1 /* Coding system handler (conversion, detection, and etc).
2 Copyright (C) 1995, 1997 Electrotechnical Laboratory, JAPAN.
3 Licensed to the Free Software Foundation.
5 This file is part of GNU Emacs.
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)
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.
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. */
22 /*** TABLE OF CONTENTS ***
25 2. Emacs' internal format (emacs-mule) 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
35 /*** GENERAL NOTE on CODING SYSTEM ***
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
44 0. Emacs' internal format (emacs-mule)
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.
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.
56 2. SJIS (or Shift-JIS or MS-Kanji-Code)
58 A coding system to encode character sets: ASCII, JISX0201, and
59 JISX0208. Widely used for PC's in Japan. Details are described in
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.
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.
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.
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.
89 /*** GENERAL NOTES on END-OF-LINE FORMAT ***
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'.
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.
103 /*** GENERAL NOTES on `detect_coding_XXX ()' functions ***
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. */
112 detect_coding_emacs_mule (src
, src_end
)
113 unsigned char *src
, *src_end
;
119 /*** GENERAL NOTES on `decode_coding_XXX ()' functions ***
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. */
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
;
138 /*** GENERAL NOTES on `encode_coding_XXX ()' functions ***
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. */
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
;
157 /*** COMMONLY USED MACROS ***/
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. */
165 #define ONE_MORE_BYTE(c1) \
170 goto label_end_of_loop; \
173 #define TWO_MORE_BYTES(c1, c2) \
175 if (src + 1 < src_end) \
176 c1 = *src++, c2 = *src++; \
178 goto label_end_of_loop; \
181 #define THREE_MORE_BYTES(c1, c2, c3) \
183 if (src + 2 < src_end) \
184 c1 = *src++, c2 = *src++, c3 = *src++; \
186 goto label_end_of_loop; \
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. */
196 /* Decode one ASCII character C. */
198 #define DECODE_CHARACTER_ASCII(c) \
200 if (COMPOSING_P (coding->composing)) \
201 *dst++ = 0xA0, *dst++ = (c) | 0x80; \
206 /* Decode one DIMENSION1 character whose charset is CHARSET and whose
207 position-code is C. */
209 #define DECODE_CHARACTER_DIMENSION1(charset, c) \
211 unsigned char leading_code = CHARSET_LEADING_CODE_BASE (charset); \
212 if (COMPOSING_P (coding->composing)) \
213 *dst++ = leading_code + 0x20; \
215 *dst++ = leading_code; \
216 if (leading_code = CHARSET_LEADING_CODE_EXT (charset)) \
217 *dst++ = leading_code; \
218 *dst++ = (c) | 0x80; \
221 /* Decode one DIMENSION2 character whose charset is CHARSET and whose
222 position-codes are C1 and C2. */
224 #define DECODE_CHARACTER_DIMENSION2(charset, c1, c2) \
226 DECODE_CHARACTER_DIMENSION1 (charset, c1); \
227 *dst++ = (c2) | 0x80; \
231 /*** 1. Preamble ***/
245 #else /* not emacs */
249 #endif /* not emacs */
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
;
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
;
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
267 int eol_mnemonic_undecided
;
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. */
275 Lisp_Object Vcoding_system_list
, Vcoding_system_alist
;
277 Lisp_Object Qcoding_system_p
, Qcoding_system_error
;
279 /* Coding system emacs-mule is for converting only end-of-line format. */
280 Lisp_Object Qemacs_mule
;
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
;
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
;
295 /* Flag to inhibit code conversion of end-of-line format. */
296 int inhibit_eol_conversion
;
298 /* Coding system to be used to encode text for terminal display. */
299 struct coding_system terminal_coding
;
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
;
305 /* Coding system of what is sent from terminal keyboard. */
306 struct coding_system keyboard_coding
;
308 Lisp_Object Vfile_coding_system_alist
;
309 Lisp_Object Vprocess_coding_system_alist
;
310 Lisp_Object Vnetwork_coding_system_alist
;
314 Lisp_Object Qcoding_category_index
;
316 /* List of symbols `coding-category-xxx' ordered by priority. */
317 Lisp_Object Vcoding_category_list
;
319 /* Table of coding-systems currently assigned to each coding-category. */
320 Lisp_Object coding_category_table
[CODING_CATEGORY_IDX_MAX
];
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"
336 /* Flag to tell if we look up unification table on character code
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
;
344 Lisp_Object Qcharacter_unification_table
;
345 Lisp_Object Qcharacter_unification_table_for_decode
;
346 Lisp_Object Qcharacter_unification_table_for_encode
;
348 /* Alist of charsets vs revision number. */
349 Lisp_Object Vcharset_revision_alist
;
351 /* Default coding systems used for process I/O. */
352 Lisp_Object Vdefault_process_coding_system
;
355 /*** 2. Emacs internal format (emacs-mule) handlers ***/
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.
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
379 --- CODE RANGE of Emacs' internal format ---
380 (character set) (range)
382 ELSE (1st byte) 0x80 .. 0x9F
383 (rest bytes) 0xA0 .. 0xFF
384 ---------------------------------------------
388 enum emacs_code_class_type emacs_code_class
[256];
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 \
394 if (src >= src_end) \
395 goto label_end_of_switch; \
396 else if (*src++ < 0xA0) \
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. */
405 detect_coding_emacs_mule (src
, src_end
)
406 unsigned char *src
, *src_end
;
411 while (src
< src_end
)
423 switch (emacs_code_class
[c
])
425 case EMACS_ascii_code
:
426 case EMACS_linefeed_code
:
429 case EMACS_control_code
:
430 if (c
== ISO_CODE_ESC
|| c
== ISO_CODE_SI
|| c
== ISO_CODE_SO
)
434 case EMACS_invalid_code
:
437 case EMACS_leading_code_composition
: /* c == 0x80 */
439 CHECK_CODE_RANGE_A0_FF
;
444 case EMACS_leading_code_4
:
445 CHECK_CODE_RANGE_A0_FF
;
446 /* fall down to check it two more times ... */
448 case EMACS_leading_code_3
:
449 CHECK_CODE_RANGE_A0_FF
;
450 /* fall down to check it one more time ... */
452 case EMACS_leading_code_2
:
453 CHECK_CODE_RANGE_A0_FF
;
461 return CODING_CATEGORY_MASK_EMACS_MULE
;
465 /*** 3. ISO2022 handlers ***/
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.
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).
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.
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).
496 Note (*): ECMA = European Computer Manufacturers Association
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
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
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.
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.
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.
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
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'.
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 ----------------------------------------------------------------------
574 In this list, "DIMENSION1_CHARS94<F>" means a graphic character set
575 of dimension 1, chars 94, and final character <F>, and etc.
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.
582 Note (**): If <F> is '@', 'A', or 'B', the intermediate character
583 '(' can be omitted. We call this as "short-form" here after.
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.
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.
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.
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. */
610 enum iso_code_class_type iso_code_class
[256];
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,
624 detect_coding_iso2022 (src
, src_end
)
625 unsigned char *src
, *src_end
;
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
633 int g1
= 0; /* 1 iff designating to G1. */
635 struct coding_system coding_iso_8_1
, coding_iso_8_2
;
637 /* Coding systems of these categories may accept latin extra codes. */
639 (XSYMBOL (coding_category_table
[CODING_CATEGORY_IDX_ISO_8_1
])->value
,
642 (XSYMBOL (coding_category_table
[CODING_CATEGORY_IDX_ISO_8_2
])->value
,
645 while (mask
&& src
< src_end
)
654 if ((c
>= '(' && c
<= '/'))
656 /* Designation sequence for a charset of dimension 1. */
660 if (c
< ' ' || c
>= 0x80)
661 /* Invalid designation sequence. */
666 /* Designation sequence for a charset of dimension 2. */
670 if (c
>= '@' && c
<= 'B')
671 /* Designation for JISX0208.1978, GB2312, or JISX0208. */
673 else if (c
>= '(' && c
<= '/')
678 if (c
< ' ' || c
>= 0x80)
679 /* Invalid designation sequence. */
683 /* Invalid designation sequence. */
686 else if (c
== 'N' || c
== 'O' || c
== 'n' || c
== 'o')
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. */
694 /* Invalid escape sequence. */
699 mask
&= (CODING_CATEGORY_MASK_ISO_7_ELSE
700 | CODING_CATEGORY_MASK_ISO_8_ELSE
);
707 int newmask
= CODING_CATEGORY_MASK_ISO_8_ELSE
;
709 if (c
!= ISO_CODE_CSI
)
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
;
716 if (VECTORP (Vlatin_extra_code_table
)
717 && !NILP (XVECTOR (Vlatin_extra_code_table
)->contents
[c
]))
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
;
733 if (VECTORP (Vlatin_extra_code_table
)
734 && !NILP (XVECTOR (Vlatin_extra_code_table
)->contents
[c
]))
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
;
749 unsigned char *src_begin
= src
;
751 mask
&= ~(CODING_CATEGORY_MASK_ISO_7
752 | CODING_CATEGORY_MASK_ISO_7_ELSE
);
753 while (src
< src_end
&& *src
>= 0xA0)
755 if ((src
- src_begin
- 1) & 1 && src
< src_end
)
756 mask
&= ~CODING_CATEGORY_MASK_ISO_8_2
;
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
771 #define DECODE_ISO_CHARACTER(charset, c1) \
773 int c_alt, charset_alt = (charset); \
774 if (COMPOSING_HEAD_P (coding->composing)) \
776 *dst++ = LEADING_CODE_COMPOSITION; \
777 if (COMPOSING_WITH_RULE_P (coding->composing)) \
778 /* To tell composition rules are embeded. */ \
780 coding->composing += 2; \
782 if ((charset) >= 0) \
784 if (CHARSET_DIMENSION (charset) == 2) \
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) \
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); \
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); \
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; \
810 /* Set designation state into CODING. */
811 #define DECODE_DESIGNATION(reg, dimension, chars, final_char) \
813 int charset = ISO_CHARSET_TABLE (make_number (dimension), \
814 make_number (chars), \
815 make_number (final_char)); \
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; \
825 /* See the above "GENERAL NOTES on `decode_coding_XXX ()' functions". */
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
;
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;
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
;
850 if (!NILP (Venable_character_unification
) && NILP (unification_table
))
851 unification_table
= Vstandard_character_unification_table_for_decode
;
853 while (src
< src_end
&& dst
< adjusted_dst_end
)
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
;
863 switch (iso_code_class
[c1
])
865 case ISO_0x20_or_0x7F
:
866 if (!coding
->composing
867 && (charset0
< 0 || CHARSET_CHARS (charset0
) == 94))
869 /* This is SPACE or DEL. */
873 /* This is a graphic character, we fall down ... */
875 case ISO_graphic_plane_0
:
876 if (coding
->composing
== COMPOSING_WITH_RULE_RULE
)
878 /* This is a composition rule. */
880 coding
->composing
= COMPOSING_WITH_RULE_TAIL
;
883 DECODE_ISO_CHARACTER (charset0
, c1
);
886 case ISO_0xA0_or_0xFF
:
887 if (charset1
< 0 || CHARSET_CHARS (charset1
) == 94)
893 /* This is a graphic character, we fall down ... */
895 case ISO_graphic_plane_1
:
896 DECODE_ISO_CHARACTER (charset1
, c1
);
899 case ISO_control_code
:
900 /* All ISO2022 control characters in this class have the
901 same representation in Emacs internal format. */
905 case ISO_carriage_return
:
906 if (coding
->eol_type
== CODING_EOL_CR
)
910 else if (coding
->eol_type
== CODING_EOL_CRLF
)
913 if (c1
== ISO_CODE_LF
)
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);
935 CODING_SPEC_ISO_INVOCATION (coding
, 0) = 0;
936 charset0
= CODING_SPEC_ISO_PLANE_CHARSET (coding
, 0);
939 case ISO_single_shift_2_7
:
940 case ISO_single_shift_2
:
941 /* SS2 is handled as an escape sequence of ESC 'N' */
943 goto label_escape_sequence
;
945 case ISO_single_shift_3
:
946 /* SS2 is handled as an escape sequence of ESC 'O' */
948 goto label_escape_sequence
;
950 case ISO_control_sequence_introducer
:
951 /* CSI is handled as an escape sequence of ESC '[' ... */
953 goto label_escape_sequence
;
957 label_escape_sequence
:
958 /* Escape sequences handled by Emacs are invocation,
959 designation, direction specification, and character
960 composition specification. */
963 case '&': /* revision of following character set */
965 if (!(c1
>= '@' && c1
<= '~'))
966 goto label_invalid_escape_sequence
;
968 if (c1
!= ISO_CODE_ESC
)
969 goto label_invalid_escape_sequence
;
971 goto label_escape_sequence
;
973 case '$': /* designation of 2-byte character set */
975 if (c1
>= '@' && c1
<= 'B')
976 { /* designation of JISX0208.1978, GB2312.1980,
978 DECODE_DESIGNATION (0, 2, 94, c1
);
980 else if (c1
>= 0x28 && c1
<= 0x2B)
981 { /* designation of DIMENSION2_CHARS94 character set */
983 DECODE_DESIGNATION (c1
- 0x28, 2, 94, c2
);
985 else if (c1
>= 0x2C && c1
<= 0x2F)
986 { /* designation of DIMENSION2_CHARS96 character set */
988 DECODE_DESIGNATION (c1
- 0x2C, 2, 96, c2
);
991 goto label_invalid_escape_sequence
;
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);
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);
1008 case 'N': /* invocation of single-shift-2 */
1009 if (CODING_SPEC_ISO_DESIGNATION (coding
, 2) < 0)
1010 goto label_invalid_escape_sequence
;
1012 charset
= CODING_SPEC_ISO_DESIGNATION (coding
, 2);
1013 DECODE_ISO_CHARACTER (charset
, c1
);
1016 case 'O': /* invocation of single-shift-3 */
1017 if (CODING_SPEC_ISO_DESIGNATION (coding
, 3) < 0)
1018 goto label_invalid_escape_sequence
;
1020 charset
= CODING_SPEC_ISO_DESIGNATION (coding
, 3);
1021 DECODE_ISO_CHARACTER (charset
, c1
);
1024 case '0': /* start composing without embeded rules */
1025 coding
->composing
= COMPOSING_NO_RULE_HEAD
;
1028 case '1': /* end composing */
1029 coding
->composing
= COMPOSING_NO
;
1032 case '2': /* start composing with embeded rules */
1033 coding
->composing
= COMPOSING_WITH_RULE_HEAD
;
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. */
1043 case ']': /* end of the current direction */
1044 coding
->direction
= 0;
1046 case '0': /* end of the current direction */
1047 case '1': /* start of left-to-right direction */
1050 coding
->direction
= 0;
1052 goto label_invalid_escape_sequence
;
1055 case '2': /* start of right-to-left direction */
1058 coding
->direction
= 1;
1060 goto label_invalid_escape_sequence
;
1064 goto label_invalid_escape_sequence
;
1069 if (c1
>= 0x28 && c1
<= 0x2B)
1070 { /* designation of DIMENSION1_CHARS94 character set */
1072 DECODE_DESIGNATION (c1
- 0x28, 1, 94, c2
);
1074 else if (c1
>= 0x2C && c1
<= 0x2F)
1075 { /* designation of DIMENSION1_CHARS96 character set */
1077 DECODE_DESIGNATION (c1
- 0x2C, 1, 96, c2
);
1081 goto label_invalid_escape_sequence
;
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);
1089 label_invalid_escape_sequence
:
1091 int length
= src
- src_base
;
1093 bcopy (src_base
, dst
, length
);
1100 coding
->carryover_size
= src
- src_base
;
1101 bcopy (src_base
, coding
->carryover
, coding
->carryover_size
);
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
)
1111 bcopy (src
, dst
, src_end
- src
);
1112 dst
+= (src_end
- src
);
1115 *consumed
= src
- source
;
1116 return dst
- destination
;
1119 /* ISO2022 encoding stuff. */
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
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
1145 #define ENCODE_DESIGNATION(charset, reg, coding) \
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) \
1153 *dst++ = ISO_CODE_ESC; \
1155 *dst++ = '@' + revision; \
1157 *dst++ = ISO_CODE_ESC; \
1158 if (CHARSET_DIMENSION (charset) == 1) \
1160 if (CHARSET_CHARS (charset) == 94) \
1161 *dst++ = (unsigned char) (intermediate_char_94[reg]); \
1163 *dst++ = (unsigned char) (intermediate_char_96[reg]); \
1168 if (CHARSET_CHARS (charset) == 94) \
1170 if (! (coding->flags & CODING_FLAG_ISO_SHORT_FORM) \
1172 || final_char < '@' || final_char > 'B') \
1173 *dst++ = (unsigned char) (intermediate_char_94[reg]); \
1176 *dst++ = (unsigned char) (intermediate_char_96[reg]); \
1178 *dst++ = final_char; \
1179 CODING_SPEC_ISO_DESIGNATION (coding, reg) = charset; \
1182 /* The following two macros produce codes (control character or escape
1183 sequence) for ISO2022 single-shift functions (single-shift-2 and
1186 #define ENCODE_SINGLE_SHIFT_2 \
1188 if (coding->flags & CODING_FLAG_ISO_SEVEN_BITS) \
1189 *dst++ = ISO_CODE_ESC, *dst++ = 'N'; \
1191 *dst++ = ISO_CODE_SS2; \
1192 CODING_SPEC_ISO_SINGLE_SHIFTING (coding) = 1; \
1195 #define ENCODE_SINGLE_SHIFT_3 \
1197 if (coding->flags & CODING_FLAG_ISO_SEVEN_BITS) \
1198 *dst++ = ISO_CODE_ESC, *dst++ = 'O'; \
1200 *dst++ = ISO_CODE_SS3; \
1201 CODING_SPEC_ISO_SINGLE_SHIFTING (coding) = 1; \
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). */
1208 #define ENCODE_SHIFT_IN \
1210 *dst++ = ISO_CODE_SI; \
1211 CODING_SPEC_ISO_INVOCATION (coding, 0) = 0; \
1214 #define ENCODE_SHIFT_OUT \
1216 *dst++ = ISO_CODE_SO; \
1217 CODING_SPEC_ISO_INVOCATION (coding, 0) = 1; \
1220 #define ENCODE_LOCKING_SHIFT_2 \
1222 *dst++ = ISO_CODE_ESC, *dst++ = 'n'; \
1223 CODING_SPEC_ISO_INVOCATION (coding, 0) = 2; \
1226 #define ENCODE_LOCKING_SHIFT_3 \
1228 *dst++ = ISO_CODE_ESC, *dst++ = 'o'; \
1229 CODING_SPEC_ISO_INVOCATION (coding, 0) = 3; \
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. */
1237 #define ENCODE_ISO_CHARACTER_DIMENSION1(charset, c1) \
1239 if (CODING_SPEC_ISO_SINGLE_SHIFTING (coding)) \
1241 if (coding->flags & CODING_FLAG_ISO_SEVEN_BITS) \
1242 *dst++ = c1 & 0x7F; \
1244 *dst++ = c1 | 0x80; \
1245 CODING_SPEC_ISO_SINGLE_SHIFTING (coding) = 0; \
1248 else if (charset == CODING_SPEC_ISO_PLANE_CHARSET (coding, 0)) \
1250 *dst++ = c1 & 0x7F; \
1253 else if (charset == CODING_SPEC_ISO_PLANE_CHARSET (coding, 1)) \
1255 *dst++ = c1 | 0x80; \
1258 else if (coding->flags & CODING_FLAG_ISO_SAFE \
1259 && !coding->safe_charsets[charset]) \
1261 /* We should not encode this character, instead produce one or \
1263 *dst++ = CODING_INHIBIT_CHARACTER_SUBSTITUTION; \
1264 if (CHARSET_WIDTH (charset) == 2) \
1265 *dst++ = CODING_INHIBIT_CHARACTER_SUBSTITUTION; \
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 \
1273 dst = encode_invocation_designation (charset, coding, dst); \
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. */
1280 #define ENCODE_ISO_CHARACTER_DIMENSION2(charset, c1, c2) \
1282 if (CODING_SPEC_ISO_SINGLE_SHIFTING (coding)) \
1284 if (coding->flags & CODING_FLAG_ISO_SEVEN_BITS) \
1285 *dst++ = c1 & 0x7F, *dst++ = c2 & 0x7F; \
1287 *dst++ = c1 | 0x80, *dst++ = c2 | 0x80; \
1288 CODING_SPEC_ISO_SINGLE_SHIFTING (coding) = 0; \
1291 else if (charset == CODING_SPEC_ISO_PLANE_CHARSET (coding, 0)) \
1293 *dst++ = c1 & 0x7F, *dst++= c2 & 0x7F; \
1296 else if (charset == CODING_SPEC_ISO_PLANE_CHARSET (coding, 1)) \
1298 *dst++ = c1 | 0x80, *dst++= c2 | 0x80; \
1301 else if (coding->flags & CODING_FLAG_ISO_SAFE \
1302 && !coding->safe_charsets[charset]) \
1304 /* We should not encode this character, instead produce one or \
1306 *dst++ = CODING_INHIBIT_CHARACTER_SUBSTITUTION; \
1307 if (CHARSET_WIDTH (charset) == 2) \
1308 *dst++ = CODING_INHIBIT_CHARACTER_SUBSTITUTION; \
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 \
1316 dst = encode_invocation_designation (charset, coding, dst); \
1319 #define ENCODE_ISO_CHARACTER(charset, c1, c2) \
1321 int c_alt, charset_alt; \
1322 if (!NILP (unification_table) \
1323 && ((c_alt = unify_char (unification_table, -1, charset, c1, c2)) \
1325 SPLIT_CHAR (c_alt, charset_alt, c1, c2); \
1327 charset_alt = charset; \
1328 if (CHARSET_DIMENSION (charset_alt) == 1) \
1329 ENCODE_ISO_CHARACTER_DIMENSION1 (charset_alt, c1); \
1331 ENCODE_ISO_CHARACTER_DIMENSION2 (charset_alt, c1, c2); \
1334 /* Produce designation and invocation codes at a place pointed by DST
1335 to use CHARSET. The element `spec.iso2022' of *CODING is updated.
1339 encode_invocation_designation (charset
, coding
, dst
)
1341 struct coding_system
*coding
;
1344 int reg
; /* graphic register number */
1346 /* At first, check designations. */
1347 for (reg
= 0; reg
< 4; reg
++)
1348 if (charset
== CODING_SPEC_ISO_DESIGNATION (coding
, reg
))
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. */
1361 ENCODE_DESIGNATION (charset
, reg
, coding
);
1364 if (CODING_SPEC_ISO_INVOCATION (coding
, 0) != reg
1365 && CODING_SPEC_ISO_INVOCATION (coding
, 1) != reg
)
1367 /* Since the graphic register REG is not invoked to any graphic
1368 planes, invoke it to graphic plane 0. */
1371 case 0: /* graphic register 0 */
1375 case 1: /* graphic register 1 */
1379 case 2: /* graphic register 2 */
1380 if (coding
->flags
& CODING_FLAG_ISO_SINGLE_SHIFT
)
1381 ENCODE_SINGLE_SHIFT_2
;
1383 ENCODE_LOCKING_SHIFT_2
;
1386 case 3: /* graphic register 3 */
1387 if (coding
->flags
& CODING_FLAG_ISO_SINGLE_SHIFT
)
1388 ENCODE_SINGLE_SHIFT_3
;
1390 ENCODE_LOCKING_SHIFT_3
;
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'
1402 /* The following three macros produce codes for indicating direction
1404 #define ENCODE_CONTROL_SEQUENCE_INTRODUCER \
1406 if (coding->flags == CODING_FLAG_ISO_SEVEN_BITS) \
1407 *dst++ = ISO_CODE_ESC, *dst++ = '['; \
1409 *dst++ = ISO_CODE_CSI; \
1412 #define ENCODE_DIRECTION_R2L \
1413 ENCODE_CONTROL_SEQUENCE_INTRODUCER, *dst++ = '2', *dst++ = ']'
1415 #define ENCODE_DIRECTION_L2R \
1416 ENCODE_CONTROL_SEQUENCE_INTRODUCER, *dst++ = '0', *dst++ = ']'
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 \
1423 if (CODING_SPEC_ISO_INVOCATION (coding, 0) != 0) \
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); \
1433 /* Produce designation sequences of charsets in the line started from
1434 *SRC to a place pointed by DSTP.
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
;
1441 unsigned char *src
, *src_end
, **dstp
;
1443 int charset
, c
, found
= 0, reg
;
1444 /* Table of charsets to be designated to each graphic register. */
1446 unsigned char *dst
= *dstp
;
1448 for (reg
= 0; reg
< 4; reg
++)
1451 while (src
< src_end
&& *src
!= '\n' && found
< 4)
1453 int bytes
= BYTES_BY_CHAR_HEAD (*src
);
1456 charset
= CHARSET_AT (src
);
1460 unsigned char c1
, c2
;
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
);
1467 reg
= CODING_SPEC_ISO_REQUESTED_DESIGNATION (coding
, charset
);
1479 for (reg
= 0; reg
< 4; reg
++)
1481 && CODING_SPEC_ISO_DESIGNATION (coding
, reg
) != r
[reg
])
1482 ENCODE_DESIGNATION (r
[reg
], reg
, coding
);
1487 /* See the above "GENERAL NOTES on `encode_coding_XXX ()' functions". */
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
;
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
1504 unsigned char *adjusted_dst_end
= dst_end
- 19;
1505 Lisp_Object unification_table
1506 = coding
->character_unification_table_for_encode
;
1508 if (!NILP (Venable_character_unification
) && NILP (unification_table
))
1509 unification_table
= Vstandard_character_unification_table_for_encode
;
1511 while (src
< src_end
&& dst
< adjusted_dst_end
)
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
;
1521 if (coding
->flags
& CODING_FLAG_ISO_DESIGNATE_AT_BOL
1522 && CODING_SPEC_ISO_BOL (coding
))
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;
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
))
1540 /* We are not in a composite character any longer. */
1541 coding
->composing
= COMPOSING_NO
;
1542 ENCODE_COMPOSITION_END
;
1546 if (coding
->composing
== COMPOSING_WITH_RULE_RULE
)
1549 coding
->composing
= COMPOSING_WITH_RULE_HEAD
;
1552 else if (coding
->composing
== COMPOSING_WITH_RULE_HEAD
)
1553 coding
->composing
= COMPOSING_WITH_RULE_RULE
;
1556 /* This is an ASCII component. */
1561 /* This is a leading-code of non ASCII component. */
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
])
1570 case EMACS_ascii_code
:
1571 ENCODE_ISO_CHARACTER (CHARSET_ASCII
, c1
, /* dummy */ c2
);
1574 case EMACS_control_code
:
1575 if (coding
->flags
& CODING_FLAG_ISO_RESET_AT_CNTL
)
1576 ENCODE_RESET_PLANE_AND_REGISTER
;
1580 case EMACS_carriage_return_code
:
1581 if (!coding
->selective
)
1583 if (coding
->flags
& CODING_FLAG_ISO_RESET_AT_CNTL
)
1584 ENCODE_RESET_PLANE_AND_REGISTER
;
1588 /* fall down to treat '\r' as '\n' ... */
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
;
1603 *dst
++ = ISO_CODE_CR
;
1604 CODING_SPEC_ISO_BOL (coding
) = 1;
1607 case EMACS_leading_code_2
:
1611 /* invalid sequence */
1616 ENCODE_ISO_CHARACTER (c1
, c2
, /* dummy */ c3
);
1619 case EMACS_leading_code_3
:
1620 TWO_MORE_BYTES (c2
, c3
);
1621 if (c2
< 0xA0 || c3
< 0xA0)
1623 /* invalid sequence */
1628 else if (c1
< LEADING_CODE_PRIVATE_11
)
1629 ENCODE_ISO_CHARACTER (c1
, c2
, c3
);
1631 ENCODE_ISO_CHARACTER (c2
, c3
, /* dummy */ c4
);
1634 case EMACS_leading_code_4
:
1635 THREE_MORE_BYTES (c2
, c3
, c4
);
1636 if (c2
< 0xA0 || c3
< 0xA0 || c4
< 0xA0)
1638 /* invalid sequence */
1645 ENCODE_ISO_CHARACTER (c2
, c3
, c4
);
1648 case EMACS_leading_code_composition
:
1652 /* invalid sequence */
1656 else if (c2
== 0xFF)
1658 coding
->composing
= COMPOSING_WITH_RULE_HEAD
;
1659 ENCODE_COMPOSITION_WITH_RULE_START
;
1663 /* Rewind one byte because it is a character code of
1664 composition elements. */
1666 coding
->composing
= COMPOSING_NO_RULE_HEAD
;
1667 ENCODE_COMPOSITION_NO_RULE_START
;
1671 case EMACS_invalid_code
:
1677 /* We reach here because the source date ends not at character
1679 coding
->carryover_size
= src_end
- src_base
;
1680 bcopy (src_base
, coding
->carryover
, coding
->carryover_size
);
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
)
1689 ENCODE_RESET_PLANE_AND_REGISTER
;
1690 if (coding
->carryover_size
> 0
1691 && coding
->carryover_size
< (dst_end
- dst
))
1693 bcopy (coding
->carryover
, dst
, coding
->carryover_size
);
1694 dst
+= coding
->carryover_size
;
1695 coding
->carryover_size
= 0;
1698 *consumed
= src
- source
;
1699 return dst
- destination
;
1703 /*** 4. SJIS and BIG5 handlers ***/
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. */
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.
1716 --- CODE RANGE of SJIS ---
1717 (character set) (range)
1719 KATAKANA-JISX0201 0xA0 .. 0xDF
1720 JISX0208 (1st byte) 0x80 .. 0x9F and 0xE0 .. 0xFF
1721 (2nd byte) 0x40 .. 0xFF
1722 -------------------------------
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.
1730 --- CODE RANGE of BIG5 ---
1731 (character set) (range)
1733 Big5 (1st byte) 0xA1 .. 0xFE
1734 (2nd byte) 0x40 .. 0x7E and 0xA1 .. 0xFE
1735 --------------------------
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. */
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'. */
1749 /* Number of Big5 characters which have the same code in 1st byte. */
1750 #define BIG5_SAME_ROW (0xFF - 0xA1 + 0x7F - 0x40)
1752 #define DECODE_BIG5(b1, b2, charset, c1, c2) \
1755 = (b1 - 0xA1) * BIG5_SAME_ROW + b2 - (b2 < 0x7F ? 0x40 : 0x62); \
1757 charset = charset_big5_1; \
1760 charset = charset_big5_2; \
1761 temp -= (0xC9 - 0xA1) * BIG5_SAME_ROW; \
1763 c1 = temp / (0xFF - 0xA1) + 0x21; \
1764 c2 = temp % (0xFF - 0xA1) + 0x21; \
1767 #define ENCODE_BIG5(charset, c1, c2, b1, b2) \
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; \
1777 #define DECODE_SJIS_BIG5_CHARACTER(charset, c1, c2) \
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); \
1789 DECODE_CHARACTER_DIMENSION2 (charset_alt, c1, c2); \
1792 #define ENCODE_SJIS_BIG5_CHARACTER(charset, c1, c2) \
1794 int c_alt, charset_alt; \
1795 if (!NILP (unification_table) \
1796 && ((c_alt = unify_char (unification_table, -1, charset, c1, c2)) \
1798 SPLIT_CHAR (c_alt, charset_alt, c1, c2); \
1800 charset_alt = charset; \
1801 if (charset_alt == charset_ascii) \
1803 else if (CHARSET_DIMENSION (charset_alt) == 1) \
1805 if (sjis_p && charset_alt == charset_katakana_jisx0201) \
1808 *dst++ = charset_alt, *dst++ = c1; \
1812 c1 &= 0x7F, c2 &= 0x7F; \
1813 if (sjis_p && charset_alt == charset_jisx0208) \
1815 unsigned char s1, s2; \
1817 ENCODE_SJIS (c1, c2, s1, s2); \
1818 *dst++ = s1, *dst++ = s2; \
1821 && (charset_alt == charset_big5_1 \
1822 || charset_alt == charset_big5_2)) \
1824 unsigned char b1, b2; \
1826 ENCODE_BIG5 (charset_alt, c1, c2, b1, b2); \
1827 *dst++ = b1, *dst++ = b2; \
1830 *dst++ = charset_alt, *dst++ = c1, *dst++ = c2; \
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. */
1839 detect_coding_sjis (src
, src_end
)
1840 unsigned char *src
, *src_end
;
1844 while (src
< src_end
)
1847 if (c
== ISO_CODE_ESC
|| c
== ISO_CODE_SI
|| c
== ISO_CODE_SO
)
1849 if ((c
>= 0x80 && c
< 0xA0) || c
>= 0xE0)
1851 if (src
< src_end
&& *src
++ < 0x40)
1855 return CODING_CATEGORY_MASK_SJIS
;
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. */
1863 detect_coding_big5 (src
, src_end
)
1864 unsigned char *src
, *src_end
;
1868 while (src
< src_end
)
1871 if (c
== ISO_CODE_ESC
|| c
== ISO_CODE_SI
|| c
== ISO_CODE_SO
)
1878 if (c
< 0x40 || (c
>= 0x7F && c
<= 0xA0))
1882 return CODING_CATEGORY_MASK_BIG5
;
1885 /* See the above "GENERAL NOTES on `decode_coding_XXX ()' functions".
1886 If SJIS_P is 1, decode SJIS text, else decode BIG5 test. */
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
;
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
1904 unsigned char *adjusted_dst_end
= dst_end
- 3;
1905 Lisp_Object unification_table
1906 = coding
->character_unification_table_for_decode
;
1908 if (!NILP (Venable_character_unification
) && NILP (unification_table
))
1909 unification_table
= Vstandard_character_unification_table_for_decode
;
1911 while (src
< src_end
&& dst
< adjusted_dst_end
)
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
;
1922 if (coding
->eol_type
== CODING_EOL_CRLF
)
1928 /* To process C2 again, SRC is subtracted by 1. */
1931 else if (coding
->eol_type
== CODING_EOL_CR
)
1939 DECODE_SJIS_BIG5_CHARACTER (charset_ascii
, c1
, /* dummy */ c2
);
1940 else if (c1
< 0xA0 || c1
>= 0xE0)
1942 /* SJIS -> JISX0208, BIG5 -> Big5 (only if 0xE0 <= c1 < 0xFF) */
1946 DECODE_SJIS (c1
, c2
, c3
, c4
);
1947 DECODE_SJIS_BIG5_CHARACTER (charset_jisx0208
, c3
, c4
);
1949 else if (c1
>= 0xE0 && c1
< 0xFF)
1954 DECODE_BIG5 (c1
, c2
, charset
, c3
, c4
);
1955 DECODE_SJIS_BIG5_CHARACTER (charset
, c3
, c4
);
1957 else /* Invalid code */
1962 /* SJIS -> JISX0201-Kana, BIG5 -> Big5 */
1964 DECODE_SJIS_BIG5_CHARACTER (charset_katakana_jisx0201
, c1
, /* dummy */ c2
);
1970 DECODE_BIG5 (c1
, c2
, charset
, c3
, c4
);
1971 DECODE_SJIS_BIG5_CHARACTER (charset
, c3
, c4
);
1977 coding
->carryover_size
= src
- src_base
;
1978 bcopy (src_base
, coding
->carryover
, coding
->carryover_size
);
1983 *consumed
= src
- source
;
1984 return dst
- destination
;
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. */
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
;
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
2011 unsigned char *adjusted_dst_end
= dst_end
- 1;
2012 Lisp_Object unification_table
2013 = coding
->character_unification_table_for_encode
;
2015 if (!NILP (Venable_character_unification
) && NILP (unification_table
))
2016 unification_table
= Vstandard_character_unification_table_for_encode
;
2018 while (src
< src_end
&& dst
< adjusted_dst_end
)
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
2025 unsigned char *src_base
= src
;
2026 unsigned char c1
= *src
++, c2
, c3
, c4
;
2028 if (coding
->composing
)
2035 else if (c1
>= 0xA0)
2038 coding
->composing
= 0;
2041 switch (emacs_code_class
[c1
])
2043 case EMACS_ascii_code
:
2044 ENCODE_SJIS_BIG5_CHARACTER (charset_ascii
, c1
, /* dummy */ c2
);
2047 case EMACS_control_code
:
2051 case EMACS_carriage_return_code
:
2052 if (!coding
->selective
)
2057 /* fall down to treat '\r' as '\n' ... */
2059 case EMACS_linefeed_code
:
2060 if (coding
->eol_type
== CODING_EOL_LF
2061 || coding
->eol_type
== CODING_EOL_UNDECIDED
)
2063 else if (coding
->eol_type
== CODING_EOL_CRLF
)
2064 *dst
++ = '\r', *dst
++ = '\n';
2069 case EMACS_leading_code_2
:
2071 ENCODE_SJIS_BIG5_CHARACTER (c1
, c2
, /* dummy */ c3
);
2074 case EMACS_leading_code_3
:
2075 TWO_MORE_BYTES (c2
, c3
);
2076 ENCODE_SJIS_BIG5_CHARACTER (c1
, c2
, c3
);
2079 case EMACS_leading_code_4
:
2080 THREE_MORE_BYTES (c2
, c3
, c4
);
2081 ENCODE_SJIS_BIG5_CHARACTER (c2
, c3
, c4
);
2084 case EMACS_leading_code_composition
:
2085 coding
->composing
= 1;
2088 default: /* i.e. case EMACS_invalid_code: */
2094 coding
->carryover_size
= src_end
- src_base
;
2095 bcopy (src_base
, coding
->carryover
, coding
->carryover_size
);
2100 *consumed
= src
- source
;
2101 return dst
- destination
;
2105 /*** 5. End-of-line handlers ***/
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. */
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
;
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
;
2123 switch (coding
->eol_type
)
2125 case CODING_EOL_CRLF
:
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;
2132 while (src
< src_end
&& dst
< adjusted_dst_end
)
2134 unsigned char *src_base
= src
;
2135 unsigned char c
= *src
++;
2148 coding
->carryover_size
= src
- src_base
;
2149 bcopy (src_base
, coding
->carryover
, coding
->carryover_size
);
2153 *consumed
= src
- source
;
2154 produced
= dst
- destination
;
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
;
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
;
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
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
;
2188 unsigned char *src
= source
;
2189 unsigned char *dst
= destination
;
2195 switch (coding
->eol_type
)
2198 case CODING_EOL_UNDECIDED
:
2199 produced
= (src_bytes
> dst_bytes
) ? dst_bytes
: src_bytes
;
2200 bcopy (source
, destination
, produced
);
2201 if (coding
->selective
)
2205 if (*dst
++ == '\r') dst
[-1] = '\n';
2207 *consumed
= produced
;
2209 case CODING_EOL_CRLF
:
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;
2219 while (src
< src_end
&& dst
< adjusted_dst_end
)
2222 if (c
== '\n' || (c
== '\r' && coding
->selective
))
2223 *dst
++ = '\r', *dst
++ = '\n';
2227 produced
= dst
- destination
;
2228 *consumed
= src
- source
;
2232 default: /* i.e. case CODING_EOL_CR: */
2233 produced
= (src_bytes
> dst_bytes
) ? dst_bytes
: src_bytes
;
2234 bcopy (source
, destination
, produced
);
2238 if (*dst
++ == '\n') dst
[-1] = '\r';
2240 *consumed
= produced
;
2247 /*** 6. C library functions ***/
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'.
2257 A value of property `coding-system' can be a symbol of another
2258 subsidiary coding-system. In that case, Emacs gets coding-vector
2261 `element[0]' contains information to be set in `coding->type'. The
2262 value and its meaning is as follows:
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)
2273 `element[4]' contains information to be set in `coding->flags' and
2274 `coding->spec'. The meaning varies by `coding->type'.
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:
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.
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.
2289 If the value is nil, graphic register N is never used on
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.
2296 If `coding->type' is `coding_type_big5', element[4] is t to denote
2297 BIG5-ETen or nil to denote BIG5-HKU.
2299 If `coding->type' takes the other value, element[4] is ignored.
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
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
2316 setup_coding_system (coding_system
, coding
)
2317 Lisp_Object coding_system
;
2318 struct coding_system
*coding
;
2320 Lisp_Object coding_spec
, plist
, type
, eol_type
;
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
;
2334 coding
->symbol
= coding_system
;
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
);
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
);
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
);
2360 val
= Fget (val
, Qcharacter_unification_table_for_encode
);
2361 coding
->character_unification_table_for_encode
2362 = CHAR_TABLE_P (val
) ? val
: Qnil
;
2364 val
= Fplist_get (plist
, Qsafe_charsets
);
2367 for (i
= 0; i
<= MAX_CHARSET
; i
++)
2368 coding
->safe_charsets
[i
] = 1;
2372 bzero (coding
->safe_charsets
, MAX_CHARSET
+ 1);
2375 if ((i
= get_charset_id (XCONS (val
)->car
)) >= 0)
2376 coding
->safe_charsets
[i
] = 1;
2377 val
= XCONS (val
)->cdr
;
2381 if (VECTORP (eol_type
))
2383 coding
->eol_type
= CODING_EOL_UNDECIDED
;
2384 coding
->common_flags
= CODING_REQUIRE_DETECTION_MASK
;
2386 else if (XFASTINT (eol_type
) == 1)
2388 coding
->eol_type
= CODING_EOL_CRLF
;
2389 coding
->common_flags
2390 = CODING_REQUIRE_DECODING_MASK
| CODING_REQUIRE_ENCODING_MASK
;
2392 else if (XFASTINT (eol_type
) == 2)
2394 coding
->eol_type
= CODING_EOL_CR
;
2395 coding
->common_flags
2396 = CODING_REQUIRE_DECODING_MASK
| CODING_REQUIRE_ENCODING_MASK
;
2400 coding
->eol_type
= CODING_EOL_LF
;
2401 coding
->common_flags
= 0;
2404 type
= XVECTOR (coding_spec
)->contents
[0];
2405 switch (XFASTINT (type
))
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
;
2416 coding
->type
= coding_type_sjis
;
2417 coding
->common_flags
2418 |= CODING_REQUIRE_DECODING_MASK
| CODING_REQUIRE_ENCODING_MASK
;
2422 coding
->type
= coding_type_iso2022
;
2423 coding
->common_flags
2424 |= CODING_REQUIRE_DECODING_MASK
| CODING_REQUIRE_ENCODING_MASK
;
2426 Lisp_Object val
, temp
;
2428 int i
, charset
, default_reg_bits
= 0;
2430 val
= XVECTOR (coding_spec
)->contents
[4];
2432 if (!VECTORP (val
) || XVECTOR (val
)->size
!= 32)
2433 goto label_invalid_coding_system
;
2435 flags
= XVECTOR (val
)->contents
;
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
)
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;
2462 for (charset
= 0; charset
<= MAX_CHARSET
; charset
++)
2463 CODING_SPEC_ISO_REVISION_NUMBER (coding
, charset
) = 255;
2464 val
= Vcharset_revision_alist
;
2467 charset
= get_charset_id (Fcar_safe (XCONS (val
)->car
));
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
;
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
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
++)
2490 if (INTEGERP (flags
[i
])
2491 && (charset
= XINT (flags
[i
]), CHARSET_VALID_P (charset
))
2492 || (charset
= get_charset_id (flags
[i
])) >= 0)
2494 CODING_SPEC_ISO_INITIAL_DESIGNATION (coding
, i
) = charset
;
2495 CODING_SPEC_ISO_REQUESTED_DESIGNATION (coding
, charset
) = i
;
2497 else if (EQ (flags
[i
], Qt
))
2499 CODING_SPEC_ISO_INITIAL_DESIGNATION (coding
, i
) = -1;
2500 default_reg_bits
|= 1 << i
;
2502 else if (CONSP (flags
[i
]))
2504 Lisp_Object tail
= flags
[i
];
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)
2511 CODING_SPEC_ISO_INITIAL_DESIGNATION (coding
, i
) = charset
;
2512 CODING_SPEC_ISO_REQUESTED_DESIGNATION (coding
, charset
) =i
;
2515 CODING_SPEC_ISO_INITIAL_DESIGNATION (coding
, i
) = -1;
2516 tail
= XCONS (tail
)->cdr
;
2517 while (CONSP (tail
))
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
)
2525 else if (EQ (XCONS (tail
)->car
, Qt
))
2526 default_reg_bits
|= 1 << i
;
2527 tail
= XCONS (tail
)->cdr
;
2531 CODING_SPEC_ISO_INITIAL_DESIGNATION (coding
, i
) = -1;
2533 CODING_SPEC_ISO_DESIGNATION (coding
, i
)
2534 = CODING_SPEC_ISO_INITIAL_DESIGNATION (coding
, i
);
2537 if (! (coding
->flags
& CODING_FLAG_ISO_LOCKING_SHIFT
))
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;
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
))
2552 /* We have not yet decided where to designate CHARSET. */
2553 int reg_bits
= default_reg_bits
;
2555 if (CHARSET_CHARS (charset
) == 96)
2556 /* A charset of CHARS96 can't be designated to REG 0. */
2560 /* There exist some default graphic register. */
2561 CODING_SPEC_ISO_REQUESTED_DESIGNATION (coding
, charset
)
2563 ? 0 : (reg_bits
& 2 ? 1 : (reg_bits
& 4 ? 2 : 3)));
2565 /* We anyway have to designate CHARSET to somewhere. */
2566 CODING_SPEC_ISO_REQUESTED_DESIGNATION (coding
, charset
)
2567 = (CHARSET_CHARS (charset
) == 94
2569 : ((coding
->flags
& CODING_FLAG_ISO_LOCKING_SHIFT
2570 || ! coding
->flags
& CODING_FLAG_ISO_SEVEN_BITS
)
2572 : (coding
->flags
& CODING_FLAG_ISO_SINGLE_SHIFT
2576 coding
->common_flags
|= CODING_REQUIRE_FLUSHING_MASK
;
2580 coding
->type
= coding_type_big5
;
2581 coding
->common_flags
2582 |= CODING_REQUIRE_DECODING_MASK
| CODING_REQUIRE_ENCODING_MASK
;
2584 = (NILP (XVECTOR (coding_spec
)->contents
[4])
2585 ? CODING_FLAG_BIG5_HKU
2586 : CODING_FLAG_BIG5_ETEN
);
2590 coding
->type
= coding_type_ccl
;
2591 coding
->common_flags
2592 |= CODING_REQUIRE_DECODING_MASK
| CODING_REQUIRE_ENCODING_MASK
;
2594 Lisp_Object val
= XVECTOR (coding_spec
)->contents
[4];
2596 && VECTORP (XCONS (val
)->car
)
2597 && VECTORP (XCONS (val
)->cdr
))
2599 setup_ccl_program (&(coding
->spec
.ccl
.decoder
), XCONS (val
)->car
);
2600 setup_ccl_program (&(coding
->spec
.ccl
.encoder
), XCONS (val
)->cdr
);
2603 goto label_invalid_coding_system
;
2605 coding
->common_flags
|= CODING_REQUIRE_FLUSHING_MASK
;
2609 coding
->type
= coding_type_raw_text
;
2615 coding
->type
= coding_type_undecided
;
2616 coding
->common_flags
|= CODING_REQUIRE_DETECTION_MASK
;
2619 coding
->type
= coding_type_no_conversion
;
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
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:
2639 o coding-category-emacs-mule
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.
2645 o coding-category-sjis
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.
2651 o coding-category-iso-7
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.
2658 o coding-category-iso-8-1
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.
2666 o coding-category-iso-8-2
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.
2674 o coding-category-iso-7-else
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.
2681 o coding-category-iso-8-else
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.
2688 o coding-category-big5
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.
2694 o coding-category-binary
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.
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'.
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'. */
2716 detect_coding_mask (src
, src_bytes
)
2720 register unsigned char c
;
2721 unsigned char *src_end
= src
+ src_bytes
;
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
)
2731 || (c
== ISO_CODE_ESC
|| c
== ISO_CODE_SI
|| c
== ISO_CODE_SO
))
2737 /* We found nothing other than ASCII. There's nothing to do. */
2738 return CODING_CATEGORY_MASK_ANY
;
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. */
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
);
2749 /* No valid ISO2022 code follows C. Try again. */
2750 goto label_loop_detect_coding
;
2751 mask
|= CODING_CATEGORY_MASK_RAW_TEXT
;
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
2765 || (src
+ 1 < src_end
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
);
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
);
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
);
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. */
2796 detect_coding (coding
, src
, src_bytes
)
2797 struct coding_system
*coding
;
2801 int mask
= detect_coding_mask (src
, src_bytes
);
2803 Lisp_Object val
= Vcoding_category_list
;
2805 if (mask
== CODING_CATEGORY_MASK_ANY
)
2806 /* We found nothing other than ASCII. There's nothing to do. */
2809 /* We found some plausible coding systems. Let's use a coding
2810 system of the highest priority. */
2815 idx
= XFASTINT (Fget (XCONS (val
)->car
, Qcoding_category_index
));
2816 if ((idx
< CODING_CATEGORY_IDX_MAX
) && (mask
& (1 << idx
)))
2818 val
= XCONS (val
)->cdr
;
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
))
2831 setup_coding_system (XSYMBOL (coding_category_table
[idx
])->value
, coding
);
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. */
2838 #define MAX_EOL_CHECK_COUNT 3
2841 detect_eol_type (src
, src_bytes
)
2845 unsigned char *src_end
= src
+ src_bytes
;
2847 int total
= 0; /* How many end-of-lines are found so far. */
2848 int eol_type
= CODING_EOL_UNDECIDED
;
2851 while (src
< src_end
&& total
< MAX_EOL_CHECK_COUNT
)
2854 if (c
== '\n' || c
== '\r')
2858 this_eol_type
= CODING_EOL_LF
;
2859 else if (src
>= src_end
|| *src
!= '\n')
2860 this_eol_type
= CODING_EOL_CR
;
2862 this_eol_type
= CODING_EOL_CRLF
, src
++;
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
;
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. */
2882 detect_eol (coding
, src
, src_bytes
)
2883 struct coding_system
*coding
;
2888 int eol_type
= detect_eol_type (src
, src_bytes
);
2890 if (eol_type
== CODING_EOL_UNDECIDED
)
2891 /* We found no end-of-line in the source text. */
2894 if (eol_type
== CODING_EOL_INCONSISTENT
)
2897 /* This code is suppressed until we find a better way to
2898 distinguish raw text file and binary file. */
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
)
2904 setup_coding_system (Qno_conversion
, coding
);
2907 /* Else, let's decode only text code anyway. */
2909 eol_type
= CODING_EOL_LF
;
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
);
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. */
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
;
2936 if (coding
->type
== coding_type_undecided
)
2937 detect_coding (coding
, source
, src_bytes
);
2939 if (coding
->eol_type
== CODING_EOL_UNDECIDED
)
2940 detect_eol (coding
, source
, src_bytes
);
2942 coding
->carryover_size
= 0;
2943 switch (coding
->type
)
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
;
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
);
2962 case coding_type_sjis
:
2963 produced
= decode_coding_sjis_big5 (coding
, source
, destination
,
2964 src_bytes
, dst_bytes
, consumed
,
2968 case coding_type_iso2022
:
2969 produced
= decode_coding_iso2022 (coding
, source
, destination
,
2970 src_bytes
, dst_bytes
, consumed
);
2973 case coding_type_big5
:
2974 produced
= decode_coding_sjis_big5 (coding
, source
, destination
,
2975 src_bytes
, dst_bytes
, consumed
,
2979 case coding_type_ccl
:
2980 produced
= ccl_driver (&coding
->spec
.ccl
.decoder
, source
, destination
,
2981 src_bytes
, dst_bytes
, consumed
);
2988 /* See "GENERAL NOTES about `encode_coding_XXX ()' functions". */
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
;
2999 switch (coding
->type
)
3001 case coding_type_no_conversion
:
3002 label_no_conversion
:
3003 produced
= (src_bytes
> dst_bytes
) ? dst_bytes
: src_bytes
;
3006 bcopy (source
, destination
, produced
);
3007 if (coding
->selective
)
3009 unsigned char *p
= destination
, *pend
= destination
+ produced
;
3011 if (*p
++ == '\015') p
[-1] = '\n';
3014 *consumed
= produced
;
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
);
3027 case coding_type_sjis
:
3028 produced
= encode_coding_sjis_big5 (coding
, source
, destination
,
3029 src_bytes
, dst_bytes
, consumed
,
3033 case coding_type_iso2022
:
3034 produced
= encode_coding_iso2022 (coding
, source
, destination
,
3035 src_bytes
, dst_bytes
, consumed
);
3038 case coding_type_big5
:
3039 produced
= encode_coding_sjis_big5 (coding
, source
, destination
,
3040 src_bytes
, dst_bytes
, consumed
,
3044 case coding_type_ccl
:
3045 produced
= ccl_driver (&coding
->spec
.ccl
.encoder
, source
, destination
,
3046 src_bytes
, dst_bytes
, consumed
);
3053 #define CONVERSION_BUFFER_EXTRA_ROOM 256
3055 /* Return maximum size (bytes) of a buffer enough for decoding
3056 SRC_BYTES of text encoded in CODING. */
3059 decoding_buffer_size (coding
, src_bytes
)
3060 struct coding_system
*coding
;
3065 if (coding
->type
== coding_type_iso2022
)
3067 else if (coding
->type
== coding_type_ccl
)
3068 magnification
= coding
->spec
.ccl
.decoder
.buf_magnification
;
3072 return (src_bytes
* magnification
+ CONVERSION_BUFFER_EXTRA_ROOM
);
3075 /* Return maximum size (bytes) of a buffer enough for encoding
3076 SRC_BYTES of text to CODING. */
3079 encoding_buffer_size (coding
, src_bytes
)
3080 struct coding_system
*coding
;
3085 if (coding
->type
== coding_type_ccl
)
3086 magnification
= coding
->spec
.ccl
.encoder
.buf_magnification
;
3090 return (src_bytes
* magnification
+ CONVERSION_BUFFER_EXTRA_ROOM
);
3093 #ifndef MINIMUM_CONVERSION_BUFFER_SIZE
3094 #define MINIMUM_CONVERSION_BUFFER_SIZE 1024
3097 char *conversion_buffer
;
3098 int conversion_buffer_size
;
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. */
3105 get_conversion_buffer (size
)
3108 if (size
> conversion_buffer_size
)
3111 int real_size
= conversion_buffer_size
* 2;
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
;
3119 return conversion_buffer
;
3124 /*** 7. Emacs Lisp library functions ***/
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.")
3136 /* Get coding-spec vector for OBJ. */
3137 obj
= Fget (obj
, Qcoding_system
);
3138 return ((VECTORP (obj
) && XVECTOR (obj
)->size
== 5)
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.")
3151 val
= Fcompleting_read (prompt
, Vcoding_system_alist
, Qnil
,
3152 Qt
, Qnil
, Qcoding_system_history
, Qnil
, Qnil
);
3154 while (XSTRING (val
)->size
== 0);
3155 return (Fintern (val
, Qnil
));
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
;
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
));
3173 DEFUN ("check-coding-system", Fcheck_coding_system
, Scheck_coding_system
,
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.")
3180 Lisp_Object coding_system
;
3182 CHECK_SYMBOL (coding_system
, 0);
3183 if (!NILP (Fcoding_system_p (coding_system
)))
3184 return coding_system
;
3186 Fsignal (Qcoding_system_error
, Fcons (coding_system
, Qnil
));
3189 DEFUN ("detect-coding-region", Fdetect_coding_region
, Sdetect_coding_region
,
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.")
3198 int coding_mask
, eol_type
;
3202 validate_region (&b
, &e
);
3203 beg
= XINT (b
), end
= XINT (e
);
3204 if (beg
< GPT
&& end
>= GPT
) move_gap (end
);
3206 coding_mask
= detect_coding_mask (POS_ADDR (beg
), end
- beg
);
3207 eol_type
= detect_eol_type (POS_ADDR (beg
), end
- beg
);
3209 if (coding_mask
== CODING_CATEGORY_MASK_ANY
)
3212 if (eol_type
!= CODING_EOL_UNDECIDED
3213 && eol_type
!= CODING_EOL_INCONSISTENT
)
3216 val2
= Fget (Qundecided
, Qeol_type
);
3218 val
= XVECTOR (val2
)->contents
[eol_type
];
3225 /* At first, gather possible coding-systems in VAL in a reverse
3228 for (val2
= Vcoding_category_list
;
3230 val2
= XCONS (val2
)->cdr
)
3233 = XFASTINT (Fget (XCONS (val2
)->car
, Qcoding_category_index
));
3234 if (coding_mask
& (1 << idx
))
3237 /* This code is suppressed until we find a better way to
3238 distinguish raw text file and binary file. */
3240 if (idx
== CODING_CATEGORY_IDX_RAW_TEXT
3241 && eol_type
== CODING_EOL_INCONSISTENT
)
3242 val
= Fcons (Qno_conversion
, val
);
3245 val
= Fcons (Fsymbol_value (XCONS (val2
)->car
), val
);
3249 /* Then, change the order of the list, while getting subsidiary
3253 if (eol_type
== CODING_EOL_INCONSISTENT
)
3254 eol_type
== CODING_EOL_UNDECIDED
;
3255 for (; !NILP (val2
); val2
= XCONS (val2
)->cdr
)
3257 if (eol_type
== CODING_EOL_UNDECIDED
)
3258 val
= Fcons (XCONS (val2
)->car
, val
);
3262 val3
= Fget (XCONS (val2
)->car
, Qeol_type
);
3264 val
= Fcons (XVECTOR (val3
)->contents
[eol_type
], val
);
3266 val
= Fcons (XCONS (val2
)->car
, val
);
3274 /* Scan text in the region between *BEGP and *ENDP, skip characters
3275 which we never have to encode to (iff ENCODEP is 1) or decode from
3276 coding system CODING at the head and tail, then set BEGP and ENDP
3277 to the addresses of start and end of the text we actually convert. */
3280 shrink_conversion_area (begp
, endp
, coding
, encodep
)
3281 unsigned char **begp
, **endp
;
3282 struct coding_system
*coding
;
3285 register unsigned char *beg_addr
= *begp
, *end_addr
= *endp
;
3287 if (coding
->eol_type
!= CODING_EOL_LF
3288 && coding
->eol_type
!= CODING_EOL_UNDECIDED
)
3289 /* Since we anyway have to convert end-of-line format, it is not
3290 worth skipping at most 100 bytes or so. */
3293 if (encodep
) /* for encoding */
3295 switch (coding
->type
)
3297 case coding_type_no_conversion
:
3298 case coding_type_emacs_mule
:
3299 case coding_type_undecided
:
3300 case coding_type_raw_text
:
3301 /* We need no conversion. */
3304 case coding_type_ccl
:
3305 /* We can't skip any data. */
3307 case coding_type_iso2022
:
3308 if (coding
->flags
& CODING_FLAG_ISO_DESIGNATE_AT_BOL
)
3310 unsigned char *bol
= beg_addr
;
3311 while (beg_addr
< end_addr
&& *beg_addr
< 0x80)
3314 if (*(beg_addr
- 1) == '\n')
3318 goto label_skip_tail
;
3322 /* We can skip all ASCII characters at the head and tail. */
3323 while (beg_addr
< end_addr
&& *beg_addr
< 0x80) beg_addr
++;
3325 while (beg_addr
< end_addr
&& *(end_addr
- 1) < 0x80) end_addr
--;
3329 else /* for decoding */
3331 switch (coding
->type
)
3333 case coding_type_no_conversion
:
3334 /* We need no conversion. */
3337 case coding_type_emacs_mule
:
3338 case coding_type_raw_text
:
3339 if (coding
->eol_type
== CODING_EOL_LF
)
3341 /* We need no conversion. */
3345 /* We can skip all but carriage-return. */
3346 while (beg_addr
< end_addr
&& *beg_addr
!= '\r') beg_addr
++;
3347 while (beg_addr
< end_addr
&& *(end_addr
- 1) != '\r') end_addr
--;
3349 case coding_type_sjis
:
3350 case coding_type_big5
:
3351 /* We can skip all ASCII characters at the head. */
3352 while (beg_addr
< end_addr
&& *beg_addr
< 0x80) beg_addr
++;
3353 /* We can skip all ASCII characters at the tail except for
3354 the second byte of SJIS or BIG5 code. */
3355 while (beg_addr
< end_addr
&& *(end_addr
- 1) < 0x80) end_addr
--;
3356 if (end_addr
!= *endp
)
3359 case coding_type_ccl
:
3360 /* We can't skip any data. */
3362 default: /* i.e. case coding_type_iso2022: */
3366 /* We can skip all ASCII characters except for a few
3367 control codes at the head. */
3368 while (beg_addr
< end_addr
&& (c
= *beg_addr
) < 0x80
3369 && c
!= ISO_CODE_CR
&& c
!= ISO_CODE_SO
3370 && c
!= ISO_CODE_SI
&& c
!= ISO_CODE_ESC
)
3381 /* Encode to (iff ENCODEP is 1) or decode form coding system CODING a
3382 text between B and E. B and E are buffer position. */
3385 code_convert_region (b
, e
, coding
, encodep
)
3387 struct coding_system
*coding
;
3390 int beg
, end
, len
, consumed
, produced
;
3392 unsigned char *begp
, *endp
;
3395 validate_region (&b
, &e
);
3396 beg
= XINT (b
), end
= XINT (e
);
3397 if (beg
< GPT
&& end
>= GPT
)
3400 if (encodep
&& !NILP (coding
->pre_write_conversion
))
3402 /* We must call a pre-conversion function which may put a new
3403 text to be converted in a new buffer. */
3404 struct buffer
*old
= current_buffer
, *new;
3407 call2 (coding
->pre_write_conversion
, b
, e
);
3408 if (old
!= current_buffer
)
3410 /* Replace the original text by the text just generated. */
3412 new = current_buffer
;
3413 set_buffer_internal (old
);
3414 del_range (beg
, end
);
3415 insert_from_buffer (new, 1, len
, 0);
3420 /* We may be able to shrink the conversion region. */
3421 begp
= POS_ADDR (beg
); endp
= begp
+ (end
- beg
);
3422 shrink_conversion_area (&begp
, &endp
, coding
, encodep
);
3425 /* We need no conversion. */
3429 beg
+= begp
- POS_ADDR (beg
);
3430 end
= beg
+ (endp
- begp
);
3433 len
= encoding_buffer_size (coding
, end
- beg
);
3435 len
= decoding_buffer_size (coding
, end
- beg
);
3436 buf
= get_conversion_buffer (len
);
3438 coding
->last_block
= 1;
3440 ? encode_coding (coding
, POS_ADDR (beg
), buf
, end
- beg
, len
,
3442 : decode_coding (coding
, POS_ADDR (beg
), buf
, end
- beg
, len
,
3445 len
= produced
+ (beg
- XINT (b
)) + (XINT (e
) - end
);
3448 insert (buf
, produced
);
3449 del_range (PT
, PT
+ end
- beg
);
3451 pos
= PT
+ (pos
- end
);
3457 if (!encodep
&& !NILP (coding
->post_read_conversion
))
3459 /* We must call a post-conversion function which may alter
3460 the text just converted. */
3465 insval
= call1 (coding
->post_read_conversion
, make_number (len
));
3466 CHECK_NUMBER (insval
, 0);
3467 if (pos
>= beg
+ len
)
3468 pos
+= XINT (insval
) - len
;
3472 len
= XINT (insval
);
3475 return make_number (len
);
3479 code_convert_string (str
, coding
, encodep
, nocopy
)
3480 Lisp_Object str
, nocopy
;
3481 struct coding_system
*coding
;
3484 int len
, consumed
, produced
;
3486 unsigned char *begp
, *endp
;
3487 int head_skip
, tail_skip
;
3488 struct gcpro gcpro1
;
3490 if (encodep
&& !NILP (coding
->pre_write_conversion
)
3491 || !encodep
&& !NILP (coding
->post_read_conversion
))
3493 /* Since we have to call Lisp functions which assume target text
3494 is in a buffer, after setting a temporary buffer, call
3495 code_convert_region. */
3496 int count
= specpdl_ptr
- specpdl
;
3497 int len
= XSTRING (str
)->size
;
3499 struct buffer
*old
= current_buffer
;
3501 record_unwind_protect (Fset_buffer
, Fcurrent_buffer ());
3502 temp_output_buffer_setup (" *code-converting-work*");
3503 set_buffer_internal (XBUFFER (Vstandard_output
));
3504 insert_from_string (str
, 0, len
, 0);
3505 code_convert_region (make_number (BEGV
), make_number (ZV
),
3507 result
= make_buffer_string (BEGV
, ZV
, 0);
3508 set_buffer_internal (old
);
3509 return unbind_to (count
, result
);
3512 /* We may be able to shrink the conversion region. */
3513 begp
= XSTRING (str
)->data
;
3514 endp
= begp
+ XSTRING (str
)->size
;
3515 shrink_conversion_area (&begp
, &endp
, coding
, encodep
);
3518 /* We need no conversion. */
3519 return (NILP (nocopy
) ? Fcopy_sequence (str
) : str
);
3521 head_skip
= begp
- XSTRING (str
)->data
;
3522 tail_skip
= XSTRING (str
)->size
- head_skip
- (endp
- begp
);
3527 len
= encoding_buffer_size (coding
, endp
- begp
);
3529 len
= decoding_buffer_size (coding
, endp
- begp
);
3530 buf
= get_conversion_buffer (len
+ head_skip
+ tail_skip
);
3532 bcopy (XSTRING (str
)->data
, buf
, head_skip
);
3533 coding
->last_block
= 1;
3535 ? encode_coding (coding
, XSTRING (str
)->data
+ head_skip
,
3536 buf
+ head_skip
, endp
- begp
, len
, &consumed
)
3537 : decode_coding (coding
, XSTRING (str
)->data
+ head_skip
,
3538 buf
+ head_skip
, endp
- begp
, len
, &consumed
));
3539 bcopy (XSTRING (str
)->data
+ head_skip
+ (endp
- begp
),
3540 buf
+ head_skip
+ produced
,
3545 return make_string (buf
, head_skip
+ produced
+ tail_skip
);
3548 DEFUN ("decode-coding-region", Fdecode_coding_region
, Sdecode_coding_region
,
3549 3, 3, "r\nzCoding system: ",
3550 "Decode current region by specified coding system.\n\
3551 When called from a program, takes three arguments:\n\
3552 START, END, and CODING-SYSTEM. START END are buffer positions.\n\
3553 Return length of decoded text.")
3554 (b
, e
, coding_system
)
3555 Lisp_Object b
, e
, coding_system
;
3557 struct coding_system coding
;
3559 CHECK_NUMBER_COERCE_MARKER (b
, 0);
3560 CHECK_NUMBER_COERCE_MARKER (e
, 1);
3561 CHECK_SYMBOL (coding_system
, 2);
3563 if (NILP (coding_system
))
3564 return make_number (XFASTINT (e
) - XFASTINT (b
));
3565 if (setup_coding_system (Fcheck_coding_system (coding_system
), &coding
) < 0)
3566 error ("Invalid coding-system: %s", XSYMBOL (coding_system
)->name
->data
);
3568 return code_convert_region (b
, e
, &coding
, 0);
3571 DEFUN ("encode-coding-region", Fencode_coding_region
, Sencode_coding_region
,
3572 3, 3, "r\nzCoding system: ",
3573 "Encode current region by specified coding system.\n\
3574 When called from a program, takes three arguments:\n\
3575 START, END, and CODING-SYSTEM. START END are buffer positions.\n\
3576 Return length of encoded text.")
3577 (b
, e
, coding_system
)
3578 Lisp_Object b
, e
, coding_system
;
3580 struct coding_system coding
;
3582 CHECK_NUMBER_COERCE_MARKER (b
, 0);
3583 CHECK_NUMBER_COERCE_MARKER (e
, 1);
3584 CHECK_SYMBOL (coding_system
, 2);
3586 if (NILP (coding_system
))
3587 return make_number (XFASTINT (e
) - XFASTINT (b
));
3588 if (setup_coding_system (Fcheck_coding_system (coding_system
), &coding
) < 0)
3589 error ("Invalid coding-system: %s", XSYMBOL (coding_system
)->name
->data
);
3591 return code_convert_region (b
, e
, &coding
, 1);
3594 DEFUN ("decode-coding-string", Fdecode_coding_string
, Sdecode_coding_string
,
3596 "Decode STRING which is encoded in CODING-SYSTEM, and return the result.\n\
3597 Optional arg NOCOPY non-nil means it is ok to return STRING itself\n\
3598 if the decoding operation is trivial.")
3599 (string
, coding_system
, nocopy
)
3600 Lisp_Object string
, coding_system
, nocopy
;
3602 struct coding_system coding
;
3604 CHECK_STRING (string
, 0);
3605 CHECK_SYMBOL (coding_system
, 1);
3607 if (NILP (coding_system
))
3608 return (NILP (nocopy
) ? Fcopy_sequence (string
) : string
);
3609 if (setup_coding_system (Fcheck_coding_system (coding_system
), &coding
) < 0)
3610 error ("Invalid coding-system: %s", XSYMBOL (coding_system
)->name
->data
);
3612 return code_convert_string (string
, &coding
, 0, nocopy
);
3615 DEFUN ("encode-coding-string", Fencode_coding_string
, Sencode_coding_string
,
3617 "Encode STRING to CODING-SYSTEM, and return the result.\n\
3618 Optional arg NOCOPY non-nil means it is ok to return STRING itself\n\
3619 if the encoding operation is trivial.")
3620 (string
, coding_system
, nocopy
)
3621 Lisp_Object string
, coding_system
, nocopy
;
3623 struct coding_system coding
;
3625 CHECK_STRING (string
, 0);
3626 CHECK_SYMBOL (coding_system
, 1);
3628 if (NILP (coding_system
))
3629 return (NILP (nocopy
) ? Fcopy_sequence (string
) : string
);
3630 if (setup_coding_system (Fcheck_coding_system (coding_system
), &coding
) < 0)
3631 error ("Invalid coding-system: %s", XSYMBOL (coding_system
)->name
->data
);
3633 return code_convert_string (string
, &coding
, 1, nocopy
);
3636 DEFUN ("decode-sjis-char", Fdecode_sjis_char
, Sdecode_sjis_char
, 1, 1, 0,
3637 "Decode a JISX0208 character of shift-jis encoding.\n\
3638 CODE is the character code in SJIS.\n\
3639 Return the corresponding character.")
3643 unsigned char c1
, c2
, s1
, s2
;
3646 CHECK_NUMBER (code
, 0);
3647 s1
= (XFASTINT (code
)) >> 8, s2
= (XFASTINT (code
)) & 0xFF;
3648 DECODE_SJIS (s1
, s2
, c1
, c2
);
3649 XSETFASTINT (val
, MAKE_NON_ASCII_CHAR (charset_jisx0208
, c1
, c2
));
3653 DEFUN ("encode-sjis-char", Fencode_sjis_char
, Sencode_sjis_char
, 1, 1, 0,
3654 "Encode a JISX0208 character CHAR to SJIS coding-system.\n\
3655 Return the corresponding character code in SJIS.")
3659 int charset
, c1
, c2
, s1
, s2
;
3662 CHECK_NUMBER (ch
, 0);
3663 SPLIT_CHAR (XFASTINT (ch
), charset
, c1
, c2
);
3664 if (charset
== charset_jisx0208
)
3666 ENCODE_SJIS (c1
, c2
, s1
, s2
);
3667 XSETFASTINT (val
, (s1
<< 8) | s2
);
3670 XSETFASTINT (val
, 0);
3674 DEFUN ("decode-big5-char", Fdecode_big5_char
, Sdecode_big5_char
, 1, 1, 0,
3675 "Decode a Big5 character CODE of BIG5 coding-system.\n\
3676 CODE is the character code in BIG5.\n\
3677 Return the corresponding character.")
3682 unsigned char b1
, b2
, c1
, c2
;
3685 CHECK_NUMBER (code
, 0);
3686 b1
= (XFASTINT (code
)) >> 8, b2
= (XFASTINT (code
)) & 0xFF;
3687 DECODE_BIG5 (b1
, b2
, charset
, c1
, c2
);
3688 XSETFASTINT (val
, MAKE_NON_ASCII_CHAR (charset
, c1
, c2
));
3692 DEFUN ("encode-big5-char", Fencode_big5_char
, Sencode_big5_char
, 1, 1, 0,
3693 "Encode the Big5 character CHAR to BIG5 coding-system.\n\
3694 Return the corresponding character code in Big5.")
3698 int charset
, c1
, c2
, b1
, b2
;
3701 CHECK_NUMBER (ch
, 0);
3702 SPLIT_CHAR (XFASTINT (ch
), charset
, c1
, c2
);
3703 if (charset
== charset_big5_1
|| charset
== charset_big5_2
)
3705 ENCODE_BIG5 (charset
, c1
, c2
, b1
, b2
);
3706 XSETFASTINT (val
, (b1
<< 8) | b2
);
3709 XSETFASTINT (val
, 0);
3713 DEFUN ("set-terminal-coding-system-internal",
3714 Fset_terminal_coding_system_internal
,
3715 Sset_terminal_coding_system_internal
, 1, 1, 0, "")
3717 Lisp_Object coding_system
;
3719 CHECK_SYMBOL (coding_system
, 0);
3720 setup_coding_system (Fcheck_coding_system (coding_system
), &terminal_coding
);
3721 /* We had better not send unsafe characters to terminal. */
3722 terminal_coding
.flags
|= CODING_FLAG_ISO_SAFE
;
3727 DEFUN ("set-safe-terminal-coding-system-internal",
3728 Fset_safe_terminal_coding_system_internal
,
3729 Sset_safe_terminal_coding_system_internal
, 1, 1, 0, "")
3731 Lisp_Object coding_system
;
3733 CHECK_SYMBOL (coding_system
, 0);
3734 setup_coding_system (Fcheck_coding_system (coding_system
),
3735 &safe_terminal_coding
);
3739 DEFUN ("terminal-coding-system",
3740 Fterminal_coding_system
, Sterminal_coding_system
, 0, 0, 0,
3741 "Return coding-system of your terminal.")
3744 return terminal_coding
.symbol
;
3747 DEFUN ("set-keyboard-coding-system-internal",
3748 Fset_keyboard_coding_system_internal
,
3749 Sset_keyboard_coding_system_internal
, 1, 1, 0, "")
3751 Lisp_Object coding_system
;
3753 CHECK_SYMBOL (coding_system
, 0);
3754 setup_coding_system (Fcheck_coding_system (coding_system
), &keyboard_coding
);
3758 DEFUN ("keyboard-coding-system",
3759 Fkeyboard_coding_system
, Skeyboard_coding_system
, 0, 0, 0,
3760 "Return coding-system of what is sent from terminal keyboard.")
3763 return keyboard_coding
.symbol
;
3767 DEFUN ("find-operation-coding-system", Ffind_operation_coding_system
,
3768 Sfind_operation_coding_system
, 1, MANY
, 0,
3769 "Choose a coding system for an operation based on the target name.\n\
3770 The value names a pair of coding systems: (DECODING-SYSTEM ENCODING-SYSTEM).\n\
3771 DECODING-SYSTEM is the coding system to use for decoding\n\
3772 \(in case OPERATION does decoding), and ENCODING-SYSTEM is the coding system\n\
3773 for encoding (in case OPERATION does encoding).\n\
3775 The first argument OPERATION specifies an I/O primitive:\n\
3776 For file I/O, `insert-file-contents' or `write-region'.\n\
3777 For process I/O, `call-process', `call-process-region', or `start-process'.\n\
3778 For network I/O, `open-network-stream'.\n\
3780 The remaining arguments should be the same arguments that were passed\n\
3781 to the primitive. Depending on which primitive, one of those arguments\n\
3782 is selected as the TARGET. For example, if OPERATION does file I/O,\n\
3783 whichever argument specifies the file name is TARGET.\n\
3785 TARGET has a meaning which depends on OPERATION:\n\
3786 For file I/O, TARGET is a file name.\n\
3787 For process I/O, TARGET is a process name.\n\
3788 For network I/O, TARGET is a service name or a port number\n\
3790 This function looks up what specified for TARGET in,\n\
3791 `file-coding-system-alist', `process-coding-system-alist',\n\
3792 or `network-coding-system-alist' depending on OPERATION.\n\
3793 They may specify a coding system, a cons of coding systems,\n\
3794 or a function symbol to call.\n\
3795 In the last case, we call the function with one argument,\n\
3796 which is a list of all the arguments given to this function.")
3801 Lisp_Object operation
, target_idx
, target
, val
;
3802 register Lisp_Object chain
;
3805 error ("Too few arguments");
3806 operation
= args
[0];
3807 if (!SYMBOLP (operation
)
3808 || !INTEGERP (target_idx
= Fget (operation
, Qtarget_idx
)))
3809 error ("Invalid first arguement");
3810 if (nargs
< 1 + XINT (target_idx
))
3811 error ("Too few arguments for operation: %s",
3812 XSYMBOL (operation
)->name
->data
);
3813 target
= args
[XINT (target_idx
) + 1];
3814 if (!(STRINGP (target
)
3815 || (EQ (operation
, Qopen_network_stream
) && INTEGERP (target
))))
3816 error ("Invalid %dth argument", XINT (target_idx
) + 1);
3818 chain
= ((EQ (operation
, Qinsert_file_contents
)
3819 || EQ (operation
, Qwrite_region
))
3820 ? Vfile_coding_system_alist
3821 : (EQ (operation
, Qopen_network_stream
)
3822 ? Vnetwork_coding_system_alist
3823 : Vprocess_coding_system_alist
));
3827 for (; CONSP (chain
); chain
= XCONS (chain
)->cdr
)
3830 elt
= XCONS (chain
)->car
;
3833 && ((STRINGP (target
)
3834 && STRINGP (XCONS (elt
)->car
)
3835 && fast_string_match (XCONS (elt
)->car
, target
) >= 0)
3836 || (INTEGERP (target
) && EQ (target
, XCONS (elt
)->car
))))
3838 val
= XCONS (elt
)->cdr
;
3839 /* Here, if VAL is both a valid coding system and a valid
3840 function symbol, we return VAL as a coding system. */
3843 if (! SYMBOLP (val
))
3845 if (! NILP (Fcoding_system_p (val
)))
3846 return Fcons (val
, val
);
3847 if (! NILP (Ffboundp (val
)))
3849 val
= call1 (val
, Flist (nargs
, args
));
3852 if (SYMBOLP (val
) && ! NILP (Fcoding_system_p (val
)))
3853 return Fcons (val
, val
);
3864 /*** 8. Post-amble ***/
3870 /* Emacs' internal format specific initialize routine. */
3871 for (i
= 0; i
<= 0x20; i
++)
3872 emacs_code_class
[i
] = EMACS_control_code
;
3873 emacs_code_class
[0x0A] = EMACS_linefeed_code
;
3874 emacs_code_class
[0x0D] = EMACS_carriage_return_code
;
3875 for (i
= 0x21 ; i
< 0x7F; i
++)
3876 emacs_code_class
[i
] = EMACS_ascii_code
;
3877 emacs_code_class
[0x7F] = EMACS_control_code
;
3878 emacs_code_class
[0x80] = EMACS_leading_code_composition
;
3879 for (i
= 0x81; i
< 0xFF; i
++)
3880 emacs_code_class
[i
] = EMACS_invalid_code
;
3881 emacs_code_class
[LEADING_CODE_PRIVATE_11
] = EMACS_leading_code_3
;
3882 emacs_code_class
[LEADING_CODE_PRIVATE_12
] = EMACS_leading_code_3
;
3883 emacs_code_class
[LEADING_CODE_PRIVATE_21
] = EMACS_leading_code_4
;
3884 emacs_code_class
[LEADING_CODE_PRIVATE_22
] = EMACS_leading_code_4
;
3886 /* ISO2022 specific initialize routine. */
3887 for (i
= 0; i
< 0x20; i
++)
3888 iso_code_class
[i
] = ISO_control_code
;
3889 for (i
= 0x21; i
< 0x7F; i
++)
3890 iso_code_class
[i
] = ISO_graphic_plane_0
;
3891 for (i
= 0x80; i
< 0xA0; i
++)
3892 iso_code_class
[i
] = ISO_control_code
;
3893 for (i
= 0xA1; i
< 0xFF; i
++)
3894 iso_code_class
[i
] = ISO_graphic_plane_1
;
3895 iso_code_class
[0x20] = iso_code_class
[0x7F] = ISO_0x20_or_0x7F
;
3896 iso_code_class
[0xA0] = iso_code_class
[0xFF] = ISO_0xA0_or_0xFF
;
3897 iso_code_class
[ISO_CODE_CR
] = ISO_carriage_return
;
3898 iso_code_class
[ISO_CODE_SO
] = ISO_shift_out
;
3899 iso_code_class
[ISO_CODE_SI
] = ISO_shift_in
;
3900 iso_code_class
[ISO_CODE_SS2_7
] = ISO_single_shift_2_7
;
3901 iso_code_class
[ISO_CODE_ESC
] = ISO_escape
;
3902 iso_code_class
[ISO_CODE_SS2
] = ISO_single_shift_2
;
3903 iso_code_class
[ISO_CODE_SS3
] = ISO_single_shift_3
;
3904 iso_code_class
[ISO_CODE_CSI
] = ISO_control_sequence_introducer
;
3906 conversion_buffer_size
= MINIMUM_CONVERSION_BUFFER_SIZE
;
3907 conversion_buffer
= (char *) xmalloc (MINIMUM_CONVERSION_BUFFER_SIZE
);
3909 setup_coding_system (Qnil
, &keyboard_coding
);
3910 setup_coding_system (Qnil
, &terminal_coding
);
3911 setup_coding_system (Qnil
, &safe_terminal_coding
);
3913 #if defined (MSDOS) || defined (WINDOWSNT)
3914 system_eol_type
= CODING_EOL_CRLF
;
3916 system_eol_type
= CODING_EOL_LF
;
3924 Qtarget_idx
= intern ("target-idx");
3925 staticpro (&Qtarget_idx
);
3927 Qcoding_system_history
= intern ("coding-system-history");
3928 staticpro (&Qcoding_system_history
);
3929 Fset (Qcoding_system_history
, Qnil
);
3931 /* Target FILENAME is the first argument. */
3932 Fput (Qinsert_file_contents
, Qtarget_idx
, make_number (0));
3933 /* Target FILENAME is the third argument. */
3934 Fput (Qwrite_region
, Qtarget_idx
, make_number (2));
3936 Qcall_process
= intern ("call-process");
3937 staticpro (&Qcall_process
);
3938 /* Target PROGRAM is the first argument. */
3939 Fput (Qcall_process
, Qtarget_idx
, make_number (0));
3941 Qcall_process_region
= intern ("call-process-region");
3942 staticpro (&Qcall_process_region
);
3943 /* Target PROGRAM is the third argument. */
3944 Fput (Qcall_process_region
, Qtarget_idx
, make_number (2));
3946 Qstart_process
= intern ("start-process");
3947 staticpro (&Qstart_process
);
3948 /* Target PROGRAM is the third argument. */
3949 Fput (Qstart_process
, Qtarget_idx
, make_number (2));
3951 Qopen_network_stream
= intern ("open-network-stream");
3952 staticpro (&Qopen_network_stream
);
3953 /* Target SERVICE is the fourth argument. */
3954 Fput (Qopen_network_stream
, Qtarget_idx
, make_number (3));
3956 Qcoding_system
= intern ("coding-system");
3957 staticpro (&Qcoding_system
);
3959 Qeol_type
= intern ("eol-type");
3960 staticpro (&Qeol_type
);
3962 Qbuffer_file_coding_system
= intern ("buffer-file-coding-system");
3963 staticpro (&Qbuffer_file_coding_system
);
3965 Qpost_read_conversion
= intern ("post-read-conversion");
3966 staticpro (&Qpost_read_conversion
);
3968 Qpre_write_conversion
= intern ("pre-write-conversion");
3969 staticpro (&Qpre_write_conversion
);
3971 Qno_conversion
= intern ("no-conversion");
3972 staticpro (&Qno_conversion
);
3974 Qundecided
= intern ("undecided");
3975 staticpro (&Qundecided
);
3977 Qcoding_system_p
= intern ("coding-system-p");
3978 staticpro (&Qcoding_system_p
);
3980 Qcoding_system_error
= intern ("coding-system-error");
3981 staticpro (&Qcoding_system_error
);
3983 Fput (Qcoding_system_error
, Qerror_conditions
,
3984 Fcons (Qcoding_system_error
, Fcons (Qerror
, Qnil
)));
3985 Fput (Qcoding_system_error
, Qerror_message
,
3986 build_string ("Invalid coding system"));
3988 Qcoding_category_index
= intern ("coding-category-index");
3989 staticpro (&Qcoding_category_index
);
3993 for (i
= 0; i
< CODING_CATEGORY_IDX_MAX
; i
++)
3995 coding_category_table
[i
] = intern (coding_category_name
[i
]);
3996 staticpro (&coding_category_table
[i
]);
3997 Fput (coding_category_table
[i
], Qcoding_category_index
,
4002 Qcharacter_unification_table
= intern ("character-unification-table");
4003 staticpro (&Qcharacter_unification_table
);
4004 Fput (Qcharacter_unification_table
, Qchar_table_extra_slots
,
4007 Qcharacter_unification_table_for_decode
4008 = intern ("character-unification-table-for-decode");
4009 staticpro (&Qcharacter_unification_table_for_decode
);
4011 Qcharacter_unification_table_for_encode
4012 = intern ("character-unification-table-for-encode");
4013 staticpro (&Qcharacter_unification_table_for_encode
);
4015 Qsafe_charsets
= intern ("safe-charsets");
4016 staticpro (&Qsafe_charsets
);
4018 Qemacs_mule
= intern ("emacs-mule");
4019 staticpro (&Qemacs_mule
);
4021 defsubr (&Scoding_system_p
);
4022 defsubr (&Sread_coding_system
);
4023 defsubr (&Sread_non_nil_coding_system
);
4024 defsubr (&Scheck_coding_system
);
4025 defsubr (&Sdetect_coding_region
);
4026 defsubr (&Sdecode_coding_region
);
4027 defsubr (&Sencode_coding_region
);
4028 defsubr (&Sdecode_coding_string
);
4029 defsubr (&Sencode_coding_string
);
4030 defsubr (&Sdecode_sjis_char
);
4031 defsubr (&Sencode_sjis_char
);
4032 defsubr (&Sdecode_big5_char
);
4033 defsubr (&Sencode_big5_char
);
4034 defsubr (&Sset_terminal_coding_system_internal
);
4035 defsubr (&Sset_safe_terminal_coding_system_internal
);
4036 defsubr (&Sterminal_coding_system
);
4037 defsubr (&Sset_keyboard_coding_system_internal
);
4038 defsubr (&Skeyboard_coding_system
);
4039 defsubr (&Sfind_operation_coding_system
);
4041 DEFVAR_LISP ("coding-system-list", &Vcoding_system_list
,
4042 "List of coding systems.\n\
4044 Do not alter the value of this variable manually. This variable should be\n\
4045 updated by the functions `make-coding-system' and\n\
4046 `define-coding-system-alias'.");
4047 Vcoding_system_list
= Qnil
;
4049 DEFVAR_LISP ("coding-system-alist", &Vcoding_system_alist
,
4050 "Alist of coding system names.\n\
4051 Each element is one element list of coding system name.\n\
4052 This variable is given to `completing-read' as TABLE argument.\n\
4054 Do not alter the value of this variable manually. This variable should be\n\
4055 updated by the functions `make-coding-system' and\n\
4056 `define-coding-system-alias'.");
4057 Vcoding_system_alist
= Qnil
;
4059 DEFVAR_LISP ("coding-category-list", &Vcoding_category_list
,
4060 "List of coding-categories (symbols) ordered by priority.");
4064 Vcoding_category_list
= Qnil
;
4065 for (i
= CODING_CATEGORY_IDX_MAX
- 1; i
>= 0; i
--)
4066 Vcoding_category_list
4067 = Fcons (coding_category_table
[i
], Vcoding_category_list
);
4070 DEFVAR_LISP ("coding-system-for-read", &Vcoding_system_for_read
,
4071 "Specify the coding system for read operations.\n\
4072 It is useful to bind this variable with `let', but do not set it globally.\n\
4073 If the value is a coding system, it is used for decoding on read operation.\n\
4074 If not, an appropriate element is used from one of the coding system alists:\n\
4075 There are three such tables, `file-coding-system-alist',\n\
4076 `process-coding-system-alist', and `network-coding-system-alist'.");
4077 Vcoding_system_for_read
= Qnil
;
4079 DEFVAR_LISP ("coding-system-for-write", &Vcoding_system_for_write
,
4080 "Specify the coding system for write operations.\n\
4081 It is useful to bind this variable with `let', but do not set it globally.\n\
4082 If the value is a coding system, it is used for encoding on write operation.\n\
4083 If not, an appropriate element is used from one of the coding system alists:\n\
4084 There are three such tables, `file-coding-system-alist',\n\
4085 `process-coding-system-alist', and `network-coding-system-alist'.");
4086 Vcoding_system_for_write
= Qnil
;
4088 DEFVAR_LISP ("last-coding-system-used", &Vlast_coding_system_used
,
4089 "Coding system used in the latest file or process I/O.");
4090 Vlast_coding_system_used
= Qnil
;
4092 DEFVAR_BOOL ("inhibit-eol-conversion", &inhibit_eol_conversion
,
4093 "*Non-nil inhibit code conversion of end-of-line format in any cases.");
4094 inhibit_eol_conversion
= 0;
4096 DEFVAR_LISP ("file-coding-system-alist", &Vfile_coding_system_alist
,
4097 "Alist to decide a coding system to use for a file I/O operation.\n\
4098 The format is ((PATTERN . VAL) ...),\n\
4099 where PATTERN is a regular expression matching a file name,\n\
4100 VAL is a coding system, a cons of coding systems, or a function symbol.\n\
4101 If VAL is a coding system, it is used for both decoding and encoding\n\
4102 the file contents.\n\
4103 If VAL is a cons of coding systems, the car part is used for decoding,\n\
4104 and the cdr part is used for encoding.\n\
4105 If VAL is a function symbol, the function must return a coding system\n\
4106 or a cons of coding systems which are used as above.\n\
4108 See also the function `find-operation-coding-system'.");
4109 Vfile_coding_system_alist
= Qnil
;
4111 DEFVAR_LISP ("process-coding-system-alist", &Vprocess_coding_system_alist
,
4112 "Alist to decide a coding system to use for a process I/O operation.\n\
4113 The format is ((PATTERN . VAL) ...),\n\
4114 where PATTERN is a regular expression matching a program name,\n\
4115 VAL is a coding system, a cons of coding systems, or a function symbol.\n\
4116 If VAL is a coding system, it is used for both decoding what received\n\
4117 from the program and encoding what sent to the program.\n\
4118 If VAL is a cons of coding systems, the car part is used for decoding,\n\
4119 and the cdr part is used for encoding.\n\
4120 If VAL is a function symbol, the function must return a coding system\n\
4121 or a cons of coding systems which are used as above.\n\
4123 See also the function `find-operation-coding-system'.");
4124 Vprocess_coding_system_alist
= Qnil
;
4126 DEFVAR_LISP ("network-coding-system-alist", &Vnetwork_coding_system_alist
,
4127 "Alist to decide a coding system to use for a network I/O operation.\n\
4128 The format is ((PATTERN . VAL) ...),\n\
4129 where PATTERN is a regular expression matching a network service name\n\
4130 or is a port number to connect to,\n\
4131 VAL is a coding system, a cons of coding systems, or a function symbol.\n\
4132 If VAL is a coding system, it is used for both decoding what received\n\
4133 from the network stream and encoding what sent to the network stream.\n\
4134 If VAL is a cons of coding systems, the car part is used for decoding,\n\
4135 and the cdr part is used for encoding.\n\
4136 If VAL is a function symbol, the function must return a coding system\n\
4137 or a cons of coding systems which are used as above.\n\
4139 See also the function `find-operation-coding-system'.");
4140 Vnetwork_coding_system_alist
= Qnil
;
4142 DEFVAR_INT ("eol-mnemonic-unix", &eol_mnemonic_unix
,
4143 "Mnemonic character indicating UNIX-like end-of-line format (i.e. LF) .");
4144 eol_mnemonic_unix
= ':';
4146 DEFVAR_INT ("eol-mnemonic-dos", &eol_mnemonic_dos
,
4147 "Mnemonic character indicating DOS-like end-of-line format (i.e. CRLF).");
4148 eol_mnemonic_dos
= '\\';
4150 DEFVAR_INT ("eol-mnemonic-mac", &eol_mnemonic_mac
,
4151 "Mnemonic character indicating MAC-like end-of-line format (i.e. CR).");
4152 eol_mnemonic_mac
= '/';
4154 DEFVAR_INT ("eol-mnemonic-undecided", &eol_mnemonic_undecided
,
4155 "Mnemonic character indicating end-of-line format is not yet decided.");
4156 eol_mnemonic_undecided
= ':';
4158 DEFVAR_LISP ("enable-character-unification", &Venable_character_unification
,
4159 "Non-nil means ISO 2022 encoder/decoder do character unification.");
4160 Venable_character_unification
= Qt
;
4162 DEFVAR_LISP ("standard-character-unification-table-for-decode",
4163 &Vstandard_character_unification_table_for_decode
,
4164 "Table for unifying characters when reading.");
4165 Vstandard_character_unification_table_for_decode
= Qnil
;
4167 DEFVAR_LISP ("standard-character-unification-table-for-encode",
4168 &Vstandard_character_unification_table_for_encode
,
4169 "Table for unifying characters when writing.");
4170 Vstandard_character_unification_table_for_encode
= Qnil
;
4172 DEFVAR_LISP ("charset-revision-table", &Vcharset_revision_alist
,
4173 "Alist of charsets vs revision numbers.\n\
4174 While encoding, if a charset (car part of an element) is found,\n\
4175 designate it with the escape sequence identifing revision (cdr part of the element).");
4176 Vcharset_revision_alist
= Qnil
;
4178 DEFVAR_LISP ("default-process-coding-system",
4179 &Vdefault_process_coding_system
,
4180 "Cons of coding systems used for process I/O by default.\n\
4181 The car part is used for decoding a process output,\n\
4182 the cdr part is used for encoding a text to be sent to a process.");
4183 Vdefault_process_coding_system
= Qnil
;
4185 DEFVAR_LISP ("latin-extra-code-table", &Vlatin_extra_code_table
,
4186 "Table of extra Latin codes in the range 128..159 (inclusive).\n\
4187 This is a vector of length 256.\n\
4188 If Nth element is non-nil, the existence of code N in a file\n\
4189 \(or output of subprocess) doesn't prevent it to be detected as\n\
4190 a coding system of ISO 2022 variant which has a flag\n\
4191 `accept-latin-extra-code' t (e.g. iso-latin-1) on reading a file\n\
4192 or reading output of a subprocess.\n\
4193 Only 128th through 159th elements has a meaning.");
4194 Vlatin_extra_code_table
= Fmake_vector (make_number (256), Qnil
);