |
| 633 | struct coding_system *, int)); |
| 634 | extern Lisp_Object Qcoding_system, Qeol_type, Qcoding_category_index; |
| 635 | extern Lisp_Object Qraw_text, Qemacs_mule; |
| 636 | extern Lisp_Object Qbuffer_file_coding_system; |
| 637 | extern Lisp_Object Vcoding_category_list; |
| 638 | |
| 639 | extern Lisp_Object Qtranslation_table; |
| 640 | extern Lisp_Object Qtranslation_table_id; |
| 641 | |
| 642 | /* Mnemonic strings to indicate each type of end-of-line. */ |
| 643 | extern Lisp_Object eol_mnemonic_unix, eol_mnemonic_dos, eol_mnemonic_mac; |
| 644 | /* Mnemonic string to indicate type of end-of-line is not yet decided. */ |
| 645 | extern Lisp_Object eol_mnemonic_undecided; |
| 646 | |
| 647 | #ifdef emacs |
| 648 | extern Lisp_Object Qfile_coding_system; |
| 649 | extern Lisp_Object Qcall_process, Qcall_process_region, Qprocess_argument; |
| 650 | extern Lisp_Object Qstart_process, Qopen_network_stream; |
| 651 | |
| 652 | extern char *emacs_strerror P_ ((int)); |
| 653 | |
| 654 | /* Coding-system for reading files and receiving data from process. */ |
| 655 | extern Lisp_Object Vcoding_system_for_read; |
| 656 | /* Coding-system for writing files and sending data to process. */ |
| 657 | extern Lisp_Object Vcoding_system_for_write; |
| 658 | /* Coding-system actually used in the latest I/O. */ |
| 659 | extern Lisp_Object Vlast_coding_system_used; |
| 660 | /* Coding-system to use with system messages (e.g. strerror). */ |
| 661 | extern Lisp_Object Vlocale_coding_system; |
| 662 | |
| 663 | /* If non-zero, process buffer inherits the coding system used to decode |
| 664 | the subprocess output. */ |
| 665 | extern int inherit_process_coding_system; |
| 666 | |
| 667 | /* Coding-system to be used for encoding terminal output. This |
| 668 | structure contains information of a coding-system specified by the |
| 669 | function `set-terminal-coding-system'. */ |
| 670 | extern struct coding_system terminal_coding; |
| 671 | |
| 672 | /* Coding system to be used to encode text for terminal display when |
| 673 | terminal coding system is nil. */ |
| 674 | extern struct coding_system safe_terminal_coding; |
| 675 | |
| 676 | /* Coding-system of what is sent from terminal keyboard. This |
| 677 | structure contains information of a coding-system specified by the |
| 678 | function `set-keyboard-coding-system'. */ |
| 679 | extern struct coding_system keyboard_coding; |
| 680 | |
| 681 | /* Default coding system to be used to write a file. */ |
| 682 | extern struct coding_system default_buffer_file_coding; |
| 683 | |
| 684 | /* Default coding systems used for process I/O. */ |
| 685 | extern Lisp_Object Vdefault_process_coding_system; |
| 686 | |
| 687 | /* Function to call to force a user to force select a propert coding |
| 688 | system. */ |
| 689 | extern Lisp_Object Vselect_safe_coding_system_function; |
| 690 | |
| 691 | /* Coding system for file names, or nil if none. */ |
| 692 | extern Lisp_Object Vfile_name_coding_system; |
| 693 | |
| 694 | /* Coding system for file names used only when |
| 695 | Vfile_name_coding_system is nil. */ |
| 696 | extern Lisp_Object Vdefault_file_name_coding_system; |
| 697 | |
| 698 | #ifdef WINDOWSNT |
| 699 | /* Coding system for w32 system strings, or nil if none. */ |
| 700 | extern Lisp_Object Vw32_system_coding_system; |
| 701 | #endif |
| 702 | #endif |
| 703 | |
| 704 | #endif /* EMACS_CODING_H */ |