| 1 | /* Coding system handler (conversion, detection, and etc). |
| 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 | /*** TABLE OF CONTENTS *** |
| 23 | |
| 24 | 1. Preamble |
| 25 | 2. Emacs' internal format (emacs-mule) handlers |
| 26 | 3. ISO2022 handlers |
| 27 | 4. Shift-JIS and BIG5 handlers |
| 28 | 5. End-of-line handlers |
| 29 | 6. C library functions |
| 30 | 7. Emacs Lisp library functions |
| 31 | 8. Post-amble |
| 32 | |
| 33 | */ |
| 34 | |
| 35 | /*** GENERAL NOTE on CODING SYSTEM *** |
| 36 | |
| 37 | Coding system is an encoding mechanism of one or more character |
| 38 | sets. Here's a list of coding systems which Emacs can handle. When |
| 39 | we say "decode", it means converting some other coding system to |
| 40 | Emacs' internal format (emacs-internal), and when we say "encode", |
| 41 | it means converting the coding system emacs-mule to some other |
| 42 | coding system. |
| 43 | |
| 44 | 0. Emacs' internal format (emacs-mule) |
| 45 | |
| 46 | Emacs itself holds a multi-lingual character in a buffer and a string |
| 47 | in a special format. Details are described in section 2. |
| 48 | |
| 49 | 1. ISO2022 |
| 50 | |
| 51 | The most famous coding system for multiple character sets. X's |
| 52 | Compound Text, various EUCs (Extended Unix Code), and coding |
| 53 | systems used in Internet communication such as ISO-2022-JP are |
| 54 | all variants of ISO2022. Details are described in section 3. |
| 55 | |
| 56 | 2. SJIS (or Shift-JIS or MS-Kanji-Code) |
| 57 | |
| 58 | A coding system to encode character sets: ASCII, JISX0201, and |
| 59 | JISX0208. Widely used for PC's in Japan. Details are described in |
| 60 | section 4. |
| 61 | |
| 62 | 3. BIG5 |
| 63 | |
| 64 | A coding system to encode character sets: ASCII and Big5. Widely |
| 65 | used by Chinese (mainly in Taiwan and Hong Kong). Details are |
| 66 | described in section 4. In this file, when we write "BIG5" |
| 67 | (all uppercase), we mean the coding system, and when we write |
| 68 | "Big5" (capitalized), we mean the character set. |
| 69 | |
| 70 | 4. Raw text |
| 71 | |
| 72 | A coding system for a text containing random 8-bit code. Emacs does |
| 73 | no code conversion on such a text except for end-of-line format. |
| 74 | |
| 75 | 5. Other |
| 76 | |
| 77 | If a user wants to read/write a text encoded in a coding system not |
| 78 | listed above, he can supply a decoder and an encoder for it in CCL |
| 79 | (Code Conversion Language) programs. Emacs executes the CCL program |
| 80 | while reading/writing. |
| 81 | |
| 82 | Emacs represents a coding-system by a Lisp symbol that has a property |
| 83 | `coding-system'. But, before actually using the coding-system, the |
| 84 | information about it is set in a structure of type `struct |
| 85 | coding_system' for rapid processing. See section 6 for more details. |
| 86 | |
| 87 | */ |
| 88 | |
| 89 | /*** GENERAL NOTES on END-OF-LINE FORMAT *** |
| 90 | |
| 91 | How end-of-line of a text is encoded depends on a system. For |
| 92 | instance, Unix's format is just one byte of `line-feed' code, |
| 93 | whereas DOS's format is two-byte sequence of `carriage-return' and |
| 94 | `line-feed' codes. MacOS's format is one byte of `carriage-return'. |
| 95 | |
| 96 | Since text characters encoding and end-of-line encoding are |
| 97 | independent, any coding system described above can take |
| 98 | any format of end-of-line. So, Emacs has information of format of |
| 99 | end-of-line in each coding-system. See section 6 for more details. |
| 100 | |
| 101 | */ |
| 102 | |
| 103 | /*** GENERAL NOTES on `detect_coding_XXX ()' functions *** |
| 104 | |
| 105 | These functions check if a text between SRC and SRC_END is encoded |
| 106 | in the coding system category XXX. Each returns an integer value in |
| 107 | which appropriate flag bits for the category XXX is set. The flag |
| 108 | bits are defined in macros CODING_CATEGORY_MASK_XXX. Below is the |
| 109 | template of these functions. */ |
| 110 | #if 0 |
| 111 | int |
| 112 | detect_coding_emacs_mule (src, src_end) |
| 113 | unsigned char *src, *src_end; |
| 114 | { |
| 115 | ... |
| 116 | } |
| 117 | #endif |
| 118 | |
| 119 | /*** GENERAL NOTES on `decode_coding_XXX ()' functions *** |
| 120 | |
| 121 | These functions decode SRC_BYTES length text at SOURCE encoded in |
| 122 | CODING to Emacs' internal format (emacs-mule). The resulting text |
| 123 | goes to a place pointed to by DESTINATION, the length of which should |
| 124 | not exceed DST_BYTES. The number of bytes actually processed is |
| 125 | returned as *CONSUMED. The return value is the length of the decoded |
| 126 | text. Below is a template of these functions. */ |
| 127 | #if 0 |
| 128 | decode_coding_XXX (coding, source, destination, src_bytes, dst_bytes, consumed) |
| 129 | struct coding_system *coding; |
| 130 | unsigned char *source, *destination; |
| 131 | int src_bytes, dst_bytes; |
| 132 | int *consumed; |
| 133 | { |
| 134 | ... |
| 135 | } |
| 136 | #endif |
| 137 | |
| 138 | /*** GENERAL NOTES on `encode_coding_XXX ()' functions *** |
| 139 | |
| 140 | These functions encode SRC_BYTES length text at SOURCE of Emacs' |
| 141 | internal format (emacs-mule) to CODING. The resulting text goes to |
| 142 | a place pointed to by DESTINATION, the length of which should not |
| 143 | exceed DST_BYTES. The number of bytes actually processed is |
| 144 | returned as *CONSUMED. The return value is the length of the |
| 145 | encoded text. Below is a template of these functions. */ |
| 146 | #if 0 |
| 147 | encode_coding_XXX (coding, source, destination, src_bytes, dst_bytes, consumed) |
| 148 | struct coding_system *coding; |
| 149 | unsigned char *source, *destination; |
| 150 | int src_bytes, dst_bytes; |
| 151 | int *consumed; |
| 152 | { |
| 153 | ... |
| 154 | } |
| 155 | #endif |
| 156 | |
| 157 | /*** COMMONLY USED MACROS ***/ |
| 158 | |
| 159 | /* The following three macros ONE_MORE_BYTE, TWO_MORE_BYTES, and |
| 160 | THREE_MORE_BYTES safely get one, two, and three bytes from the |
| 161 | source text respectively. If there are not enough bytes in the |
| 162 | source, they jump to `label_end_of_loop'. The caller should set |
| 163 | variables `src' and `src_end' to appropriate areas in advance. */ |
| 164 | |
| 165 | #define ONE_MORE_BYTE(c1) \ |
| 166 | do { \ |
| 167 | if (src < src_end) \ |
| 168 | c1 = *src++; \ |
| 169 | else \ |
| 170 | goto label_end_of_loop; \ |
| 171 | } while (0) |
| 172 | |
| 173 | #define TWO_MORE_BYTES(c1, c2) \ |
| 174 | do { \ |
| 175 | if (src + 1 < src_end) \ |
| 176 | c1 = *src++, c2 = *src++; \ |
| 177 | else \ |
| 178 | goto label_end_of_loop; \ |
| 179 | } while (0) |
| 180 | |
| 181 | #define THREE_MORE_BYTES(c1, c2, c3) \ |
| 182 | do { \ |
| 183 | if (src + 2 < src_end) \ |
| 184 | c1 = *src++, c2 = *src++, c3 = *src++; \ |
| 185 | else \ |
| 186 | goto label_end_of_loop; \ |
| 187 | } while (0) |
| 188 | |
| 189 | /* The following three macros DECODE_CHARACTER_ASCII, |
| 190 | DECODE_CHARACTER_DIMENSION1, and DECODE_CHARACTER_DIMENSION2 put |
| 191 | the multi-byte form of a character of each class at the place |
| 192 | pointed by `dst'. The caller should set the variable `dst' to |
| 193 | point to an appropriate area and the variable `coding' to point to |
| 194 | the coding-system of the currently decoding text in advance. */ |
| 195 | |
| 196 | /* Decode one ASCII character C. */ |
| 197 | |
| 198 | #define DECODE_CHARACTER_ASCII(c) \ |
| 199 | do { \ |
| 200 | if (COMPOSING_P (coding->composing)) \ |
| 201 | *dst++ = 0xA0, *dst++ = (c) | 0x80; \ |
| 202 | else \ |
| 203 | *dst++ = (c); \ |
| 204 | } while (0) |
| 205 | |
| 206 | /* Decode one DIMENSION1 character whose charset is CHARSET and whose |
| 207 | position-code is C. */ |
| 208 | |
| 209 | #define DECODE_CHARACTER_DIMENSION1(charset, c) \ |
| 210 | do { \ |
| 211 | unsigned char leading_code = CHARSET_LEADING_CODE_BASE (charset); \ |
| 212 | if (COMPOSING_P (coding->composing)) \ |
| 213 | *dst++ = leading_code + 0x20; \ |
| 214 | else \ |
| 215 | *dst++ = leading_code; \ |
| 216 | if (leading_code = CHARSET_LEADING_CODE_EXT (charset)) \ |
| 217 | *dst++ = leading_code; \ |
| 218 | *dst++ = (c) | 0x80; \ |
| 219 | } while (0) |
| 220 | |
| 221 | /* Decode one DIMENSION2 character whose charset is CHARSET and whose |
| 222 | position-codes are C1 and C2. */ |
| 223 | |
| 224 | #define DECODE_CHARACTER_DIMENSION2(charset, c1, c2) \ |
| 225 | do { \ |
| 226 | DECODE_CHARACTER_DIMENSION1 (charset, c1); \ |
| 227 | *dst++ = (c2) | 0x80; \ |
| 228 | } while (0) |
| 229 | |
| 230 | \f |
| 231 | /*** 1. Preamble ***/ |
| 232 | |
| 233 | #include <stdio.h> |
| 234 | |
| 235 | #ifdef emacs |
| 236 | |
| 237 | #include <config.h> |
| 238 | #include "lisp.h" |
| 239 | #include "buffer.h" |
| 240 | #include "charset.h" |
| 241 | #include "ccl.h" |
| 242 | #include "coding.h" |
| 243 | #include "window.h" |
| 244 | |
| 245 | #else /* not emacs */ |
| 246 | |
| 247 | #include "mulelib.h" |
| 248 | |
| 249 | #endif /* not emacs */ |
| 250 | |
| 251 | Lisp_Object Qcoding_system, Qeol_type; |
| 252 | Lisp_Object Qbuffer_file_coding_system; |
| 253 | Lisp_Object Qpost_read_conversion, Qpre_write_conversion; |
| 254 | Lisp_Object Qno_conversion, Qundecided; |
| 255 | Lisp_Object Qcoding_system_history; |
| 256 | Lisp_Object Qsafe_charsets; |
| 257 | |
| 258 | extern Lisp_Object Qinsert_file_contents, Qwrite_region; |
| 259 | Lisp_Object Qcall_process, Qcall_process_region, Qprocess_argument; |
| 260 | Lisp_Object Qstart_process, Qopen_network_stream; |
| 261 | Lisp_Object Qtarget_idx; |
| 262 | |
| 263 | /* Mnemonic character of each format of end-of-line. */ |
| 264 | int eol_mnemonic_unix, eol_mnemonic_dos, eol_mnemonic_mac; |
| 265 | /* Mnemonic character to indicate format of end-of-line is not yet |
| 266 | decided. */ |
| 267 | int eol_mnemonic_undecided; |
| 268 | |
| 269 | /* Format of end-of-line decided by system. This is CODING_EOL_LF on |
| 270 | Unix, CODING_EOL_CRLF on DOS/Windows, and CODING_EOL_CR on Mac. */ |
| 271 | int system_eol_type; |
| 272 | |
| 273 | #ifdef emacs |
| 274 | |
| 275 | Lisp_Object Vcoding_system_list, Vcoding_system_alist; |
| 276 | |
| 277 | Lisp_Object Qcoding_system_p, Qcoding_system_error; |
| 278 | |
| 279 | /* Coding system emacs-mule is for converting only end-of-line format. */ |
| 280 | Lisp_Object Qemacs_mule; |
| 281 | |
| 282 | /* Coding-systems are handed between Emacs Lisp programs and C internal |
| 283 | routines by the following three variables. */ |
| 284 | /* Coding-system for reading files and receiving data from process. */ |
| 285 | Lisp_Object Vcoding_system_for_read; |
| 286 | /* Coding-system for writing files and sending data to process. */ |
| 287 | Lisp_Object Vcoding_system_for_write; |
| 288 | /* Coding-system actually used in the latest I/O. */ |
| 289 | Lisp_Object Vlast_coding_system_used; |
| 290 | |
| 291 | /* A vector of length 256 which contains information about special |
| 292 | Latin codes (espepcially for dealing with Microsoft code). */ |
| 293 | Lisp_Object Vlatin_extra_code_table; |
| 294 | |
| 295 | /* Flag to inhibit code conversion of end-of-line format. */ |
| 296 | int inhibit_eol_conversion; |
| 297 | |
| 298 | /* Coding system to be used to encode text for terminal display. */ |
| 299 | struct coding_system terminal_coding; |
| 300 | |
| 301 | /* Coding system to be used to encode text for terminal display when |
| 302 | terminal coding system is nil. */ |
| 303 | struct coding_system safe_terminal_coding; |
| 304 | |
| 305 | /* Coding system of what is sent from terminal keyboard. */ |
| 306 | struct coding_system keyboard_coding; |
| 307 | |
| 308 | Lisp_Object Vfile_coding_system_alist; |
| 309 | Lisp_Object Vprocess_coding_system_alist; |
| 310 | Lisp_Object Vnetwork_coding_system_alist; |
| 311 | |
| 312 | #endif /* emacs */ |
| 313 | |
| 314 | Lisp_Object Qcoding_category_index; |
| 315 | |
| 316 | /* List of symbols `coding-category-xxx' ordered by priority. */ |
| 317 | Lisp_Object Vcoding_category_list; |
| 318 | |
| 319 | /* Table of coding-systems currently assigned to each coding-category. */ |
| 320 | Lisp_Object coding_category_table[CODING_CATEGORY_IDX_MAX]; |
| 321 | |
| 322 | /* Table of names of symbol for each coding-category. */ |
| 323 | char *coding_category_name[CODING_CATEGORY_IDX_MAX] = { |
| 324 | "coding-category-emacs-mule", |
| 325 | "coding-category-sjis", |
| 326 | "coding-category-iso-7", |
| 327 | "coding-category-iso-8-1", |
| 328 | "coding-category-iso-8-2", |
| 329 | "coding-category-iso-7-else", |
| 330 | "coding-category-iso-8-else", |
| 331 | "coding-category-big5", |
| 332 | "coding-category-raw-text", |
| 333 | "coding-category-binary" |
| 334 | }; |
| 335 | |
| 336 | /* Flag to tell if we look up unification table on character code |
| 337 | conversion. */ |
| 338 | Lisp_Object Venable_character_unification; |
| 339 | /* Standard unification table to look up on decoding (reading). */ |
| 340 | Lisp_Object Vstandard_character_unification_table_for_decode; |
| 341 | /* Standard unification table to look up on encoding (writing). */ |
| 342 | Lisp_Object Vstandard_character_unification_table_for_encode; |
| 343 | |
| 344 | Lisp_Object Qcharacter_unification_table; |
| 345 | Lisp_Object Qcharacter_unification_table_for_decode; |
| 346 | Lisp_Object Qcharacter_unification_table_for_encode; |
| 347 | |
| 348 | /* Alist of charsets vs revision number. */ |
| 349 | Lisp_Object Vcharset_revision_alist; |
| 350 | |
| 351 | /* Default coding systems used for process I/O. */ |
| 352 | Lisp_Object Vdefault_process_coding_system; |
| 353 | |
| 354 | \f |
| 355 | /*** 2. Emacs internal format (emacs-mule) handlers ***/ |
| 356 | |
| 357 | /* Emacs' internal format for encoding multiple character sets is a |
| 358 | kind of multi-byte encoding, i.e. characters are encoded by |
| 359 | variable-length sequences of one-byte codes. ASCII characters |
| 360 | and control characters (e.g. `tab', `newline') are represented by |
| 361 | one-byte sequences which are their ASCII codes, in the range 0x00 |
| 362 | through 0x7F. The other characters are represented by a sequence |
| 363 | of `base leading-code', optional `extended leading-code', and one |
| 364 | or two `position-code's. The length of the sequence is determined |
| 365 | by the base leading-code. Leading-code takes the range 0x80 |
| 366 | through 0x9F, whereas extended leading-code and position-code take |
| 367 | the range 0xA0 through 0xFF. See `charset.h' for more details |
| 368 | about leading-code and position-code. |
| 369 | |
| 370 | There's one exception to this rule. Special leading-code |
| 371 | `leading-code-composition' denotes that the following several |
| 372 | characters should be composed into one character. Leading-codes of |
| 373 | components (except for ASCII) are added 0x20. An ASCII character |
| 374 | component is represented by a 2-byte sequence of `0xA0' and |
| 375 | `ASCII-code + 0x80'. See also the comments in `charset.h' for the |
| 376 | details of composite character. Hence, we can summarize the code |
| 377 | range as follows: |
| 378 | |
| 379 | --- CODE RANGE of Emacs' internal format --- |
| 380 | (character set) (range) |
| 381 | ASCII 0x00 .. 0x7F |
| 382 | ELSE (1st byte) 0x80 .. 0x9F |
| 383 | (rest bytes) 0xA0 .. 0xFF |
| 384 | --------------------------------------------- |
| 385 | |
| 386 | */ |
| 387 | |
| 388 | enum emacs_code_class_type emacs_code_class[256]; |
| 389 | |
| 390 | /* Go to the next statement only if *SRC is accessible and the code is |
| 391 | greater than 0xA0. */ |
| 392 | #define CHECK_CODE_RANGE_A0_FF \ |
| 393 | do { \ |
| 394 | if (src >= src_end) \ |
| 395 | goto label_end_of_switch; \ |
| 396 | else if (*src++ < 0xA0) \ |
| 397 | return 0; \ |
| 398 | } while (0) |
| 399 | |
| 400 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". |
| 401 | Check if a text is encoded in Emacs' internal format. If it is, |
| 402 | return CODING_CATEGORY_MASK_EMASC_MULE, else return 0. */ |
| 403 | |
| 404 | int |
| 405 | detect_coding_emacs_mule (src, src_end) |
| 406 | unsigned char *src, *src_end; |
| 407 | { |
| 408 | unsigned char c; |
| 409 | int composing = 0; |
| 410 | |
| 411 | while (src < src_end) |
| 412 | { |
| 413 | c = *src++; |
| 414 | |
| 415 | if (composing) |
| 416 | { |
| 417 | if (c < 0xA0) |
| 418 | composing = 0; |
| 419 | else |
| 420 | c -= 0x20; |
| 421 | } |
| 422 | |
| 423 | switch (emacs_code_class[c]) |
| 424 | { |
| 425 | case EMACS_ascii_code: |
| 426 | case EMACS_linefeed_code: |
| 427 | break; |
| 428 | |
| 429 | case EMACS_control_code: |
| 430 | if (c == ISO_CODE_ESC || c == ISO_CODE_SI || c == ISO_CODE_SO) |
| 431 | return 0; |
| 432 | break; |
| 433 | |
| 434 | case EMACS_invalid_code: |
| 435 | return 0; |
| 436 | |
| 437 | case EMACS_leading_code_composition: /* c == 0x80 */ |
| 438 | if (composing) |
| 439 | CHECK_CODE_RANGE_A0_FF; |
| 440 | else |
| 441 | composing = 1; |
| 442 | break; |
| 443 | |
| 444 | case EMACS_leading_code_4: |
| 445 | CHECK_CODE_RANGE_A0_FF; |
| 446 | /* fall down to check it two more times ... */ |
| 447 | |
| 448 | case EMACS_leading_code_3: |
| 449 | CHECK_CODE_RANGE_A0_FF; |
| 450 | /* fall down to check it one more time ... */ |
| 451 | |
| 452 | case EMACS_leading_code_2: |
| 453 | CHECK_CODE_RANGE_A0_FF; |
| 454 | break; |
| 455 | |
| 456 | default: |
| 457 | label_end_of_switch: |
| 458 | break; |
| 459 | } |
| 460 | } |
| 461 | return CODING_CATEGORY_MASK_EMACS_MULE; |
| 462 | } |
| 463 | |
| 464 | \f |
| 465 | /*** 3. ISO2022 handlers ***/ |
| 466 | |
| 467 | /* The following note describes the coding system ISO2022 briefly. |
| 468 | Since the intention of this note is to help in understanding of |
| 469 | the programs in this file, some parts are NOT ACCURATE or OVERLY |
| 470 | SIMPLIFIED. For the thorough understanding, please refer to the |
| 471 | original document of ISO2022. |
| 472 | |
| 473 | ISO2022 provides many mechanisms to encode several character sets |
| 474 | in 7-bit and 8-bit environment. If one chooses 7-bite environment, |
| 475 | all text is encoded by codes of less than 128. This may make the |
| 476 | encoded text a little bit longer, but the text gets more stability |
| 477 | to pass through several gateways (some of them strip off the MSB). |
| 478 | |
| 479 | There are two kinds of character set: control character set and |
| 480 | graphic character set. The former contains control characters such |
| 481 | as `newline' and `escape' to provide control functions (control |
| 482 | functions are provided also by escape sequences). The latter |
| 483 | contains graphic characters such as ' A' and '-'. Emacs recognizes |
| 484 | two control character sets and many graphic character sets. |
| 485 | |
| 486 | Graphic character sets are classified into one of the following |
| 487 | four classes, DIMENSION1_CHARS94, DIMENSION1_CHARS96, |
| 488 | DIMENSION2_CHARS94, DIMENSION2_CHARS96 according to the number of |
| 489 | bytes (DIMENSION) and the number of characters in one dimension |
| 490 | (CHARS) of the set. In addition, each character set is assigned an |
| 491 | identification tag (called "final character" and denoted as <F> |
| 492 | here after) which is unique in each class. <F> of each character |
| 493 | set is decided by ECMA(*) when it is registered in ISO. Code range |
| 494 | of <F> is 0x30..0x7F (0x30..0x3F are for private use only). |
| 495 | |
| 496 | Note (*): ECMA = European Computer Manufacturers Association |
| 497 | |
| 498 | Here are examples of graphic character set [NAME(<F>)]: |
| 499 | o DIMENSION1_CHARS94 -- ASCII('B'), right-half-of-JISX0201('I'), ... |
| 500 | o DIMENSION1_CHARS96 -- right-half-of-ISO8859-1('A'), ... |
| 501 | o DIMENSION2_CHARS94 -- GB2312('A'), JISX0208('B'), ... |
| 502 | o DIMENSION2_CHARS96 -- none for the moment |
| 503 | |
| 504 | A code area (1byte=8bits) is divided into 4 areas, C0, GL, C1, and GR. |
| 505 | C0 [0x00..0x1F] -- control character plane 0 |
| 506 | GL [0x20..0x7F] -- graphic character plane 0 |
| 507 | C1 [0x80..0x9F] -- control character plane 1 |
| 508 | GR [0xA0..0xFF] -- graphic character plane 1 |
| 509 | |
| 510 | A control character set is directly designated and invoked to C0 or |
| 511 | C1 by an escape sequence. The most common case is that ISO646's |
| 512 | control character set is designated/invoked to C0 and ISO6429's |
| 513 | control character set is designated/invoked to C1, and usually |
| 514 | these designations/invocations are omitted in a coded text. With |
| 515 | 7-bit environment, only C0 can be used, and a control character for |
| 516 | C1 is encoded by an appropriate escape sequence to fit in the |
| 517 | environment. All control characters for C1 are defined the |
| 518 | corresponding escape sequences. |
| 519 | |
| 520 | A graphic character set is at first designated to one of four |
| 521 | graphic registers (G0 through G3), then these graphic registers are |
| 522 | invoked to GL or GR. These designations and invocations can be |
| 523 | done independently. The most common case is that G0 is invoked to |
| 524 | GL, G1 is invoked to GR, and ASCII is designated to G0, and usually |
| 525 | these invocations and designations are omitted in a coded text. |
| 526 | With 7-bit environment, only GL can be used. |
| 527 | |
| 528 | When a graphic character set of CHARS94 is invoked to GL, code 0x20 |
| 529 | and 0x7F of GL area work as control characters SPACE and DEL |
| 530 | respectively, and code 0xA0 and 0xFF of GR area should not be used. |
| 531 | |
| 532 | There are two ways of invocation: locking-shift and single-shift. |
| 533 | With locking-shift, the invocation lasts until the next different |
| 534 | invocation, whereas with single-shift, the invocation works only |
| 535 | for the following character and doesn't affect locking-shift. |
| 536 | Invocations are done by the following control characters or escape |
| 537 | sequences. |
| 538 | |
| 539 | ---------------------------------------------------------------------- |
| 540 | function control char escape sequence description |
| 541 | ---------------------------------------------------------------------- |
| 542 | SI (shift-in) 0x0F none invoke G0 to GL |
| 543 | SO (shift-out) 0x0E none invoke G1 to GL |
| 544 | LS2 (locking-shift-2) none ESC 'n' invoke G2 into GL |
| 545 | LS3 (locking-shift-3) none ESC 'o' invoke G3 into GL |
| 546 | SS2 (single-shift-2) 0x8E ESC 'N' invoke G2 into GL |
| 547 | SS3 (single-shift-3) 0x8F ESC 'O' invoke G3 into GL |
| 548 | ---------------------------------------------------------------------- |
| 549 | The first four are for locking-shift. Control characters for these |
| 550 | functions are defined by macros ISO_CODE_XXX in `coding.h'. |
| 551 | |
| 552 | Designations are done by the following escape sequences. |
| 553 | ---------------------------------------------------------------------- |
| 554 | escape sequence description |
| 555 | ---------------------------------------------------------------------- |
| 556 | ESC '(' <F> designate DIMENSION1_CHARS94<F> to G0 |
| 557 | ESC ')' <F> designate DIMENSION1_CHARS94<F> to G1 |
| 558 | ESC '*' <F> designate DIMENSION1_CHARS94<F> to G2 |
| 559 | ESC '+' <F> designate DIMENSION1_CHARS94<F> to G3 |
| 560 | ESC ',' <F> designate DIMENSION1_CHARS96<F> to G0 (*) |
| 561 | ESC '-' <F> designate DIMENSION1_CHARS96<F> to G1 |
| 562 | ESC '.' <F> designate DIMENSION1_CHARS96<F> to G2 |
| 563 | ESC '/' <F> designate DIMENSION1_CHARS96<F> to G3 |
| 564 | ESC '$' '(' <F> designate DIMENSION2_CHARS94<F> to G0 (**) |
| 565 | ESC '$' ')' <F> designate DIMENSION2_CHARS94<F> to G1 |
| 566 | ESC '$' '*' <F> designate DIMENSION2_CHARS94<F> to G2 |
| 567 | ESC '$' '+' <F> designate DIMENSION2_CHARS94<F> to G3 |
| 568 | ESC '$' ',' <F> designate DIMENSION2_CHARS96<F> to G0 (*) |
| 569 | ESC '$' '-' <F> designate DIMENSION2_CHARS96<F> to G1 |
| 570 | ESC '$' '.' <F> designate DIMENSION2_CHARS96<F> to G2 |
| 571 | ESC '$' '/' <F> designate DIMENSION2_CHARS96<F> to G3 |
| 572 | ---------------------------------------------------------------------- |
| 573 | |
| 574 | In this list, "DIMENSION1_CHARS94<F>" means a graphic character set |
| 575 | of dimension 1, chars 94, and final character <F>, and etc. |
| 576 | |
| 577 | Note (*): Although these designations are not allowed in ISO2022, |
| 578 | Emacs accepts them on decoding, and produces them on encoding |
| 579 | CHARS96 character set in a coding system which is characterized as |
| 580 | 7-bit environment, non-locking-shift, and non-single-shift. |
| 581 | |
| 582 | Note (**): If <F> is '@', 'A', or 'B', the intermediate character |
| 583 | '(' can be omitted. We call this as "short-form" here after. |
| 584 | |
| 585 | Now you may notice that there are a lot of ways for encoding the |
| 586 | same multilingual text in ISO2022. Actually, there exists many |
| 587 | coding systems such as Compound Text (used in X's inter client |
| 588 | communication, ISO-2022-JP (used in Japanese Internet), ISO-2022-KR |
| 589 | (used in Korean Internet), EUC (Extended UNIX Code, used in Asian |
| 590 | localized platforms), and all of these are variants of ISO2022. |
| 591 | |
| 592 | In addition to the above, Emacs handles two more kinds of escape |
| 593 | sequences: ISO6429's direction specification and Emacs' private |
| 594 | sequence for specifying character composition. |
| 595 | |
| 596 | ISO6429's direction specification takes the following format: |
| 597 | o CSI ']' -- end of the current direction |
| 598 | o CSI '0' ']' -- end of the current direction |
| 599 | o CSI '1' ']' -- start of left-to-right text |
| 600 | o CSI '2' ']' -- start of right-to-left text |
| 601 | The control character CSI (0x9B: control sequence introducer) is |
| 602 | abbreviated to the escape sequence ESC '[' in 7-bit environment. |
| 603 | |
| 604 | Character composition specification takes the following format: |
| 605 | o ESC '0' -- start character composition |
| 606 | o ESC '1' -- end character composition |
| 607 | Since these are not standard escape sequences of any ISO, the use |
| 608 | of them for these meaning is restricted to Emacs only. */ |
| 609 | |
| 610 | enum iso_code_class_type iso_code_class[256]; |
| 611 | |
| 612 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". |
| 613 | Check if a text is encoded in ISO2022. If it is, returns an |
| 614 | integer in which appropriate flag bits any of: |
| 615 | CODING_CATEGORY_MASK_ISO_7 |
| 616 | CODING_CATEGORY_MASK_ISO_8_1 |
| 617 | CODING_CATEGORY_MASK_ISO_8_2 |
| 618 | CODING_CATEGORY_MASK_ISO_7_ELSE |
| 619 | CODING_CATEGORY_MASK_ISO_8_ELSE |
| 620 | are set. If a code which should never appear in ISO2022 is found, |
| 621 | returns 0. */ |
| 622 | |
| 623 | int |
| 624 | detect_coding_iso2022 (src, src_end) |
| 625 | unsigned char *src, *src_end; |
| 626 | { |
| 627 | int mask = (CODING_CATEGORY_MASK_ISO_7 |
| 628 | | CODING_CATEGORY_MASK_ISO_8_1 |
| 629 | | CODING_CATEGORY_MASK_ISO_8_2 |
| 630 | | CODING_CATEGORY_MASK_ISO_7_ELSE |
| 631 | | CODING_CATEGORY_MASK_ISO_8_ELSE |
| 632 | ); |
| 633 | int g1 = 0; /* 1 iff designating to G1. */ |
| 634 | int c, i; |
| 635 | struct coding_system coding_iso_8_1, coding_iso_8_2; |
| 636 | |
| 637 | /* Coding systems of these categories may accept latin extra codes. */ |
| 638 | setup_coding_system |
| 639 | (XSYMBOL (coding_category_table[CODING_CATEGORY_IDX_ISO_8_1])->value, |
| 640 | &coding_iso_8_1); |
| 641 | setup_coding_system |
| 642 | (XSYMBOL (coding_category_table[CODING_CATEGORY_IDX_ISO_8_2])->value, |
| 643 | &coding_iso_8_2); |
| 644 | |
| 645 | while (mask && src < src_end) |
| 646 | { |
| 647 | c = *src++; |
| 648 | switch (c) |
| 649 | { |
| 650 | case ISO_CODE_ESC: |
| 651 | if (src >= src_end) |
| 652 | break; |
| 653 | c = *src++; |
| 654 | if ((c >= '(' && c <= '/')) |
| 655 | { |
| 656 | /* Designation sequence for a charset of dimension 1. */ |
| 657 | if (src >= src_end) |
| 658 | break; |
| 659 | c = *src++; |
| 660 | if (c < ' ' || c >= 0x80) |
| 661 | /* Invalid designation sequence. */ |
| 662 | return 0; |
| 663 | } |
| 664 | else if (c == '$') |
| 665 | { |
| 666 | /* Designation sequence for a charset of dimension 2. */ |
| 667 | if (src >= src_end) |
| 668 | break; |
| 669 | c = *src++; |
| 670 | if (c >= '@' && c <= 'B') |
| 671 | /* Designation for JISX0208.1978, GB2312, or JISX0208. */ |
| 672 | ; |
| 673 | else if (c >= '(' && c <= '/') |
| 674 | { |
| 675 | if (src >= src_end) |
| 676 | break; |
| 677 | c = *src++; |
| 678 | if (c < ' ' || c >= 0x80) |
| 679 | /* Invalid designation sequence. */ |
| 680 | return 0; |
| 681 | } |
| 682 | else |
| 683 | /* Invalid designation sequence. */ |
| 684 | return 0; |
| 685 | } |
| 686 | else if (c == 'N' || c == 'O' || c == 'n' || c == 'o') |
| 687 | /* Locking shift. */ |
| 688 | mask &= (CODING_CATEGORY_MASK_ISO_7_ELSE |
| 689 | | CODING_CATEGORY_MASK_ISO_8_ELSE); |
| 690 | else if (c == '0' || c == '1' || c == '2') |
| 691 | /* Start/end composition. */ |
| 692 | ; |
| 693 | else |
| 694 | /* Invalid escape sequence. */ |
| 695 | return 0; |
| 696 | break; |
| 697 | |
| 698 | case ISO_CODE_SO: |
| 699 | mask &= (CODING_CATEGORY_MASK_ISO_7_ELSE |
| 700 | | CODING_CATEGORY_MASK_ISO_8_ELSE); |
| 701 | break; |
| 702 | |
| 703 | case ISO_CODE_CSI: |
| 704 | case ISO_CODE_SS2: |
| 705 | case ISO_CODE_SS3: |
| 706 | { |
| 707 | int newmask = CODING_CATEGORY_MASK_ISO_8_ELSE; |
| 708 | |
| 709 | if (c != ISO_CODE_CSI) |
| 710 | { |
| 711 | if (coding_iso_8_1.flags & CODING_FLAG_ISO_SINGLE_SHIFT) |
| 712 | newmask |= CODING_CATEGORY_MASK_ISO_8_1; |
| 713 | if (coding_iso_8_2.flags & CODING_FLAG_ISO_SINGLE_SHIFT) |
| 714 | newmask |= CODING_CATEGORY_MASK_ISO_8_2; |
| 715 | } |
| 716 | if (VECTORP (Vlatin_extra_code_table) |
| 717 | && !NILP (XVECTOR (Vlatin_extra_code_table)->contents[c])) |
| 718 | { |
| 719 | if (coding_iso_8_1.flags & CODING_FLAG_ISO_LATIN_EXTRA) |
| 720 | newmask |= CODING_CATEGORY_MASK_ISO_8_1; |
| 721 | if (coding_iso_8_2.flags & CODING_FLAG_ISO_LATIN_EXTRA) |
| 722 | newmask |= CODING_CATEGORY_MASK_ISO_8_2; |
| 723 | } |
| 724 | mask &= newmask; |
| 725 | } |
| 726 | break; |
| 727 | |
| 728 | default: |
| 729 | if (c < 0x80) |
| 730 | break; |
| 731 | else if (c < 0xA0) |
| 732 | { |
| 733 | if (VECTORP (Vlatin_extra_code_table) |
| 734 | && !NILP (XVECTOR (Vlatin_extra_code_table)->contents[c])) |
| 735 | { |
| 736 | int newmask = 0; |
| 737 | |
| 738 | if (coding_iso_8_1.flags & CODING_FLAG_ISO_LATIN_EXTRA) |
| 739 | newmask |= CODING_CATEGORY_MASK_ISO_8_1; |
| 740 | if (coding_iso_8_2.flags & CODING_FLAG_ISO_LATIN_EXTRA) |
| 741 | newmask |= CODING_CATEGORY_MASK_ISO_8_2; |
| 742 | mask &= newmask; |
| 743 | } |
| 744 | else |
| 745 | return 0; |
| 746 | } |
| 747 | else |
| 748 | { |
| 749 | unsigned char *src_begin = src; |
| 750 | |
| 751 | mask &= ~(CODING_CATEGORY_MASK_ISO_7 |
| 752 | | CODING_CATEGORY_MASK_ISO_7_ELSE); |
| 753 | while (src < src_end && *src >= 0xA0) |
| 754 | src++; |
| 755 | if ((src - src_begin - 1) & 1 && src < src_end) |
| 756 | mask &= ~CODING_CATEGORY_MASK_ISO_8_2; |
| 757 | } |
| 758 | break; |
| 759 | } |
| 760 | } |
| 761 | |
| 762 | return mask; |
| 763 | } |
| 764 | |
| 765 | /* Decode a character of which charset is CHARSET and the 1st position |
| 766 | code is C1. If dimension of CHARSET is 2, the 2nd position code is |
| 767 | fetched from SRC and set to C2. If CHARSET is negative, it means |
| 768 | that we are decoding ill formed text, and what we can do is just to |
| 769 | read C1 as is. */ |
| 770 | |
| 771 | #define DECODE_ISO_CHARACTER(charset, c1) \ |
| 772 | do { \ |
| 773 | int c_alt, charset_alt = (charset); \ |
| 774 | if (COMPOSING_HEAD_P (coding->composing)) \ |
| 775 | { \ |
| 776 | *dst++ = LEADING_CODE_COMPOSITION; \ |
| 777 | if (COMPOSING_WITH_RULE_P (coding->composing)) \ |
| 778 | /* To tell composition rules are embeded. */ \ |
| 779 | *dst++ = 0xFF; \ |
| 780 | coding->composing += 2; \ |
| 781 | } \ |
| 782 | if ((charset) >= 0) \ |
| 783 | { \ |
| 784 | if (CHARSET_DIMENSION (charset) == 2) \ |
| 785 | { \ |
| 786 | ONE_MORE_BYTE (c2); \ |
| 787 | if (iso_code_class[(c2) & 0x7F] != ISO_0x20_or_0x7F \ |
| 788 | && iso_code_class[(c2) & 0x7F] != ISO_graphic_plane_0) \ |
| 789 | { \ |
| 790 | src--; \ |
| 791 | c2 = ' '; \ |
| 792 | } \ |
| 793 | } \ |
| 794 | if (!NILP (unification_table) \ |
| 795 | && ((c_alt = unify_char (unification_table, \ |
| 796 | -1, (charset), c1, c2)) >= 0)) \ |
| 797 | SPLIT_CHAR (c_alt, charset_alt, c1, c2); \ |
| 798 | } \ |
| 799 | if (charset_alt == CHARSET_ASCII || charset_alt < 0) \ |
| 800 | DECODE_CHARACTER_ASCII (c1); \ |
| 801 | else if (CHARSET_DIMENSION (charset_alt) == 1) \ |
| 802 | DECODE_CHARACTER_DIMENSION1 (charset_alt, c1); \ |
| 803 | else \ |
| 804 | DECODE_CHARACTER_DIMENSION2 (charset_alt, c1, c2); \ |
| 805 | if (COMPOSING_WITH_RULE_P (coding->composing)) \ |
| 806 | /* To tell a composition rule follows. */ \ |
| 807 | coding->composing = COMPOSING_WITH_RULE_RULE; \ |
| 808 | } while (0) |
| 809 | |
| 810 | /* Set designation state into CODING. */ |
| 811 | #define DECODE_DESIGNATION(reg, dimension, chars, final_char) \ |
| 812 | do { \ |
| 813 | int charset = ISO_CHARSET_TABLE (make_number (dimension), \ |
| 814 | make_number (chars), \ |
| 815 | make_number (final_char)); \ |
| 816 | if (charset >= 0) \ |
| 817 | { \ |
| 818 | if (coding->direction == 1 \ |
| 819 | && CHARSET_REVERSE_CHARSET (charset) >= 0) \ |
| 820 | charset = CHARSET_REVERSE_CHARSET (charset); \ |
| 821 | CODING_SPEC_ISO_DESIGNATION (coding, reg) = charset; \ |
| 822 | } \ |
| 823 | } while (0) |
| 824 | |
| 825 | /* See the above "GENERAL NOTES on `decode_coding_XXX ()' functions". */ |
| 826 | |
| 827 | int |
| 828 | decode_coding_iso2022 (coding, source, destination, |
| 829 | src_bytes, dst_bytes, consumed) |
| 830 | struct coding_system *coding; |
| 831 | unsigned char *source, *destination; |
| 832 | int src_bytes, dst_bytes; |
| 833 | int *consumed; |
| 834 | { |
| 835 | unsigned char *src = source; |
| 836 | unsigned char *src_end = source + src_bytes; |
| 837 | unsigned char *dst = destination; |
| 838 | unsigned char *dst_end = destination + dst_bytes; |
| 839 | /* Since the maximum bytes produced by each loop is 7, we subtract 6 |
| 840 | from DST_END to assure that overflow checking is necessary only |
| 841 | at the head of loop. */ |
| 842 | unsigned char *adjusted_dst_end = dst_end - 6; |
| 843 | int charset; |
| 844 | /* Charsets invoked to graphic plane 0 and 1 respectively. */ |
| 845 | int charset0 = CODING_SPEC_ISO_PLANE_CHARSET (coding, 0); |
| 846 | int charset1 = CODING_SPEC_ISO_PLANE_CHARSET (coding, 1); |
| 847 | Lisp_Object unification_table |
| 848 | = coding->character_unification_table_for_decode; |
| 849 | |
| 850 | if (!NILP (Venable_character_unification) && NILP (unification_table)) |
| 851 | unification_table = Vstandard_character_unification_table_for_decode; |
| 852 | |
| 853 | while (src < src_end && dst < adjusted_dst_end) |
| 854 | { |
| 855 | /* SRC_BASE remembers the start position in source in each loop. |
| 856 | The loop will be exited when there's not enough source text |
| 857 | to analyze long escape sequence or 2-byte code (within macros |
| 858 | ONE_MORE_BYTE or TWO_MORE_BYTES). In that case, SRC is reset |
| 859 | to SRC_BASE before exiting. */ |
| 860 | unsigned char *src_base = src; |
| 861 | int c1 = *src++, c2; |
| 862 | |
| 863 | switch (iso_code_class [c1]) |
| 864 | { |
| 865 | case ISO_0x20_or_0x7F: |
| 866 | if (!coding->composing |
| 867 | && (charset0 < 0 || CHARSET_CHARS (charset0) == 94)) |
| 868 | { |
| 869 | /* This is SPACE or DEL. */ |
| 870 | *dst++ = c1; |
| 871 | break; |
| 872 | } |
| 873 | /* This is a graphic character, we fall down ... */ |
| 874 | |
| 875 | case ISO_graphic_plane_0: |
| 876 | if (coding->composing == COMPOSING_WITH_RULE_RULE) |
| 877 | { |
| 878 | /* This is a composition rule. */ |
| 879 | *dst++ = c1 | 0x80; |
| 880 | coding->composing = COMPOSING_WITH_RULE_TAIL; |
| 881 | } |
| 882 | else |
| 883 | DECODE_ISO_CHARACTER (charset0, c1); |
| 884 | break; |
| 885 | |
| 886 | case ISO_0xA0_or_0xFF: |
| 887 | if (charset1 < 0 || CHARSET_CHARS (charset1) == 94) |
| 888 | { |
| 889 | /* Invalid code. */ |
| 890 | *dst++ = c1; |
| 891 | break; |
| 892 | } |
| 893 | /* This is a graphic character, we fall down ... */ |
| 894 | |
| 895 | case ISO_graphic_plane_1: |
| 896 | DECODE_ISO_CHARACTER (charset1, c1); |
| 897 | break; |
| 898 | |
| 899 | case ISO_control_code: |
| 900 | /* All ISO2022 control characters in this class have the |
| 901 | same representation in Emacs internal format. */ |
| 902 | *dst++ = c1; |
| 903 | break; |
| 904 | |
| 905 | case ISO_carriage_return: |
| 906 | if (coding->eol_type == CODING_EOL_CR) |
| 907 | { |
| 908 | *dst++ = '\n'; |
| 909 | } |
| 910 | else if (coding->eol_type == CODING_EOL_CRLF) |
| 911 | { |
| 912 | ONE_MORE_BYTE (c1); |
| 913 | if (c1 == ISO_CODE_LF) |
| 914 | *dst++ = '\n'; |
| 915 | else |
| 916 | { |
| 917 | src--; |
| 918 | *dst++ = c1; |
| 919 | } |
| 920 | } |
| 921 | else |
| 922 | { |
| 923 | *dst++ = c1; |
| 924 | } |
| 925 | break; |
| 926 | |
| 927 | case ISO_shift_out: |
| 928 | if (CODING_SPEC_ISO_DESIGNATION (coding, 1) < 0) |
| 929 | goto label_invalid_escape_sequence; |
| 930 | CODING_SPEC_ISO_INVOCATION (coding, 0) = 1; |
| 931 | charset0 = CODING_SPEC_ISO_PLANE_CHARSET (coding, 0); |
| 932 | break; |
| 933 | |
| 934 | case ISO_shift_in: |
| 935 | CODING_SPEC_ISO_INVOCATION (coding, 0) = 0; |
| 936 | charset0 = CODING_SPEC_ISO_PLANE_CHARSET (coding, 0); |
| 937 | break; |
| 938 | |
| 939 | case ISO_single_shift_2_7: |
| 940 | case ISO_single_shift_2: |
| 941 | /* SS2 is handled as an escape sequence of ESC 'N' */ |
| 942 | c1 = 'N'; |
| 943 | goto label_escape_sequence; |
| 944 | |
| 945 | case ISO_single_shift_3: |
| 946 | /* SS2 is handled as an escape sequence of ESC 'O' */ |
| 947 | c1 = 'O'; |
| 948 | goto label_escape_sequence; |
| 949 | |
| 950 | case ISO_control_sequence_introducer: |
| 951 | /* CSI is handled as an escape sequence of ESC '[' ... */ |
| 952 | c1 = '['; |
| 953 | goto label_escape_sequence; |
| 954 | |
| 955 | case ISO_escape: |
| 956 | ONE_MORE_BYTE (c1); |
| 957 | label_escape_sequence: |
| 958 | /* Escape sequences handled by Emacs are invocation, |
| 959 | designation, direction specification, and character |
| 960 | composition specification. */ |
| 961 | switch (c1) |
| 962 | { |
| 963 | case '&': /* revision of following character set */ |
| 964 | ONE_MORE_BYTE (c1); |
| 965 | if (!(c1 >= '@' && c1 <= '~')) |
| 966 | goto label_invalid_escape_sequence; |
| 967 | ONE_MORE_BYTE (c1); |
| 968 | if (c1 != ISO_CODE_ESC) |
| 969 | goto label_invalid_escape_sequence; |
| 970 | ONE_MORE_BYTE (c1); |
| 971 | goto label_escape_sequence; |
| 972 | |
| 973 | case '$': /* designation of 2-byte character set */ |
| 974 | ONE_MORE_BYTE (c1); |
| 975 | if (c1 >= '@' && c1 <= 'B') |
| 976 | { /* designation of JISX0208.1978, GB2312.1980, |
| 977 | or JISX0208.1980 */ |
| 978 | DECODE_DESIGNATION (0, 2, 94, c1); |
| 979 | } |
| 980 | else if (c1 >= 0x28 && c1 <= 0x2B) |
| 981 | { /* designation of DIMENSION2_CHARS94 character set */ |
| 982 | ONE_MORE_BYTE (c2); |
| 983 | DECODE_DESIGNATION (c1 - 0x28, 2, 94, c2); |
| 984 | } |
| 985 | else if (c1 >= 0x2C && c1 <= 0x2F) |
| 986 | { /* designation of DIMENSION2_CHARS96 character set */ |
| 987 | ONE_MORE_BYTE (c2); |
| 988 | DECODE_DESIGNATION (c1 - 0x2C, 2, 96, c2); |
| 989 | } |
| 990 | else |
| 991 | goto label_invalid_escape_sequence; |
| 992 | break; |
| 993 | |
| 994 | case 'n': /* invocation of locking-shift-2 */ |
| 995 | if (CODING_SPEC_ISO_DESIGNATION (coding, 2) < 0) |
| 996 | goto label_invalid_escape_sequence; |
| 997 | CODING_SPEC_ISO_INVOCATION (coding, 0) = 2; |
| 998 | charset0 = CODING_SPEC_ISO_PLANE_CHARSET (coding, 0); |
| 999 | break; |
| 1000 | |
| 1001 | case 'o': /* invocation of locking-shift-3 */ |
| 1002 | if (CODING_SPEC_ISO_DESIGNATION (coding, 3) < 0) |
| 1003 | goto label_invalid_escape_sequence; |
| 1004 | CODING_SPEC_ISO_INVOCATION (coding, 0) = 3; |
| 1005 | charset0 = CODING_SPEC_ISO_PLANE_CHARSET (coding, 0); |
| 1006 | break; |
| 1007 | |
| 1008 | case 'N': /* invocation of single-shift-2 */ |
| 1009 | if (CODING_SPEC_ISO_DESIGNATION (coding, 2) < 0) |
| 1010 | goto label_invalid_escape_sequence; |
| 1011 | ONE_MORE_BYTE (c1); |
| 1012 | charset = CODING_SPEC_ISO_DESIGNATION (coding, 2); |
| 1013 | DECODE_ISO_CHARACTER (charset, c1); |
| 1014 | break; |
| 1015 | |
| 1016 | case 'O': /* invocation of single-shift-3 */ |
| 1017 | if (CODING_SPEC_ISO_DESIGNATION (coding, 3) < 0) |
| 1018 | goto label_invalid_escape_sequence; |
| 1019 | ONE_MORE_BYTE (c1); |
| 1020 | charset = CODING_SPEC_ISO_DESIGNATION (coding, 3); |
| 1021 | DECODE_ISO_CHARACTER (charset, c1); |
| 1022 | break; |
| 1023 | |
| 1024 | case '0': /* start composing without embeded rules */ |
| 1025 | coding->composing = COMPOSING_NO_RULE_HEAD; |
| 1026 | break; |
| 1027 | |
| 1028 | case '1': /* end composing */ |
| 1029 | coding->composing = COMPOSING_NO; |
| 1030 | break; |
| 1031 | |
| 1032 | case '2': /* start composing with embeded rules */ |
| 1033 | coding->composing = COMPOSING_WITH_RULE_HEAD; |
| 1034 | break; |
| 1035 | |
| 1036 | case '[': /* specification of direction */ |
| 1037 | /* For the moment, nested direction is not supported. |
| 1038 | So, the value of `coding->direction' is 0 or 1: 0 |
| 1039 | means left-to-right, 1 means right-to-left. */ |
| 1040 | ONE_MORE_BYTE (c1); |
| 1041 | switch (c1) |
| 1042 | { |
| 1043 | case ']': /* end of the current direction */ |
| 1044 | coding->direction = 0; |
| 1045 | |
| 1046 | case '0': /* end of the current direction */ |
| 1047 | case '1': /* start of left-to-right direction */ |
| 1048 | ONE_MORE_BYTE (c1); |
| 1049 | if (c1 == ']') |
| 1050 | coding->direction = 0; |
| 1051 | else |
| 1052 | goto label_invalid_escape_sequence; |
| 1053 | break; |
| 1054 | |
| 1055 | case '2': /* start of right-to-left direction */ |
| 1056 | ONE_MORE_BYTE (c1); |
| 1057 | if (c1 == ']') |
| 1058 | coding->direction= 1; |
| 1059 | else |
| 1060 | goto label_invalid_escape_sequence; |
| 1061 | break; |
| 1062 | |
| 1063 | default: |
| 1064 | goto label_invalid_escape_sequence; |
| 1065 | } |
| 1066 | break; |
| 1067 | |
| 1068 | default: |
| 1069 | if (c1 >= 0x28 && c1 <= 0x2B) |
| 1070 | { /* designation of DIMENSION1_CHARS94 character set */ |
| 1071 | ONE_MORE_BYTE (c2); |
| 1072 | DECODE_DESIGNATION (c1 - 0x28, 1, 94, c2); |
| 1073 | } |
| 1074 | else if (c1 >= 0x2C && c1 <= 0x2F) |
| 1075 | { /* designation of DIMENSION1_CHARS96 character set */ |
| 1076 | ONE_MORE_BYTE (c2); |
| 1077 | DECODE_DESIGNATION (c1 - 0x2C, 1, 96, c2); |
| 1078 | } |
| 1079 | else |
| 1080 | { |
| 1081 | goto label_invalid_escape_sequence; |
| 1082 | } |
| 1083 | } |
| 1084 | /* We must update these variables now. */ |
| 1085 | charset0 = CODING_SPEC_ISO_PLANE_CHARSET (coding, 0); |
| 1086 | charset1 = CODING_SPEC_ISO_PLANE_CHARSET (coding, 1); |
| 1087 | break; |
| 1088 | |
| 1089 | label_invalid_escape_sequence: |
| 1090 | { |
| 1091 | int length = src - src_base; |
| 1092 | |
| 1093 | bcopy (src_base, dst, length); |
| 1094 | dst += length; |
| 1095 | } |
| 1096 | } |
| 1097 | continue; |
| 1098 | |
| 1099 | label_end_of_loop: |
| 1100 | coding->carryover_size = src - src_base; |
| 1101 | bcopy (src_base, coding->carryover, coding->carryover_size); |
| 1102 | src = src_base; |
| 1103 | break; |
| 1104 | } |
| 1105 | |
| 1106 | /* If this is the last block of the text to be decoded, we had |
| 1107 | better just flush out all remaining codes in the text although |
| 1108 | they are not valid characters. */ |
| 1109 | if (coding->last_block) |
| 1110 | { |
| 1111 | bcopy (src, dst, src_end - src); |
| 1112 | dst += (src_end - src); |
| 1113 | src = src_end; |
| 1114 | } |
| 1115 | *consumed = src - source; |
| 1116 | return dst - destination; |
| 1117 | } |
| 1118 | |
| 1119 | /* ISO2022 encoding stuff. */ |
| 1120 | |
| 1121 | /* |
| 1122 | It is not enough to say just "ISO2022" on encoding, we have to |
| 1123 | specify more details. In Emacs, each coding-system of ISO2022 |
| 1124 | variant has the following specifications: |
| 1125 | 1. Initial designation to G0 thru G3. |
| 1126 | 2. Allows short-form designation? |
| 1127 | 3. ASCII should be designated to G0 before control characters? |
| 1128 | 4. ASCII should be designated to G0 at end of line? |
| 1129 | 5. 7-bit environment or 8-bit environment? |
| 1130 | 6. Use locking-shift? |
| 1131 | 7. Use Single-shift? |
| 1132 | And the following two are only for Japanese: |
| 1133 | 8. Use ASCII in place of JIS0201-1976-Roman? |
| 1134 | 9. Use JISX0208-1983 in place of JISX0208-1978? |
| 1135 | These specifications are encoded in `coding->flags' as flag bits |
| 1136 | defined by macros CODING_FLAG_ISO_XXX. See `coding.h' for more |
| 1137 | details. |
| 1138 | */ |
| 1139 | |
| 1140 | /* Produce codes (escape sequence) for designating CHARSET to graphic |
| 1141 | register REG. If <final-char> of CHARSET is '@', 'A', or 'B' and |
| 1142 | the coding system CODING allows, produce designation sequence of |
| 1143 | short-form. */ |
| 1144 | |
| 1145 | #define ENCODE_DESIGNATION(charset, reg, coding) \ |
| 1146 | do { \ |
| 1147 | unsigned char final_char = CHARSET_ISO_FINAL_CHAR (charset); \ |
| 1148 | char *intermediate_char_94 = "()*+"; \ |
| 1149 | char *intermediate_char_96 = ",-./"; \ |
| 1150 | int revision = CODING_SPEC_ISO_REVISION_NUMBER(coding, charset); \ |
| 1151 | if (revision < 255) \ |
| 1152 | { \ |
| 1153 | *dst++ = ISO_CODE_ESC; \ |
| 1154 | *dst++ = '&'; \ |
| 1155 | *dst++ = '@' + revision; \ |
| 1156 | } \ |
| 1157 | *dst++ = ISO_CODE_ESC; \ |
| 1158 | if (CHARSET_DIMENSION (charset) == 1) \ |
| 1159 | { \ |
| 1160 | if (CHARSET_CHARS (charset) == 94) \ |
| 1161 | *dst++ = (unsigned char) (intermediate_char_94[reg]); \ |
| 1162 | else \ |
| 1163 | *dst++ = (unsigned char) (intermediate_char_96[reg]); \ |
| 1164 | } \ |
| 1165 | else \ |
| 1166 | { \ |
| 1167 | *dst++ = '$'; \ |
| 1168 | if (CHARSET_CHARS (charset) == 94) \ |
| 1169 | { \ |
| 1170 | if (! (coding->flags & CODING_FLAG_ISO_SHORT_FORM) \ |
| 1171 | || reg != 0 \ |
| 1172 | || final_char < '@' || final_char > 'B') \ |
| 1173 | *dst++ = (unsigned char) (intermediate_char_94[reg]); \ |
| 1174 | } \ |
| 1175 | else \ |
| 1176 | *dst++ = (unsigned char) (intermediate_char_96[reg]); \ |
| 1177 | } \ |
| 1178 | *dst++ = final_char; \ |
| 1179 | CODING_SPEC_ISO_DESIGNATION (coding, reg) = charset; \ |
| 1180 | } while (0) |
| 1181 | |
| 1182 | /* The following two macros produce codes (control character or escape |
| 1183 | sequence) for ISO2022 single-shift functions (single-shift-2 and |
| 1184 | single-shift-3). */ |
| 1185 | |
| 1186 | #define ENCODE_SINGLE_SHIFT_2 \ |
| 1187 | do { \ |
| 1188 | if (coding->flags & CODING_FLAG_ISO_SEVEN_BITS) \ |
| 1189 | *dst++ = ISO_CODE_ESC, *dst++ = 'N'; \ |
| 1190 | else \ |
| 1191 | *dst++ = ISO_CODE_SS2; \ |
| 1192 | CODING_SPEC_ISO_SINGLE_SHIFTING (coding) = 1; \ |
| 1193 | } while (0) |
| 1194 | |
| 1195 | #define ENCODE_SINGLE_SHIFT_3 \ |
| 1196 | do { \ |
| 1197 | if (coding->flags & CODING_FLAG_ISO_SEVEN_BITS) \ |
| 1198 | *dst++ = ISO_CODE_ESC, *dst++ = 'O'; \ |
| 1199 | else \ |
| 1200 | *dst++ = ISO_CODE_SS3; \ |
| 1201 | CODING_SPEC_ISO_SINGLE_SHIFTING (coding) = 1; \ |
| 1202 | } while (0) |
| 1203 | |
| 1204 | /* The following four macros produce codes (control character or |
| 1205 | escape sequence) for ISO2022 locking-shift functions (shift-in, |
| 1206 | shift-out, locking-shift-2, and locking-shift-3). */ |
| 1207 | |
| 1208 | #define ENCODE_SHIFT_IN \ |
| 1209 | do { \ |
| 1210 | *dst++ = ISO_CODE_SI; \ |
| 1211 | CODING_SPEC_ISO_INVOCATION (coding, 0) = 0; \ |
| 1212 | } while (0) |
| 1213 | |
| 1214 | #define ENCODE_SHIFT_OUT \ |
| 1215 | do { \ |
| 1216 | *dst++ = ISO_CODE_SO; \ |
| 1217 | CODING_SPEC_ISO_INVOCATION (coding, 0) = 1; \ |
| 1218 | } while (0) |
| 1219 | |
| 1220 | #define ENCODE_LOCKING_SHIFT_2 \ |
| 1221 | do { \ |
| 1222 | *dst++ = ISO_CODE_ESC, *dst++ = 'n'; \ |
| 1223 | CODING_SPEC_ISO_INVOCATION (coding, 0) = 2; \ |
| 1224 | } while (0) |
| 1225 | |
| 1226 | #define ENCODE_LOCKING_SHIFT_3 \ |
| 1227 | do { \ |
| 1228 | *dst++ = ISO_CODE_ESC, *dst++ = 'o'; \ |
| 1229 | CODING_SPEC_ISO_INVOCATION (coding, 0) = 3; \ |
| 1230 | } while (0) |
| 1231 | |
| 1232 | /* Produce codes for a DIMENSION1 character whose character set is |
| 1233 | CHARSET and whose position-code is C1. Designation and invocation |
| 1234 | sequences are also produced in advance if necessary. */ |
| 1235 | |
| 1236 | |
| 1237 | #define ENCODE_ISO_CHARACTER_DIMENSION1(charset, c1) \ |
| 1238 | do { \ |
| 1239 | if (CODING_SPEC_ISO_SINGLE_SHIFTING (coding)) \ |
| 1240 | { \ |
| 1241 | if (coding->flags & CODING_FLAG_ISO_SEVEN_BITS) \ |
| 1242 | *dst++ = c1 & 0x7F; \ |
| 1243 | else \ |
| 1244 | *dst++ = c1 | 0x80; \ |
| 1245 | CODING_SPEC_ISO_SINGLE_SHIFTING (coding) = 0; \ |
| 1246 | break; \ |
| 1247 | } \ |
| 1248 | else if (charset == CODING_SPEC_ISO_PLANE_CHARSET (coding, 0)) \ |
| 1249 | { \ |
| 1250 | *dst++ = c1 & 0x7F; \ |
| 1251 | break; \ |
| 1252 | } \ |
| 1253 | else if (charset == CODING_SPEC_ISO_PLANE_CHARSET (coding, 1)) \ |
| 1254 | { \ |
| 1255 | *dst++ = c1 | 0x80; \ |
| 1256 | break; \ |
| 1257 | } \ |
| 1258 | else if (coding->flags & CODING_FLAG_ISO_SAFE \ |
| 1259 | && !coding->safe_charsets[charset]) \ |
| 1260 | { \ |
| 1261 | /* We should not encode this character, instead produce one or \ |
| 1262 | two `?'s. */ \ |
| 1263 | *dst++ = CODING_INHIBIT_CHARACTER_SUBSTITUTION; \ |
| 1264 | if (CHARSET_WIDTH (charset) == 2) \ |
| 1265 | *dst++ = CODING_INHIBIT_CHARACTER_SUBSTITUTION; \ |
| 1266 | break; \ |
| 1267 | } \ |
| 1268 | else \ |
| 1269 | /* Since CHARSET is not yet invoked to any graphic planes, we \ |
| 1270 | must invoke it, or, at first, designate it to some graphic \ |
| 1271 | register. Then repeat the loop to actually produce the \ |
| 1272 | character. */ \ |
| 1273 | dst = encode_invocation_designation (charset, coding, dst); \ |
| 1274 | } while (1) |
| 1275 | |
| 1276 | /* Produce codes for a DIMENSION2 character whose character set is |
| 1277 | CHARSET and whose position-codes are C1 and C2. Designation and |
| 1278 | invocation codes are also produced in advance if necessary. */ |
| 1279 | |
| 1280 | #define ENCODE_ISO_CHARACTER_DIMENSION2(charset, c1, c2) \ |
| 1281 | do { \ |
| 1282 | if (CODING_SPEC_ISO_SINGLE_SHIFTING (coding)) \ |
| 1283 | { \ |
| 1284 | if (coding->flags & CODING_FLAG_ISO_SEVEN_BITS) \ |
| 1285 | *dst++ = c1 & 0x7F, *dst++ = c2 & 0x7F; \ |
| 1286 | else \ |
| 1287 | *dst++ = c1 | 0x80, *dst++ = c2 | 0x80; \ |
| 1288 | CODING_SPEC_ISO_SINGLE_SHIFTING (coding) = 0; \ |
| 1289 | break; \ |
| 1290 | } \ |
| 1291 | else if (charset == CODING_SPEC_ISO_PLANE_CHARSET (coding, 0)) \ |
| 1292 | { \ |
| 1293 | *dst++ = c1 & 0x7F, *dst++= c2 & 0x7F; \ |
| 1294 | break; \ |
| 1295 | } \ |
| 1296 | else if (charset == CODING_SPEC_ISO_PLANE_CHARSET (coding, 1)) \ |
| 1297 | { \ |
| 1298 | *dst++ = c1 | 0x80, *dst++= c2 | 0x80; \ |
| 1299 | break; \ |
| 1300 | } \ |
| 1301 | else if (coding->flags & CODING_FLAG_ISO_SAFE \ |
| 1302 | && !coding->safe_charsets[charset]) \ |
| 1303 | { \ |
| 1304 | /* We should not encode this character, instead produce one or \ |
| 1305 | two `?'s. */ \ |
| 1306 | *dst++ = CODING_INHIBIT_CHARACTER_SUBSTITUTION; \ |
| 1307 | if (CHARSET_WIDTH (charset) == 2) \ |
| 1308 | *dst++ = CODING_INHIBIT_CHARACTER_SUBSTITUTION; \ |
| 1309 | break; \ |
| 1310 | } \ |
| 1311 | else \ |
| 1312 | /* Since CHARSET is not yet invoked to any graphic planes, we \ |
| 1313 | must invoke it, or, at first, designate it to some graphic \ |
| 1314 | register. Then repeat the loop to actually produce the \ |
| 1315 | character. */ \ |
| 1316 | dst = encode_invocation_designation (charset, coding, dst); \ |
| 1317 | } while (1) |
| 1318 | |
| 1319 | #define ENCODE_ISO_CHARACTER(charset, c1, c2) \ |
| 1320 | do { \ |
| 1321 | int c_alt, charset_alt; \ |
| 1322 | if (!NILP (unification_table) \ |
| 1323 | && ((c_alt = unify_char (unification_table, -1, charset, c1, c2)) \ |
| 1324 | >= 0)) \ |
| 1325 | SPLIT_CHAR (c_alt, charset_alt, c1, c2); \ |
| 1326 | else \ |
| 1327 | charset_alt = charset; \ |
| 1328 | if (CHARSET_DIMENSION (charset_alt) == 1) \ |
| 1329 | ENCODE_ISO_CHARACTER_DIMENSION1 (charset_alt, c1); \ |
| 1330 | else \ |
| 1331 | ENCODE_ISO_CHARACTER_DIMENSION2 (charset_alt, c1, c2); \ |
| 1332 | } while (0) |
| 1333 | |
| 1334 | /* Produce designation and invocation codes at a place pointed by DST |
| 1335 | to use CHARSET. The element `spec.iso2022' of *CODING is updated. |
| 1336 | Return new DST. */ |
| 1337 | |
| 1338 | unsigned char * |
| 1339 | encode_invocation_designation (charset, coding, dst) |
| 1340 | int charset; |
| 1341 | struct coding_system *coding; |
| 1342 | unsigned char *dst; |
| 1343 | { |
| 1344 | int reg; /* graphic register number */ |
| 1345 | |
| 1346 | /* At first, check designations. */ |
| 1347 | for (reg = 0; reg < 4; reg++) |
| 1348 | if (charset == CODING_SPEC_ISO_DESIGNATION (coding, reg)) |
| 1349 | break; |
| 1350 | |
| 1351 | if (reg >= 4) |
| 1352 | { |
| 1353 | /* CHARSET is not yet designated to any graphic registers. */ |
| 1354 | /* At first check the requested designation. */ |
| 1355 | reg = CODING_SPEC_ISO_REQUESTED_DESIGNATION (coding, charset); |
| 1356 | if (reg == CODING_SPEC_ISO_NO_REQUESTED_DESIGNATION) |
| 1357 | /* Since CHARSET requests no special designation, designate it |
| 1358 | to graphic register 0. */ |
| 1359 | reg = 0; |
| 1360 | |
| 1361 | ENCODE_DESIGNATION (charset, reg, coding); |
| 1362 | } |
| 1363 | |
| 1364 | if (CODING_SPEC_ISO_INVOCATION (coding, 0) != reg |
| 1365 | && CODING_SPEC_ISO_INVOCATION (coding, 1) != reg) |
| 1366 | { |
| 1367 | /* Since the graphic register REG is not invoked to any graphic |
| 1368 | planes, invoke it to graphic plane 0. */ |
| 1369 | switch (reg) |
| 1370 | { |
| 1371 | case 0: /* graphic register 0 */ |
| 1372 | ENCODE_SHIFT_IN; |
| 1373 | break; |
| 1374 | |
| 1375 | case 1: /* graphic register 1 */ |
| 1376 | ENCODE_SHIFT_OUT; |
| 1377 | break; |
| 1378 | |
| 1379 | case 2: /* graphic register 2 */ |
| 1380 | if (coding->flags & CODING_FLAG_ISO_SINGLE_SHIFT) |
| 1381 | ENCODE_SINGLE_SHIFT_2; |
| 1382 | else |
| 1383 | ENCODE_LOCKING_SHIFT_2; |
| 1384 | break; |
| 1385 | |
| 1386 | case 3: /* graphic register 3 */ |
| 1387 | if (coding->flags & CODING_FLAG_ISO_SINGLE_SHIFT) |
| 1388 | ENCODE_SINGLE_SHIFT_3; |
| 1389 | else |
| 1390 | ENCODE_LOCKING_SHIFT_3; |
| 1391 | break; |
| 1392 | } |
| 1393 | } |
| 1394 | return dst; |
| 1395 | } |
| 1396 | |
| 1397 | /* The following two macros produce codes for indicating composition. */ |
| 1398 | #define ENCODE_COMPOSITION_NO_RULE_START *dst++ = ISO_CODE_ESC, *dst++ = '0' |
| 1399 | #define ENCODE_COMPOSITION_WITH_RULE_START *dst++ = ISO_CODE_ESC, *dst++ = '2' |
| 1400 | #define ENCODE_COMPOSITION_END *dst++ = ISO_CODE_ESC, *dst++ = '1' |
| 1401 | |
| 1402 | /* The following three macros produce codes for indicating direction |
| 1403 | of text. */ |
| 1404 | #define ENCODE_CONTROL_SEQUENCE_INTRODUCER \ |
| 1405 | do { \ |
| 1406 | if (coding->flags == CODING_FLAG_ISO_SEVEN_BITS) \ |
| 1407 | *dst++ = ISO_CODE_ESC, *dst++ = '['; \ |
| 1408 | else \ |
| 1409 | *dst++ = ISO_CODE_CSI; \ |
| 1410 | } while (0) |
| 1411 | |
| 1412 | #define ENCODE_DIRECTION_R2L \ |
| 1413 | ENCODE_CONTROL_SEQUENCE_INTRODUCER, *dst++ = '2', *dst++ = ']' |
| 1414 | |
| 1415 | #define ENCODE_DIRECTION_L2R \ |
| 1416 | ENCODE_CONTROL_SEQUENCE_INTRODUCER, *dst++ = '0', *dst++ = ']' |
| 1417 | |
| 1418 | /* Produce codes for designation and invocation to reset the graphic |
| 1419 | planes and registers to initial state. */ |
| 1420 | #define ENCODE_RESET_PLANE_AND_REGISTER \ |
| 1421 | do { \ |
| 1422 | int reg; \ |
| 1423 | if (CODING_SPEC_ISO_INVOCATION (coding, 0) != 0) \ |
| 1424 | ENCODE_SHIFT_IN; \ |
| 1425 | for (reg = 0; reg < 4; reg++) \ |
| 1426 | if (CODING_SPEC_ISO_INITIAL_DESIGNATION (coding, reg) >= 0 \ |
| 1427 | && (CODING_SPEC_ISO_DESIGNATION (coding, reg) \ |
| 1428 | != CODING_SPEC_ISO_INITIAL_DESIGNATION (coding, reg))) \ |
| 1429 | ENCODE_DESIGNATION \ |
| 1430 | (CODING_SPEC_ISO_INITIAL_DESIGNATION (coding, reg), reg, coding); \ |
| 1431 | } while (0) |
| 1432 | |
| 1433 | /* Produce designation sequences of charsets in the line started from |
| 1434 | *SRC to a place pointed by DSTP. |
| 1435 | |
| 1436 | If the current block ends before any end-of-line, we may fail to |
| 1437 | find all the necessary *designations. */ |
| 1438 | encode_designation_at_bol (coding, table, src, src_end, dstp) |
| 1439 | struct coding_system *coding; |
| 1440 | Lisp_Object table; |
| 1441 | unsigned char *src, *src_end, **dstp; |
| 1442 | { |
| 1443 | int charset, c, found = 0, reg; |
| 1444 | /* Table of charsets to be designated to each graphic register. */ |
| 1445 | int r[4]; |
| 1446 | unsigned char *dst = *dstp; |
| 1447 | |
| 1448 | for (reg = 0; reg < 4; reg++) |
| 1449 | r[reg] = -1; |
| 1450 | |
| 1451 | while (src < src_end && *src != '\n' && found < 4) |
| 1452 | { |
| 1453 | int bytes = BYTES_BY_CHAR_HEAD (*src); |
| 1454 | |
| 1455 | if (NILP (table)) |
| 1456 | charset = CHARSET_AT (src); |
| 1457 | else |
| 1458 | { |
| 1459 | int c_alt; |
| 1460 | unsigned char c1, c2; |
| 1461 | |
| 1462 | SPLIT_STRING(src, bytes, charset, c1, c2); |
| 1463 | if ((c_alt = unify_char (table, -1, charset, c1, c2)) >= 0) |
| 1464 | charset = CHAR_CHARSET (c_alt); |
| 1465 | } |
| 1466 | |
| 1467 | reg = CODING_SPEC_ISO_REQUESTED_DESIGNATION (coding, charset); |
| 1468 | if (r[reg] < 0) |
| 1469 | { |
| 1470 | found++; |
| 1471 | r[reg] = charset; |
| 1472 | } |
| 1473 | |
| 1474 | src += bytes; |
| 1475 | } |
| 1476 | |
| 1477 | if (found) |
| 1478 | { |
| 1479 | for (reg = 0; reg < 4; reg++) |
| 1480 | if (r[reg] >= 0 |
| 1481 | && CODING_SPEC_ISO_DESIGNATION (coding, reg) != r[reg]) |
| 1482 | ENCODE_DESIGNATION (r[reg], reg, coding); |
| 1483 | *dstp = dst; |
| 1484 | } |
| 1485 | } |
| 1486 | |
| 1487 | /* See the above "GENERAL NOTES on `encode_coding_XXX ()' functions". */ |
| 1488 | |
| 1489 | int |
| 1490 | encode_coding_iso2022 (coding, source, destination, |
| 1491 | src_bytes, dst_bytes, consumed) |
| 1492 | struct coding_system *coding; |
| 1493 | unsigned char *source, *destination; |
| 1494 | int src_bytes, dst_bytes; |
| 1495 | int *consumed; |
| 1496 | { |
| 1497 | unsigned char *src = source; |
| 1498 | unsigned char *src_end = source + src_bytes; |
| 1499 | unsigned char *dst = destination; |
| 1500 | unsigned char *dst_end = destination + dst_bytes; |
| 1501 | /* Since the maximum bytes produced by each loop is 20, we subtract 19 |
| 1502 | from DST_END to assure overflow checking is necessary only at the |
| 1503 | head of loop. */ |
| 1504 | unsigned char *adjusted_dst_end = dst_end - 19; |
| 1505 | Lisp_Object unification_table |
| 1506 | = coding->character_unification_table_for_encode; |
| 1507 | |
| 1508 | if (!NILP (Venable_character_unification) && NILP (unification_table)) |
| 1509 | unification_table = Vstandard_character_unification_table_for_encode; |
| 1510 | |
| 1511 | while (src < src_end && dst < adjusted_dst_end) |
| 1512 | { |
| 1513 | /* SRC_BASE remembers the start position in source in each loop. |
| 1514 | The loop will be exited when there's not enough source text |
| 1515 | to analyze multi-byte codes (within macros ONE_MORE_BYTE, |
| 1516 | TWO_MORE_BYTES, and THREE_MORE_BYTES). In that case, SRC is |
| 1517 | reset to SRC_BASE before exiting. */ |
| 1518 | unsigned char *src_base = src; |
| 1519 | int charset, c1, c2, c3, c4; |
| 1520 | |
| 1521 | if (coding->flags & CODING_FLAG_ISO_DESIGNATE_AT_BOL |
| 1522 | && CODING_SPEC_ISO_BOL (coding)) |
| 1523 | { |
| 1524 | /* We have to produce designation sequences if any now. */ |
| 1525 | encode_designation_at_bol (coding, unification_table, |
| 1526 | src, src_end, &dst); |
| 1527 | CODING_SPEC_ISO_BOL (coding) = 0; |
| 1528 | } |
| 1529 | |
| 1530 | c1 = *src++; |
| 1531 | /* If we are seeing a component of a composite character, we are |
| 1532 | seeing a leading-code specially encoded for composition, or a |
| 1533 | composition rule if composing with rule. We must set C1 |
| 1534 | to a normal leading-code or an ASCII code. If we are not at |
| 1535 | a composed character, we must reset the composition state. */ |
| 1536 | if (COMPOSING_P (coding->composing)) |
| 1537 | { |
| 1538 | if (c1 < 0xA0) |
| 1539 | { |
| 1540 | /* We are not in a composite character any longer. */ |
| 1541 | coding->composing = COMPOSING_NO; |
| 1542 | ENCODE_COMPOSITION_END; |
| 1543 | } |
| 1544 | else |
| 1545 | { |
| 1546 | if (coding->composing == COMPOSING_WITH_RULE_RULE) |
| 1547 | { |
| 1548 | *dst++ = c1 & 0x7F; |
| 1549 | coding->composing = COMPOSING_WITH_RULE_HEAD; |
| 1550 | continue; |
| 1551 | } |
| 1552 | else if (coding->composing == COMPOSING_WITH_RULE_HEAD) |
| 1553 | coding->composing = COMPOSING_WITH_RULE_RULE; |
| 1554 | if (c1 == 0xA0) |
| 1555 | { |
| 1556 | /* This is an ASCII component. */ |
| 1557 | ONE_MORE_BYTE (c1); |
| 1558 | c1 &= 0x7F; |
| 1559 | } |
| 1560 | else |
| 1561 | /* This is a leading-code of non ASCII component. */ |
| 1562 | c1 -= 0x20; |
| 1563 | } |
| 1564 | } |
| 1565 | |
| 1566 | /* Now encode one character. C1 is a control character, an |
| 1567 | ASCII character, or a leading-code of multi-byte character. */ |
| 1568 | switch (emacs_code_class[c1]) |
| 1569 | { |
| 1570 | case EMACS_ascii_code: |
| 1571 | ENCODE_ISO_CHARACTER (CHARSET_ASCII, c1, /* dummy */ c2); |
| 1572 | break; |
| 1573 | |
| 1574 | case EMACS_control_code: |
| 1575 | if (coding->flags & CODING_FLAG_ISO_RESET_AT_CNTL) |
| 1576 | ENCODE_RESET_PLANE_AND_REGISTER; |
| 1577 | *dst++ = c1; |
| 1578 | break; |
| 1579 | |
| 1580 | case EMACS_carriage_return_code: |
| 1581 | if (!coding->selective) |
| 1582 | { |
| 1583 | if (coding->flags & CODING_FLAG_ISO_RESET_AT_CNTL) |
| 1584 | ENCODE_RESET_PLANE_AND_REGISTER; |
| 1585 | *dst++ = c1; |
| 1586 | break; |
| 1587 | } |
| 1588 | /* fall down to treat '\r' as '\n' ... */ |
| 1589 | |
| 1590 | case EMACS_linefeed_code: |
| 1591 | if (coding->flags & CODING_FLAG_ISO_RESET_AT_EOL) |
| 1592 | ENCODE_RESET_PLANE_AND_REGISTER; |
| 1593 | if (coding->flags & CODING_FLAG_ISO_INIT_AT_BOL) |
| 1594 | bcopy (coding->spec.iso2022.initial_designation, |
| 1595 | coding->spec.iso2022.current_designation, |
| 1596 | sizeof coding->spec.iso2022.initial_designation); |
| 1597 | if (coding->eol_type == CODING_EOL_LF |
| 1598 | || coding->eol_type == CODING_EOL_UNDECIDED) |
| 1599 | *dst++ = ISO_CODE_LF; |
| 1600 | else if (coding->eol_type == CODING_EOL_CRLF) |
| 1601 | *dst++ = ISO_CODE_CR, *dst++ = ISO_CODE_LF; |
| 1602 | else |
| 1603 | *dst++ = ISO_CODE_CR; |
| 1604 | CODING_SPEC_ISO_BOL (coding) = 1; |
| 1605 | break; |
| 1606 | |
| 1607 | case EMACS_leading_code_2: |
| 1608 | ONE_MORE_BYTE (c2); |
| 1609 | if (c2 < 0xA0) |
| 1610 | { |
| 1611 | /* invalid sequence */ |
| 1612 | *dst++ = c1; |
| 1613 | *dst++ = c2; |
| 1614 | } |
| 1615 | else |
| 1616 | ENCODE_ISO_CHARACTER (c1, c2, /* dummy */ c3); |
| 1617 | break; |
| 1618 | |
| 1619 | case EMACS_leading_code_3: |
| 1620 | TWO_MORE_BYTES (c2, c3); |
| 1621 | if (c2 < 0xA0 || c3 < 0xA0) |
| 1622 | { |
| 1623 | /* invalid sequence */ |
| 1624 | *dst++ = c1; |
| 1625 | *dst++ = c2; |
| 1626 | *dst++ = c3; |
| 1627 | } |
| 1628 | else if (c1 < LEADING_CODE_PRIVATE_11) |
| 1629 | ENCODE_ISO_CHARACTER (c1, c2, c3); |
| 1630 | else |
| 1631 | ENCODE_ISO_CHARACTER (c2, c3, /* dummy */ c4); |
| 1632 | break; |
| 1633 | |
| 1634 | case EMACS_leading_code_4: |
| 1635 | THREE_MORE_BYTES (c2, c3, c4); |
| 1636 | if (c2 < 0xA0 || c3 < 0xA0 || c4 < 0xA0) |
| 1637 | { |
| 1638 | /* invalid sequence */ |
| 1639 | *dst++ = c1; |
| 1640 | *dst++ = c2; |
| 1641 | *dst++ = c3; |
| 1642 | *dst++ = c4; |
| 1643 | } |
| 1644 | else |
| 1645 | ENCODE_ISO_CHARACTER (c2, c3, c4); |
| 1646 | break; |
| 1647 | |
| 1648 | case EMACS_leading_code_composition: |
| 1649 | ONE_MORE_BYTE (c2); |
| 1650 | if (c2 < 0xA0) |
| 1651 | { |
| 1652 | /* invalid sequence */ |
| 1653 | *dst++ = c1; |
| 1654 | *dst++ = c2; |
| 1655 | } |
| 1656 | else if (c2 == 0xFF) |
| 1657 | { |
| 1658 | coding->composing = COMPOSING_WITH_RULE_HEAD; |
| 1659 | ENCODE_COMPOSITION_WITH_RULE_START; |
| 1660 | } |
| 1661 | else |
| 1662 | { |
| 1663 | /* Rewind one byte because it is a character code of |
| 1664 | composition elements. */ |
| 1665 | src--; |
| 1666 | coding->composing = COMPOSING_NO_RULE_HEAD; |
| 1667 | ENCODE_COMPOSITION_NO_RULE_START; |
| 1668 | } |
| 1669 | break; |
| 1670 | |
| 1671 | case EMACS_invalid_code: |
| 1672 | *dst++ = c1; |
| 1673 | break; |
| 1674 | } |
| 1675 | continue; |
| 1676 | label_end_of_loop: |
| 1677 | /* We reach here because the source date ends not at character |
| 1678 | boundary. */ |
| 1679 | coding->carryover_size = src_end - src_base; |
| 1680 | bcopy (src_base, coding->carryover, coding->carryover_size); |
| 1681 | src = src_end; |
| 1682 | break; |
| 1683 | } |
| 1684 | |
| 1685 | /* If this is the last block of the text to be encoded, we must |
| 1686 | reset graphic planes and registers to the initial state. */ |
| 1687 | if (src >= src_end && coding->last_block) |
| 1688 | { |
| 1689 | ENCODE_RESET_PLANE_AND_REGISTER; |
| 1690 | if (coding->carryover_size > 0 |
| 1691 | && coding->carryover_size < (dst_end - dst)) |
| 1692 | { |
| 1693 | bcopy (coding->carryover, dst, coding->carryover_size); |
| 1694 | dst += coding->carryover_size; |
| 1695 | coding->carryover_size = 0; |
| 1696 | } |
| 1697 | } |
| 1698 | *consumed = src - source; |
| 1699 | return dst - destination; |
| 1700 | } |
| 1701 | |
| 1702 | \f |
| 1703 | /*** 4. SJIS and BIG5 handlers ***/ |
| 1704 | |
| 1705 | /* Although SJIS and BIG5 are not ISO's coding system, they are used |
| 1706 | quite widely. So, for the moment, Emacs supports them in the bare |
| 1707 | C code. But, in the future, they may be supported only by CCL. */ |
| 1708 | |
| 1709 | /* SJIS is a coding system encoding three character sets: ASCII, right |
| 1710 | half of JISX0201-Kana, and JISX0208. An ASCII character is encoded |
| 1711 | as is. A character of charset katakana-jisx0201 is encoded by |
| 1712 | "position-code + 0x80". A character of charset japanese-jisx0208 |
| 1713 | is encoded in 2-byte but two position-codes are divided and shifted |
| 1714 | so that it fit in the range below. |
| 1715 | |
| 1716 | --- CODE RANGE of SJIS --- |
| 1717 | (character set) (range) |
| 1718 | ASCII 0x00 .. 0x7F |
| 1719 | KATAKANA-JISX0201 0xA0 .. 0xDF |
| 1720 | JISX0208 (1st byte) 0x80 .. 0x9F and 0xE0 .. 0xFF |
| 1721 | (2nd byte) 0x40 .. 0xFF |
| 1722 | ------------------------------- |
| 1723 | |
| 1724 | */ |
| 1725 | |
| 1726 | /* BIG5 is a coding system encoding two character sets: ASCII and |
| 1727 | Big5. An ASCII character is encoded as is. Big5 is a two-byte |
| 1728 | character set and is encoded in two-byte. |
| 1729 | |
| 1730 | --- CODE RANGE of BIG5 --- |
| 1731 | (character set) (range) |
| 1732 | ASCII 0x00 .. 0x7F |
| 1733 | Big5 (1st byte) 0xA1 .. 0xFE |
| 1734 | (2nd byte) 0x40 .. 0x7E and 0xA1 .. 0xFE |
| 1735 | -------------------------- |
| 1736 | |
| 1737 | Since the number of characters in Big5 is larger than maximum |
| 1738 | characters in Emacs' charset (96x96), it can't be handled as one |
| 1739 | charset. So, in Emacs, Big5 is divided into two: `charset-big5-1' |
| 1740 | and `charset-big5-2'. Both are DIMENSION2 and CHARS94. The former |
| 1741 | contains frequently used characters and the latter contains less |
| 1742 | frequently used characters. */ |
| 1743 | |
| 1744 | /* Macros to decode or encode a character of Big5 in BIG5. B1 and B2 |
| 1745 | are the 1st and 2nd position-codes of Big5 in BIG5 coding system. |
| 1746 | C1 and C2 are the 1st and 2nd position-codes of of Emacs' internal |
| 1747 | format. CHARSET is `charset_big5_1' or `charset_big5_2'. */ |
| 1748 | |
| 1749 | /* Number of Big5 characters which have the same code in 1st byte. */ |
| 1750 | #define BIG5_SAME_ROW (0xFF - 0xA1 + 0x7F - 0x40) |
| 1751 | |
| 1752 | #define DECODE_BIG5(b1, b2, charset, c1, c2) \ |
| 1753 | do { \ |
| 1754 | unsigned int temp \ |
| 1755 | = (b1 - 0xA1) * BIG5_SAME_ROW + b2 - (b2 < 0x7F ? 0x40 : 0x62); \ |
| 1756 | if (b1 < 0xC9) \ |
| 1757 | charset = charset_big5_1; \ |
| 1758 | else \ |
| 1759 | { \ |
| 1760 | charset = charset_big5_2; \ |
| 1761 | temp -= (0xC9 - 0xA1) * BIG5_SAME_ROW; \ |
| 1762 | } \ |
| 1763 | c1 = temp / (0xFF - 0xA1) + 0x21; \ |
| 1764 | c2 = temp % (0xFF - 0xA1) + 0x21; \ |
| 1765 | } while (0) |
| 1766 | |
| 1767 | #define ENCODE_BIG5(charset, c1, c2, b1, b2) \ |
| 1768 | do { \ |
| 1769 | unsigned int temp = (c1 - 0x21) * (0xFF - 0xA1) + (c2 - 0x21); \ |
| 1770 | if (charset == charset_big5_2) \ |
| 1771 | temp += BIG5_SAME_ROW * (0xC9 - 0xA1); \ |
| 1772 | b1 = temp / BIG5_SAME_ROW + 0xA1; \ |
| 1773 | b2 = temp % BIG5_SAME_ROW; \ |
| 1774 | b2 += b2 < 0x3F ? 0x40 : 0x62; \ |
| 1775 | } while (0) |
| 1776 | |
| 1777 | #define DECODE_SJIS_BIG5_CHARACTER(charset, c1, c2) \ |
| 1778 | do { \ |
| 1779 | int c_alt, charset_alt = (charset); \ |
| 1780 | if (!NILP (unification_table) \ |
| 1781 | && ((c_alt = unify_char (unification_table, \ |
| 1782 | -1, (charset), c1, c2)) >= 0)) \ |
| 1783 | SPLIT_CHAR (c_alt, charset_alt, c1, c2); \ |
| 1784 | if (charset_alt == CHARSET_ASCII || charset_alt < 0) \ |
| 1785 | DECODE_CHARACTER_ASCII (c1); \ |
| 1786 | else if (CHARSET_DIMENSION (charset_alt) == 1) \ |
| 1787 | DECODE_CHARACTER_DIMENSION1 (charset_alt, c1); \ |
| 1788 | else \ |
| 1789 | DECODE_CHARACTER_DIMENSION2 (charset_alt, c1, c2); \ |
| 1790 | } while (0) |
| 1791 | |
| 1792 | #define ENCODE_SJIS_BIG5_CHARACTER(charset, c1, c2) \ |
| 1793 | do { \ |
| 1794 | int c_alt, charset_alt; \ |
| 1795 | if (!NILP (unification_table) \ |
| 1796 | && ((c_alt = unify_char (unification_table, -1, charset, c1, c2)) \ |
| 1797 | >= 0)) \ |
| 1798 | SPLIT_CHAR (c_alt, charset_alt, c1, c2); \ |
| 1799 | else \ |
| 1800 | charset_alt = charset; \ |
| 1801 | if (charset_alt == charset_ascii) \ |
| 1802 | *dst++ = c1; \ |
| 1803 | else if (CHARSET_DIMENSION (charset_alt) == 1) \ |
| 1804 | { \ |
| 1805 | if (sjis_p && charset_alt == charset_katakana_jisx0201) \ |
| 1806 | *dst++ = c1; \ |
| 1807 | else \ |
| 1808 | *dst++ = charset_alt, *dst++ = c1; \ |
| 1809 | } \ |
| 1810 | else \ |
| 1811 | { \ |
| 1812 | c1 &= 0x7F, c2 &= 0x7F; \ |
| 1813 | if (sjis_p && charset_alt == charset_jisx0208) \ |
| 1814 | { \ |
| 1815 | unsigned char s1, s2; \ |
| 1816 | \ |
| 1817 | ENCODE_SJIS (c1, c2, s1, s2); \ |
| 1818 | *dst++ = s1, *dst++ = s2; \ |
| 1819 | } \ |
| 1820 | else if (!sjis_p \ |
| 1821 | && (charset_alt == charset_big5_1 \ |
| 1822 | || charset_alt == charset_big5_2)) \ |
| 1823 | { \ |
| 1824 | unsigned char b1, b2; \ |
| 1825 | \ |
| 1826 | ENCODE_BIG5 (charset_alt, c1, c2, b1, b2); \ |
| 1827 | *dst++ = b1, *dst++ = b2; \ |
| 1828 | } \ |
| 1829 | else \ |
| 1830 | *dst++ = charset_alt, *dst++ = c1, *dst++ = c2; \ |
| 1831 | } \ |
| 1832 | } while (0); |
| 1833 | |
| 1834 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". |
| 1835 | Check if a text is encoded in SJIS. If it is, return |
| 1836 | CODING_CATEGORY_MASK_SJIS, else return 0. */ |
| 1837 | |
| 1838 | int |
| 1839 | detect_coding_sjis (src, src_end) |
| 1840 | unsigned char *src, *src_end; |
| 1841 | { |
| 1842 | unsigned char c; |
| 1843 | |
| 1844 | while (src < src_end) |
| 1845 | { |
| 1846 | c = *src++; |
| 1847 | if (c == ISO_CODE_ESC || c == ISO_CODE_SI || c == ISO_CODE_SO) |
| 1848 | return 0; |
| 1849 | if ((c >= 0x80 && c < 0xA0) || c >= 0xE0) |
| 1850 | { |
| 1851 | if (src < src_end && *src++ < 0x40) |
| 1852 | return 0; |
| 1853 | } |
| 1854 | } |
| 1855 | return CODING_CATEGORY_MASK_SJIS; |
| 1856 | } |
| 1857 | |
| 1858 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". |
| 1859 | Check if a text is encoded in BIG5. If it is, return |
| 1860 | CODING_CATEGORY_MASK_BIG5, else return 0. */ |
| 1861 | |
| 1862 | int |
| 1863 | detect_coding_big5 (src, src_end) |
| 1864 | unsigned char *src, *src_end; |
| 1865 | { |
| 1866 | unsigned char c; |
| 1867 | |
| 1868 | while (src < src_end) |
| 1869 | { |
| 1870 | c = *src++; |
| 1871 | if (c == ISO_CODE_ESC || c == ISO_CODE_SI || c == ISO_CODE_SO) |
| 1872 | return 0; |
| 1873 | if (c >= 0xA1) |
| 1874 | { |
| 1875 | if (src >= src_end) |
| 1876 | break; |
| 1877 | c = *src++; |
| 1878 | if (c < 0x40 || (c >= 0x7F && c <= 0xA0)) |
| 1879 | return 0; |
| 1880 | } |
| 1881 | } |
| 1882 | return CODING_CATEGORY_MASK_BIG5; |
| 1883 | } |
| 1884 | |
| 1885 | /* See the above "GENERAL NOTES on `decode_coding_XXX ()' functions". |
| 1886 | If SJIS_P is 1, decode SJIS text, else decode BIG5 test. */ |
| 1887 | |
| 1888 | int |
| 1889 | decode_coding_sjis_big5 (coding, source, destination, |
| 1890 | src_bytes, dst_bytes, consumed, sjis_p) |
| 1891 | struct coding_system *coding; |
| 1892 | unsigned char *source, *destination; |
| 1893 | int src_bytes, dst_bytes; |
| 1894 | int *consumed; |
| 1895 | int sjis_p; |
| 1896 | { |
| 1897 | unsigned char *src = source; |
| 1898 | unsigned char *src_end = source + src_bytes; |
| 1899 | unsigned char *dst = destination; |
| 1900 | unsigned char *dst_end = destination + dst_bytes; |
| 1901 | /* Since the maximum bytes produced by each loop is 4, we subtract 3 |
| 1902 | from DST_END to assure overflow checking is necessary only at the |
| 1903 | head of loop. */ |
| 1904 | unsigned char *adjusted_dst_end = dst_end - 3; |
| 1905 | Lisp_Object unification_table |
| 1906 | = coding->character_unification_table_for_decode; |
| 1907 | |
| 1908 | if (!NILP (Venable_character_unification) && NILP (unification_table)) |
| 1909 | unification_table = Vstandard_character_unification_table_for_decode; |
| 1910 | |
| 1911 | while (src < src_end && dst < adjusted_dst_end) |
| 1912 | { |
| 1913 | /* SRC_BASE remembers the start position in source in each loop. |
| 1914 | The loop will be exited when there's not enough source text |
| 1915 | to analyze two-byte character (within macro ONE_MORE_BYTE). |
| 1916 | In that case, SRC is reset to SRC_BASE before exiting. */ |
| 1917 | unsigned char *src_base = src; |
| 1918 | unsigned char c1 = *src++, c2, c3, c4; |
| 1919 | |
| 1920 | if (c1 == '\r') |
| 1921 | { |
| 1922 | if (coding->eol_type == CODING_EOL_CRLF) |
| 1923 | { |
| 1924 | ONE_MORE_BYTE (c2); |
| 1925 | if (c2 == '\n') |
| 1926 | *dst++ = c2; |
| 1927 | else |
| 1928 | /* To process C2 again, SRC is subtracted by 1. */ |
| 1929 | *dst++ = c1, src--; |
| 1930 | } |
| 1931 | else if (coding->eol_type == CODING_EOL_CR) |
| 1932 | *dst++ = '\n'; |
| 1933 | else |
| 1934 | *dst++ = c1; |
| 1935 | } |
| 1936 | else if (c1 < 0x20) |
| 1937 | *dst++ = c1; |
| 1938 | else if (c1 < 0x80) |
| 1939 | DECODE_SJIS_BIG5_CHARACTER (charset_ascii, c1, /* dummy */ c2); |
| 1940 | else if (c1 < 0xA0 || c1 >= 0xE0) |
| 1941 | { |
| 1942 | /* SJIS -> JISX0208, BIG5 -> Big5 (only if 0xE0 <= c1 < 0xFF) */ |
| 1943 | if (sjis_p) |
| 1944 | { |
| 1945 | ONE_MORE_BYTE (c2); |
| 1946 | DECODE_SJIS (c1, c2, c3, c4); |
| 1947 | DECODE_SJIS_BIG5_CHARACTER (charset_jisx0208, c3, c4); |
| 1948 | } |
| 1949 | else if (c1 >= 0xE0 && c1 < 0xFF) |
| 1950 | { |
| 1951 | int charset; |
| 1952 | |
| 1953 | ONE_MORE_BYTE (c2); |
| 1954 | DECODE_BIG5 (c1, c2, charset, c3, c4); |
| 1955 | DECODE_SJIS_BIG5_CHARACTER (charset, c3, c4); |
| 1956 | } |
| 1957 | else /* Invalid code */ |
| 1958 | *dst++ = c1; |
| 1959 | } |
| 1960 | else |
| 1961 | { |
| 1962 | /* SJIS -> JISX0201-Kana, BIG5 -> Big5 */ |
| 1963 | if (sjis_p) |
| 1964 | DECODE_SJIS_BIG5_CHARACTER (charset_katakana_jisx0201, c1, /* dummy */ c2); |
| 1965 | else |
| 1966 | { |
| 1967 | int charset; |
| 1968 | |
| 1969 | ONE_MORE_BYTE (c2); |
| 1970 | DECODE_BIG5 (c1, c2, charset, c3, c4); |
| 1971 | DECODE_SJIS_BIG5_CHARACTER (charset, c3, c4); |
| 1972 | } |
| 1973 | } |
| 1974 | continue; |
| 1975 | |
| 1976 | label_end_of_loop: |
| 1977 | coding->carryover_size = src - src_base; |
| 1978 | bcopy (src_base, coding->carryover, coding->carryover_size); |
| 1979 | src = src_base; |
| 1980 | break; |
| 1981 | } |
| 1982 | |
| 1983 | *consumed = src - source; |
| 1984 | return dst - destination; |
| 1985 | } |
| 1986 | |
| 1987 | /* See the above "GENERAL NOTES on `encode_coding_XXX ()' functions". |
| 1988 | This function can encode `charset_ascii', `charset_katakana_jisx0201', |
| 1989 | `charset_jisx0208', `charset_big5_1', and `charset_big5-2'. We are |
| 1990 | sure that all these charsets are registered as official charset |
| 1991 | (i.e. do not have extended leading-codes). Characters of other |
| 1992 | charsets are produced without any encoding. If SJIS_P is 1, encode |
| 1993 | SJIS text, else encode BIG5 text. */ |
| 1994 | |
| 1995 | int |
| 1996 | encode_coding_sjis_big5 (coding, source, destination, |
| 1997 | src_bytes, dst_bytes, consumed, sjis_p) |
| 1998 | struct coding_system *coding; |
| 1999 | unsigned char *source, *destination; |
| 2000 | int src_bytes, dst_bytes; |
| 2001 | int *consumed; |
| 2002 | int sjis_p; |
| 2003 | { |
| 2004 | unsigned char *src = source; |
| 2005 | unsigned char *src_end = source + src_bytes; |
| 2006 | unsigned char *dst = destination; |
| 2007 | unsigned char *dst_end = destination + dst_bytes; |
| 2008 | /* Since the maximum bytes produced by each loop is 2, we subtract 1 |
| 2009 | from DST_END to assure overflow checking is necessary only at the |
| 2010 | head of loop. */ |
| 2011 | unsigned char *adjusted_dst_end = dst_end - 1; |
| 2012 | Lisp_Object unification_table |
| 2013 | = coding->character_unification_table_for_encode; |
| 2014 | |
| 2015 | if (!NILP (Venable_character_unification) && NILP (unification_table)) |
| 2016 | unification_table = Vstandard_character_unification_table_for_encode; |
| 2017 | |
| 2018 | while (src < src_end && dst < adjusted_dst_end) |
| 2019 | { |
| 2020 | /* SRC_BASE remembers the start position in source in each loop. |
| 2021 | The loop will be exited when there's not enough source text |
| 2022 | to analyze multi-byte codes (within macros ONE_MORE_BYTE and |
| 2023 | TWO_MORE_BYTES). In that case, SRC is reset to SRC_BASE |
| 2024 | before exiting. */ |
| 2025 | unsigned char *src_base = src; |
| 2026 | unsigned char c1 = *src++, c2, c3, c4; |
| 2027 | |
| 2028 | if (coding->composing) |
| 2029 | { |
| 2030 | if (c1 == 0xA0) |
| 2031 | { |
| 2032 | ONE_MORE_BYTE (c1); |
| 2033 | c1 &= 0x7F; |
| 2034 | } |
| 2035 | else if (c1 >= 0xA0) |
| 2036 | c1 -= 0x20; |
| 2037 | else |
| 2038 | coding->composing = 0; |
| 2039 | } |
| 2040 | |
| 2041 | switch (emacs_code_class[c1]) |
| 2042 | { |
| 2043 | case EMACS_ascii_code: |
| 2044 | ENCODE_SJIS_BIG5_CHARACTER (charset_ascii, c1, /* dummy */ c2); |
| 2045 | break; |
| 2046 | |
| 2047 | case EMACS_control_code: |
| 2048 | *dst++ = c1; |
| 2049 | break; |
| 2050 | |
| 2051 | case EMACS_carriage_return_code: |
| 2052 | if (!coding->selective) |
| 2053 | { |
| 2054 | *dst++ = c1; |
| 2055 | break; |
| 2056 | } |
| 2057 | /* fall down to treat '\r' as '\n' ... */ |
| 2058 | |
| 2059 | case EMACS_linefeed_code: |
| 2060 | if (coding->eol_type == CODING_EOL_LF |
| 2061 | || coding->eol_type == CODING_EOL_UNDECIDED) |
| 2062 | *dst++ = '\n'; |
| 2063 | else if (coding->eol_type == CODING_EOL_CRLF) |
| 2064 | *dst++ = '\r', *dst++ = '\n'; |
| 2065 | else |
| 2066 | *dst++ = '\r'; |
| 2067 | break; |
| 2068 | |
| 2069 | case EMACS_leading_code_2: |
| 2070 | ONE_MORE_BYTE (c2); |
| 2071 | ENCODE_SJIS_BIG5_CHARACTER (c1, c2, /* dummy */ c3); |
| 2072 | break; |
| 2073 | |
| 2074 | case EMACS_leading_code_3: |
| 2075 | TWO_MORE_BYTES (c2, c3); |
| 2076 | ENCODE_SJIS_BIG5_CHARACTER (c1, c2, c3); |
| 2077 | break; |
| 2078 | |
| 2079 | case EMACS_leading_code_4: |
| 2080 | THREE_MORE_BYTES (c2, c3, c4); |
| 2081 | ENCODE_SJIS_BIG5_CHARACTER (c2, c3, c4); |
| 2082 | break; |
| 2083 | |
| 2084 | case EMACS_leading_code_composition: |
| 2085 | coding->composing = 1; |
| 2086 | break; |
| 2087 | |
| 2088 | default: /* i.e. case EMACS_invalid_code: */ |
| 2089 | *dst++ = c1; |
| 2090 | } |
| 2091 | continue; |
| 2092 | |
| 2093 | label_end_of_loop: |
| 2094 | coding->carryover_size = src_end - src_base; |
| 2095 | bcopy (src_base, coding->carryover, coding->carryover_size); |
| 2096 | src = src_end; |
| 2097 | break; |
| 2098 | } |
| 2099 | |
| 2100 | *consumed = src - source; |
| 2101 | return dst - destination; |
| 2102 | } |
| 2103 | |
| 2104 | \f |
| 2105 | /*** 5. End-of-line handlers ***/ |
| 2106 | |
| 2107 | /* See the above "GENERAL NOTES on `decode_coding_XXX ()' functions". |
| 2108 | This function is called only when `coding->eol_type' is |
| 2109 | CODING_EOL_CRLF or CODING_EOL_CR. */ |
| 2110 | |
| 2111 | decode_eol (coding, source, destination, src_bytes, dst_bytes, consumed) |
| 2112 | struct coding_system *coding; |
| 2113 | unsigned char *source, *destination; |
| 2114 | int src_bytes, dst_bytes; |
| 2115 | int *consumed; |
| 2116 | { |
| 2117 | unsigned char *src = source; |
| 2118 | unsigned char *src_end = source + src_bytes; |
| 2119 | unsigned char *dst = destination; |
| 2120 | unsigned char *dst_end = destination + dst_bytes; |
| 2121 | int produced; |
| 2122 | |
| 2123 | switch (coding->eol_type) |
| 2124 | { |
| 2125 | case CODING_EOL_CRLF: |
| 2126 | { |
| 2127 | /* Since the maximum bytes produced by each loop is 2, we |
| 2128 | subtract 1 from DST_END to assure overflow checking is |
| 2129 | necessary only at the head of loop. */ |
| 2130 | unsigned char *adjusted_dst_end = dst_end - 1; |
| 2131 | |
| 2132 | while (src < src_end && dst < adjusted_dst_end) |
| 2133 | { |
| 2134 | unsigned char *src_base = src; |
| 2135 | unsigned char c = *src++; |
| 2136 | if (c == '\r') |
| 2137 | { |
| 2138 | ONE_MORE_BYTE (c); |
| 2139 | if (c != '\n') |
| 2140 | *dst++ = '\r'; |
| 2141 | *dst++ = c; |
| 2142 | } |
| 2143 | else |
| 2144 | *dst++ = c; |
| 2145 | continue; |
| 2146 | |
| 2147 | label_end_of_loop: |
| 2148 | coding->carryover_size = src - src_base; |
| 2149 | bcopy (src_base, coding->carryover, coding->carryover_size); |
| 2150 | src = src_base; |
| 2151 | break; |
| 2152 | } |
| 2153 | *consumed = src - source; |
| 2154 | produced = dst - destination; |
| 2155 | break; |
| 2156 | } |
| 2157 | |
| 2158 | case CODING_EOL_CR: |
| 2159 | produced = (src_bytes > dst_bytes) ? dst_bytes : src_bytes; |
| 2160 | bcopy (source, destination, produced); |
| 2161 | dst_end = destination + produced; |
| 2162 | while (dst < dst_end) |
| 2163 | if (*dst++ == '\r') dst[-1] = '\n'; |
| 2164 | *consumed = produced; |
| 2165 | break; |
| 2166 | |
| 2167 | default: /* i.e. case: CODING_EOL_LF */ |
| 2168 | produced = (src_bytes > dst_bytes) ? dst_bytes : src_bytes; |
| 2169 | bcopy (source, destination, produced); |
| 2170 | *consumed = produced; |
| 2171 | break; |
| 2172 | } |
| 2173 | |
| 2174 | return produced; |
| 2175 | } |
| 2176 | |
| 2177 | /* See "GENERAL NOTES about `encode_coding_XXX ()' functions". Encode |
| 2178 | format of end-of-line according to `coding->eol_type'. If |
| 2179 | `coding->selective' is 1, code '\r' in source text also means |
| 2180 | end-of-line. */ |
| 2181 | |
| 2182 | encode_eol (coding, source, destination, src_bytes, dst_bytes, consumed) |
| 2183 | struct coding_system *coding; |
| 2184 | unsigned char *source, *destination; |
| 2185 | int src_bytes, dst_bytes; |
| 2186 | int *consumed; |
| 2187 | { |
| 2188 | unsigned char *src = source; |
| 2189 | unsigned char *dst = destination; |
| 2190 | int produced; |
| 2191 | |
| 2192 | if (src_bytes <= 0) |
| 2193 | return 0; |
| 2194 | |
| 2195 | switch (coding->eol_type) |
| 2196 | { |
| 2197 | case CODING_EOL_LF: |
| 2198 | case CODING_EOL_UNDECIDED: |
| 2199 | produced = (src_bytes > dst_bytes) ? dst_bytes : src_bytes; |
| 2200 | bcopy (source, destination, produced); |
| 2201 | if (coding->selective) |
| 2202 | { |
| 2203 | int i = produced; |
| 2204 | while (i--) |
| 2205 | if (*dst++ == '\r') dst[-1] = '\n'; |
| 2206 | } |
| 2207 | *consumed = produced; |
| 2208 | |
| 2209 | case CODING_EOL_CRLF: |
| 2210 | { |
| 2211 | unsigned char c; |
| 2212 | unsigned char *src_end = source + src_bytes; |
| 2213 | unsigned char *dst_end = destination + dst_bytes; |
| 2214 | /* Since the maximum bytes produced by each loop is 2, we |
| 2215 | subtract 1 from DST_END to assure overflow checking is |
| 2216 | necessary only at the head of loop. */ |
| 2217 | unsigned char *adjusted_dst_end = dst_end - 1; |
| 2218 | |
| 2219 | while (src < src_end && dst < adjusted_dst_end) |
| 2220 | { |
| 2221 | c = *src++; |
| 2222 | if (c == '\n' || (c == '\r' && coding->selective)) |
| 2223 | *dst++ = '\r', *dst++ = '\n'; |
| 2224 | else |
| 2225 | *dst++ = c; |
| 2226 | } |
| 2227 | produced = dst - destination; |
| 2228 | *consumed = src - source; |
| 2229 | break; |
| 2230 | } |
| 2231 | |
| 2232 | default: /* i.e. case CODING_EOL_CR: */ |
| 2233 | produced = (src_bytes > dst_bytes) ? dst_bytes : src_bytes; |
| 2234 | bcopy (source, destination, produced); |
| 2235 | { |
| 2236 | int i = produced; |
| 2237 | while (i--) |
| 2238 | if (*dst++ == '\n') dst[-1] = '\r'; |
| 2239 | } |
| 2240 | *consumed = produced; |
| 2241 | } |
| 2242 | |
| 2243 | return produced; |
| 2244 | } |
| 2245 | |
| 2246 | \f |
| 2247 | /*** 6. C library functions ***/ |
| 2248 | |
| 2249 | /* In Emacs Lisp, coding system is represented by a Lisp symbol which |
| 2250 | has a property `coding-system'. The value of this property is a |
| 2251 | vector of length 5 (called as coding-vector). Among elements of |
| 2252 | this vector, the first (element[0]) and the fifth (element[4]) |
| 2253 | carry important information for decoding/encoding. Before |
| 2254 | decoding/encoding, this information should be set in fields of a |
| 2255 | structure of type `coding_system'. |
| 2256 | |
| 2257 | A value of property `coding-system' can be a symbol of another |
| 2258 | subsidiary coding-system. In that case, Emacs gets coding-vector |
| 2259 | from that symbol. |
| 2260 | |
| 2261 | `element[0]' contains information to be set in `coding->type'. The |
| 2262 | value and its meaning is as follows: |
| 2263 | |
| 2264 | 0 -- coding_type_emacs_mule |
| 2265 | 1 -- coding_type_sjis |
| 2266 | 2 -- coding_type_iso2022 |
| 2267 | 3 -- coding_type_big5 |
| 2268 | 4 -- coding_type_ccl encoder/decoder written in CCL |
| 2269 | nil -- coding_type_no_conversion |
| 2270 | t -- coding_type_undecided (automatic conversion on decoding, |
| 2271 | no-conversion on encoding) |
| 2272 | |
| 2273 | `element[4]' contains information to be set in `coding->flags' and |
| 2274 | `coding->spec'. The meaning varies by `coding->type'. |
| 2275 | |
| 2276 | If `coding->type' is `coding_type_iso2022', element[4] is a vector |
| 2277 | of length 32 (of which the first 13 sub-elements are used now). |
| 2278 | Meanings of these sub-elements are: |
| 2279 | |
| 2280 | sub-element[N] where N is 0 through 3: to be set in `coding->spec.iso2022' |
| 2281 | If the value is an integer of valid charset, the charset is |
| 2282 | assumed to be designated to graphic register N initially. |
| 2283 | |
| 2284 | If the value is minus, it is a minus value of charset which |
| 2285 | reserves graphic register N, which means that the charset is |
| 2286 | not designated initially but should be designated to graphic |
| 2287 | register N just before encoding a character in that charset. |
| 2288 | |
| 2289 | If the value is nil, graphic register N is never used on |
| 2290 | encoding. |
| 2291 | |
| 2292 | sub-element[N] where N is 4 through 11: to be set in `coding->flags' |
| 2293 | Each value takes t or nil. See the section ISO2022 of |
| 2294 | `coding.h' for more information. |
| 2295 | |
| 2296 | If `coding->type' is `coding_type_big5', element[4] is t to denote |
| 2297 | BIG5-ETen or nil to denote BIG5-HKU. |
| 2298 | |
| 2299 | If `coding->type' takes the other value, element[4] is ignored. |
| 2300 | |
| 2301 | Emacs Lisp's coding system also carries information about format of |
| 2302 | end-of-line in a value of property `eol-type'. If the value is |
| 2303 | integer, 0 means CODING_EOL_LF, 1 means CODING_EOL_CRLF, and 2 |
| 2304 | means CODING_EOL_CR. If it is not integer, it should be a vector |
| 2305 | of subsidiary coding systems of which property `eol-type' has one |
| 2306 | of above values. |
| 2307 | |
| 2308 | */ |
| 2309 | |
| 2310 | /* Extract information for decoding/encoding from CODING_SYSTEM_SYMBOL |
| 2311 | and set it in CODING. If CODING_SYSTEM_SYMBOL is invalid, CODING |
| 2312 | is setup so that no conversion is necessary and return -1, else |
| 2313 | return 0. */ |
| 2314 | |
| 2315 | int |
| 2316 | setup_coding_system (coding_system, coding) |
| 2317 | Lisp_Object coding_system; |
| 2318 | struct coding_system *coding; |
| 2319 | { |
| 2320 | Lisp_Object coding_spec, plist, type, eol_type; |
| 2321 | Lisp_Object val; |
| 2322 | int i; |
| 2323 | |
| 2324 | /* At first, set several fields to default values. */ |
| 2325 | coding->last_block = 0; |
| 2326 | coding->selective = 0; |
| 2327 | coding->composing = 0; |
| 2328 | coding->direction = 0; |
| 2329 | coding->carryover_size = 0; |
| 2330 | coding->post_read_conversion = coding->pre_write_conversion = Qnil; |
| 2331 | coding->character_unification_table_for_decode = Qnil; |
| 2332 | coding->character_unification_table_for_encode = Qnil; |
| 2333 | |
| 2334 | coding->symbol = coding_system; |
| 2335 | eol_type = Qnil; |
| 2336 | |
| 2337 | /* Get values of property `coding-system' and `eol-type'. |
| 2338 | Also get values of coding system properties: |
| 2339 | `post-read-conversion', `pre-write-conversion', |
| 2340 | `character-unification-table-for-decode', |
| 2341 | `character-unification-table-for-encode'. */ |
| 2342 | coding_spec = Fget (coding_system, Qcoding_system); |
| 2343 | if (!VECTORP (coding_spec) |
| 2344 | || XVECTOR (coding_spec)->size != 5 |
| 2345 | || !CONSP (XVECTOR (coding_spec)->contents[3])) |
| 2346 | goto label_invalid_coding_system; |
| 2347 | if (!inhibit_eol_conversion) |
| 2348 | eol_type = Fget (coding_system, Qeol_type); |
| 2349 | |
| 2350 | plist = XVECTOR (coding_spec)->contents[3]; |
| 2351 | coding->post_read_conversion = Fplist_get (plist, Qpost_read_conversion); |
| 2352 | coding->pre_write_conversion = Fplist_get (plist, Qpre_write_conversion); |
| 2353 | val = Fplist_get (plist, Qcharacter_unification_table_for_decode); |
| 2354 | if (SYMBOLP (val)) |
| 2355 | val = Fget (val, Qcharacter_unification_table_for_decode); |
| 2356 | coding->character_unification_table_for_decode |
| 2357 | = CHAR_TABLE_P (val) ? val : Qnil; |
| 2358 | val = Fplist_get (plist, Qcharacter_unification_table_for_encode); |
| 2359 | if (SYMBOLP (val)) |
| 2360 | val = Fget (val, Qcharacter_unification_table_for_encode); |
| 2361 | coding->character_unification_table_for_encode |
| 2362 | = CHAR_TABLE_P (val) ? val : Qnil; |
| 2363 | |
| 2364 | val = Fplist_get (plist, Qsafe_charsets); |
| 2365 | if (EQ (val, Qt)) |
| 2366 | { |
| 2367 | for (i = 0; i <= MAX_CHARSET; i++) |
| 2368 | coding->safe_charsets[i] = 1; |
| 2369 | } |
| 2370 | else |
| 2371 | { |
| 2372 | bzero (coding->safe_charsets, MAX_CHARSET + 1); |
| 2373 | while (CONSP (val)) |
| 2374 | { |
| 2375 | if ((i = get_charset_id (XCONS (val)->car)) >= 0) |
| 2376 | coding->safe_charsets[i] = 1; |
| 2377 | val = XCONS (val)->cdr; |
| 2378 | } |
| 2379 | } |
| 2380 | |
| 2381 | if (VECTORP (eol_type)) |
| 2382 | { |
| 2383 | coding->eol_type = CODING_EOL_UNDECIDED; |
| 2384 | coding->common_flags = CODING_REQUIRE_DETECTION_MASK; |
| 2385 | } |
| 2386 | else if (XFASTINT (eol_type) == 1) |
| 2387 | { |
| 2388 | coding->eol_type = CODING_EOL_CRLF; |
| 2389 | coding->common_flags |
| 2390 | = CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK; |
| 2391 | } |
| 2392 | else if (XFASTINT (eol_type) == 2) |
| 2393 | { |
| 2394 | coding->eol_type = CODING_EOL_CR; |
| 2395 | coding->common_flags |
| 2396 | = CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK; |
| 2397 | } |
| 2398 | else |
| 2399 | { |
| 2400 | coding->eol_type = CODING_EOL_LF; |
| 2401 | coding->common_flags = 0; |
| 2402 | } |
| 2403 | |
| 2404 | type = XVECTOR (coding_spec)->contents[0]; |
| 2405 | switch (XFASTINT (type)) |
| 2406 | { |
| 2407 | case 0: |
| 2408 | coding->type = coding_type_emacs_mule; |
| 2409 | if (!NILP (coding->post_read_conversion)) |
| 2410 | coding->common_flags |= CODING_REQUIRE_DECODING_MASK; |
| 2411 | if (!NILP (coding->pre_write_conversion)) |
| 2412 | coding->common_flags |= CODING_REQUIRE_ENCODING_MASK; |
| 2413 | break; |
| 2414 | |
| 2415 | case 1: |
| 2416 | coding->type = coding_type_sjis; |
| 2417 | coding->common_flags |
| 2418 | |= CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK; |
| 2419 | break; |
| 2420 | |
| 2421 | case 2: |
| 2422 | coding->type = coding_type_iso2022; |
| 2423 | coding->common_flags |
| 2424 | |= CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK; |
| 2425 | { |
| 2426 | Lisp_Object val, temp; |
| 2427 | Lisp_Object *flags; |
| 2428 | int i, charset, default_reg_bits = 0; |
| 2429 | |
| 2430 | val = XVECTOR (coding_spec)->contents[4]; |
| 2431 | |
| 2432 | if (!VECTORP (val) || XVECTOR (val)->size != 32) |
| 2433 | goto label_invalid_coding_system; |
| 2434 | |
| 2435 | flags = XVECTOR (val)->contents; |
| 2436 | coding->flags |
| 2437 | = ((NILP (flags[4]) ? 0 : CODING_FLAG_ISO_SHORT_FORM) |
| 2438 | | (NILP (flags[5]) ? 0 : CODING_FLAG_ISO_RESET_AT_EOL) |
| 2439 | | (NILP (flags[6]) ? 0 : CODING_FLAG_ISO_RESET_AT_CNTL) |
| 2440 | | (NILP (flags[7]) ? 0 : CODING_FLAG_ISO_SEVEN_BITS) |
| 2441 | | (NILP (flags[8]) ? 0 : CODING_FLAG_ISO_LOCKING_SHIFT) |
| 2442 | | (NILP (flags[9]) ? 0 : CODING_FLAG_ISO_SINGLE_SHIFT) |
| 2443 | | (NILP (flags[10]) ? 0 : CODING_FLAG_ISO_USE_ROMAN) |
| 2444 | | (NILP (flags[11]) ? 0 : CODING_FLAG_ISO_USE_OLDJIS) |
| 2445 | | (NILP (flags[12]) ? 0 : CODING_FLAG_ISO_NO_DIRECTION) |
| 2446 | | (NILP (flags[13]) ? 0 : CODING_FLAG_ISO_INIT_AT_BOL) |
| 2447 | | (NILP (flags[14]) ? 0 : CODING_FLAG_ISO_DESIGNATE_AT_BOL) |
| 2448 | | (NILP (flags[15]) ? 0 : CODING_FLAG_ISO_SAFE) |
| 2449 | | (NILP (flags[16]) ? 0 : CODING_FLAG_ISO_LATIN_EXTRA) |
| 2450 | ); |
| 2451 | |
| 2452 | /* Invoke graphic register 0 to plane 0. */ |
| 2453 | CODING_SPEC_ISO_INVOCATION (coding, 0) = 0; |
| 2454 | /* Invoke graphic register 1 to plane 1 if we can use full 8-bit. */ |
| 2455 | CODING_SPEC_ISO_INVOCATION (coding, 1) |
| 2456 | = (coding->flags & CODING_FLAG_ISO_SEVEN_BITS ? -1 : 1); |
| 2457 | /* Not single shifting at first. */ |
| 2458 | CODING_SPEC_ISO_SINGLE_SHIFTING (coding) = 0; |
| 2459 | /* Beginning of buffer should also be regarded as bol. */ |
| 2460 | CODING_SPEC_ISO_BOL (coding) = 1; |
| 2461 | |
| 2462 | for (charset = 0; charset <= MAX_CHARSET; charset++) |
| 2463 | CODING_SPEC_ISO_REVISION_NUMBER (coding, charset) = 255; |
| 2464 | val = Vcharset_revision_alist; |
| 2465 | while (CONSP (val)) |
| 2466 | { |
| 2467 | charset = get_charset_id (Fcar_safe (XCONS (val)->car)); |
| 2468 | if (charset >= 0 |
| 2469 | && (temp = Fcdr_safe (XCONS (val)->car), INTEGERP (temp)) |
| 2470 | && (i = XINT (temp), (i >= 0 && (i + '@') < 128))) |
| 2471 | CODING_SPEC_ISO_REVISION_NUMBER (coding, charset) = i; |
| 2472 | val = XCONS (val)->cdr; |
| 2473 | } |
| 2474 | |
| 2475 | /* Checks FLAGS[REG] (REG = 0, 1, 2 3) and decide designations. |
| 2476 | FLAGS[REG] can be one of below: |
| 2477 | integer CHARSET: CHARSET occupies register I, |
| 2478 | t: designate nothing to REG initially, but can be used |
| 2479 | by any charsets, |
| 2480 | list of integer, nil, or t: designate the first |
| 2481 | element (if integer) to REG initially, the remaining |
| 2482 | elements (if integer) is designated to REG on request, |
| 2483 | if an element is t, REG can be used by any charset, |
| 2484 | nil: REG is never used. */ |
| 2485 | for (charset = 0; charset <= MAX_CHARSET; charset++) |
| 2486 | CODING_SPEC_ISO_REQUESTED_DESIGNATION (coding, charset) |
| 2487 | = CODING_SPEC_ISO_NO_REQUESTED_DESIGNATION; |
| 2488 | for (i = 0; i < 4; i++) |
| 2489 | { |
| 2490 | if (INTEGERP (flags[i]) |
| 2491 | && (charset = XINT (flags[i]), CHARSET_VALID_P (charset)) |
| 2492 | || (charset = get_charset_id (flags[i])) >= 0) |
| 2493 | { |
| 2494 | CODING_SPEC_ISO_INITIAL_DESIGNATION (coding, i) = charset; |
| 2495 | CODING_SPEC_ISO_REQUESTED_DESIGNATION (coding, charset) = i; |
| 2496 | } |
| 2497 | else if (EQ (flags[i], Qt)) |
| 2498 | { |
| 2499 | CODING_SPEC_ISO_INITIAL_DESIGNATION (coding, i) = -1; |
| 2500 | default_reg_bits |= 1 << i; |
| 2501 | } |
| 2502 | else if (CONSP (flags[i])) |
| 2503 | { |
| 2504 | Lisp_Object tail = flags[i]; |
| 2505 | |
| 2506 | if (INTEGERP (XCONS (tail)->car) |
| 2507 | && (charset = XINT (XCONS (tail)->car), |
| 2508 | CHARSET_VALID_P (charset)) |
| 2509 | || (charset = get_charset_id (XCONS (tail)->car)) >= 0) |
| 2510 | { |
| 2511 | CODING_SPEC_ISO_INITIAL_DESIGNATION (coding, i) = charset; |
| 2512 | CODING_SPEC_ISO_REQUESTED_DESIGNATION (coding, charset) =i; |
| 2513 | } |
| 2514 | else |
| 2515 | CODING_SPEC_ISO_INITIAL_DESIGNATION (coding, i) = -1; |
| 2516 | tail = XCONS (tail)->cdr; |
| 2517 | while (CONSP (tail)) |
| 2518 | { |
| 2519 | if (INTEGERP (XCONS (tail)->car) |
| 2520 | && (charset = XINT (XCONS (tail)->car), |
| 2521 | CHARSET_VALID_P (charset)) |
| 2522 | || (charset = get_charset_id (XCONS (tail)->car)) >= 0) |
| 2523 | CODING_SPEC_ISO_REQUESTED_DESIGNATION (coding, charset) |
| 2524 | = i; |
| 2525 | else if (EQ (XCONS (tail)->car, Qt)) |
| 2526 | default_reg_bits |= 1 << i; |
| 2527 | tail = XCONS (tail)->cdr; |
| 2528 | } |
| 2529 | } |
| 2530 | else |
| 2531 | CODING_SPEC_ISO_INITIAL_DESIGNATION (coding, i) = -1; |
| 2532 | |
| 2533 | CODING_SPEC_ISO_DESIGNATION (coding, i) |
| 2534 | = CODING_SPEC_ISO_INITIAL_DESIGNATION (coding, i); |
| 2535 | } |
| 2536 | |
| 2537 | if (! (coding->flags & CODING_FLAG_ISO_LOCKING_SHIFT)) |
| 2538 | { |
| 2539 | /* REG 1 can be used only by locking shift in 7-bit env. */ |
| 2540 | if (coding->flags & CODING_FLAG_ISO_SEVEN_BITS) |
| 2541 | default_reg_bits &= ~2; |
| 2542 | if (! (coding->flags & CODING_FLAG_ISO_SINGLE_SHIFT)) |
| 2543 | /* Without any shifting, only REG 0 and 1 can be used. */ |
| 2544 | default_reg_bits &= 3; |
| 2545 | } |
| 2546 | |
| 2547 | for (charset = 0; charset <= MAX_CHARSET; charset++) |
| 2548 | if (CHARSET_VALID_P (charset) |
| 2549 | && (CODING_SPEC_ISO_REQUESTED_DESIGNATION (coding, charset) |
| 2550 | == CODING_SPEC_ISO_NO_REQUESTED_DESIGNATION)) |
| 2551 | { |
| 2552 | /* We have not yet decided where to designate CHARSET. */ |
| 2553 | int reg_bits = default_reg_bits; |
| 2554 | |
| 2555 | if (CHARSET_CHARS (charset) == 96) |
| 2556 | /* A charset of CHARS96 can't be designated to REG 0. */ |
| 2557 | reg_bits &= ~1; |
| 2558 | |
| 2559 | if (reg_bits) |
| 2560 | /* There exist some default graphic register. */ |
| 2561 | CODING_SPEC_ISO_REQUESTED_DESIGNATION (coding, charset) |
| 2562 | = (reg_bits & 1 |
| 2563 | ? 0 : (reg_bits & 2 ? 1 : (reg_bits & 4 ? 2 : 3))); |
| 2564 | else |
| 2565 | /* We anyway have to designate CHARSET to somewhere. */ |
| 2566 | CODING_SPEC_ISO_REQUESTED_DESIGNATION (coding, charset) |
| 2567 | = (CHARSET_CHARS (charset) == 94 |
| 2568 | ? 0 |
| 2569 | : ((coding->flags & CODING_FLAG_ISO_LOCKING_SHIFT |
| 2570 | || ! coding->flags & CODING_FLAG_ISO_SEVEN_BITS) |
| 2571 | ? 1 |
| 2572 | : (coding->flags & CODING_FLAG_ISO_SINGLE_SHIFT |
| 2573 | ? 2 : 0))); |
| 2574 | } |
| 2575 | } |
| 2576 | coding->common_flags |= CODING_REQUIRE_FLUSHING_MASK; |
| 2577 | break; |
| 2578 | |
| 2579 | case 3: |
| 2580 | coding->type = coding_type_big5; |
| 2581 | coding->common_flags |
| 2582 | |= CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK; |
| 2583 | coding->flags |
| 2584 | = (NILP (XVECTOR (coding_spec)->contents[4]) |
| 2585 | ? CODING_FLAG_BIG5_HKU |
| 2586 | : CODING_FLAG_BIG5_ETEN); |
| 2587 | break; |
| 2588 | |
| 2589 | case 4: |
| 2590 | coding->type = coding_type_ccl; |
| 2591 | coding->common_flags |
| 2592 | |= CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK; |
| 2593 | { |
| 2594 | Lisp_Object val = XVECTOR (coding_spec)->contents[4]; |
| 2595 | if (CONSP (val) |
| 2596 | && VECTORP (XCONS (val)->car) |
| 2597 | && VECTORP (XCONS (val)->cdr)) |
| 2598 | { |
| 2599 | setup_ccl_program (&(coding->spec.ccl.decoder), XCONS (val)->car); |
| 2600 | setup_ccl_program (&(coding->spec.ccl.encoder), XCONS (val)->cdr); |
| 2601 | } |
| 2602 | else |
| 2603 | goto label_invalid_coding_system; |
| 2604 | } |
| 2605 | coding->common_flags |= CODING_REQUIRE_FLUSHING_MASK; |
| 2606 | break; |
| 2607 | |
| 2608 | case 5: |
| 2609 | coding->type = coding_type_raw_text; |
| 2610 | break; |
| 2611 | |
| 2612 | default: |
| 2613 | if (EQ (type, Qt)) |
| 2614 | { |
| 2615 | coding->type = coding_type_undecided; |
| 2616 | coding->common_flags |= CODING_REQUIRE_DETECTION_MASK; |
| 2617 | } |
| 2618 | else |
| 2619 | coding->type = coding_type_no_conversion; |
| 2620 | break; |
| 2621 | } |
| 2622 | return 0; |
| 2623 | |
| 2624 | label_invalid_coding_system: |
| 2625 | coding->type = coding_type_no_conversion; |
| 2626 | coding->common_flags = 0; |
| 2627 | coding->eol_type = CODING_EOL_LF; |
| 2628 | coding->symbol = coding->pre_write_conversion = coding->post_read_conversion |
| 2629 | = Qnil; |
| 2630 | return -1; |
| 2631 | } |
| 2632 | |
| 2633 | /* Emacs has a mechanism to automatically detect a coding system if it |
| 2634 | is one of Emacs' internal format, ISO2022, SJIS, and BIG5. But, |
| 2635 | it's impossible to distinguish some coding systems accurately |
| 2636 | because they use the same range of codes. So, at first, coding |
| 2637 | systems are categorized into 7, those are: |
| 2638 | |
| 2639 | o coding-category-emacs-mule |
| 2640 | |
| 2641 | The category for a coding system which has the same code range |
| 2642 | as Emacs' internal format. Assigned the coding-system (Lisp |
| 2643 | symbol) `emacs-mule' by default. |
| 2644 | |
| 2645 | o coding-category-sjis |
| 2646 | |
| 2647 | The category for a coding system which has the same code range |
| 2648 | as SJIS. Assigned the coding-system (Lisp |
| 2649 | symbol) `japanese-shift-jis' by default. |
| 2650 | |
| 2651 | o coding-category-iso-7 |
| 2652 | |
| 2653 | The category for a coding system which has the same code range |
| 2654 | as ISO2022 of 7-bit environment. This doesn't use any locking |
| 2655 | shift and single shift functions. Assigned the coding-system |
| 2656 | (Lisp symbol) `iso-2022-7bit' by default. |
| 2657 | |
| 2658 | o coding-category-iso-8-1 |
| 2659 | |
| 2660 | The category for a coding system which has the same code range |
| 2661 | as ISO2022 of 8-bit environment and graphic plane 1 used only |
| 2662 | for DIMENSION1 charset. This doesn't use any locking shift |
| 2663 | and single shift functions. Assigned the coding-system (Lisp |
| 2664 | symbol) `iso-latin-1' by default. |
| 2665 | |
| 2666 | o coding-category-iso-8-2 |
| 2667 | |
| 2668 | The category for a coding system which has the same code range |
| 2669 | as ISO2022 of 8-bit environment and graphic plane 1 used only |
| 2670 | for DIMENSION2 charset. This doesn't use any locking shift |
| 2671 | and single shift functions. Assigned the coding-system (Lisp |
| 2672 | symbol) `japanese-iso-8bit' by default. |
| 2673 | |
| 2674 | o coding-category-iso-7-else |
| 2675 | |
| 2676 | The category for a coding system which has the same code range |
| 2677 | as ISO2022 of 7-bit environemnt but uses locking shift or |
| 2678 | single shift functions. Assigned the coding-system (Lisp |
| 2679 | symbol) `iso-2022-7bit-lock' by default. |
| 2680 | |
| 2681 | o coding-category-iso-8-else |
| 2682 | |
| 2683 | The category for a coding system which has the same code range |
| 2684 | as ISO2022 of 8-bit environemnt but uses locking shift or |
| 2685 | single shift functions. Assigned the coding-system (Lisp |
| 2686 | symbol) `iso-2022-8bit-ss2' by default. |
| 2687 | |
| 2688 | o coding-category-big5 |
| 2689 | |
| 2690 | The category for a coding system which has the same code range |
| 2691 | as BIG5. Assigned the coding-system (Lisp symbol) |
| 2692 | `cn-big5' by default. |
| 2693 | |
| 2694 | o coding-category-binary |
| 2695 | |
| 2696 | The category for a coding system not categorized in any of the |
| 2697 | above. Assigned the coding-system (Lisp symbol) |
| 2698 | `no-conversion' by default. |
| 2699 | |
| 2700 | Each of them is a Lisp symbol and the value is an actual |
| 2701 | `coding-system's (this is also a Lisp symbol) assigned by a user. |
| 2702 | What Emacs does actually is to detect a category of coding system. |
| 2703 | Then, it uses a `coding-system' assigned to it. If Emacs can't |
| 2704 | decide only one possible category, it selects a category of the |
| 2705 | highest priority. Priorities of categories are also specified by a |
| 2706 | user in a Lisp variable `coding-category-list'. |
| 2707 | |
| 2708 | */ |
| 2709 | |
| 2710 | /* Detect how a text of length SRC_BYTES pointed by SRC is encoded. |
| 2711 | If it detects possible coding systems, return an integer in which |
| 2712 | appropriate flag bits are set. Flag bits are defined by macros |
| 2713 | CODING_CATEGORY_MASK_XXX in `coding.h'. */ |
| 2714 | |
| 2715 | int |
| 2716 | detect_coding_mask (src, src_bytes) |
| 2717 | unsigned char *src; |
| 2718 | int src_bytes; |
| 2719 | { |
| 2720 | register unsigned char c; |
| 2721 | unsigned char *src_end = src + src_bytes; |
| 2722 | int mask; |
| 2723 | |
| 2724 | /* At first, skip all ASCII characters and control characters except |
| 2725 | for three ISO2022 specific control characters. */ |
| 2726 | label_loop_detect_coding: |
| 2727 | while (src < src_end) |
| 2728 | { |
| 2729 | c = *src; |
| 2730 | if (c >= 0x80 |
| 2731 | || (c == ISO_CODE_ESC || c == ISO_CODE_SI || c == ISO_CODE_SO)) |
| 2732 | break; |
| 2733 | src++; |
| 2734 | } |
| 2735 | |
| 2736 | if (src >= src_end) |
| 2737 | /* We found nothing other than ASCII. There's nothing to do. */ |
| 2738 | return CODING_CATEGORY_MASK_ANY; |
| 2739 | |
| 2740 | /* The text seems to be encoded in some multilingual coding system. |
| 2741 | Now, try to find in which coding system the text is encoded. */ |
| 2742 | if (c < 0x80) |
| 2743 | { |
| 2744 | /* i.e. (c == ISO_CODE_ESC || c == ISO_CODE_SI || c == ISO_CODE_SO) */ |
| 2745 | /* C is an ISO2022 specific control code of C0. */ |
| 2746 | mask = detect_coding_iso2022 (src, src_end); |
| 2747 | src++; |
| 2748 | if (mask == 0) |
| 2749 | /* No valid ISO2022 code follows C. Try again. */ |
| 2750 | goto label_loop_detect_coding; |
| 2751 | mask |= CODING_CATEGORY_MASK_RAW_TEXT; |
| 2752 | } |
| 2753 | else if (c < 0xA0) |
| 2754 | { |
| 2755 | /* If C is a special latin extra code, |
| 2756 | or is an ISO2022 specific control code of C1 (SS2 or SS3), |
| 2757 | or is an ISO2022 control-sequence-introducer (CSI), |
| 2758 | we should also consider the possibility of ISO2022 codings. */ |
| 2759 | if ((VECTORP (Vlatin_extra_code_table) |
| 2760 | && !NILP (XVECTOR (Vlatin_extra_code_table)->contents[c])) |
| 2761 | || (c == ISO_CODE_SS2 || c == ISO_CODE_SS3) |
| 2762 | || (c == ISO_CODE_CSI |
| 2763 | && (src < src_end |
| 2764 | && (*src == ']' |
| 2765 | || (src + 1 < src_end |
| 2766 | && src[1] == ']' |
| 2767 | && (*src == '0' || *src == '1' || *src == '2')))))) |
| 2768 | mask = (detect_coding_iso2022 (src, src_end) |
| 2769 | | detect_coding_sjis (src, src_end) |
| 2770 | | detect_coding_emacs_mule (src, src_end) |
| 2771 | | CODING_CATEGORY_MASK_RAW_TEXT); |
| 2772 | |
| 2773 | else |
| 2774 | /* C is the first byte of SJIS character code, |
| 2775 | or a leading-code of Emacs' internal format (emacs-mule). */ |
| 2776 | mask = (detect_coding_sjis (src, src_end) |
| 2777 | | detect_coding_emacs_mule (src, src_end) |
| 2778 | | CODING_CATEGORY_MASK_RAW_TEXT); |
| 2779 | } |
| 2780 | else |
| 2781 | /* C is a character of ISO2022 in graphic plane right, |
| 2782 | or a SJIS's 1-byte character code (i.e. JISX0201), |
| 2783 | or the first byte of BIG5's 2-byte code. */ |
| 2784 | mask = (detect_coding_iso2022 (src, src_end) |
| 2785 | | detect_coding_sjis (src, src_end) |
| 2786 | | detect_coding_big5 (src, src_end) |
| 2787 | | CODING_CATEGORY_MASK_RAW_TEXT); |
| 2788 | |
| 2789 | return mask; |
| 2790 | } |
| 2791 | |
| 2792 | /* Detect how a text of length SRC_BYTES pointed by SRC is encoded. |
| 2793 | The information of the detected coding system is set in CODING. */ |
| 2794 | |
| 2795 | void |
| 2796 | detect_coding (coding, src, src_bytes) |
| 2797 | struct coding_system *coding; |
| 2798 | unsigned char *src; |
| 2799 | int src_bytes; |
| 2800 | { |
| 2801 | int mask = detect_coding_mask (src, src_bytes); |
| 2802 | int idx; |
| 2803 | Lisp_Object val = Vcoding_category_list; |
| 2804 | |
| 2805 | if (mask == CODING_CATEGORY_MASK_ANY) |
| 2806 | /* We found nothing other than ASCII. There's nothing to do. */ |
| 2807 | return; |
| 2808 | |
| 2809 | /* We found some plausible coding systems. Let's use a coding |
| 2810 | system of the highest priority. */ |
| 2811 | |
| 2812 | if (CONSP (val)) |
| 2813 | while (!NILP (val)) |
| 2814 | { |
| 2815 | idx = XFASTINT (Fget (XCONS (val)->car, Qcoding_category_index)); |
| 2816 | if ((idx < CODING_CATEGORY_IDX_MAX) && (mask & (1 << idx))) |
| 2817 | break; |
| 2818 | val = XCONS (val)->cdr; |
| 2819 | } |
| 2820 | else |
| 2821 | val = Qnil; |
| 2822 | |
| 2823 | if (NILP (val)) |
| 2824 | { |
| 2825 | /* For unknown reason, `Vcoding_category_list' contains none of |
| 2826 | found categories. Let's use any of them. */ |
| 2827 | for (idx = 0; idx < CODING_CATEGORY_IDX_MAX; idx++) |
| 2828 | if (mask & (1 << idx)) |
| 2829 | break; |
| 2830 | } |
| 2831 | setup_coding_system (XSYMBOL (coding_category_table[idx])->value, coding); |
| 2832 | } |
| 2833 | |
| 2834 | /* Detect how end-of-line of a text of length SRC_BYTES pointed by SRC |
| 2835 | is encoded. Return one of CODING_EOL_LF, CODING_EOL_CRLF, |
| 2836 | CODING_EOL_CR, and CODING_EOL_UNDECIDED. */ |
| 2837 | |
| 2838 | #define MAX_EOL_CHECK_COUNT 3 |
| 2839 | |
| 2840 | int |
| 2841 | detect_eol_type (src, src_bytes) |
| 2842 | unsigned char *src; |
| 2843 | int src_bytes; |
| 2844 | { |
| 2845 | unsigned char *src_end = src + src_bytes; |
| 2846 | unsigned char c; |
| 2847 | int total = 0; /* How many end-of-lines are found so far. */ |
| 2848 | int eol_type = CODING_EOL_UNDECIDED; |
| 2849 | int this_eol_type; |
| 2850 | |
| 2851 | while (src < src_end && total < MAX_EOL_CHECK_COUNT) |
| 2852 | { |
| 2853 | c = *src++; |
| 2854 | if (c == '\n' || c == '\r') |
| 2855 | { |
| 2856 | total++; |
| 2857 | if (c == '\n') |
| 2858 | this_eol_type = CODING_EOL_LF; |
| 2859 | else if (src >= src_end || *src != '\n') |
| 2860 | this_eol_type = CODING_EOL_CR; |
| 2861 | else |
| 2862 | this_eol_type = CODING_EOL_CRLF, src++; |
| 2863 | |
| 2864 | if (eol_type == CODING_EOL_UNDECIDED) |
| 2865 | /* This is the first end-of-line. */ |
| 2866 | eol_type = this_eol_type; |
| 2867 | else if (eol_type != this_eol_type) |
| 2868 | /* The found type is different from what found before. |
| 2869 | Let's notice the caller about this inconsistency. */ |
| 2870 | return CODING_EOL_INCONSISTENT; |
| 2871 | } |
| 2872 | } |
| 2873 | |
| 2874 | return eol_type; |
| 2875 | } |
| 2876 | |
| 2877 | /* Detect how end-of-line of a text of length SRC_BYTES pointed by SRC |
| 2878 | is encoded. If it detects an appropriate format of end-of-line, it |
| 2879 | sets the information in *CODING. */ |
| 2880 | |
| 2881 | void |
| 2882 | detect_eol (coding, src, src_bytes) |
| 2883 | struct coding_system *coding; |
| 2884 | unsigned char *src; |
| 2885 | int src_bytes; |
| 2886 | { |
| 2887 | Lisp_Object val; |
| 2888 | int eol_type = detect_eol_type (src, src_bytes); |
| 2889 | |
| 2890 | if (eol_type == CODING_EOL_UNDECIDED) |
| 2891 | /* We found no end-of-line in the source text. */ |
| 2892 | return; |
| 2893 | |
| 2894 | if (eol_type == CODING_EOL_INCONSISTENT) |
| 2895 | { |
| 2896 | #if 0 |
| 2897 | /* This code is suppressed until we find a better way to |
| 2898 | distinguish raw text file and binary file. */ |
| 2899 | |
| 2900 | /* If we have already detected that the coding is raw-text, the |
| 2901 | coding should actually be no-conversion. */ |
| 2902 | if (coding->type == coding_type_raw_text) |
| 2903 | { |
| 2904 | setup_coding_system (Qno_conversion, coding); |
| 2905 | return; |
| 2906 | } |
| 2907 | /* Else, let's decode only text code anyway. */ |
| 2908 | #endif /* 0 */ |
| 2909 | eol_type = CODING_EOL_LF; |
| 2910 | } |
| 2911 | |
| 2912 | val = Fget (coding->symbol, Qeol_type); |
| 2913 | if (VECTORP (val) && XVECTOR (val)->size == 3) |
| 2914 | setup_coding_system (XVECTOR (val)->contents[eol_type], coding); |
| 2915 | } |
| 2916 | |
| 2917 | /* See "GENERAL NOTES about `decode_coding_XXX ()' functions". Before |
| 2918 | decoding, it may detect coding system and format of end-of-line if |
| 2919 | those are not yet decided. */ |
| 2920 | |
| 2921 | int |
| 2922 | decode_coding (coding, source, destination, src_bytes, dst_bytes, consumed) |
| 2923 | struct coding_system *coding; |
| 2924 | unsigned char *source, *destination; |
| 2925 | int src_bytes, dst_bytes; |
| 2926 | int *consumed; |
| 2927 | { |
| 2928 | int produced; |
| 2929 | |
| 2930 | if (src_bytes <= 0) |
| 2931 | { |
| 2932 | *consumed = 0; |
| 2933 | return 0; |
| 2934 | } |
| 2935 | |
| 2936 | if (coding->type == coding_type_undecided) |
| 2937 | detect_coding (coding, source, src_bytes); |
| 2938 | |
| 2939 | if (coding->eol_type == CODING_EOL_UNDECIDED) |
| 2940 | detect_eol (coding, source, src_bytes); |
| 2941 | |
| 2942 | coding->carryover_size = 0; |
| 2943 | switch (coding->type) |
| 2944 | { |
| 2945 | case coding_type_no_conversion: |
| 2946 | label_no_conversion: |
| 2947 | produced = (src_bytes > dst_bytes) ? dst_bytes : src_bytes; |
| 2948 | bcopy (source, destination, produced); |
| 2949 | *consumed = produced; |
| 2950 | break; |
| 2951 | |
| 2952 | case coding_type_emacs_mule: |
| 2953 | case coding_type_undecided: |
| 2954 | case coding_type_raw_text: |
| 2955 | if (coding->eol_type == CODING_EOL_LF |
| 2956 | || coding->eol_type == CODING_EOL_UNDECIDED) |
| 2957 | goto label_no_conversion; |
| 2958 | produced = decode_eol (coding, source, destination, |
| 2959 | src_bytes, dst_bytes, consumed); |
| 2960 | break; |
| 2961 | |
| 2962 | case coding_type_sjis: |
| 2963 | produced = decode_coding_sjis_big5 (coding, source, destination, |
| 2964 | src_bytes, dst_bytes, consumed, |
| 2965 | 1); |
| 2966 | break; |
| 2967 | |
| 2968 | case coding_type_iso2022: |
| 2969 | produced = decode_coding_iso2022 (coding, source, destination, |
| 2970 | src_bytes, dst_bytes, consumed); |
| 2971 | break; |
| 2972 | |
| 2973 | case coding_type_big5: |
| 2974 | produced = decode_coding_sjis_big5 (coding, source, destination, |
| 2975 | src_bytes, dst_bytes, consumed, |
| 2976 | 0); |
| 2977 | break; |
| 2978 | |
| 2979 | case coding_type_ccl: |
| 2980 | produced = ccl_driver (&coding->spec.ccl.decoder, source, destination, |
| 2981 | src_bytes, dst_bytes, consumed); |
| 2982 | break; |
| 2983 | } |
| 2984 | |
| 2985 | return produced; |
| 2986 | } |
| 2987 | |
| 2988 | /* See "GENERAL NOTES about `encode_coding_XXX ()' functions". */ |
| 2989 | |
| 2990 | int |
| 2991 | encode_coding (coding, source, destination, src_bytes, dst_bytes, consumed) |
| 2992 | struct coding_system *coding; |
| 2993 | unsigned char *source, *destination; |
| 2994 | int src_bytes, dst_bytes; |
| 2995 | int *consumed; |
| 2996 | { |
| 2997 | int produced; |
| 2998 | |
| 2999 | switch (coding->type) |
| 3000 | { |
| 3001 | case coding_type_no_conversion: |
| 3002 | label_no_conversion: |
| 3003 | produced = (src_bytes > dst_bytes) ? dst_bytes : src_bytes; |
| 3004 | if (produced > 0) |
| 3005 | { |
| 3006 | bcopy (source, destination, produced); |
| 3007 | if (coding->selective) |
| 3008 | { |
| 3009 | unsigned char *p = destination, *pend = destination + produced; |
| 3010 | while (p < pend) |
| 3011 | if (*p++ == '\015') p[-1] = '\n'; |
| 3012 | } |
| 3013 | } |
| 3014 | *consumed = produced; |
| 3015 | break; |
| 3016 | |
| 3017 | case coding_type_emacs_mule: |
| 3018 | case coding_type_undecided: |
| 3019 | case coding_type_raw_text: |
| 3020 | if (coding->eol_type == CODING_EOL_LF |
| 3021 | || coding->eol_type == CODING_EOL_UNDECIDED) |
| 3022 | goto label_no_conversion; |
| 3023 | produced = encode_eol (coding, source, destination, |
| 3024 | src_bytes, dst_bytes, consumed); |
| 3025 | break; |
| 3026 | |
| 3027 | case coding_type_sjis: |
| 3028 | produced = encode_coding_sjis_big5 (coding, source, destination, |
| 3029 | src_bytes, dst_bytes, consumed, |
| 3030 | 1); |
| 3031 | break; |
| 3032 | |
| 3033 | case coding_type_iso2022: |
| 3034 | produced = encode_coding_iso2022 (coding, source, destination, |
| 3035 | src_bytes, dst_bytes, consumed); |
| 3036 | break; |
| 3037 | |
| 3038 | case coding_type_big5: |
| 3039 | produced = encode_coding_sjis_big5 (coding, source, destination, |
| 3040 | src_bytes, dst_bytes, consumed, |
| 3041 | 0); |
| 3042 | break; |
| 3043 | |
| 3044 | case coding_type_ccl: |
| 3045 | produced = ccl_driver (&coding->spec.ccl.encoder, source, destination, |
| 3046 | src_bytes, dst_bytes, consumed); |
| 3047 | break; |
| 3048 | } |
| 3049 | |
| 3050 | return produced; |
| 3051 | } |
| 3052 | |
| 3053 | #define CONVERSION_BUFFER_EXTRA_ROOM 256 |
| 3054 | |
| 3055 | /* Return maximum size (bytes) of a buffer enough for decoding |
| 3056 | SRC_BYTES of text encoded in CODING. */ |
| 3057 | |
| 3058 | int |
| 3059 | decoding_buffer_size (coding, src_bytes) |
| 3060 | struct coding_system *coding; |
| 3061 | int src_bytes; |
| 3062 | { |
| 3063 | int magnification; |
| 3064 | |
| 3065 | if (coding->type == coding_type_iso2022) |
| 3066 | magnification = 3; |
| 3067 | else if (coding->type == coding_type_ccl) |
| 3068 | magnification = coding->spec.ccl.decoder.buf_magnification; |
| 3069 | else |
| 3070 | magnification = 2; |
| 3071 | |
| 3072 | return (src_bytes * magnification + CONVERSION_BUFFER_EXTRA_ROOM); |
| 3073 | } |
| 3074 | |
| 3075 | /* Return maximum size (bytes) of a buffer enough for encoding |
| 3076 | SRC_BYTES of text to CODING. */ |
| 3077 | |
| 3078 | int |
| 3079 | encoding_buffer_size (coding, src_bytes) |
| 3080 | struct coding_system *coding; |
| 3081 | int src_bytes; |
| 3082 | { |
| 3083 | int magnification; |
| 3084 | |
| 3085 | if (coding->type == coding_type_ccl) |
| 3086 | magnification = coding->spec.ccl.encoder.buf_magnification; |
| 3087 | else |
| 3088 | magnification = 3; |
| 3089 | |
| 3090 | return (src_bytes * magnification + CONVERSION_BUFFER_EXTRA_ROOM); |
| 3091 | } |
| 3092 | |
| 3093 | #ifndef MINIMUM_CONVERSION_BUFFER_SIZE |
| 3094 | #define MINIMUM_CONVERSION_BUFFER_SIZE 1024 |
| 3095 | #endif |
| 3096 | |
| 3097 | char *conversion_buffer; |
| 3098 | int conversion_buffer_size; |
| 3099 | |
| 3100 | /* Return a pointer to a SIZE bytes of buffer to be used for encoding |
| 3101 | or decoding. Sufficient memory is allocated automatically. If we |
| 3102 | run out of memory, return NULL. */ |
| 3103 | |
| 3104 | char * |
| 3105 | get_conversion_buffer (size) |
| 3106 | int size; |
| 3107 | { |
| 3108 | if (size > conversion_buffer_size) |
| 3109 | { |
| 3110 | char *buf; |
| 3111 | int real_size = conversion_buffer_size * 2; |
| 3112 | |
| 3113 | while (real_size < size) real_size *= 2; |
| 3114 | buf = (char *) xmalloc (real_size); |
| 3115 | xfree (conversion_buffer); |
| 3116 | conversion_buffer = buf; |
| 3117 | conversion_buffer_size = real_size; |
| 3118 | } |
| 3119 | return conversion_buffer; |
| 3120 | } |
| 3121 | |
| 3122 | \f |
| 3123 | #ifdef emacs |
| 3124 | /*** 7. Emacs Lisp library functions ***/ |
| 3125 | |
| 3126 | DEFUN ("coding-system-p", Fcoding_system_p, Scoding_system_p, 1, 1, 0, |
| 3127 | "Return t if OBJECT is nil or a coding-system.\n\ |
| 3128 | See document of make-coding-system for coding-system object.") |
| 3129 | (obj) |
| 3130 | Lisp_Object obj; |
| 3131 | { |
| 3132 | if (NILP (obj)) |
| 3133 | return Qt; |
| 3134 | if (!SYMBOLP (obj)) |
| 3135 | return Qnil; |
| 3136 | /* Get coding-spec vector for OBJ. */ |
| 3137 | obj = Fget (obj, Qcoding_system); |
| 3138 | return ((VECTORP (obj) && XVECTOR (obj)->size == 5) |
| 3139 | ? Qt : Qnil); |
| 3140 | } |
| 3141 | |
| 3142 | DEFUN ("read-non-nil-coding-system", Fread_non_nil_coding_system, |
| 3143 | Sread_non_nil_coding_system, 1, 1, 0, |
| 3144 | "Read a coding system from the minibuffer, prompting with string PROMPT.") |
| 3145 | (prompt) |
| 3146 | Lisp_Object prompt; |
| 3147 | { |
| 3148 | Lisp_Object val; |
| 3149 | do |
| 3150 | { |
| 3151 | val = Fcompleting_read (prompt, Vcoding_system_alist, Qnil, |
| 3152 | Qt, Qnil, Qcoding_system_history, Qnil, Qnil); |
| 3153 | } |
| 3154 | while (XSTRING (val)->size == 0); |
| 3155 | return (Fintern (val, Qnil)); |
| 3156 | } |
| 3157 | |
| 3158 | DEFUN ("read-coding-system", Fread_coding_system, Sread_coding_system, 1, 2, 0, |
| 3159 | "Read a coding system from the minibuffer, prompting with string PROMPT.\n\ |
| 3160 | If the user enters null input, return second argument DEFAULT-CODING-SYSTEM.") |
| 3161 | (prompt, default_coding_system) |
| 3162 | Lisp_Object prompt, default_coding_system; |
| 3163 | { |
| 3164 | Lisp_Object val; |
| 3165 | if (SYMBOLP (default_coding_system)) |
| 3166 | XSETSTRING (default_coding_system, XSYMBOL (default_coding_system)->name); |
| 3167 | val = Fcompleting_read (prompt, Vcoding_system_alist, Qnil, |
| 3168 | Qt, Qnil, Qcoding_system_history, |
| 3169 | default_coding_system, Qnil); |
| 3170 | return (XSTRING (val)->size == 0 ? Qnil : Fintern (val, Qnil)); |
| 3171 | } |
| 3172 | |
| 3173 | DEFUN ("check-coding-system", Fcheck_coding_system, Scheck_coding_system, |
| 3174 | 1, 1, 0, |
| 3175 | "Check validity of CODING-SYSTEM.\n\ |
| 3176 | If valid, return CODING-SYSTEM, else `coding-system-error' is signaled.\n\ |
| 3177 | CODING-SYSTEM is valid if it is a symbol and has \"coding-system\" property.\n\ |
| 3178 | The value of property should be a vector of length 5.") |
| 3179 | (coding_system) |
| 3180 | Lisp_Object coding_system; |
| 3181 | { |
| 3182 | CHECK_SYMBOL (coding_system, 0); |
| 3183 | if (!NILP (Fcoding_system_p (coding_system))) |
| 3184 | return coding_system; |
| 3185 | while (1) |
| 3186 | Fsignal (Qcoding_system_error, Fcons (coding_system, Qnil)); |
| 3187 | } |
| 3188 | |
| 3189 | DEFUN ("detect-coding-region", Fdetect_coding_region, Sdetect_coding_region, |
| 3190 | 2, 2, 0, |
| 3191 | "Detect coding system of the text in the region between START and END.\n\ |
| 3192 | Return a list of possible coding systems ordered by priority.\n\ |
| 3193 | If only ASCII characters are found, it returns `undecided'\n\ |
| 3194 | or its subsidiary coding system according to a detected end-of-line format.") |
| 3195 | (b, e) |
| 3196 | Lisp_Object b, e; |
| 3197 | { |
| 3198 | int coding_mask, eol_type; |
| 3199 | Lisp_Object val; |
| 3200 | int beg, end; |
| 3201 | int beg_byte, end_byte; |
| 3202 | |
| 3203 | validate_region (&b, &e); |
| 3204 | beg = XINT (b), end = XINT (e); |
| 3205 | beg_byte = CHAR_TO_BYTE (beg); |
| 3206 | end_byte = CHAR_TO_BYTE (end); |
| 3207 | |
| 3208 | if (beg < GPT && end >= GPT) |
| 3209 | move_gap_both (end, end_byte); |
| 3210 | |
| 3211 | coding_mask = detect_coding_mask (BYTE_POS_ADDR (beg_byte), |
| 3212 | end_byte - beg_byte); |
| 3213 | eol_type = detect_eol_type (BYTE_POS_ADDR (beg_byte), end_byte - beg_byte); |
| 3214 | |
| 3215 | if (coding_mask == CODING_CATEGORY_MASK_ANY) |
| 3216 | { |
| 3217 | val = Qundecided; |
| 3218 | if (eol_type != CODING_EOL_UNDECIDED |
| 3219 | && eol_type != CODING_EOL_INCONSISTENT) |
| 3220 | { |
| 3221 | Lisp_Object val2; |
| 3222 | val2 = Fget (Qundecided, Qeol_type); |
| 3223 | if (VECTORP (val2)) |
| 3224 | val = XVECTOR (val2)->contents[eol_type]; |
| 3225 | } |
| 3226 | } |
| 3227 | else |
| 3228 | { |
| 3229 | Lisp_Object val2; |
| 3230 | |
| 3231 | /* At first, gather possible coding-systems in VAL in a reverse |
| 3232 | order. */ |
| 3233 | val = Qnil; |
| 3234 | for (val2 = Vcoding_category_list; |
| 3235 | !NILP (val2); |
| 3236 | val2 = XCONS (val2)->cdr) |
| 3237 | { |
| 3238 | int idx |
| 3239 | = XFASTINT (Fget (XCONS (val2)->car, Qcoding_category_index)); |
| 3240 | if (coding_mask & (1 << idx)) |
| 3241 | { |
| 3242 | #if 0 |
| 3243 | /* This code is suppressed until we find a better way to |
| 3244 | distinguish raw text file and binary file. */ |
| 3245 | |
| 3246 | if (idx == CODING_CATEGORY_IDX_RAW_TEXT |
| 3247 | && eol_type == CODING_EOL_INCONSISTENT) |
| 3248 | val = Fcons (Qno_conversion, val); |
| 3249 | else |
| 3250 | #endif /* 0 */ |
| 3251 | val = Fcons (Fsymbol_value (XCONS (val2)->car), val); |
| 3252 | } |
| 3253 | } |
| 3254 | |
| 3255 | /* Then, change the order of the list, while getting subsidiary |
| 3256 | coding-systems. */ |
| 3257 | val2 = val; |
| 3258 | val = Qnil; |
| 3259 | if (eol_type == CODING_EOL_INCONSISTENT) |
| 3260 | eol_type == CODING_EOL_UNDECIDED; |
| 3261 | for (; !NILP (val2); val2 = XCONS (val2)->cdr) |
| 3262 | { |
| 3263 | if (eol_type == CODING_EOL_UNDECIDED) |
| 3264 | val = Fcons (XCONS (val2)->car, val); |
| 3265 | else |
| 3266 | { |
| 3267 | Lisp_Object val3; |
| 3268 | val3 = Fget (XCONS (val2)->car, Qeol_type); |
| 3269 | if (VECTORP (val3)) |
| 3270 | val = Fcons (XVECTOR (val3)->contents[eol_type], val); |
| 3271 | else |
| 3272 | val = Fcons (XCONS (val2)->car, val); |
| 3273 | } |
| 3274 | } |
| 3275 | } |
| 3276 | |
| 3277 | return val; |
| 3278 | } |
| 3279 | |
| 3280 | /* Scan text in the region between *BEGP and *ENDP, skip characters |
| 3281 | which we never have to encode to (iff ENCODEP is 1) or decode from |
| 3282 | coding system CODING at the head and tail, then set BEGP and ENDP |
| 3283 | to the addresses of start and end of the text we actually convert. */ |
| 3284 | |
| 3285 | void |
| 3286 | shrink_conversion_area (begp, endp, coding, encodep) |
| 3287 | unsigned char **begp, **endp; |
| 3288 | struct coding_system *coding; |
| 3289 | int encodep; |
| 3290 | { |
| 3291 | register unsigned char *beg_addr = *begp, *end_addr = *endp; |
| 3292 | |
| 3293 | if (coding->eol_type != CODING_EOL_LF |
| 3294 | && coding->eol_type != CODING_EOL_UNDECIDED) |
| 3295 | /* Since we anyway have to convert end-of-line format, it is not |
| 3296 | worth skipping at most 100 bytes or so. */ |
| 3297 | return; |
| 3298 | |
| 3299 | if (encodep) /* for encoding */ |
| 3300 | { |
| 3301 | switch (coding->type) |
| 3302 | { |
| 3303 | case coding_type_no_conversion: |
| 3304 | case coding_type_emacs_mule: |
| 3305 | case coding_type_undecided: |
| 3306 | case coding_type_raw_text: |
| 3307 | /* We need no conversion. */ |
| 3308 | *begp = *endp; |
| 3309 | return; |
| 3310 | case coding_type_ccl: |
| 3311 | /* We can't skip any data. */ |
| 3312 | return; |
| 3313 | case coding_type_iso2022: |
| 3314 | if (coding->flags & CODING_FLAG_ISO_DESIGNATE_AT_BOL) |
| 3315 | { |
| 3316 | unsigned char *bol = beg_addr; |
| 3317 | while (beg_addr < end_addr && *beg_addr < 0x80) |
| 3318 | { |
| 3319 | beg_addr++; |
| 3320 | if (*(beg_addr - 1) == '\n') |
| 3321 | bol = beg_addr; |
| 3322 | } |
| 3323 | beg_addr = bol; |
| 3324 | goto label_skip_tail; |
| 3325 | } |
| 3326 | /* fall down ... */ |
| 3327 | default: |
| 3328 | /* We can skip all ASCII characters at the head and tail. */ |
| 3329 | while (beg_addr < end_addr && *beg_addr < 0x80) beg_addr++; |
| 3330 | label_skip_tail: |
| 3331 | while (beg_addr < end_addr && *(end_addr - 1) < 0x80) end_addr--; |
| 3332 | break; |
| 3333 | } |
| 3334 | } |
| 3335 | else /* for decoding */ |
| 3336 | { |
| 3337 | switch (coding->type) |
| 3338 | { |
| 3339 | case coding_type_no_conversion: |
| 3340 | /* We need no conversion. */ |
| 3341 | *begp = *endp; |
| 3342 | return; |
| 3343 | case coding_type_emacs_mule: |
| 3344 | case coding_type_raw_text: |
| 3345 | if (coding->eol_type == CODING_EOL_LF) |
| 3346 | { |
| 3347 | /* We need no conversion. */ |
| 3348 | *begp = *endp; |
| 3349 | return; |
| 3350 | } |
| 3351 | /* We can skip all but carriage-return. */ |
| 3352 | while (beg_addr < end_addr && *beg_addr != '\r') beg_addr++; |
| 3353 | while (beg_addr < end_addr && *(end_addr - 1) != '\r') end_addr--; |
| 3354 | break; |
| 3355 | case coding_type_sjis: |
| 3356 | case coding_type_big5: |
| 3357 | /* We can skip all ASCII characters at the head. */ |
| 3358 | while (beg_addr < end_addr && *beg_addr < 0x80) beg_addr++; |
| 3359 | /* We can skip all ASCII characters at the tail except for |
| 3360 | the second byte of SJIS or BIG5 code. */ |
| 3361 | while (beg_addr < end_addr && *(end_addr - 1) < 0x80) end_addr--; |
| 3362 | if (end_addr != *endp) |
| 3363 | end_addr++; |
| 3364 | break; |
| 3365 | case coding_type_ccl: |
| 3366 | /* We can't skip any data. */ |
| 3367 | return; |
| 3368 | default: /* i.e. case coding_type_iso2022: */ |
| 3369 | { |
| 3370 | unsigned char c; |
| 3371 | |
| 3372 | /* We can skip all ASCII characters except for a few |
| 3373 | control codes at the head. */ |
| 3374 | while (beg_addr < end_addr && (c = *beg_addr) < 0x80 |
| 3375 | && c != ISO_CODE_CR && c != ISO_CODE_SO |
| 3376 | && c != ISO_CODE_SI && c != ISO_CODE_ESC) |
| 3377 | beg_addr++; |
| 3378 | } |
| 3379 | break; |
| 3380 | } |
| 3381 | } |
| 3382 | *begp = beg_addr; |
| 3383 | *endp = end_addr; |
| 3384 | return; |
| 3385 | } |
| 3386 | |
| 3387 | /* Encode into or decode from (according to ENCODEP) coding system CODING |
| 3388 | the text between char positions B and E. */ |
| 3389 | |
| 3390 | Lisp_Object |
| 3391 | code_convert_region (b, e, coding, encodep) |
| 3392 | Lisp_Object b, e; |
| 3393 | struct coding_system *coding; |
| 3394 | int encodep; |
| 3395 | { |
| 3396 | int beg, end, len, consumed, produced; |
| 3397 | char *buf; |
| 3398 | unsigned char *begp, *endp; |
| 3399 | int opoint = PT, opoint_byte = PT_BYTE; |
| 3400 | int beg_byte, end_byte, len_byte; |
| 3401 | int zv_before = ZV; |
| 3402 | int zv_byte_before = ZV_BYTE; |
| 3403 | |
| 3404 | validate_region (&b, &e); |
| 3405 | beg = XINT (b), end = XINT (e); |
| 3406 | beg_byte = CHAR_TO_BYTE (beg); |
| 3407 | end_byte = CHAR_TO_BYTE (end); |
| 3408 | |
| 3409 | if (beg < GPT && end >= GPT) |
| 3410 | move_gap_both (end, end_byte); |
| 3411 | |
| 3412 | if (encodep && !NILP (coding->pre_write_conversion)) |
| 3413 | { |
| 3414 | /* We must call a pre-conversion function which may put a new |
| 3415 | text to be converted in a new buffer. */ |
| 3416 | struct buffer *old = current_buffer, *new; |
| 3417 | |
| 3418 | TEMP_SET_PT_BOTH (beg, beg_byte); |
| 3419 | call2 (coding->pre_write_conversion, b, e); |
| 3420 | if (old != current_buffer) |
| 3421 | { |
| 3422 | /* Replace the original text by the text just generated. */ |
| 3423 | len = ZV - BEGV; |
| 3424 | len_byte = ZV_BYTE - BEGV_BYTE; |
| 3425 | new = current_buffer; |
| 3426 | set_buffer_internal (old); |
| 3427 | del_range_both (beg, end, beg_byte, end_byte, 1); |
| 3428 | insert_from_buffer (new, 1, len, 0); |
| 3429 | end = beg + len; |
| 3430 | end_byte = len_byte; |
| 3431 | } |
| 3432 | } |
| 3433 | |
| 3434 | /* We may be able to shrink the conversion region. */ |
| 3435 | begp = BYTE_POS_ADDR (beg_byte); |
| 3436 | endp = begp + (end_byte - beg_byte); |
| 3437 | shrink_conversion_area (&begp, &endp, coding, encodep); |
| 3438 | |
| 3439 | if (begp == endp) |
| 3440 | /* We need no conversion. */ |
| 3441 | len = end - beg; |
| 3442 | else |
| 3443 | { |
| 3444 | int shrunk_beg_byte, shrunk_end_byte; |
| 3445 | int shrunk_beg; |
| 3446 | int shrunk_len_byte; |
| 3447 | int new_len_byte; |
| 3448 | int buflen; |
| 3449 | int zv_before; |
| 3450 | |
| 3451 | shrunk_beg_byte = PTR_BYTE_POS (begp); |
| 3452 | shrunk_beg = BYTE_TO_CHAR (shrunk_beg_byte); |
| 3453 | shrunk_end_byte = PTR_BYTE_POS (endp); |
| 3454 | shrunk_len_byte = shrunk_end_byte - shrunk_beg_byte; |
| 3455 | |
| 3456 | if (encodep) |
| 3457 | buflen = encoding_buffer_size (coding, shrunk_len_byte); |
| 3458 | else |
| 3459 | buflen = decoding_buffer_size (coding, shrunk_len_byte); |
| 3460 | buf = get_conversion_buffer (buflen); |
| 3461 | |
| 3462 | coding->last_block = 1; |
| 3463 | produced = (encodep |
| 3464 | ? encode_coding (coding, begp, buf, shrunk_len_byte, buflen, |
| 3465 | &consumed) |
| 3466 | : decode_coding (coding, begp, buf, shrunk_len_byte, buflen, |
| 3467 | &consumed)); |
| 3468 | |
| 3469 | TEMP_SET_PT_BOTH (shrunk_beg, shrunk_beg_byte); |
| 3470 | insert (buf, produced); |
| 3471 | del_range_byte (PT_BYTE, PT_BYTE + shrunk_len_byte, 1); |
| 3472 | |
| 3473 | if (opoint >= end) |
| 3474 | { |
| 3475 | opoint += ZV - zv_before; |
| 3476 | opoint_byte += ZV_BYTE - zv_byte_before; |
| 3477 | } |
| 3478 | else if (opoint > beg) |
| 3479 | { |
| 3480 | opoint = beg; |
| 3481 | opoint_byte = beg_byte; |
| 3482 | } |
| 3483 | TEMP_SET_PT_BOTH (opoint, opoint_byte); |
| 3484 | |
| 3485 | end += ZV - zv_before; |
| 3486 | } |
| 3487 | |
| 3488 | if (!encodep && !NILP (coding->post_read_conversion)) |
| 3489 | { |
| 3490 | Lisp_Object insval; |
| 3491 | |
| 3492 | /* We must call a post-conversion function which may alter |
| 3493 | the text just converted. */ |
| 3494 | zv_before = ZV; |
| 3495 | zv_byte_before = ZV_BYTE; |
| 3496 | |
| 3497 | TEMP_SET_PT_BOTH (beg, beg_byte); |
| 3498 | insval = call1 (coding->post_read_conversion, make_number (end - beg)); |
| 3499 | CHECK_NUMBER (insval, 0); |
| 3500 | |
| 3501 | if (opoint >= beg + ZV - zv_before) |
| 3502 | { |
| 3503 | opoint += ZV - zv_before; |
| 3504 | opoint_byte += ZV_BYTE - zv_byte_before; |
| 3505 | } |
| 3506 | else if (opoint > beg) |
| 3507 | { |
| 3508 | opoint = beg; |
| 3509 | opoint_byte = beg_byte; |
| 3510 | } |
| 3511 | TEMP_SET_PT_BOTH (opoint, opoint_byte); |
| 3512 | len = XINT (insval); |
| 3513 | } |
| 3514 | |
| 3515 | return make_number (len); |
| 3516 | } |
| 3517 | |
| 3518 | /* Encode or decode (according to ENCODEP) the text of string STR |
| 3519 | using coding CODING. If NOCOPY is nil, we never return STR |
| 3520 | itself, but always a copy. If NOCOPY is non-nil, we return STR |
| 3521 | if no change is needed. */ |
| 3522 | |
| 3523 | Lisp_Object |
| 3524 | code_convert_string (str, coding, encodep, nocopy) |
| 3525 | Lisp_Object str, nocopy; |
| 3526 | struct coding_system *coding; |
| 3527 | int encodep; |
| 3528 | { |
| 3529 | int len, consumed, produced; |
| 3530 | char *buf; |
| 3531 | unsigned char *begp, *endp; |
| 3532 | int head_skip, tail_skip; |
| 3533 | struct gcpro gcpro1; |
| 3534 | |
| 3535 | if (encodep && !NILP (coding->pre_write_conversion) |
| 3536 | || !encodep && !NILP (coding->post_read_conversion)) |
| 3537 | { |
| 3538 | /* Since we have to call Lisp functions which assume target text |
| 3539 | is in a buffer, after setting a temporary buffer, call |
| 3540 | code_convert_region. */ |
| 3541 | int count = specpdl_ptr - specpdl; |
| 3542 | int len = XSTRING (str)->size; |
| 3543 | Lisp_Object result; |
| 3544 | struct buffer *old = current_buffer; |
| 3545 | |
| 3546 | record_unwind_protect (Fset_buffer, Fcurrent_buffer ()); |
| 3547 | temp_output_buffer_setup (" *code-converting-work*"); |
| 3548 | set_buffer_internal (XBUFFER (Vstandard_output)); |
| 3549 | insert_from_string (str, 0, len, 0); |
| 3550 | code_convert_region (make_number (BEGV), make_number (ZV), |
| 3551 | coding, encodep); |
| 3552 | result = make_buffer_string (BEGV, ZV, 0); |
| 3553 | set_buffer_internal (old); |
| 3554 | return unbind_to (count, result); |
| 3555 | } |
| 3556 | |
| 3557 | /* We may be able to shrink the conversion region. */ |
| 3558 | begp = XSTRING (str)->data; |
| 3559 | endp = begp + XSTRING (str)->size; |
| 3560 | shrink_conversion_area (&begp, &endp, coding, encodep); |
| 3561 | |
| 3562 | if (begp == endp) |
| 3563 | /* We need no conversion. */ |
| 3564 | return (NILP (nocopy) ? Fcopy_sequence (str) : str); |
| 3565 | |
| 3566 | head_skip = begp - XSTRING (str)->data; |
| 3567 | tail_skip = XSTRING (str)->size - head_skip - (endp - begp); |
| 3568 | |
| 3569 | GCPRO1 (str); |
| 3570 | |
| 3571 | if (encodep) |
| 3572 | len = encoding_buffer_size (coding, endp - begp); |
| 3573 | else |
| 3574 | len = decoding_buffer_size (coding, endp - begp); |
| 3575 | buf = get_conversion_buffer (len + head_skip + tail_skip); |
| 3576 | |
| 3577 | bcopy (XSTRING (str)->data, buf, head_skip); |
| 3578 | coding->last_block = 1; |
| 3579 | produced = (encodep |
| 3580 | ? encode_coding (coding, XSTRING (str)->data + head_skip, |
| 3581 | buf + head_skip, endp - begp, len, &consumed) |
| 3582 | : decode_coding (coding, XSTRING (str)->data + head_skip, |
| 3583 | buf + head_skip, endp - begp, len, &consumed)); |
| 3584 | bcopy (XSTRING (str)->data + head_skip + (endp - begp), |
| 3585 | buf + head_skip + produced, |
| 3586 | tail_skip); |
| 3587 | |
| 3588 | UNGCPRO; |
| 3589 | |
| 3590 | return make_string (buf, head_skip + produced + tail_skip); |
| 3591 | } |
| 3592 | |
| 3593 | DEFUN ("decode-coding-region", Fdecode_coding_region, Sdecode_coding_region, |
| 3594 | 3, 3, "r\nzCoding system: ", |
| 3595 | "Decode current region by specified coding system.\n\ |
| 3596 | When called from a program, takes three arguments:\n\ |
| 3597 | START, END, and CODING-SYSTEM. START END are buffer positions.\n\ |
| 3598 | Return length of decoded text.") |
| 3599 | (b, e, coding_system) |
| 3600 | Lisp_Object b, e, coding_system; |
| 3601 | { |
| 3602 | struct coding_system coding; |
| 3603 | |
| 3604 | CHECK_NUMBER_COERCE_MARKER (b, 0); |
| 3605 | CHECK_NUMBER_COERCE_MARKER (e, 1); |
| 3606 | CHECK_SYMBOL (coding_system, 2); |
| 3607 | |
| 3608 | if (NILP (coding_system)) |
| 3609 | return make_number (XFASTINT (e) - XFASTINT (b)); |
| 3610 | if (setup_coding_system (Fcheck_coding_system (coding_system), &coding) < 0) |
| 3611 | error ("Invalid coding-system: %s", XSYMBOL (coding_system)->name->data); |
| 3612 | |
| 3613 | return code_convert_region (b, e, &coding, 0); |
| 3614 | } |
| 3615 | |
| 3616 | DEFUN ("encode-coding-region", Fencode_coding_region, Sencode_coding_region, |
| 3617 | 3, 3, "r\nzCoding system: ", |
| 3618 | "Encode current region by specified coding system.\n\ |
| 3619 | When called from a program, takes three arguments:\n\ |
| 3620 | START, END, and CODING-SYSTEM. START END are buffer positions.\n\ |
| 3621 | Return length of encoded text.") |
| 3622 | (b, e, coding_system) |
| 3623 | Lisp_Object b, e, coding_system; |
| 3624 | { |
| 3625 | struct coding_system coding; |
| 3626 | |
| 3627 | CHECK_NUMBER_COERCE_MARKER (b, 0); |
| 3628 | CHECK_NUMBER_COERCE_MARKER (e, 1); |
| 3629 | CHECK_SYMBOL (coding_system, 2); |
| 3630 | |
| 3631 | if (NILP (coding_system)) |
| 3632 | return make_number (XFASTINT (e) - XFASTINT (b)); |
| 3633 | if (setup_coding_system (Fcheck_coding_system (coding_system), &coding) < 0) |
| 3634 | error ("Invalid coding-system: %s", XSYMBOL (coding_system)->name->data); |
| 3635 | |
| 3636 | return code_convert_region (b, e, &coding, 1); |
| 3637 | } |
| 3638 | |
| 3639 | DEFUN ("decode-coding-string", Fdecode_coding_string, Sdecode_coding_string, |
| 3640 | 2, 3, 0, |
| 3641 | "Decode STRING which is encoded in CODING-SYSTEM, and return the result.\n\ |
| 3642 | Optional arg NOCOPY non-nil means it is ok to return STRING itself\n\ |
| 3643 | if the decoding operation is trivial.") |
| 3644 | (string, coding_system, nocopy) |
| 3645 | Lisp_Object string, coding_system, nocopy; |
| 3646 | { |
| 3647 | struct coding_system coding; |
| 3648 | |
| 3649 | CHECK_STRING (string, 0); |
| 3650 | CHECK_SYMBOL (coding_system, 1); |
| 3651 | |
| 3652 | if (NILP (coding_system)) |
| 3653 | return (NILP (nocopy) ? Fcopy_sequence (string) : string); |
| 3654 | if (setup_coding_system (Fcheck_coding_system (coding_system), &coding) < 0) |
| 3655 | error ("Invalid coding-system: %s", XSYMBOL (coding_system)->name->data); |
| 3656 | |
| 3657 | return code_convert_string (string, &coding, 0, nocopy); |
| 3658 | } |
| 3659 | |
| 3660 | DEFUN ("encode-coding-string", Fencode_coding_string, Sencode_coding_string, |
| 3661 | 2, 3, 0, |
| 3662 | "Encode STRING to CODING-SYSTEM, and return the result.\n\ |
| 3663 | Optional arg NOCOPY non-nil means it is ok to return STRING itself\n\ |
| 3664 | if the encoding operation is trivial.") |
| 3665 | (string, coding_system, nocopy) |
| 3666 | Lisp_Object string, coding_system, nocopy; |
| 3667 | { |
| 3668 | struct coding_system coding; |
| 3669 | |
| 3670 | CHECK_STRING (string, 0); |
| 3671 | CHECK_SYMBOL (coding_system, 1); |
| 3672 | |
| 3673 | if (NILP (coding_system)) |
| 3674 | return (NILP (nocopy) ? Fcopy_sequence (string) : string); |
| 3675 | if (setup_coding_system (Fcheck_coding_system (coding_system), &coding) < 0) |
| 3676 | error ("Invalid coding-system: %s", XSYMBOL (coding_system)->name->data); |
| 3677 | |
| 3678 | return code_convert_string (string, &coding, 1, nocopy); |
| 3679 | } |
| 3680 | |
| 3681 | DEFUN ("decode-sjis-char", Fdecode_sjis_char, Sdecode_sjis_char, 1, 1, 0, |
| 3682 | "Decode a JISX0208 character of shift-jis encoding.\n\ |
| 3683 | CODE is the character code in SJIS.\n\ |
| 3684 | Return the corresponding character.") |
| 3685 | (code) |
| 3686 | Lisp_Object code; |
| 3687 | { |
| 3688 | unsigned char c1, c2, s1, s2; |
| 3689 | Lisp_Object val; |
| 3690 | |
| 3691 | CHECK_NUMBER (code, 0); |
| 3692 | s1 = (XFASTINT (code)) >> 8, s2 = (XFASTINT (code)) & 0xFF; |
| 3693 | DECODE_SJIS (s1, s2, c1, c2); |
| 3694 | XSETFASTINT (val, MAKE_NON_ASCII_CHAR (charset_jisx0208, c1, c2)); |
| 3695 | return val; |
| 3696 | } |
| 3697 | |
| 3698 | DEFUN ("encode-sjis-char", Fencode_sjis_char, Sencode_sjis_char, 1, 1, 0, |
| 3699 | "Encode a JISX0208 character CHAR to SJIS coding-system.\n\ |
| 3700 | Return the corresponding character code in SJIS.") |
| 3701 | (ch) |
| 3702 | Lisp_Object ch; |
| 3703 | { |
| 3704 | int charset, c1, c2, s1, s2; |
| 3705 | Lisp_Object val; |
| 3706 | |
| 3707 | CHECK_NUMBER (ch, 0); |
| 3708 | SPLIT_CHAR (XFASTINT (ch), charset, c1, c2); |
| 3709 | if (charset == charset_jisx0208) |
| 3710 | { |
| 3711 | ENCODE_SJIS (c1, c2, s1, s2); |
| 3712 | XSETFASTINT (val, (s1 << 8) | s2); |
| 3713 | } |
| 3714 | else |
| 3715 | XSETFASTINT (val, 0); |
| 3716 | return val; |
| 3717 | } |
| 3718 | |
| 3719 | DEFUN ("decode-big5-char", Fdecode_big5_char, Sdecode_big5_char, 1, 1, 0, |
| 3720 | "Decode a Big5 character CODE of BIG5 coding-system.\n\ |
| 3721 | CODE is the character code in BIG5.\n\ |
| 3722 | Return the corresponding character.") |
| 3723 | (code) |
| 3724 | Lisp_Object code; |
| 3725 | { |
| 3726 | int charset; |
| 3727 | unsigned char b1, b2, c1, c2; |
| 3728 | Lisp_Object val; |
| 3729 | |
| 3730 | CHECK_NUMBER (code, 0); |
| 3731 | b1 = (XFASTINT (code)) >> 8, b2 = (XFASTINT (code)) & 0xFF; |
| 3732 | DECODE_BIG5 (b1, b2, charset, c1, c2); |
| 3733 | XSETFASTINT (val, MAKE_NON_ASCII_CHAR (charset, c1, c2)); |
| 3734 | return val; |
| 3735 | } |
| 3736 | |
| 3737 | DEFUN ("encode-big5-char", Fencode_big5_char, Sencode_big5_char, 1, 1, 0, |
| 3738 | "Encode the Big5 character CHAR to BIG5 coding-system.\n\ |
| 3739 | Return the corresponding character code in Big5.") |
| 3740 | (ch) |
| 3741 | Lisp_Object ch; |
| 3742 | { |
| 3743 | int charset, c1, c2, b1, b2; |
| 3744 | Lisp_Object val; |
| 3745 | |
| 3746 | CHECK_NUMBER (ch, 0); |
| 3747 | SPLIT_CHAR (XFASTINT (ch), charset, c1, c2); |
| 3748 | if (charset == charset_big5_1 || charset == charset_big5_2) |
| 3749 | { |
| 3750 | ENCODE_BIG5 (charset, c1, c2, b1, b2); |
| 3751 | XSETFASTINT (val, (b1 << 8) | b2); |
| 3752 | } |
| 3753 | else |
| 3754 | XSETFASTINT (val, 0); |
| 3755 | return val; |
| 3756 | } |
| 3757 | |
| 3758 | DEFUN ("set-terminal-coding-system-internal", |
| 3759 | Fset_terminal_coding_system_internal, |
| 3760 | Sset_terminal_coding_system_internal, 1, 1, 0, "") |
| 3761 | (coding_system) |
| 3762 | Lisp_Object coding_system; |
| 3763 | { |
| 3764 | CHECK_SYMBOL (coding_system, 0); |
| 3765 | setup_coding_system (Fcheck_coding_system (coding_system), &terminal_coding); |
| 3766 | /* We had better not send unsafe characters to terminal. */ |
| 3767 | terminal_coding.flags |= CODING_FLAG_ISO_SAFE; |
| 3768 | |
| 3769 | return Qnil; |
| 3770 | } |
| 3771 | |
| 3772 | DEFUN ("set-safe-terminal-coding-system-internal", |
| 3773 | Fset_safe_terminal_coding_system_internal, |
| 3774 | Sset_safe_terminal_coding_system_internal, 1, 1, 0, "") |
| 3775 | (coding_system) |
| 3776 | Lisp_Object coding_system; |
| 3777 | { |
| 3778 | CHECK_SYMBOL (coding_system, 0); |
| 3779 | setup_coding_system (Fcheck_coding_system (coding_system), |
| 3780 | &safe_terminal_coding); |
| 3781 | return Qnil; |
| 3782 | } |
| 3783 | |
| 3784 | DEFUN ("terminal-coding-system", |
| 3785 | Fterminal_coding_system, Sterminal_coding_system, 0, 0, 0, |
| 3786 | "Return coding-system of your terminal.") |
| 3787 | () |
| 3788 | { |
| 3789 | return terminal_coding.symbol; |
| 3790 | } |
| 3791 | |
| 3792 | DEFUN ("set-keyboard-coding-system-internal", |
| 3793 | Fset_keyboard_coding_system_internal, |
| 3794 | Sset_keyboard_coding_system_internal, 1, 1, 0, "") |
| 3795 | (coding_system) |
| 3796 | Lisp_Object coding_system; |
| 3797 | { |
| 3798 | CHECK_SYMBOL (coding_system, 0); |
| 3799 | setup_coding_system (Fcheck_coding_system (coding_system), &keyboard_coding); |
| 3800 | return Qnil; |
| 3801 | } |
| 3802 | |
| 3803 | DEFUN ("keyboard-coding-system", |
| 3804 | Fkeyboard_coding_system, Skeyboard_coding_system, 0, 0, 0, |
| 3805 | "Return coding-system of what is sent from terminal keyboard.") |
| 3806 | () |
| 3807 | { |
| 3808 | return keyboard_coding.symbol; |
| 3809 | } |
| 3810 | |
| 3811 | \f |
| 3812 | DEFUN ("find-operation-coding-system", Ffind_operation_coding_system, |
| 3813 | Sfind_operation_coding_system, 1, MANY, 0, |
| 3814 | "Choose a coding system for an operation based on the target name.\n\ |
| 3815 | The value names a pair of coding systems: (DECODING-SYSTEM ENCODING-SYSTEM).\n\ |
| 3816 | DECODING-SYSTEM is the coding system to use for decoding\n\ |
| 3817 | \(in case OPERATION does decoding), and ENCODING-SYSTEM is the coding system\n\ |
| 3818 | for encoding (in case OPERATION does encoding).\n\ |
| 3819 | \n\ |
| 3820 | The first argument OPERATION specifies an I/O primitive:\n\ |
| 3821 | For file I/O, `insert-file-contents' or `write-region'.\n\ |
| 3822 | For process I/O, `call-process', `call-process-region', or `start-process'.\n\ |
| 3823 | For network I/O, `open-network-stream'.\n\ |
| 3824 | \n\ |
| 3825 | The remaining arguments should be the same arguments that were passed\n\ |
| 3826 | to the primitive. Depending on which primitive, one of those arguments\n\ |
| 3827 | is selected as the TARGET. For example, if OPERATION does file I/O,\n\ |
| 3828 | whichever argument specifies the file name is TARGET.\n\ |
| 3829 | \n\ |
| 3830 | TARGET has a meaning which depends on OPERATION:\n\ |
| 3831 | For file I/O, TARGET is a file name.\n\ |
| 3832 | For process I/O, TARGET is a process name.\n\ |
| 3833 | For network I/O, TARGET is a service name or a port number\n\ |
| 3834 | \n\ |
| 3835 | This function looks up what specified for TARGET in,\n\ |
| 3836 | `file-coding-system-alist', `process-coding-system-alist',\n\ |
| 3837 | or `network-coding-system-alist' depending on OPERATION.\n\ |
| 3838 | They may specify a coding system, a cons of coding systems,\n\ |
| 3839 | or a function symbol to call.\n\ |
| 3840 | In the last case, we call the function with one argument,\n\ |
| 3841 | which is a list of all the arguments given to this function.") |
| 3842 | (nargs, args) |
| 3843 | int nargs; |
| 3844 | Lisp_Object *args; |
| 3845 | { |
| 3846 | Lisp_Object operation, target_idx, target, val; |
| 3847 | register Lisp_Object chain; |
| 3848 | |
| 3849 | if (nargs < 2) |
| 3850 | error ("Too few arguments"); |
| 3851 | operation = args[0]; |
| 3852 | if (!SYMBOLP (operation) |
| 3853 | || !INTEGERP (target_idx = Fget (operation, Qtarget_idx))) |
| 3854 | error ("Invalid first arguement"); |
| 3855 | if (nargs < 1 + XINT (target_idx)) |
| 3856 | error ("Too few arguments for operation: %s", |
| 3857 | XSYMBOL (operation)->name->data); |
| 3858 | target = args[XINT (target_idx) + 1]; |
| 3859 | if (!(STRINGP (target) |
| 3860 | || (EQ (operation, Qopen_network_stream) && INTEGERP (target)))) |
| 3861 | error ("Invalid %dth argument", XINT (target_idx) + 1); |
| 3862 | |
| 3863 | chain = ((EQ (operation, Qinsert_file_contents) |
| 3864 | || EQ (operation, Qwrite_region)) |
| 3865 | ? Vfile_coding_system_alist |
| 3866 | : (EQ (operation, Qopen_network_stream) |
| 3867 | ? Vnetwork_coding_system_alist |
| 3868 | : Vprocess_coding_system_alist)); |
| 3869 | if (NILP (chain)) |
| 3870 | return Qnil; |
| 3871 | |
| 3872 | for (; CONSP (chain); chain = XCONS (chain)->cdr) |
| 3873 | { |
| 3874 | Lisp_Object elt; |
| 3875 | elt = XCONS (chain)->car; |
| 3876 | |
| 3877 | if (CONSP (elt) |
| 3878 | && ((STRINGP (target) |
| 3879 | && STRINGP (XCONS (elt)->car) |
| 3880 | && fast_string_match (XCONS (elt)->car, target) >= 0) |
| 3881 | || (INTEGERP (target) && EQ (target, XCONS (elt)->car)))) |
| 3882 | { |
| 3883 | val = XCONS (elt)->cdr; |
| 3884 | /* Here, if VAL is both a valid coding system and a valid |
| 3885 | function symbol, we return VAL as a coding system. */ |
| 3886 | if (CONSP (val)) |
| 3887 | return val; |
| 3888 | if (! SYMBOLP (val)) |
| 3889 | return Qnil; |
| 3890 | if (! NILP (Fcoding_system_p (val))) |
| 3891 | return Fcons (val, val); |
| 3892 | if (! NILP (Ffboundp (val))) |
| 3893 | { |
| 3894 | val = call1 (val, Flist (nargs, args)); |
| 3895 | if (CONSP (val)) |
| 3896 | return val; |
| 3897 | if (SYMBOLP (val) && ! NILP (Fcoding_system_p (val))) |
| 3898 | return Fcons (val, val); |
| 3899 | } |
| 3900 | return Qnil; |
| 3901 | } |
| 3902 | } |
| 3903 | return Qnil; |
| 3904 | } |
| 3905 | |
| 3906 | #endif /* emacs */ |
| 3907 | |
| 3908 | \f |
| 3909 | /*** 8. Post-amble ***/ |
| 3910 | |
| 3911 | init_coding_once () |
| 3912 | { |
| 3913 | int i; |
| 3914 | |
| 3915 | /* Emacs' internal format specific initialize routine. */ |
| 3916 | for (i = 0; i <= 0x20; i++) |
| 3917 | emacs_code_class[i] = EMACS_control_code; |
| 3918 | emacs_code_class[0x0A] = EMACS_linefeed_code; |
| 3919 | emacs_code_class[0x0D] = EMACS_carriage_return_code; |
| 3920 | for (i = 0x21 ; i < 0x7F; i++) |
| 3921 | emacs_code_class[i] = EMACS_ascii_code; |
| 3922 | emacs_code_class[0x7F] = EMACS_control_code; |
| 3923 | emacs_code_class[0x80] = EMACS_leading_code_composition; |
| 3924 | for (i = 0x81; i < 0xFF; i++) |
| 3925 | emacs_code_class[i] = EMACS_invalid_code; |
| 3926 | emacs_code_class[LEADING_CODE_PRIVATE_11] = EMACS_leading_code_3; |
| 3927 | emacs_code_class[LEADING_CODE_PRIVATE_12] = EMACS_leading_code_3; |
| 3928 | emacs_code_class[LEADING_CODE_PRIVATE_21] = EMACS_leading_code_4; |
| 3929 | emacs_code_class[LEADING_CODE_PRIVATE_22] = EMACS_leading_code_4; |
| 3930 | |
| 3931 | /* ISO2022 specific initialize routine. */ |
| 3932 | for (i = 0; i < 0x20; i++) |
| 3933 | iso_code_class[i] = ISO_control_code; |
| 3934 | for (i = 0x21; i < 0x7F; i++) |
| 3935 | iso_code_class[i] = ISO_graphic_plane_0; |
| 3936 | for (i = 0x80; i < 0xA0; i++) |
| 3937 | iso_code_class[i] = ISO_control_code; |
| 3938 | for (i = 0xA1; i < 0xFF; i++) |
| 3939 | iso_code_class[i] = ISO_graphic_plane_1; |
| 3940 | iso_code_class[0x20] = iso_code_class[0x7F] = ISO_0x20_or_0x7F; |
| 3941 | iso_code_class[0xA0] = iso_code_class[0xFF] = ISO_0xA0_or_0xFF; |
| 3942 | iso_code_class[ISO_CODE_CR] = ISO_carriage_return; |
| 3943 | iso_code_class[ISO_CODE_SO] = ISO_shift_out; |
| 3944 | iso_code_class[ISO_CODE_SI] = ISO_shift_in; |
| 3945 | iso_code_class[ISO_CODE_SS2_7] = ISO_single_shift_2_7; |
| 3946 | iso_code_class[ISO_CODE_ESC] = ISO_escape; |
| 3947 | iso_code_class[ISO_CODE_SS2] = ISO_single_shift_2; |
| 3948 | iso_code_class[ISO_CODE_SS3] = ISO_single_shift_3; |
| 3949 | iso_code_class[ISO_CODE_CSI] = ISO_control_sequence_introducer; |
| 3950 | |
| 3951 | conversion_buffer_size = MINIMUM_CONVERSION_BUFFER_SIZE; |
| 3952 | conversion_buffer = (char *) xmalloc (MINIMUM_CONVERSION_BUFFER_SIZE); |
| 3953 | |
| 3954 | setup_coding_system (Qnil, &keyboard_coding); |
| 3955 | setup_coding_system (Qnil, &terminal_coding); |
| 3956 | setup_coding_system (Qnil, &safe_terminal_coding); |
| 3957 | |
| 3958 | #if defined (MSDOS) || defined (WINDOWSNT) |
| 3959 | system_eol_type = CODING_EOL_CRLF; |
| 3960 | #else |
| 3961 | system_eol_type = CODING_EOL_LF; |
| 3962 | #endif |
| 3963 | } |
| 3964 | |
| 3965 | #ifdef emacs |
| 3966 | |
| 3967 | syms_of_coding () |
| 3968 | { |
| 3969 | Qtarget_idx = intern ("target-idx"); |
| 3970 | staticpro (&Qtarget_idx); |
| 3971 | |
| 3972 | Qcoding_system_history = intern ("coding-system-history"); |
| 3973 | staticpro (&Qcoding_system_history); |
| 3974 | Fset (Qcoding_system_history, Qnil); |
| 3975 | |
| 3976 | /* Target FILENAME is the first argument. */ |
| 3977 | Fput (Qinsert_file_contents, Qtarget_idx, make_number (0)); |
| 3978 | /* Target FILENAME is the third argument. */ |
| 3979 | Fput (Qwrite_region, Qtarget_idx, make_number (2)); |
| 3980 | |
| 3981 | Qcall_process = intern ("call-process"); |
| 3982 | staticpro (&Qcall_process); |
| 3983 | /* Target PROGRAM is the first argument. */ |
| 3984 | Fput (Qcall_process, Qtarget_idx, make_number (0)); |
| 3985 | |
| 3986 | Qcall_process_region = intern ("call-process-region"); |
| 3987 | staticpro (&Qcall_process_region); |
| 3988 | /* Target PROGRAM is the third argument. */ |
| 3989 | Fput (Qcall_process_region, Qtarget_idx, make_number (2)); |
| 3990 | |
| 3991 | Qstart_process = intern ("start-process"); |
| 3992 | staticpro (&Qstart_process); |
| 3993 | /* Target PROGRAM is the third argument. */ |
| 3994 | Fput (Qstart_process, Qtarget_idx, make_number (2)); |
| 3995 | |
| 3996 | Qopen_network_stream = intern ("open-network-stream"); |
| 3997 | staticpro (&Qopen_network_stream); |
| 3998 | /* Target SERVICE is the fourth argument. */ |
| 3999 | Fput (Qopen_network_stream, Qtarget_idx, make_number (3)); |
| 4000 | |
| 4001 | Qcoding_system = intern ("coding-system"); |
| 4002 | staticpro (&Qcoding_system); |
| 4003 | |
| 4004 | Qeol_type = intern ("eol-type"); |
| 4005 | staticpro (&Qeol_type); |
| 4006 | |
| 4007 | Qbuffer_file_coding_system = intern ("buffer-file-coding-system"); |
| 4008 | staticpro (&Qbuffer_file_coding_system); |
| 4009 | |
| 4010 | Qpost_read_conversion = intern ("post-read-conversion"); |
| 4011 | staticpro (&Qpost_read_conversion); |
| 4012 | |
| 4013 | Qpre_write_conversion = intern ("pre-write-conversion"); |
| 4014 | staticpro (&Qpre_write_conversion); |
| 4015 | |
| 4016 | Qno_conversion = intern ("no-conversion"); |
| 4017 | staticpro (&Qno_conversion); |
| 4018 | |
| 4019 | Qundecided = intern ("undecided"); |
| 4020 | staticpro (&Qundecided); |
| 4021 | |
| 4022 | Qcoding_system_p = intern ("coding-system-p"); |
| 4023 | staticpro (&Qcoding_system_p); |
| 4024 | |
| 4025 | Qcoding_system_error = intern ("coding-system-error"); |
| 4026 | staticpro (&Qcoding_system_error); |
| 4027 | |
| 4028 | Fput (Qcoding_system_error, Qerror_conditions, |
| 4029 | Fcons (Qcoding_system_error, Fcons (Qerror, Qnil))); |
| 4030 | Fput (Qcoding_system_error, Qerror_message, |
| 4031 | build_string ("Invalid coding system")); |
| 4032 | |
| 4033 | Qcoding_category_index = intern ("coding-category-index"); |
| 4034 | staticpro (&Qcoding_category_index); |
| 4035 | |
| 4036 | { |
| 4037 | int i; |
| 4038 | for (i = 0; i < CODING_CATEGORY_IDX_MAX; i++) |
| 4039 | { |
| 4040 | coding_category_table[i] = intern (coding_category_name[i]); |
| 4041 | staticpro (&coding_category_table[i]); |
| 4042 | Fput (coding_category_table[i], Qcoding_category_index, |
| 4043 | make_number (i)); |
| 4044 | } |
| 4045 | } |
| 4046 | |
| 4047 | Qcharacter_unification_table = intern ("character-unification-table"); |
| 4048 | staticpro (&Qcharacter_unification_table); |
| 4049 | Fput (Qcharacter_unification_table, Qchar_table_extra_slots, |
| 4050 | make_number (0)); |
| 4051 | |
| 4052 | Qcharacter_unification_table_for_decode |
| 4053 | = intern ("character-unification-table-for-decode"); |
| 4054 | staticpro (&Qcharacter_unification_table_for_decode); |
| 4055 | |
| 4056 | Qcharacter_unification_table_for_encode |
| 4057 | = intern ("character-unification-table-for-encode"); |
| 4058 | staticpro (&Qcharacter_unification_table_for_encode); |
| 4059 | |
| 4060 | Qsafe_charsets = intern ("safe-charsets"); |
| 4061 | staticpro (&Qsafe_charsets); |
| 4062 | |
| 4063 | Qemacs_mule = intern ("emacs-mule"); |
| 4064 | staticpro (&Qemacs_mule); |
| 4065 | |
| 4066 | defsubr (&Scoding_system_p); |
| 4067 | defsubr (&Sread_coding_system); |
| 4068 | defsubr (&Sread_non_nil_coding_system); |
| 4069 | defsubr (&Scheck_coding_system); |
| 4070 | defsubr (&Sdetect_coding_region); |
| 4071 | defsubr (&Sdecode_coding_region); |
| 4072 | defsubr (&Sencode_coding_region); |
| 4073 | defsubr (&Sdecode_coding_string); |
| 4074 | defsubr (&Sencode_coding_string); |
| 4075 | defsubr (&Sdecode_sjis_char); |
| 4076 | defsubr (&Sencode_sjis_char); |
| 4077 | defsubr (&Sdecode_big5_char); |
| 4078 | defsubr (&Sencode_big5_char); |
| 4079 | defsubr (&Sset_terminal_coding_system_internal); |
| 4080 | defsubr (&Sset_safe_terminal_coding_system_internal); |
| 4081 | defsubr (&Sterminal_coding_system); |
| 4082 | defsubr (&Sset_keyboard_coding_system_internal); |
| 4083 | defsubr (&Skeyboard_coding_system); |
| 4084 | defsubr (&Sfind_operation_coding_system); |
| 4085 | |
| 4086 | DEFVAR_LISP ("coding-system-list", &Vcoding_system_list, |
| 4087 | "List of coding systems.\n\ |
| 4088 | \n\ |
| 4089 | Do not alter the value of this variable manually. This variable should be\n\ |
| 4090 | updated by the functions `make-coding-system' and\n\ |
| 4091 | `define-coding-system-alias'."); |
| 4092 | Vcoding_system_list = Qnil; |
| 4093 | |
| 4094 | DEFVAR_LISP ("coding-system-alist", &Vcoding_system_alist, |
| 4095 | "Alist of coding system names.\n\ |
| 4096 | Each element is one element list of coding system name.\n\ |
| 4097 | This variable is given to `completing-read' as TABLE argument.\n\ |
| 4098 | \n\ |
| 4099 | Do not alter the value of this variable manually. This variable should be\n\ |
| 4100 | updated by the functions `make-coding-system' and\n\ |
| 4101 | `define-coding-system-alias'."); |
| 4102 | Vcoding_system_alist = Qnil; |
| 4103 | |
| 4104 | DEFVAR_LISP ("coding-category-list", &Vcoding_category_list, |
| 4105 | "List of coding-categories (symbols) ordered by priority."); |
| 4106 | { |
| 4107 | int i; |
| 4108 | |
| 4109 | Vcoding_category_list = Qnil; |
| 4110 | for (i = CODING_CATEGORY_IDX_MAX - 1; i >= 0; i--) |
| 4111 | Vcoding_category_list |
| 4112 | = Fcons (coding_category_table[i], Vcoding_category_list); |
| 4113 | } |
| 4114 | |
| 4115 | DEFVAR_LISP ("coding-system-for-read", &Vcoding_system_for_read, |
| 4116 | "Specify the coding system for read operations.\n\ |
| 4117 | It is useful to bind this variable with `let', but do not set it globally.\n\ |
| 4118 | If the value is a coding system, it is used for decoding on read operation.\n\ |
| 4119 | If not, an appropriate element is used from one of the coding system alists:\n\ |
| 4120 | There are three such tables, `file-coding-system-alist',\n\ |
| 4121 | `process-coding-system-alist', and `network-coding-system-alist'."); |
| 4122 | Vcoding_system_for_read = Qnil; |
| 4123 | |
| 4124 | DEFVAR_LISP ("coding-system-for-write", &Vcoding_system_for_write, |
| 4125 | "Specify the coding system for write operations.\n\ |
| 4126 | It is useful to bind this variable with `let', but do not set it globally.\n\ |
| 4127 | If the value is a coding system, it is used for encoding on write operation.\n\ |
| 4128 | If not, an appropriate element is used from one of the coding system alists:\n\ |
| 4129 | There are three such tables, `file-coding-system-alist',\n\ |
| 4130 | `process-coding-system-alist', and `network-coding-system-alist'."); |
| 4131 | Vcoding_system_for_write = Qnil; |
| 4132 | |
| 4133 | DEFVAR_LISP ("last-coding-system-used", &Vlast_coding_system_used, |
| 4134 | "Coding system used in the latest file or process I/O."); |
| 4135 | Vlast_coding_system_used = Qnil; |
| 4136 | |
| 4137 | DEFVAR_BOOL ("inhibit-eol-conversion", &inhibit_eol_conversion, |
| 4138 | "*Non-nil inhibit code conversion of end-of-line format in any cases."); |
| 4139 | inhibit_eol_conversion = 0; |
| 4140 | |
| 4141 | DEFVAR_LISP ("file-coding-system-alist", &Vfile_coding_system_alist, |
| 4142 | "Alist to decide a coding system to use for a file I/O operation.\n\ |
| 4143 | The format is ((PATTERN . VAL) ...),\n\ |
| 4144 | where PATTERN is a regular expression matching a file name,\n\ |
| 4145 | VAL is a coding system, a cons of coding systems, or a function symbol.\n\ |
| 4146 | If VAL is a coding system, it is used for both decoding and encoding\n\ |
| 4147 | the file contents.\n\ |
| 4148 | If VAL is a cons of coding systems, the car part is used for decoding,\n\ |
| 4149 | and the cdr part is used for encoding.\n\ |
| 4150 | If VAL is a function symbol, the function must return a coding system\n\ |
| 4151 | or a cons of coding systems which are used as above.\n\ |
| 4152 | \n\ |
| 4153 | See also the function `find-operation-coding-system'."); |
| 4154 | Vfile_coding_system_alist = Qnil; |
| 4155 | |
| 4156 | DEFVAR_LISP ("process-coding-system-alist", &Vprocess_coding_system_alist, |
| 4157 | "Alist to decide a coding system to use for a process I/O operation.\n\ |
| 4158 | The format is ((PATTERN . VAL) ...),\n\ |
| 4159 | where PATTERN is a regular expression matching a program name,\n\ |
| 4160 | VAL is a coding system, a cons of coding systems, or a function symbol.\n\ |
| 4161 | If VAL is a coding system, it is used for both decoding what received\n\ |
| 4162 | from the program and encoding what sent to the program.\n\ |
| 4163 | If VAL is a cons of coding systems, the car part is used for decoding,\n\ |
| 4164 | and the cdr part is used for encoding.\n\ |
| 4165 | If VAL is a function symbol, the function must return a coding system\n\ |
| 4166 | or a cons of coding systems which are used as above.\n\ |
| 4167 | \n\ |
| 4168 | See also the function `find-operation-coding-system'."); |
| 4169 | Vprocess_coding_system_alist = Qnil; |
| 4170 | |
| 4171 | DEFVAR_LISP ("network-coding-system-alist", &Vnetwork_coding_system_alist, |
| 4172 | "Alist to decide a coding system to use for a network I/O operation.\n\ |
| 4173 | The format is ((PATTERN . VAL) ...),\n\ |
| 4174 | where PATTERN is a regular expression matching a network service name\n\ |
| 4175 | or is a port number to connect to,\n\ |
| 4176 | VAL is a coding system, a cons of coding systems, or a function symbol.\n\ |
| 4177 | If VAL is a coding system, it is used for both decoding what received\n\ |
| 4178 | from the network stream and encoding what sent to the network stream.\n\ |
| 4179 | If VAL is a cons of coding systems, the car part is used for decoding,\n\ |
| 4180 | and the cdr part is used for encoding.\n\ |
| 4181 | If VAL is a function symbol, the function must return a coding system\n\ |
| 4182 | or a cons of coding systems which are used as above.\n\ |
| 4183 | \n\ |
| 4184 | See also the function `find-operation-coding-system'."); |
| 4185 | Vnetwork_coding_system_alist = Qnil; |
| 4186 | |
| 4187 | DEFVAR_INT ("eol-mnemonic-unix", &eol_mnemonic_unix, |
| 4188 | "Mnemonic character indicating UNIX-like end-of-line format (i.e. LF) ."); |
| 4189 | eol_mnemonic_unix = ':'; |
| 4190 | |
| 4191 | DEFVAR_INT ("eol-mnemonic-dos", &eol_mnemonic_dos, |
| 4192 | "Mnemonic character indicating DOS-like end-of-line format (i.e. CRLF)."); |
| 4193 | eol_mnemonic_dos = '\\'; |
| 4194 | |
| 4195 | DEFVAR_INT ("eol-mnemonic-mac", &eol_mnemonic_mac, |
| 4196 | "Mnemonic character indicating MAC-like end-of-line format (i.e. CR)."); |
| 4197 | eol_mnemonic_mac = '/'; |
| 4198 | |
| 4199 | DEFVAR_INT ("eol-mnemonic-undecided", &eol_mnemonic_undecided, |
| 4200 | "Mnemonic character indicating end-of-line format is not yet decided."); |
| 4201 | eol_mnemonic_undecided = ':'; |
| 4202 | |
| 4203 | DEFVAR_LISP ("enable-character-unification", &Venable_character_unification, |
| 4204 | "Non-nil means ISO 2022 encoder/decoder do character unification."); |
| 4205 | Venable_character_unification = Qt; |
| 4206 | |
| 4207 | DEFVAR_LISP ("standard-character-unification-table-for-decode", |
| 4208 | &Vstandard_character_unification_table_for_decode, |
| 4209 | "Table for unifying characters when reading."); |
| 4210 | Vstandard_character_unification_table_for_decode = Qnil; |
| 4211 | |
| 4212 | DEFVAR_LISP ("standard-character-unification-table-for-encode", |
| 4213 | &Vstandard_character_unification_table_for_encode, |
| 4214 | "Table for unifying characters when writing."); |
| 4215 | Vstandard_character_unification_table_for_encode = Qnil; |
| 4216 | |
| 4217 | DEFVAR_LISP ("charset-revision-table", &Vcharset_revision_alist, |
| 4218 | "Alist of charsets vs revision numbers.\n\ |
| 4219 | While encoding, if a charset (car part of an element) is found,\n\ |
| 4220 | designate it with the escape sequence identifing revision (cdr part of the element)."); |
| 4221 | Vcharset_revision_alist = Qnil; |
| 4222 | |
| 4223 | DEFVAR_LISP ("default-process-coding-system", |
| 4224 | &Vdefault_process_coding_system, |
| 4225 | "Cons of coding systems used for process I/O by default.\n\ |
| 4226 | The car part is used for decoding a process output,\n\ |
| 4227 | the cdr part is used for encoding a text to be sent to a process."); |
| 4228 | Vdefault_process_coding_system = Qnil; |
| 4229 | |
| 4230 | DEFVAR_LISP ("latin-extra-code-table", &Vlatin_extra_code_table, |
| 4231 | "Table of extra Latin codes in the range 128..159 (inclusive).\n\ |
| 4232 | This is a vector of length 256.\n\ |
| 4233 | If Nth element is non-nil, the existence of code N in a file\n\ |
| 4234 | \(or output of subprocess) doesn't prevent it to be detected as\n\ |
| 4235 | a coding system of ISO 2022 variant which has a flag\n\ |
| 4236 | `accept-latin-extra-code' t (e.g. iso-latin-1) on reading a file\n\ |
| 4237 | or reading output of a subprocess.\n\ |
| 4238 | Only 128th through 159th elements has a meaning."); |
| 4239 | Vlatin_extra_code_table = Fmake_vector (make_number (256), Qnil); |
| 4240 | } |
| 4241 | |
| 4242 | #endif /* emacs */ |