| 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 _CODING_H |
| 23 | #define _CODING_H |
| 24 | |
| 25 | #ifndef _CCL_H |
| 26 | #include "../src/ccl.h" |
| 27 | #endif |
| 28 | |
| 29 | /*** EMACS' INTERNAL FORMAT (emacs-mule) section ***/ |
| 30 | |
| 31 | /* All code (1-byte) of Emacs' internal format is classified into one |
| 32 | of the followings. See also `charset.h'. */ |
| 33 | enum emacs_code_class_type |
| 34 | { |
| 35 | EMACS_control_code, /* Control codes in the range |
| 36 | 0x00..0x1F and 0x7F except for the |
| 37 | following two codes. */ |
| 38 | EMACS_linefeed_code, /* 0x0A (linefeed) to denote |
| 39 | end-of-line. */ |
| 40 | EMACS_carriage_return_code, /* 0x0D (carriage-return) to be used |
| 41 | in selective display mode. */ |
| 42 | EMACS_ascii_code, /* ASCII characters. */ |
| 43 | EMACS_leading_code_composition, /* Leading code of a composite |
| 44 | character. */ |
| 45 | EMACS_leading_code_2, /* Base leading code of official |
| 46 | TYPE9N character. */ |
| 47 | EMACS_leading_code_3, /* Base leading code of private TYPE9N |
| 48 | or official TYPE9Nx9N character. */ |
| 49 | EMACS_leading_code_4, /* Base leading code of private |
| 50 | TYPE9Nx9N character. */ |
| 51 | EMACS_invalid_code /* Invalid code, i.e. a base leading |
| 52 | code not yet assigned to any |
| 53 | charset, or a code of the range |
| 54 | 0xA0..0xFF. */ |
| 55 | }; |
| 56 | |
| 57 | extern enum emacs_code_class_type emacs_code_class[256]; |
| 58 | |
| 59 | /*** ISO2022 section ***/ |
| 60 | |
| 61 | /* Macros to define code of control characters for ISO2022's functions. */ |
| 62 | /* code */ /* function */ |
| 63 | #define ISO_CODE_LF 0x0A /* line-feed */ |
| 64 | #define ISO_CODE_CR 0x0D /* carriage-return */ |
| 65 | #define ISO_CODE_SO 0x0E /* shift-out */ |
| 66 | #define ISO_CODE_SI 0x0F /* shift-in */ |
| 67 | #define ISO_CODE_SS2_7 0x19 /* single-shift-2 for 7-bit code */ |
| 68 | #define ISO_CODE_ESC 0x1B /* escape */ |
| 69 | #define ISO_CODE_SS2 0x8E /* single-shift-2 */ |
| 70 | #define ISO_CODE_SS3 0x8F /* single-shift-3 */ |
| 71 | #define ISO_CODE_CSI 0x9B /* control-sequence-introduce */ |
| 72 | |
| 73 | /* All code (1-byte) of ISO2022 is classified into one of the |
| 74 | followings. */ |
| 75 | enum iso_code_class_type |
| 76 | { |
| 77 | ISO_control_code, /* Control codes in the range |
| 78 | 0x00..0x1F, 0x7F, and 0x80..0x9F, |
| 79 | except for the following seven |
| 80 | codes. */ |
| 81 | ISO_carriage_return, /* ISO_CODE_CR (0x0D) */ |
| 82 | ISO_shift_out, /* ISO_CODE_SO (0x0E) */ |
| 83 | ISO_shift_in, /* ISO_CODE_SI (0x0F) */ |
| 84 | ISO_single_shift_2_7, /* ISO_CODE_SS2_7 (0x19) */ |
| 85 | ISO_escape, /* ISO_CODE_SO (0x1B) */ |
| 86 | ISO_single_shift_2, /* ISO_CODE_SS2 (0x8E) */ |
| 87 | ISO_single_shift_3, /* ISO_CODE_SS3 (0x8F) */ |
| 88 | ISO_control_sequence_introducer, /* ISO_CODE_CSI (0x9B) */ |
| 89 | ISO_0x20_or_0x7F, /* Codes of the values 0x20 or 0x7F. */ |
| 90 | ISO_graphic_plane_0, /* Graphic codes in the range 0x21..0x7E. */ |
| 91 | ISO_0xA0_or_0xFF, /* Codes of the values 0xA0 or 0xFF. */ |
| 92 | ISO_graphic_plane_1 /* Graphic codes in the range 0xA1..0xFE. */ |
| 93 | }; |
| 94 | |
| 95 | /** The macros CODING_FLAG_ISO_XXX defines a flag bit of the `flags' |
| 96 | element in the structure `coding_system'. This information is used |
| 97 | while encoding a text to ISO2022. **/ |
| 98 | |
| 99 | /* If set, produce short-form designation sequence (e.g. ESC $ A) |
| 100 | instead of long-form sequence (e.g. ESC $ ( A). */ |
| 101 | #define CODING_FLAG_ISO_SHORT_FORM 0x0001 |
| 102 | |
| 103 | /* If set, reset graphic planes and registers at end-of-line to the |
| 104 | initial state. */ |
| 105 | #define CODING_FLAG_ISO_RESET_AT_EOL 0x0002 |
| 106 | |
| 107 | /* If set, reset graphic planes and registers before any control |
| 108 | characters to the initial state. */ |
| 109 | #define CODING_FLAG_ISO_RESET_AT_CNTL 0x0004 |
| 110 | |
| 111 | /* If set, encode by 7-bit environment. */ |
| 112 | #define CODING_FLAG_ISO_SEVEN_BITS 0x0008 |
| 113 | |
| 114 | /* If set, use locking-shift function. */ |
| 115 | #define CODING_FLAG_ISO_LOCKING_SHIFT 0x0010 |
| 116 | |
| 117 | /* If set, use single-shift function. Overwrite |
| 118 | CODING_FLAG_ISO_LOCKING_SHIFT. */ |
| 119 | #define CODING_FLAG_ISO_SINGLE_SHIFT 0x0020 |
| 120 | |
| 121 | /* If set, designate JISX0201-Roman instead of ASCII. */ |
| 122 | #define CODING_FLAG_ISO_USE_ROMAN 0x0040 |
| 123 | |
| 124 | /* If set, designate JISX0208-1978 instead of JISX0208-1983. */ |
| 125 | #define CODING_FLAG_ISO_USE_OLDJIS 0x0080 |
| 126 | |
| 127 | /* If set, do not produce ISO6429's direction specifying sequence. */ |
| 128 | #define CODING_FLAG_ISO_NO_DIRECTION 0x0100 |
| 129 | |
| 130 | /* If set, assume designation states are reset at beginning of line on |
| 131 | output. */ |
| 132 | #define CODING_FLAG_ISO_INIT_AT_BOL 0x0200 |
| 133 | |
| 134 | /* If set, designation sequence should be placed at beginning of line |
| 135 | on output. */ |
| 136 | #define CODING_FLAG_ISO_DESIGNATE_AT_BOL 0x0400 |
| 137 | |
| 138 | /* If set, do not encode unsafe charactes on output. */ |
| 139 | #define CODING_FLAG_ISO_SAFE 0x0800 |
| 140 | |
| 141 | /* If set, extra latin codes (128..159) are accepted as a valid code |
| 142 | on input. */ |
| 143 | #define CODING_FLAG_ISO_LATIN_EXTRA 0x1000 |
| 144 | |
| 145 | /* If set, use designation escape sequence. */ |
| 146 | #define CODING_FLAG_ISO_DESIGNATION 0x10000 |
| 147 | |
| 148 | /* A character to be produced on output if encoding of the original |
| 149 | character is prohibited by CODING_FLAG_ISO_SAFE. */ |
| 150 | #define CODING_INHIBIT_CHARACTER_SUBSTITUTION 077 /* 077 == `?' */ |
| 151 | |
| 152 | /* Structure of the field `spec.iso2022' in the structure `coding_system'. */ |
| 153 | struct iso2022_spec |
| 154 | { |
| 155 | /* The current graphic register invoked to each graphic plane. */ |
| 156 | int current_invocation[2]; |
| 157 | |
| 158 | /* The current charset designated to each graphic register. */ |
| 159 | int current_designation[4]; |
| 160 | |
| 161 | /* A charset initially designated to each graphic register. */ |
| 162 | int initial_designation[4]; |
| 163 | |
| 164 | /* If not -1, it is a graphic register specified in an invalid |
| 165 | designation sequence. */ |
| 166 | int last_invalid_designation_register; |
| 167 | |
| 168 | /* A graphic register to which each charset should be designated. */ |
| 169 | unsigned char requested_designation[MAX_CHARSET + 1]; |
| 170 | |
| 171 | /* A revision number to be specified for each charset on encoding. |
| 172 | The value 255 means no revision number for the corresponding |
| 173 | charset. */ |
| 174 | unsigned char charset_revision_number[MAX_CHARSET + 1]; |
| 175 | |
| 176 | /* Set to 1 temporarily only when graphic register 2 or 3 is invoked |
| 177 | by single-shift while encoding. */ |
| 178 | int single_shifting; |
| 179 | |
| 180 | /* Set to 1 temporarily only when processing at beginning of line. */ |
| 181 | int bol; |
| 182 | }; |
| 183 | |
| 184 | /* Macros to access each field in the structure `spec.iso2022'. */ |
| 185 | #define CODING_SPEC_ISO_INVOCATION(coding, plane) \ |
| 186 | (coding)->spec.iso2022.current_invocation[plane] |
| 187 | #define CODING_SPEC_ISO_DESIGNATION(coding, reg) \ |
| 188 | (coding)->spec.iso2022.current_designation[reg] |
| 189 | #define CODING_SPEC_ISO_INITIAL_DESIGNATION(coding, reg) \ |
| 190 | (coding)->spec.iso2022.initial_designation[reg] |
| 191 | #define CODING_SPEC_ISO_REQUESTED_DESIGNATION(coding, charset) \ |
| 192 | (coding)->spec.iso2022.requested_designation[charset] |
| 193 | #define CODING_SPEC_ISO_REVISION_NUMBER(coding, charset) \ |
| 194 | (coding)->spec.iso2022.charset_revision_number[charset] |
| 195 | #define CODING_SPEC_ISO_SINGLE_SHIFTING(coding) \ |
| 196 | (coding)->spec.iso2022.single_shifting |
| 197 | #define CODING_SPEC_ISO_BOL(coding) \ |
| 198 | (coding)->spec.iso2022.bol |
| 199 | |
| 200 | /* A value which may appear in |
| 201 | coding->spec.iso2022.requested_designation indicating that the |
| 202 | corresponding charset does not request any graphic register to be |
| 203 | designated. */ |
| 204 | #define CODING_SPEC_ISO_NO_REQUESTED_DESIGNATION 4 |
| 205 | |
| 206 | /* Return a charset which is currently designated to the graphic plane |
| 207 | PLANE in the coding-system CODING. */ |
| 208 | #define CODING_SPEC_ISO_PLANE_CHARSET(coding, plane) \ |
| 209 | ((CODING_SPEC_ISO_INVOCATION (coding, plane) < 0) \ |
| 210 | ? -1 \ |
| 211 | : CODING_SPEC_ISO_DESIGNATION (coding, \ |
| 212 | CODING_SPEC_ISO_INVOCATION (coding, plane))) |
| 213 | |
| 214 | /*** BIG5 section ***/ |
| 215 | |
| 216 | /* Macros to denote each type of BIG5 coding system. */ |
| 217 | #define CODING_FLAG_BIG5_HKU 0x00 /* BIG5-HKU is one of variants of |
| 218 | BIG5 developed by Hong Kong |
| 219 | University. */ |
| 220 | #define CODING_FLAG_BIG5_ETEN 0x01 /* BIG5_ETen is one of variants |
| 221 | of BIG5 developed by the |
| 222 | company ETen in Taiwan. */ |
| 223 | |
| 224 | /*** GENERAL section ***/ |
| 225 | |
| 226 | /* Types of coding system. */ |
| 227 | enum coding_type |
| 228 | { |
| 229 | coding_type_no_conversion, /* A coding system which requires no |
| 230 | conversion for reading and writing |
| 231 | including end-of-line format. */ |
| 232 | coding_type_emacs_mule, /* A coding system used in Emacs' |
| 233 | buffer and string. Requires no |
| 234 | conversion for reading and writing |
| 235 | except for end-of-line format. */ |
| 236 | coding_type_undecided, /* A coding system which requires |
| 237 | automatic detection of a real |
| 238 | coding system. */ |
| 239 | coding_type_sjis, /* SJIS coding system for Japanese. */ |
| 240 | coding_type_iso2022, /* Any coding system of ISO2022 |
| 241 | variants. */ |
| 242 | coding_type_big5, /* BIG5 coding system for Chinese. */ |
| 243 | coding_type_ccl, /* The coding system of which decoder |
| 244 | and encoder are written in CCL. */ |
| 245 | coding_type_raw_text /* A coding system for a text |
| 246 | containing ramdom 8-bit code which |
| 247 | does not require code conversion |
| 248 | except for end-of-line format. */ |
| 249 | }; |
| 250 | |
| 251 | /* Formats of end-of-line. */ |
| 252 | #define CODING_EOL_LF 0 /* Line-feed only, same as Emacs' |
| 253 | internal format. */ |
| 254 | #define CODING_EOL_CRLF 1 /* Sequence of carriage-return and |
| 255 | line-feed. */ |
| 256 | #define CODING_EOL_CR 2 /* Carriage-return only. */ |
| 257 | #define CODING_EOL_UNDECIDED 3 /* This value is used to denote the |
| 258 | eol-type is not yet decided. */ |
| 259 | #define CODING_EOL_INCONSISTENT 4 /* This value is used to denote the |
| 260 | eol-type is not consistent |
| 261 | through the file. */ |
| 262 | |
| 263 | /* Character composition status while encoding/decoding. */ |
| 264 | #define COMPOSING_NO 0 /* not composing */ |
| 265 | #define COMPOSING_WITH_RULE_HEAD 1 /* 1st char of with-rule composing follow */ |
| 266 | #define COMPOSING_NO_RULE_HEAD 2 /* 1st char of no-rule composing follow */ |
| 267 | #define COMPOSING_WITH_RULE_TAIL 3 /* Nth char of with-rule composing follow */ |
| 268 | #define COMPOSING_NO_RULE_TAIL 4 /* Nth char of no-rule composing follow */ |
| 269 | #define COMPOSING_WITH_RULE_RULE 5 /* composition rule follow */ |
| 270 | |
| 271 | /* 1 iff composing. */ |
| 272 | #define COMPOSING_P(composing) (composing) |
| 273 | /* 1 iff 1st char of composing element follows. */ |
| 274 | #define COMPOSING_HEAD_P(composing) \ |
| 275 | ((composing) && (composing) <= COMPOSING_NO_RULE_HEAD) |
| 276 | /* 1 iff composing with embeded composition rule. */ |
| 277 | #define COMPOSING_WITH_RULE_P(composing) ((composing) & 1) |
| 278 | |
| 279 | /* Macros used for the member finish_status of the struct |
| 280 | coding_system. */ |
| 281 | #define CODING_FINISH_NORMAL 0 |
| 282 | #define CODING_FINISH_INSUFFICIENT_SRC 1 |
| 283 | #define CODING_FINISH_INSUFFICIENT_DST 2 |
| 284 | #define CODING_FINISH_INCONSISTENT_EOL 3 |
| 285 | |
| 286 | /* Macros used for the member `mode' of the struct coding_system. */ |
| 287 | |
| 288 | /* If set, recover the original CR or LF of the already decoded text |
| 289 | when the decoding routine encounters an inconsistent eol format. */ |
| 290 | #define CODING_MODE_INHIBIT_INCONSISTENT_EOL 0x01 |
| 291 | |
| 292 | /* If set, the decoding/encoding routines treat the current data as |
| 293 | the last block of the whole text to be converted, and do |
| 294 | appropriate fisishing job. */ |
| 295 | #define CODING_MODE_LAST_BLOCK 0x02 |
| 296 | |
| 297 | /* If set, it means that the current source text is in a buffer which |
| 298 | enables selective display. */ |
| 299 | #define CODING_MODE_SELECTIVE_DISPLAY 0x04 |
| 300 | |
| 301 | /* This flag is used by the decoding/encoding routines on the fly. If |
| 302 | set, it means that right-to-left text is being processed. */ |
| 303 | #define CODING_MODE_DIRECTION 0x08 |
| 304 | |
| 305 | struct coding_system |
| 306 | { |
| 307 | /* Type of the coding system. */ |
| 308 | enum coding_type type; |
| 309 | |
| 310 | /* Type of end-of-line format (LF, CRLF, or CR) of the coding system. */ |
| 311 | int eol_type; |
| 312 | |
| 313 | /* Flag bits of the coding system. The meaning of each bit is common |
| 314 | to all types of coding systems. */ |
| 315 | unsigned int common_flags; |
| 316 | |
| 317 | /* Flag bits of the coding system. The meaning of each bit depends |
| 318 | on the type of the coding system. */ |
| 319 | unsigned int flags; |
| 320 | |
| 321 | /* Mode bits of the coding system. See the comments of the macros |
| 322 | CODING_MODE_XXX. */ |
| 323 | unsigned int mode; |
| 324 | |
| 325 | /* Table of safe character sets for this coding system. If the Nth |
| 326 | element is 0, the charset of ID N is not a safe character set. |
| 327 | Such a character set is not encoded when CODING_ISO_FLAG_SAFE is |
| 328 | set. */ |
| 329 | unsigned char safe_charsets[MAX_CHARSET + 1]; |
| 330 | |
| 331 | /* Non-zero means that characters are being composed currently while |
| 332 | decoding or encoding. See macros COMPOSING_XXXX above for the |
| 333 | meaing of each non-zero value. */ |
| 334 | int composing; |
| 335 | |
| 336 | /* Detailed information specific to each type of coding system. */ |
| 337 | union spec |
| 338 | { |
| 339 | struct iso2022_spec iso2022; |
| 340 | struct ccl_spec ccl; /* Defined in ccl.h. */ |
| 341 | } spec; |
| 342 | |
| 343 | /* Index number of coding category of the coding system. */ |
| 344 | int category_idx; |
| 345 | |
| 346 | /* How may heading bytes we can skip for decoding. This member is |
| 347 | set by the function detect_coding. The initial value is -1 which |
| 348 | means detect_coding has not yet been called. */ |
| 349 | int heading_ascii; |
| 350 | |
| 351 | /* The following members are set by encoding/decoding routine. */ |
| 352 | int produced, produced_char, consumed, consumed_char; |
| 353 | |
| 354 | /* Encoding routines set this to 1 when they produce a byte sequence |
| 355 | which can be parsed as a multibyte character. Decoding routines |
| 356 | set this to 1 when they encounter an invalid code and, as the |
| 357 | result, produce an unexpected multibyte character. */ |
| 358 | int fake_multibyte; |
| 359 | |
| 360 | /* The following members are all Lisp symbols. We don't have to |
| 361 | protect them from GC because the current garbage collection |
| 362 | doesn't relocate Lisp symbols. But, when it is changed, we must |
| 363 | find a way to protect them. */ |
| 364 | |
| 365 | /* Backward pointer to the Lisp symbol of the coding system. */ |
| 366 | Lisp_Object symbol; |
| 367 | |
| 368 | /* Lisp function (symbol) to be called after decoding to do |
| 369 | additional conversion, or nil. */ |
| 370 | Lisp_Object post_read_conversion; |
| 371 | |
| 372 | /* Lisp function (symbol) to be called before encoding to do |
| 373 | additional conversion, or nil. */ |
| 374 | Lisp_Object pre_write_conversion; |
| 375 | |
| 376 | /* Character unification tables to look up, or nil. */ |
| 377 | Lisp_Object character_unification_table_for_decode; |
| 378 | Lisp_Object character_unification_table_for_encode; |
| 379 | }; |
| 380 | |
| 381 | #define CODING_REQUIRE_FLUSHING_MASK 1 |
| 382 | #define CODING_REQUIRE_DECODING_MASK 2 |
| 383 | #define CODING_REQUIRE_ENCODING_MASK 4 |
| 384 | #define CODING_REQUIRE_DETECTION_MASK 8 |
| 385 | |
| 386 | /* Return 1 if the coding system CODING requires specific code to be |
| 387 | attached at the tail of converted text. */ |
| 388 | #define CODING_REQUIRE_FLUSHING(coding) \ |
| 389 | ((coding)->common_flags & CODING_REQUIRE_FLUSHING_MASK) |
| 390 | |
| 391 | /* Return 1 if the coding system CODING requires code conversion on |
| 392 | decoding. */ |
| 393 | #define CODING_REQUIRE_DECODING(coding) \ |
| 394 | ((coding)->common_flags & CODING_REQUIRE_DECODING_MASK) |
| 395 | |
| 396 | /* Return 1 if the coding system CODING requires code conversion on |
| 397 | encoding. */ |
| 398 | #define CODING_REQUIRE_ENCODING(coding) \ |
| 399 | ((coding)->common_flags & CODING_REQUIRE_ENCODING_MASK) |
| 400 | |
| 401 | /* Return 1 if the coding system CODING requires some kind of code |
| 402 | detection. */ |
| 403 | #define CODING_REQUIRE_DETECTION(coding) \ |
| 404 | ((coding)->common_flags & CODING_REQUIRE_DETECTION_MASK) |
| 405 | |
| 406 | #define CODING_MAY_REQUIRE_DECODING(coding) \ |
| 407 | ((coding)->common_flags \ |
| 408 | & (CODING_REQUIRE_DETECTION_MASK | CODING_REQUIRE_DECODING_MASK)) |
| 409 | |
| 410 | /* Index for each coding category in `coding_category_table' */ |
| 411 | #define CODING_CATEGORY_IDX_EMACS_MULE 0 |
| 412 | #define CODING_CATEGORY_IDX_SJIS 1 |
| 413 | #define CODING_CATEGORY_IDX_ISO_7 2 |
| 414 | #define CODING_CATEGORY_IDX_ISO_7_TIGHT 3 |
| 415 | #define CODING_CATEGORY_IDX_ISO_8_1 4 |
| 416 | #define CODING_CATEGORY_IDX_ISO_8_2 5 |
| 417 | #define CODING_CATEGORY_IDX_ISO_7_ELSE 6 |
| 418 | #define CODING_CATEGORY_IDX_ISO_8_ELSE 7 |
| 419 | #define CODING_CATEGORY_IDX_BIG5 8 |
| 420 | #define CODING_CATEGORY_IDX_RAW_TEXT 9 |
| 421 | #define CODING_CATEGORY_IDX_BINARY 10 |
| 422 | #define CODING_CATEGORY_IDX_MAX 11 |
| 423 | |
| 424 | /* Definitions of flag bits returned by the function |
| 425 | detect_coding_mask (). */ |
| 426 | #define CODING_CATEGORY_MASK_EMACS_MULE (1 << CODING_CATEGORY_IDX_EMACS_MULE) |
| 427 | #define CODING_CATEGORY_MASK_SJIS (1 << CODING_CATEGORY_IDX_SJIS) |
| 428 | #define CODING_CATEGORY_MASK_ISO_7 (1 << CODING_CATEGORY_IDX_ISO_7) |
| 429 | #define CODING_CATEGORY_MASK_ISO_7_TIGHT (1 << CODING_CATEGORY_IDX_ISO_7_TIGHT) |
| 430 | #define CODING_CATEGORY_MASK_ISO_8_1 (1 << CODING_CATEGORY_IDX_ISO_8_1) |
| 431 | #define CODING_CATEGORY_MASK_ISO_8_2 (1 << CODING_CATEGORY_IDX_ISO_8_2) |
| 432 | #define CODING_CATEGORY_MASK_ISO_7_ELSE (1 << CODING_CATEGORY_IDX_ISO_7_ELSE) |
| 433 | #define CODING_CATEGORY_MASK_ISO_8_ELSE (1 << CODING_CATEGORY_IDX_ISO_8_ELSE) |
| 434 | #define CODING_CATEGORY_MASK_BIG5 (1 << CODING_CATEGORY_IDX_BIG5) |
| 435 | #define CODING_CATEGORY_MASK_RAW_TEXT (1 << CODING_CATEGORY_IDX_RAW_TEXT) |
| 436 | #define CODING_CATEGORY_MASK_BINARY (1 << CODING_CATEGORY_IDX_BINARY) |
| 437 | |
| 438 | /* This value is returned if detect_coding_mask () find nothing other |
| 439 | than ASCII characters. */ |
| 440 | #define CODING_CATEGORY_MASK_ANY \ |
| 441 | ( CODING_CATEGORY_MASK_EMACS_MULE \ |
| 442 | | CODING_CATEGORY_MASK_SJIS \ |
| 443 | | CODING_CATEGORY_MASK_ISO_7 \ |
| 444 | | CODING_CATEGORY_MASK_ISO_7_TIGHT \ |
| 445 | | CODING_CATEGORY_MASK_ISO_8_1 \ |
| 446 | | CODING_CATEGORY_MASK_ISO_8_2 \ |
| 447 | | CODING_CATEGORY_MASK_ISO_7_ELSE \ |
| 448 | | CODING_CATEGORY_MASK_ISO_8_ELSE \ |
| 449 | | CODING_CATEGORY_MASK_BIG5) |
| 450 | |
| 451 | #define CODING_CATEGORY_MASK_ISO_7BIT \ |
| 452 | (CODING_CATEGORY_MASK_ISO_7 | CODING_CATEGORY_MASK_ISO_7_TIGHT) |
| 453 | |
| 454 | #define CODING_CATEGORY_MASK_ISO_8BIT \ |
| 455 | (CODING_CATEGORY_MASK_ISO_8_1 | CODING_CATEGORY_MASK_ISO_8_2) |
| 456 | |
| 457 | #define CODING_CATEGORY_MASK_ISO_SHIFT \ |
| 458 | (CODING_CATEGORY_MASK_ISO_7_ELSE | CODING_CATEGORY_MASK_ISO_8_ELSE) |
| 459 | |
| 460 | #define CODING_CATEGORY_MASK_ISO \ |
| 461 | ( CODING_CATEGORY_MASK_ISO_7BIT \ |
| 462 | | CODING_CATEGORY_MASK_ISO_SHIFT \ |
| 463 | | CODING_CATEGORY_MASK_ISO_8BIT) |
| 464 | |
| 465 | /* Macros to decode or encode a character of JISX0208 in SJIS. S1 and |
| 466 | S2 are the 1st and 2nd position-codes of JISX0208 in SJIS coding |
| 467 | system. C1 and C2 are the 1st and 2nd position codes of Emacs' |
| 468 | internal format. */ |
| 469 | |
| 470 | #define DECODE_SJIS(s1, s2, c1, c2) \ |
| 471 | do { \ |
| 472 | if (s2 >= 0x9F) \ |
| 473 | c1 = s1 * 2 - (s1 >= 0xE0 ? 0x160 : 0xE0), \ |
| 474 | c2 = s2 - 0x7E; \ |
| 475 | else \ |
| 476 | c1 = s1 * 2 - ((s1 >= 0xE0) ? 0x161 : 0xE1), \ |
| 477 | c2 = s2 - ((s2 >= 0x7F) ? 0x20 : 0x1F); \ |
| 478 | } while (0) |
| 479 | |
| 480 | #define ENCODE_SJIS(c1, c2, s1, s2) \ |
| 481 | do { \ |
| 482 | if (c1 & 1) \ |
| 483 | s1 = c1 / 2 + ((c1 < 0x5F) ? 0x71 : 0xB1), \ |
| 484 | s2 = c2 + ((c2 >= 0x60) ? 0x20 : 0x1F); \ |
| 485 | else \ |
| 486 | s1 = c1 / 2 + ((c1 < 0x5F) ? 0x70 : 0xB0), \ |
| 487 | s2 = c2 + 0x7E; \ |
| 488 | } while (0) |
| 489 | |
| 490 | /* Encode the file name NAME using the specified coding system |
| 491 | for file names, if any. */ |
| 492 | #define ENCODE_FILE(name) \ |
| 493 | (! NILP (Vfile_name_coding_system) \ |
| 494 | && XFASTINT (Vfile_name_coding_system) != 0 \ |
| 495 | ? Fencode_coding_string (name, Vfile_name_coding_system, Qt) \ |
| 496 | : (! NILP (Vdefault_file_name_coding_system) \ |
| 497 | && XFASTINT (Vdefault_file_name_coding_system) \ |
| 498 | ? Fencode_coding_string (name, Vdefault_file_name_coding_system, Qt) \ |
| 499 | : name)) |
| 500 | |
| 501 | /* Decode the file name NAME using the specified coding system |
| 502 | for file names, if any. */ |
| 503 | #define DECODE_FILE(name) \ |
| 504 | (! NILP (Vfile_name_coding_system) \ |
| 505 | && XFASTINT (Vfile_name_coding_system) != 0 \ |
| 506 | ? Fdecode_coding_string (name, Vfile_name_coding_system, Qt) \ |
| 507 | : (! NILP (Vdefault_file_name_coding_system) \ |
| 508 | && XFASTINT (Vdefault_file_name_coding_system) \ |
| 509 | ? Fdecode_coding_string (name, Vdefault_file_name_coding_system, Qt) \ |
| 510 | : name)) |
| 511 | |
| 512 | /* Extern declarations. */ |
| 513 | extern int decode_coding P_ ((struct coding_system *, unsigned char *, |
| 514 | unsigned char *, int, int)); |
| 515 | extern int encode_coding P_ ((struct coding_system *, unsigned char *, |
| 516 | unsigned char *, int, int)); |
| 517 | extern int decoding_buffer_size P_ ((struct coding_system *, int)); |
| 518 | extern int encoding_buffer_size P_ ((struct coding_system *, int)); |
| 519 | extern void detect_coding P_ ((struct coding_system *, unsigned char *, int)); |
| 520 | extern void detect_eol P_ ((struct coding_system *, unsigned char *, int)); |
| 521 | extern int conversion_buffer_size; |
| 522 | extern char *conversion_buffer; |
| 523 | extern char *get_conversion_buffer P_ ((int)); |
| 524 | extern int setup_coding_system P_ ((Lisp_Object, struct coding_system *)); |
| 525 | extern Lisp_Object Qcoding_system, Qeol_type, Qcoding_category_index; |
| 526 | extern Lisp_Object Qraw_text; |
| 527 | extern Lisp_Object Qbuffer_file_coding_system; |
| 528 | extern Lisp_Object Vcoding_category_list; |
| 529 | |
| 530 | /* Mnemonic character to indicate each type of end-of-line. */ |
| 531 | extern int eol_mnemonic_unix, eol_mnemonic_dos, eol_mnemonic_mac; |
| 532 | /* Mnemonic character to indicate type of end-of-line is not yet decided. */ |
| 533 | extern int eol_mnemonic_undecided; |
| 534 | |
| 535 | #ifdef emacs |
| 536 | extern Lisp_Object Qfile_coding_system; |
| 537 | extern Lisp_Object Qcall_process, Qcall_process_region, Qprocess_argument; |
| 538 | extern Lisp_Object Qstart_process, Qopen_network_stream; |
| 539 | |
| 540 | /* Coding-system for reading files and receiving data from process. */ |
| 541 | extern Lisp_Object Vcoding_system_for_read; |
| 542 | /* Coding-system for writing files and sending data to process. */ |
| 543 | extern Lisp_Object Vcoding_system_for_write; |
| 544 | /* Coding-system actually used in the latest I/O. */ |
| 545 | extern Lisp_Object Vlast_coding_system_used; |
| 546 | |
| 547 | /* Coding-system to be used for encoding terminal output. This |
| 548 | structure contains information of a coding-system specified by the |
| 549 | function `set-terminal-coding-system'. */ |
| 550 | extern struct coding_system terminal_coding; |
| 551 | |
| 552 | /* Coding system to be used to encode text for terminal display when |
| 553 | terminal coding system is nil. */ |
| 554 | extern struct coding_system safe_terminal_coding; |
| 555 | |
| 556 | /* Coding-system of what is sent from terminal keyboard. This |
| 557 | structure contains information of a coding-system specified by the |
| 558 | function `set-keyboard-coding-system'. */ |
| 559 | extern struct coding_system keyboard_coding; |
| 560 | |
| 561 | /* Default coding systems used for process I/O. */ |
| 562 | extern Lisp_Object Vdefault_process_coding_system; |
| 563 | |
| 564 | /* Function to call to force a user to force select a propert coding |
| 565 | system. */ |
| 566 | extern Lisp_Object Vselect_safe_coding_system_function; |
| 567 | |
| 568 | #endif |
| 569 | |
| 570 | #endif /* _CODING_H */ |