2. Emacs' internal format (emacs-mule) handlers
3. ISO2022 handlers
4. Shift-JIS and BIG5 handlers
- 5. End-of-line handlers
- 6. C library functions
- 7. Emacs Lisp library functions
- 8. Post-amble
+ 5. CCL handlers
+ 6. End-of-line handlers
+ 7. C library functions
+ 8. Emacs Lisp library functions
+ 9. Post-amble
*/
/* Decode one ASCII character C. */
-#define DECODE_CHARACTER_ASCII(c) \
- do { \
- if (COMPOSING_P (coding->composing)) \
- *dst++ = 0xA0, *dst++ = (c) | 0x80; \
- else \
- { \
- *dst++ = (c); \
- coding->produced_char++; \
- } \
+#define DECODE_CHARACTER_ASCII(c) \
+ do { \
+ if (COMPOSING_P (coding->composing)) \
+ { \
+ *dst++ = 0xA0, *dst++ = (c) | 0x80; \
+ coding->composed_chars++; \
+ } \
+ else \
+ { \
+ *dst++ = (c); \
+ coding->produced_char++; \
+ } \
} while (0)
/* Decode one DIMENSION1 character whose charset is CHARSET and whose
do { \
unsigned char leading_code = CHARSET_LEADING_CODE_BASE (charset); \
if (COMPOSING_P (coding->composing)) \
- *dst++ = leading_code + 0x20; \
+ { \
+ *dst++ = leading_code + 0x20; \
+ coding->composed_chars++; \
+ } \
else \
{ \
*dst++ = leading_code; \
Lisp_Object Qno_conversion, Qundecided;
Lisp_Object Qcoding_system_history;
Lisp_Object Qsafe_charsets;
+Lisp_Object Qvalid_codes;
extern Lisp_Object Qinsert_file_contents, Qwrite_region;
Lisp_Object Qcall_process, Qcall_process_region, Qprocess_argument;
Lisp_Object Vlast_coding_system_used;
/* A vector of length 256 which contains information about special
- Latin codes (espepcially for dealing with Microsoft code). */
+ Latin codes (especially for dealing with Microsoft codes). */
Lisp_Object Vlatin_extra_code_table;
/* Flag to inhibit code conversion of end-of-line format. */
int inhibit_eol_conversion;
+/* Flag to make buffer-file-coding-system inherit from process-coding. */
+int inherit_process_coding_system;
+
/* Coding system to be used to encode text for terminal display. */
struct coding_system terminal_coding;
/* Coding system of what is sent from terminal keyboard. */
struct coding_system keyboard_coding;
+/* Default coding system to be used to write a file. */
+struct coding_system default_buffer_file_coding;
+
Lisp_Object Vfile_coding_system_alist;
Lisp_Object Vprocess_coding_system_alist;
Lisp_Object Vnetwork_coding_system_alist;
"coding-category-iso-8-2",
"coding-category-iso-7-else",
"coding-category-iso-8-else",
+ "coding-category-ccl",
"coding-category-big5",
"coding-category-raw-text",
"coding-category-binary"
};
-/* Table pointers to coding systems corresponding to each coding
+/* Table of pointers to coding systems corresponding to each coding
categories. */
struct coding_system *coding_system_table[CODING_CATEGORY_IDX_MAX];
-/* Flag to tell if we look up unification table on character code
+/* Table of coding category masks. Nth element is a mask for a coding
+ cateogry of which priority is Nth. */
+static
+int coding_priorities[CODING_CATEGORY_IDX_MAX];
+
+/* Flag to tell if we look up translation table on character code
conversion. */
-Lisp_Object Venable_character_unification;
-/* Standard unification table to look up on decoding (reading). */
-Lisp_Object Vstandard_character_unification_table_for_decode;
-/* Standard unification table to look up on encoding (writing). */
-Lisp_Object Vstandard_character_unification_table_for_encode;
+Lisp_Object Venable_character_translation;
+/* Standard translation table to look up on decoding (reading). */
+Lisp_Object Vstandard_translation_table_for_decode;
+/* Standard translation table to look up on encoding (writing). */
+Lisp_Object Vstandard_translation_table_for_encode;
-Lisp_Object Qcharacter_unification_table;
-Lisp_Object Qcharacter_unification_table_for_decode;
-Lisp_Object Qcharacter_unification_table_for_encode;
+Lisp_Object Qtranslation_table;
+Lisp_Object Qtranslation_table_id;
+Lisp_Object Qtranslation_table_for_decode;
+Lisp_Object Qtranslation_table_for_encode;
/* Alist of charsets vs revision number. */
Lisp_Object Vcharset_revision_alist;
enum iso_code_class_type iso_code_class[256];
-#define CHARSET_OK(idx, charset) \
- (coding_system_table[idx]->safe_charsets[charset] \
- || (CODING_SPEC_ISO_REQUESTED_DESIGNATION \
- (coding_system_table[idx], charset) \
- != CODING_SPEC_ISO_NO_REQUESTED_DESIGNATION))
+#define CHARSET_OK(idx, charset) \
+ (coding_system_table[idx] \
+ && (coding_system_table[idx]->safe_charsets[charset] \
+ || (CODING_SPEC_ISO_REQUESTED_DESIGNATION \
+ (coding_system_table[idx], charset) \
+ != CODING_SPEC_ISO_NO_REQUESTED_DESIGNATION)))
#define SHIFT_OUT_OK(idx) \
(CODING_SPEC_ISO_INITIAL_DESIGNATION (coding_system_table[idx], 1) >= 0)
{
int mask = CODING_CATEGORY_MASK_ISO;
int mask_found = 0;
- int reg[4], shift_out = 0;
+ int reg[4], shift_out = 0, single_shifting = 0;
int c, c1, i, charset;
reg[0] = CHARSET_ASCII, reg[1] = reg[2] = reg[3] = -1;
switch (c)
{
case ISO_CODE_ESC:
+ single_shifting = 0;
if (src >= src_end)
break;
c = *src++;
/* Invalid designation sequence. Just ignore. */
break;
}
- else if (c == 'N' || c == 'n')
- {
- if (shift_out == 0
- && (reg[1] >= 0
- || SHIFT_OUT_OK (CODING_CATEGORY_IDX_ISO_7_ELSE)
- || SHIFT_OUT_OK (CODING_CATEGORY_IDX_ISO_8_ELSE)))
- {
- /* Locking shift out. */
- mask &= ~CODING_CATEGORY_MASK_ISO_7BIT;
- mask_found |= CODING_CATEGORY_MASK_ISO_SHIFT;
- shift_out = 1;
- }
- break;
- }
- else if (c == 'O' || c == 'o')
+ else if (c == 'N' || c == 'O')
{
- if (shift_out == 1)
- {
- /* Locking shift in. */
- mask &= ~CODING_CATEGORY_MASK_ISO_7BIT;
- mask_found |= CODING_CATEGORY_MASK_ISO_SHIFT;
- shift_out = 0;
- }
+ /* ESC <Fe> for SS2 or SS3. */
+ mask &= CODING_CATEGORY_MASK_ISO_7_ELSE;
break;
}
else if (c == '0' || c == '1' || c == '2')
- /* Start/end composition. Just ignore. */
+ /* ESC <Fp> for start/end composition. Just ignore. */
break;
else
/* Invalid escape sequence. Just ignore. */
mask_found |= CODING_CATEGORY_MASK_ISO_7_TIGHT;
else
mask &= ~CODING_CATEGORY_MASK_ISO_7_TIGHT;
- if (! CHARSET_OK (CODING_CATEGORY_IDX_ISO_7_ELSE, charset))
+ if (CHARSET_OK (CODING_CATEGORY_IDX_ISO_7_ELSE, charset))
+ mask_found |= CODING_CATEGORY_MASK_ISO_7_ELSE;
+ else
mask &= ~CODING_CATEGORY_MASK_ISO_7_ELSE;
- if (! CHARSET_OK (CODING_CATEGORY_IDX_ISO_8_ELSE, charset))
+ if (CHARSET_OK (CODING_CATEGORY_IDX_ISO_8_ELSE, charset))
+ mask_found |= CODING_CATEGORY_MASK_ISO_8_ELSE;
+ else
mask &= ~CODING_CATEGORY_MASK_ISO_8_ELSE;
break;
case ISO_CODE_SO:
+ single_shifting = 0;
if (shift_out == 0
&& (reg[1] >= 0
|| SHIFT_OUT_OK (CODING_CATEGORY_IDX_ISO_7_ELSE)
break;
case ISO_CODE_SI:
+ single_shifting = 0;
if (shift_out == 1)
{
/* Locking shift in. */
break;
case ISO_CODE_CSI:
+ single_shifting = 0;
case ISO_CODE_SS2:
case ISO_CODE_SS3:
{
if (coding_system_table[CODING_CATEGORY_IDX_ISO_8_2]->flags
& CODING_FLAG_ISO_SINGLE_SHIFT)
newmask |= CODING_CATEGORY_MASK_ISO_8_2;
+ single_shifting = 1;
}
if (VECTORP (Vlatin_extra_code_table)
&& !NILP (XVECTOR (Vlatin_extra_code_table)->contents[c]))
default:
if (c < 0x80)
- break;
+ {
+ single_shifting = 0;
+ break;
+ }
else if (c < 0xA0)
{
+ single_shifting = 0;
if (VECTORP (Vlatin_extra_code_table)
&& !NILP (XVECTOR (Vlatin_extra_code_table)->contents[c]))
{
mask &= ~(CODING_CATEGORY_MASK_ISO_7BIT
| CODING_CATEGORY_MASK_ISO_7_ELSE);
mask_found |= CODING_CATEGORY_MASK_ISO_8_1;
- while (src < src_end && *src >= 0xA0)
- src++;
- if ((src - src_begin - 1) & 1 && src < src_end)
- mask &= ~CODING_CATEGORY_MASK_ISO_8_2;
- else
- mask_found |= CODING_CATEGORY_MASK_ISO_8_2;
+ /* Check the length of succeeding codes of the range
+ 0xA0..0FF. If the byte length is odd, we exclude
+ CODING_CATEGORY_MASK_ISO_8_2. We can check this only
+ when we are not single shifting. */
+ if (!single_shifting)
+ {
+ while (src < src_end && *src >= 0xA0)
+ src++;
+ if ((src - src_begin - 1) & 1 && src < src_end)
+ mask &= ~CODING_CATEGORY_MASK_ISO_8_2;
+ else
+ mask_found |= CODING_CATEGORY_MASK_ISO_8_2;
+ }
}
break;
}
*dst++ = 0xFF; \
coding->composing += 2; \
} \
- if ((charset) >= 0) \
+ if (charset_alt >= 0) \
{ \
- if (CHARSET_DIMENSION (charset) == 2) \
+ if (CHARSET_DIMENSION (charset_alt) == 2) \
{ \
ONE_MORE_BYTE (c2); \
if (iso_code_class[(c2) & 0x7F] != ISO_0x20_or_0x7F \
&& iso_code_class[(c2) & 0x7F] != ISO_graphic_plane_0) \
{ \
src--; \
- c2 = ' '; \
+ charset_alt = CHARSET_ASCII; \
} \
} \
- if (!NILP (unification_table) \
- && ((c_alt = unify_char (unification_table, \
- -1, (charset), c1, c2)) >= 0)) \
+ if (!NILP (translation_table) \
+ && ((c_alt = translate_char (translation_table, \
+ -1, charset_alt, c1, c2)) >= 0)) \
SPLIT_CHAR (c_alt, charset_alt, c1, c2); \
} \
if (charset_alt == CHARSET_ASCII || charset_alt < 0) \
} \
} while (0)
-/* Check if the current composing sequence contains only valid codes.
- If the composing sequence doesn't end before SRC_END, return -1.
- Else, if it contains only valid codes, return 0.
- Else return the length of the composing sequence. */
+/* Return 0 if there's a valid composing sequence starting at SRC and
+ ending before SRC_END, else return -1. */
-int check_composing_code (coding, src, src_end)
+int
+check_composing_code (coding, src, src_end)
struct coding_system *coding;
unsigned char *src, *src_end;
{
- unsigned char *src_start = src;
- int invalid_code_found = 0;
int charset, c, c1, dim;
while (src < src_end)
{
- if (*src++ != ISO_CODE_ESC) continue;
- if (src >= src_end) break;
- if ((c = *src++) == '1') /* end of compsition */
- return (invalid_code_found ? src - src_start : 0);
- if (src + 2 >= src_end) break;
- if (!coding->flags & CODING_FLAG_ISO_DESIGNATION)
- invalid_code_found = 1;
- else
+ c = *src++;
+ if (c >= 0x20)
+ continue;
+ if (c != ISO_CODE_ESC || src >= src_end)
+ return -1;
+ c = *src++;
+ if (c == '1') /* end of compsition */
+ return 0;
+ if (src + 2 >= src_end
+ || !coding->flags & CODING_FLAG_ISO_DESIGNATION)
+ return -1;
+
+ dim = (c == '$');
+ if (dim == 1)
+ c = (*src >= '@' && *src <= 'B') ? '(' : *src++;
+ if (c >= '(' && c <= '/')
{
- dim = 0;
- if (c == '$')
- {
- dim = 1;
- c = (*src >= '@' && *src <= 'B') ? '(' : *src++;
- }
- if (c >= '(' && c <= '/')
- {
- c1 = *src++;
- if ((c1 < ' ' || c1 >= 0x80)
- || (charset = iso_charset_table[dim][c >= ','][c1]) < 0
- || ! coding->safe_charsets[charset]
- || (CODING_SPEC_ISO_REQUESTED_DESIGNATION (coding, charset)
- == CODING_SPEC_ISO_NO_REQUESTED_DESIGNATION))
- invalid_code_found = 1;
- }
- else
- invalid_code_found = 1;
+ c1 = *src++;
+ if ((c1 < ' ' || c1 >= 0x80)
+ || (charset = iso_charset_table[dim][c >= ','][c1]) < 0
+ || ! coding->safe_charsets[charset]
+ || (CODING_SPEC_ISO_REQUESTED_DESIGNATION (coding, charset)
+ == CODING_SPEC_ISO_NO_REQUESTED_DESIGNATION))
+ return -1;
}
+ else
+ return -1;
}
- return ((coding->mode & CODING_MODE_LAST_BLOCK) ? src_end - src_start : -1);
+
+ /* We have not found the sequence "ESC 1". */
+ return -1;
}
/* See the above "GENERAL NOTES on `decode_coding_XXX ()' functions". */
/* Charsets invoked to graphic plane 0 and 1 respectively. */
int charset0 = CODING_SPEC_ISO_PLANE_CHARSET (coding, 0);
int charset1 = CODING_SPEC_ISO_PLANE_CHARSET (coding, 1);
- Lisp_Object unification_table
- = coding->character_unification_table_for_decode;
+ Lisp_Object translation_table
+ = coding->translation_table_for_decode;
int result = CODING_FINISH_NORMAL;
- if (!NILP (Venable_character_unification) && NILP (unification_table))
- unification_table = Vstandard_character_unification_table_for_decode;
+ if (!NILP (Venable_character_translation) && NILP (translation_table))
+ translation_table = Vstandard_translation_table_for_decode;
coding->produced_char = 0;
+ coding->composed_chars = 0;
coding->fake_multibyte = 0;
while (src < src_end && (dst_bytes
? (dst < adjusted_dst_end)
ONE_MORE_BYTE (c1);
if (c1 >= '@' && c1 <= 'B')
{ /* designation of JISX0208.1978, GB2312.1980,
- or JISX0208.1980 */
+ or JISX0208.1980 */
DECODE_DESIGNATION (0, 2, 94, c1);
}
else if (c1 >= 0x28 && c1 <= 0x2B)
case '0': case '2': /* start composing */
/* Before processing composing, we must be sure that all
characters being composed are supported by CODING.
- If not, we must give up composing and insert the
- bunch of codes for composing as is without decoding. */
- {
- int result1;
-
- result1 = check_composing_code (coding, src, src_end);
- if (result1 == 0)
+ If not, we must give up composing. */
+ if (check_composing_code (coding, src, src_end) == 0)
+ {
+ /* We are looking at a valid composition sequence. */
coding->composing = (c1 == '0'
? COMPOSING_NO_RULE_HEAD
: COMPOSING_WITH_RULE_HEAD);
- else if (result1 > 0)
- {
- if (result1 + 2 < (dst_bytes ? dst_end : src_base) - dst)
- {
- bcopy (src_base, dst, result1 + 2);
- src += result1;
- dst += result1 + 2;
- coding->produced_char += result1 + 2;
- }
- else
- {
- result = CODING_FINISH_INSUFFICIENT_DST;
- goto label_end_of_loop_2;
- }
- }
- else
- goto label_end_of_loop;
- }
+ coding->composed_chars = 0;
+ }
+ else
+ {
+ *dst++ = ISO_CODE_ESC;
+ *dst++ = c1;
+ coding->produced_char += 2;
+ }
break;
case '1': /* end composing */
+ if (!coding->composing)
+ {
+ *dst++ = ISO_CODE_ESC;
+ *dst++ = c1;
+ coding->produced_char += 2;
+ break;
+ }
+
+ if (coding->composed_chars > 0)
+ {
+ if (coding->composed_chars == 1)
+ {
+ unsigned char *this_char_start = dst;
+ int this_bytes;
+
+ /* Only one character is in the composing
+ sequence. Make it a normal character. */
+ while (*--this_char_start != LEADING_CODE_COMPOSITION);
+ dst = (this_char_start
+ + (coding->composing == COMPOSING_NO_RULE_TAIL
+ ? 1 : 2));
+ *dst -= 0x20;
+ if (*dst == 0x80)
+ *++dst &= 0x7F;
+ this_bytes = BYTES_BY_CHAR_HEAD (*dst);
+ while (this_bytes--) *this_char_start++ = *dst++;
+ dst = this_char_start;
+ }
+ coding->produced_char++;
+ }
coding->composing = COMPOSING_NO;
- coding->produced_char++;
break;
case '[': /* specification of direction */
dst = encode_invocation_designation (charset, coding, dst); \
} while (1)
-#define ENCODE_ISO_CHARACTER(charset, c1, c2) \
- do { \
- int c_alt, charset_alt; \
- if (!NILP (unification_table) \
- && ((c_alt = unify_char (unification_table, -1, charset, c1, c2)) \
- >= 0)) \
- SPLIT_CHAR (c_alt, charset_alt, c1, c2); \
- else \
- charset_alt = charset; \
- if (CHARSET_DIMENSION (charset_alt) == 1) \
- { \
- if (charset == CHARSET_ASCII \
- && coding->flags & CODING_FLAG_ISO_USE_ROMAN) \
- charset_alt = charset_latin_jisx0201; \
- ENCODE_ISO_CHARACTER_DIMENSION1 (charset_alt, c1); \
- } \
- else \
- { \
- if (charset == charset_jisx0208 \
- && coding->flags & CODING_FLAG_ISO_USE_OLDJIS) \
- charset_alt = charset_jisx0208_1978; \
- ENCODE_ISO_CHARACTER_DIMENSION2 (charset_alt, c1, c2); \
- } \
- if (! COMPOSING_P (coding->composing)) \
- coding->consumed_char++; \
- } while (0)
+#define ENCODE_ISO_CHARACTER(charset, c1, c2) \
+ do { \
+ int c_alt, charset_alt; \
+ if (!NILP (translation_table) \
+ && ((c_alt = translate_char (translation_table, -1, \
+ charset, c1, c2)) \
+ >= 0)) \
+ SPLIT_CHAR (c_alt, charset_alt, c1, c2); \
+ else \
+ charset_alt = charset; \
+ if (CHARSET_DIMENSION (charset_alt) == 1) \
+ { \
+ if (charset == CHARSET_ASCII \
+ && coding->flags & CODING_FLAG_ISO_USE_ROMAN) \
+ charset_alt = charset_latin_jisx0201; \
+ ENCODE_ISO_CHARACTER_DIMENSION1 (charset_alt, c1); \
+ } \
+ else \
+ { \
+ if (charset == charset_jisx0208 \
+ && coding->flags & CODING_FLAG_ISO_USE_OLDJIS) \
+ charset_alt = charset_jisx0208_1978; \
+ ENCODE_ISO_CHARACTER_DIMENSION2 (charset_alt, c1, c2); \
+ } \
+ if (! COMPOSING_P (coding->composing)) \
+ coding->consumed_char++; \
+ } while (0)
/* Produce designation and invocation codes at a place pointed by DST
to use CHARSET. The element `spec.iso2022' of *CODING is updated.
If the current block ends before any end-of-line, we may fail to
find all the necessary designations. */
+void
encode_designation_at_bol (coding, table, src, src_end, dstp)
struct coding_system *coding;
Lisp_Object table;
unsigned char c1, c2;
SPLIT_STRING(src, bytes, charset, c1, c2);
- if ((c_alt = unify_char (table, -1, charset, c1, c2)) >= 0)
+ if ((c_alt = translate_char (table, -1, charset, c1, c2)) >= 0)
charset = CHAR_CHARSET (c_alt);
}
from DST_END to assure overflow checking is necessary only at the
head of loop. */
unsigned char *adjusted_dst_end = dst_end - 19;
- Lisp_Object unification_table
- = coding->character_unification_table_for_encode;
+ Lisp_Object translation_table
+ = coding->translation_table_for_encode;
int result = CODING_FINISH_NORMAL;
- if (!NILP (Venable_character_unification) && NILP (unification_table))
- unification_table = Vstandard_character_unification_table_for_encode;
+ if (!NILP (Venable_character_translation) && NILP (translation_table))
+ translation_table = Vstandard_translation_table_for_encode;
coding->consumed_char = 0;
coding->fake_multibyte = 0;
&& CODING_SPEC_ISO_BOL (coding))
{
/* We have to produce designation sequences if any now. */
- encode_designation_at_bol (coding, unification_table,
+ encode_designation_at_bol (coding, translation_table,
src, src_end, &dst);
CODING_SPEC_ISO_BOL (coding) = 0;
}
{
/* invalid sequence */
*dst++ = c1;
- *dst++ = c2;
- coding->consumed_char += 2;
+ src--;
+ coding->consumed_char++;
}
else
ENCODE_ISO_CHARACTER (c1, c2, /* dummy */ c3);
{
/* invalid sequence */
*dst++ = c1;
- *dst++ = c2;
- *dst++ = c3;
- coding->consumed_char += 3;
+ src -= 2;
+ coding->consumed_char++;
}
else if (c1 < LEADING_CODE_PRIVATE_11)
ENCODE_ISO_CHARACTER (c1, c2, c3);
{
/* invalid sequence */
*dst++ = c1;
- *dst++ = c2;
- *dst++ = c3;
- *dst++ = c4;
- coding->consumed_char += 4;
+ src -= 3;
+ coding->consumed_char++;
}
else
ENCODE_ISO_CHARACTER (c2, c3, c4);
{
/* invalid sequence */
*dst++ = c1;
- *dst++ = c2;
- coding->consumed_char += 2;
+ src--;
+ coding->consumed_char++;
}
else if (c2 == 0xFF)
{
break;
}
- if (src < src_end)
+ if (src < src_end && result == CODING_FINISH_NORMAL)
+ result = CODING_FINISH_INSUFFICIENT_DST;
+
+ /* If this is the last block of the text to be encoded, we must
+ reset graphic planes and registers to the initial state, and
+ flush out the carryover if any. */
+ if (coding->mode & CODING_MODE_LAST_BLOCK)
{
- if (result == CODING_FINISH_NORMAL)
- result = CODING_FINISH_INSUFFICIENT_DST;
- else
- /* If this is the last block of the text to be encoded, we
- must reset graphic planes and registers to the initial
- state, and flush out the carryover if any. */
- if (coding->mode & CODING_MODE_LAST_BLOCK)
- ENCODE_RESET_PLANE_AND_REGISTER;
+ ENCODE_RESET_PLANE_AND_REGISTER;
+ if (COMPOSING_P (coding->composing))
+ ENCODE_COMPOSITION_END;
+ if (result == CODING_FINISH_INSUFFICIENT_SRC)
+ {
+ while (src < src_end && dst < dst_end)
+ *dst++ = *src++;
+ }
}
-
coding->consumed = src - source;
coding->produced = coding->produced_char = dst - destination;
return result;
(character set) (range)
ASCII 0x00 .. 0x7F
KATAKANA-JISX0201 0xA0 .. 0xDF
- JISX0208 (1st byte) 0x80 .. 0x9F and 0xE0 .. 0xFF
+ JISX0208 (1st byte) 0x80 .. 0x9F and 0xE0 .. 0xEF
(2nd byte) 0x40 .. 0xFF
-------------------------------
#define DECODE_SJIS_BIG5_CHARACTER(charset, c1, c2) \
do { \
int c_alt, charset_alt = (charset); \
- if (!NILP (unification_table) \
- && ((c_alt = unify_char (unification_table, \
- -1, (charset), c1, c2)) >= 0)) \
+ if (!NILP (translation_table) \
+ && ((c_alt = translate_char (translation_table, \
+ -1, (charset), c1, c2)) >= 0)) \
SPLIT_CHAR (c_alt, charset_alt, c1, c2); \
if (charset_alt == CHARSET_ASCII || charset_alt < 0) \
DECODE_CHARACTER_ASCII (c1); \
DECODE_CHARACTER_DIMENSION2 (charset_alt, c1, c2); \
} while (0)
-#define ENCODE_SJIS_BIG5_CHARACTER(charset, c1, c2) \
- do { \
- int c_alt, charset_alt; \
- if (!NILP (unification_table) \
- && ((c_alt = unify_char (unification_table, -1, charset, c1, c2)) \
- >= 0)) \
- SPLIT_CHAR (c_alt, charset_alt, c1, c2); \
- else \
- charset_alt = charset; \
- if (charset_alt == charset_ascii) \
- *dst++ = c1; \
- else if (CHARSET_DIMENSION (charset_alt) == 1) \
- { \
- if (sjis_p && charset_alt == charset_katakana_jisx0201) \
- *dst++ = c1; \
- else \
- { \
- *dst++ = charset_alt, *dst++ = c1; \
- coding->fake_multibyte = 1; \
- } \
- } \
- else \
- { \
- c1 &= 0x7F, c2 &= 0x7F; \
- if (sjis_p && charset_alt == charset_jisx0208) \
- { \
- unsigned char s1, s2; \
- \
- ENCODE_SJIS (c1, c2, s1, s2); \
- *dst++ = s1, *dst++ = s2; \
- coding->fake_multibyte = 1; \
- } \
- else if (!sjis_p \
- && (charset_alt == charset_big5_1 \
- || charset_alt == charset_big5_2)) \
- { \
- unsigned char b1, b2; \
- \
- ENCODE_BIG5 (charset_alt, c1, c2, b1, b2); \
- *dst++ = b1, *dst++ = b2; \
- } \
- else \
- { \
- *dst++ = charset_alt, *dst++ = c1, *dst++ = c2; \
- coding->fake_multibyte = 1; \
- } \
- } \
- coding->consumed_char++; \
+#define ENCODE_SJIS_BIG5_CHARACTER(charset, c1, c2) \
+ do { \
+ int c_alt, charset_alt; \
+ if (!NILP (translation_table) \
+ && ((c_alt = translate_char (translation_table, -1, \
+ charset, c1, c2)) \
+ >= 0)) \
+ SPLIT_CHAR (c_alt, charset_alt, c1, c2); \
+ else \
+ charset_alt = charset; \
+ if (charset_alt == charset_ascii) \
+ *dst++ = c1; \
+ else if (CHARSET_DIMENSION (charset_alt) == 1) \
+ { \
+ if (sjis_p && charset_alt == charset_katakana_jisx0201) \
+ *dst++ = c1; \
+ else \
+ { \
+ *dst++ = charset_alt, *dst++ = c1; \
+ coding->fake_multibyte = 1; \
+ } \
+ } \
+ else \
+ { \
+ c1 &= 0x7F, c2 &= 0x7F; \
+ if (sjis_p && charset_alt == charset_jisx0208) \
+ { \
+ unsigned char s1, s2; \
+ \
+ ENCODE_SJIS (c1, c2, s1, s2); \
+ *dst++ = s1, *dst++ = s2; \
+ coding->fake_multibyte = 1; \
+ } \
+ else if (!sjis_p \
+ && (charset_alt == charset_big5_1 \
+ || charset_alt == charset_big5_2)) \
+ { \
+ unsigned char b1, b2; \
+ \
+ ENCODE_BIG5 (charset_alt, c1, c2, b1, b2); \
+ *dst++ = b1, *dst++ = b2; \
+ } \
+ else \
+ { \
+ *dst++ = charset_alt, *dst++ = c1, *dst++ = c2; \
+ coding->fake_multibyte = 1; \
+ } \
+ } \
+ coding->consumed_char++; \
} while (0);
/* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions".
from DST_END to assure overflow checking is necessary only at the
head of loop. */
unsigned char *adjusted_dst_end = dst_end - 3;
- Lisp_Object unification_table
- = coding->character_unification_table_for_decode;
+ Lisp_Object translation_table
+ = coding->translation_table_for_decode;
int result = CODING_FINISH_NORMAL;
- if (!NILP (Venable_character_unification) && NILP (unification_table))
- unification_table = Vstandard_character_unification_table_for_decode;
+ if (!NILP (Venable_character_translation) && NILP (translation_table))
+ translation_table = Vstandard_translation_table_for_decode;
coding->produced_char = 0;
coding->fake_multibyte = 0;
}
else if (c1 < 0x80)
DECODE_SJIS_BIG5_CHARACTER (charset_ascii, c1, /* dummy */ c2);
- else if (c1 < 0xA0)
+ else
{
- /* SJIS -> JISX0208 */
if (sjis_p)
{
- ONE_MORE_BYTE (c2);
- if (c2 >= 0x40)
+ if (c1 < 0xA0 || (c1 >= 0xE0 && c1 < 0xF0))
{
- DECODE_SJIS (c1, c2, c3, c4);
- DECODE_SJIS_BIG5_CHARACTER (charset_jisx0208, c3, c4);
+ /* SJIS -> JISX0208 */
+ ONE_MORE_BYTE (c2);
+ if (c2 >= 0x40)
+ {
+ DECODE_SJIS (c1, c2, c3, c4);
+ DECODE_SJIS_BIG5_CHARACTER (charset_jisx0208, c3, c4);
+ }
+ else
+ goto label_invalid_code_2;
}
+ else if (c1 < 0xE0)
+ /* SJIS -> JISX0201-Kana */
+ DECODE_SJIS_BIG5_CHARACTER (charset_katakana_jisx0201, c1,
+ /* dummy */ c2);
else
- goto label_invalid_code_2;
+ goto label_invalid_code_1;
}
- else
- goto label_invalid_code_1;
- }
- else if (c1 < 0xE0)
- {
- /* SJIS -> JISX0201-Kana, BIG5 -> Big5 */
- if (sjis_p)
- DECODE_SJIS_BIG5_CHARACTER (charset_katakana_jisx0201, c1,
- /* dummy */ c2);
else
{
- int charset;
-
- ONE_MORE_BYTE (c2);
- if ((c2 >= 0x40 && c2 <= 0x7E) || (c2 >= 0xA1 && c2 <= 0xFE))
+ /* BIG5 -> Big5 */
+ if (c1 >= 0xA1 && c1 <= 0xFE)
{
- DECODE_BIG5 (c1, c2, charset, c3, c4);
- DECODE_SJIS_BIG5_CHARACTER (charset, c3, c4);
- }
- else
- goto label_invalid_code_2;
- }
- }
- else /* C1 >= 0xE0 */
- {
- /* SJIS -> JISX0208, BIG5 -> Big5 */
- if (sjis_p)
- {
- ONE_MORE_BYTE (c2);
- if (c2 >= 0x40)
- {
- DECODE_SJIS (c1, c2, c3, c4);
- DECODE_SJIS_BIG5_CHARACTER (charset_jisx0208, c3, c4);
- }
- else
- goto label_invalid_code_2;
- }
- else
- {
- int charset;
+ ONE_MORE_BYTE (c2);
+ if ((c2 >= 0x40 && c2 <= 0x7E) || (c2 >= 0xA1 && c2 <= 0xFE))
+ {
+ int charset;
- ONE_MORE_BYTE (c2);
- if ((c2 >= 0x40 && c2 <= 0x7E) || (c2 >= 0xA1 && c2 <= 0xFE))
- {
- DECODE_BIG5 (c1, c2, charset, c3, c4);
- DECODE_SJIS_BIG5_CHARACTER (charset, c3, c4);
+ DECODE_BIG5 (c1, c2, charset, c3, c4);
+ DECODE_SJIS_BIG5_CHARACTER (charset, c3, c4);
+ }
+ else
+ goto label_invalid_code_2;
}
else
- goto label_invalid_code_2;
+ goto label_invalid_code_1;
}
}
continue;
from DST_END to assure overflow checking is necessary only at the
head of loop. */
unsigned char *adjusted_dst_end = dst_end - 1;
- Lisp_Object unification_table
- = coding->character_unification_table_for_encode;
+ Lisp_Object translation_table
+ = coding->translation_table_for_encode;
int result = CODING_FINISH_NORMAL;
- if (!NILP (Venable_character_unification) && NILP (unification_table))
- unification_table = Vstandard_character_unification_table_for_encode;
+ if (!NILP (Venable_character_translation) && NILP (translation_table))
+ translation_table = Vstandard_translation_table_for_encode;
coding->consumed_char = 0;
coding->fake_multibyte = 0;
}
\f
-/*** 5. End-of-line handlers ***/
+/*** 5. CCL handlers ***/
+
+/* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions".
+ Check if a text is encoded in a coding system of which
+ encoder/decoder are written in CCL program. If it is, return
+ CODING_CATEGORY_MASK_CCL, else return 0. */
+
+int
+detect_coding_ccl (src, src_end)
+ unsigned char *src, *src_end;
+{
+ unsigned char *valid;
+
+ /* No coding system is assigned to coding-category-ccl. */
+ if (!coding_system_table[CODING_CATEGORY_IDX_CCL])
+ return 0;
+
+ valid = coding_system_table[CODING_CATEGORY_IDX_CCL]->spec.ccl.valid_codes;
+ while (src < src_end)
+ {
+ if (! valid[*src]) return 0;
+ src++;
+ }
+ return CODING_CATEGORY_MASK_CCL;
+}
+
+\f
+/*** 6. End-of-line handlers ***/
/* See the above "GENERAL NOTES on `decode_coding_XXX ()' functions".
This function is called only when `coding->eol_type' is
CODING_EOL_CRLF or CODING_EOL_CR. */
+int
decode_eol (coding, source, destination, src_bytes, dst_bytes)
struct coding_system *coding;
unsigned char *source, *destination;
if (c == '\r')
{
ONE_MORE_BYTE (c);
- if (c != '\n')
+ if (c == '\n')
+ *dst++ = c;
+ else
{
if (coding->mode & CODING_MODE_INHIBIT_INCONSISTENT_EOL)
{
result = CODING_FINISH_INCONSISTENT_EOL;
goto label_end_of_loop_2;
}
+ src--;
*dst++ = '\r';
if (BASE_LEADING_CODE_P (c))
coding->fake_multibyte = 1;
}
- *dst++ = c;
}
else if (c == '\n'
&& (coding->mode & CODING_MODE_INHIBIT_INCONSISTENT_EOL))
src = src_base;
break;
}
- if (result == CODING_FINISH_NORMAL
- && src < src_end)
- result = CODING_FINISH_INSUFFICIENT_DST;
+ if (src < src_end)
+ {
+ if (result == CODING_FINISH_NORMAL)
+ result = CODING_FINISH_INSUFFICIENT_DST;
+ else if (result != CODING_FINISH_INCONSISTENT_EOL
+ && coding->mode & CODING_MODE_LAST_BLOCK)
+ {
+ /* This is the last block of the text to be decoded.
+ We flush out all remaining codes. */
+ src_bytes = src_end - src;
+ if (dst_bytes && (dst_end - dst < src_bytes))
+ src_bytes = dst_end - dst;
+ bcopy (src, dst, src_bytes);
+ dst += src_bytes;
+ src += src_bytes;
+ }
+ }
}
break;
else
safe_bcopy (source, destination, src_bytes);
src += src_bytes;
- dst += dst_bytes;
+ dst += src_bytes;
coding->fake_multibyte = 1;
break;
}
`coding->mode & CODING_MODE_SELECTIVE_DISPLAY' is nonzero, code
'\r' in source text also means end-of-line. */
+int
encode_eol (coding, source, destination, src_bytes, dst_bytes)
struct coding_system *coding;
unsigned char *source, *destination;
if (dst_bytes)
bcopy (source, destination, src_bytes);
else
- {
- safe_bcopy (source, destination, src_bytes);
- dst_bytes = src_bytes;
- }
- if (coding->eol_type == CODING_EOL_CRLF)
+ safe_bcopy (source, destination, src_bytes);
+ dst_bytes = src_bytes;
+ if (coding->eol_type == CODING_EOL_CR)
{
while (src_bytes--)
{
if ((c = *dst++) == '\n')
dst[-1] = '\r';
else if (BASE_LEADING_CODE_P (c))
- coding->fake_multibyte = 1;
+ coding->fake_multibyte = 1;
}
}
else
}
\f
-/*** 6. C library functions ***/
+/*** 7. C library functions ***/
/* In Emacs Lisp, coding system is represented by a Lisp symbol which
has a property `coding-system'. The value of this property is a
/* Initialize remaining fields. */
coding->composing = 0;
- coding->character_unification_table_for_decode = Qnil;
- coding->character_unification_table_for_encode = Qnil;
/* Get values of coding system properties:
`post-read-conversion', `pre-write-conversion',
- `character-unification-table-for-decode',
- `character-unification-table-for-encode'. */
+ `translation-table-for-decode', `translation-table-for-encode'. */
plist = XVECTOR (coding_spec)->contents[3];
coding->post_read_conversion = Fplist_get (plist, Qpost_read_conversion);
coding->pre_write_conversion = Fplist_get (plist, Qpre_write_conversion);
- val = Fplist_get (plist, Qcharacter_unification_table_for_decode);
+ val = Fplist_get (plist, Qtranslation_table_for_decode);
if (SYMBOLP (val))
- val = Fget (val, Qcharacter_unification_table_for_decode);
- coding->character_unification_table_for_decode
- = CHAR_TABLE_P (val) ? val : Qnil;
- val = Fplist_get (plist, Qcharacter_unification_table_for_encode);
+ val = Fget (val, Qtranslation_table_for_decode);
+ coding->translation_table_for_decode = CHAR_TABLE_P (val) ? val : Qnil;
+ val = Fplist_get (plist, Qtranslation_table_for_encode);
if (SYMBOLP (val))
- val = Fget (val, Qcharacter_unification_table_for_encode);
- coding->character_unification_table_for_encode
- = CHAR_TABLE_P (val) ? val : Qnil;
+ val = Fget (val, Qtranslation_table_for_encode);
+ coding->translation_table_for_encode = CHAR_TABLE_P (val) ? val : Qnil;
val = Fplist_get (plist, Qcoding_category);
if (!NILP (val))
{
}
else if (CONSP (flags[i]))
{
- Lisp_Object tail = flags[i];
+ Lisp_Object tail;
+ tail = flags[i];
coding->flags |= CODING_FLAG_ISO_DESIGNATION;
if (INTEGERP (XCONS (tail)->car)
coding->common_flags
|= CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK;
{
- Lisp_Object val = XVECTOR (coding_spec)->contents[4];
+ Lisp_Object val;
+ Lisp_Object decoder, encoder;
+
+ val = XVECTOR (coding_spec)->contents[4];
if (CONSP (val)
- && VECTORP (XCONS (val)->car)
- && VECTORP (XCONS (val)->cdr))
+ && SYMBOLP (XCONS (val)->car)
+ && !NILP (decoder = Fget (XCONS (val)->car, Qccl_program_idx))
+ && !NILP (decoder = Fcdr (Faref (Vccl_program_table, decoder)))
+ && SYMBOLP (XCONS (val)->cdr)
+ && !NILP (encoder = Fget (XCONS (val)->cdr, Qccl_program_idx))
+ && !NILP (encoder = Fcdr (Faref (Vccl_program_table, encoder))))
{
- setup_ccl_program (&(coding->spec.ccl.decoder), XCONS (val)->car);
- setup_ccl_program (&(coding->spec.ccl.encoder), XCONS (val)->cdr);
+ setup_ccl_program (&(coding->spec.ccl.decoder), decoder);
+ setup_ccl_program (&(coding->spec.ccl.encoder), encoder);
}
else
goto label_invalid_coding_system;
+
+ bzero (coding->spec.ccl.valid_codes, 256);
+ val = Fplist_get (plist, Qvalid_codes);
+ if (CONSP (val))
+ {
+ Lisp_Object this;
+
+ for (; CONSP (val); val = XCONS (val)->cdr)
+ {
+ this = XCONS (val)->car;
+ if (INTEGERP (this)
+ && XINT (this) >= 0 && XINT (this) < 256)
+ coding->spec.ccl.valid_codes[XINT (this)] = 1;
+ else if (CONSP (this)
+ && INTEGERP (XCONS (this)->car)
+ && INTEGERP (XCONS (this)->cdr))
+ {
+ int start = XINT (XCONS (this)->car);
+ int end = XINT (XCONS (this)->cdr);
+
+ if (start >= 0 && start <= end && end < 256)
+ while (start < end)
+ coding->spec.ccl.valid_codes[start++] = 1;
+ }
+ }
+ }
}
coding->common_flags |= CODING_REQUIRE_FLUSHING_MASK;
break;
return -1;
}
+/* Setup raw-text or one of its subsidiaries in the structure
+ coding_system CODING according to the already setup value eol_type
+ in CODING. CODING should be setup for some coding system in
+ advance. */
+
+void
+setup_raw_text_coding_system (coding)
+ struct coding_system *coding;
+{
+ if (coding->type != coding_type_raw_text)
+ {
+ coding->symbol = Qraw_text;
+ coding->type = coding_type_raw_text;
+ if (coding->eol_type != CODING_EOL_UNDECIDED)
+ {
+ Lisp_Object subsidiaries;
+ subsidiaries = Fget (Qraw_text, Qeol_type);
+
+ if (VECTORP (subsidiaries)
+ && XVECTOR (subsidiaries)->size == 3)
+ coding->symbol
+ = XVECTOR (subsidiaries)->contents[coding->eol_type];
+ }
+ }
+ return;
+}
+
/* Emacs has a mechanism to automatically detect a coding system if it
is one of Emacs' internal format, ISO2022, SJIS, and BIG5. But,
it's impossible to distinguish some coding systems accurately
as BIG5. Assigned the coding-system (Lisp symbol)
`cn-big5' by default.
+ o coding-category-ccl
+
+ The category for a coding system of which encoder/decoder is
+ written in CCL programs. The default value is nil, i.e., no
+ coding system is assigned.
+
o coding-category-binary
The category for a coding system not categorized in any of the
*/
+static
+int ascii_skip_code[256];
+
/* Detect how a text of length SRC_BYTES pointed by SOURCE is encoded.
If it detects possible coding systems, return an integer in which
appropriate flag bits are set. Flag bits are defined by macros
{
register unsigned char c;
unsigned char *src = source, *src_end = source + src_bytes;
- unsigned int mask = (CODING_CATEGORY_MASK_ISO_7BIT
- | CODING_CATEGORY_MASK_ISO_SHIFT);
+ unsigned int mask;
int i;
/* At first, skip all ASCII characters and control characters except
for three ISO2022 specific control characters. */
+ ascii_skip_code[ISO_CODE_SO] = 0;
+ ascii_skip_code[ISO_CODE_SI] = 0;
+ ascii_skip_code[ISO_CODE_ESC] = 0;
+
label_loop_detect_coding:
- while (src < src_end)
- {
- c = *src;
- if (c >= 0x80
- || ((mask & CODING_CATEGORY_MASK_ISO_7BIT)
- && c == ISO_CODE_ESC)
- || ((mask & CODING_CATEGORY_MASK_ISO_SHIFT)
- && (c == ISO_CODE_SI || c == ISO_CODE_SO)))
- break;
- src++;
- }
+ while (src < src_end && ascii_skip_code[*src]) src++;
*skip = src - source;
if (src >= src_end)
/* We found nothing other than ASCII. There's nothing to do. */
return 0;
+ c = *src;
/* The text seems to be encoded in some multilingual coding system.
Now, try to find in which coding system the text is encoded. */
if (c < 0x80)
{
/* No valid ISO2022 code follows C. Try again. */
src++;
- mask = (c != ISO_CODE_ESC
- ? CODING_CATEGORY_MASK_ISO_7BIT
- : CODING_CATEGORY_MASK_ISO_SHIFT);
+ if (c == ISO_CODE_ESC)
+ ascii_skip_code[ISO_CODE_ESC] = 1;
+ else
+ ascii_skip_code[ISO_CODE_SO] = ascii_skip_code[ISO_CODE_SI] = 1;
goto label_loop_detect_coding;
}
if (priorities)
| CODING_CATEGORY_MASK_SJIS
| CODING_CATEGORY_MASK_BIG5);
+ /* Or, we may have to consider the possibility of CCL. */
+ if (coding_system_table[CODING_CATEGORY_IDX_CCL]
+ && (coding_system_table[CODING_CATEGORY_IDX_CCL]
+ ->spec.ccl.valid_codes)[c])
+ try |= CODING_CATEGORY_MASK_CCL;
+
mask = 0;
if (priorities)
{
for (i = 0; i < CODING_CATEGORY_IDX_MAX; i++)
{
- priorities[i] &= try;
- if (priorities[i] & CODING_CATEGORY_MASK_ISO)
+ if (priorities[i] & try & CODING_CATEGORY_MASK_ISO)
mask = detect_coding_iso2022 (src, src_end);
- else if (priorities[i] & CODING_CATEGORY_MASK_SJIS)
+ else if (priorities[i] & try & CODING_CATEGORY_MASK_SJIS)
mask = detect_coding_sjis (src, src_end);
- else if (priorities[i] & CODING_CATEGORY_MASK_BIG5)
+ else if (priorities[i] & try & CODING_CATEGORY_MASK_BIG5)
mask = detect_coding_big5 (src, src_end);
- else if (priorities[i] & CODING_CATEGORY_MASK_EMACS_MULE)
+ else if (priorities[i] & try & CODING_CATEGORY_MASK_EMACS_MULE)
mask = detect_coding_emacs_mule (src, src_end);
+ else if (priorities[i] & try & CODING_CATEGORY_MASK_CCL)
+ mask = detect_coding_ccl (src, src_end);
+ else if (priorities[i] & CODING_CATEGORY_MASK_RAW_TEXT)
+ mask = CODING_CATEGORY_MASK_RAW_TEXT;
+ else if (priorities[i] & CODING_CATEGORY_MASK_BINARY)
+ mask = CODING_CATEGORY_MASK_BINARY;
if (mask)
goto label_return_highest_only;
}
if (try & CODING_CATEGORY_MASK_BIG5)
mask |= detect_coding_big5 (src, src_end);
if (try & CODING_CATEGORY_MASK_EMACS_MULE)
- mask |= detect_coding_emacs_mule (src, src_end);
+ mask |= detect_coding_emacs_mule (src, src_end);
+ if (try & CODING_CATEGORY_MASK_CCL)
+ mask |= detect_coding_ccl (src, src_end);
}
- return (mask | CODING_CATEGORY_MASK_RAW_TEXT);
+ return (mask | CODING_CATEGORY_MASK_RAW_TEXT | CODING_CATEGORY_MASK_BINARY);
label_return_highest_only:
for (i = 0; i < CODING_CATEGORY_IDX_MAX; i++)
{
unsigned int idx;
int skip, mask, i;
- int priorities[CODING_CATEGORY_IDX_MAX];
- Lisp_Object val = Vcoding_category_list;
-
- i = 0;
- while (CONSP (val) && i < CODING_CATEGORY_IDX_MAX)
- {
- if (! SYMBOLP (XCONS (val)->car))
- break;
- idx = XFASTINT (Fget (XCONS (val)->car, Qcoding_category_index));
- if (idx >= CODING_CATEGORY_IDX_MAX)
- break;
- priorities[i++] = (1 << idx);
- val = XCONS (val)->cdr;
- }
- /* If coding-category-list is valid and contains all coding
- categories, `i' should be CODING_CATEGORY_IDX_MAX now. If not,
- the following code saves Emacs from craching. */
- while (i < CODING_CATEGORY_IDX_MAX)
- priorities[i++] = CODING_CATEGORY_MASK_RAW_TEXT;
+ Lisp_Object val;
- mask = detect_coding_mask (src, src_bytes, priorities, &skip);
+ val = Vcoding_category_list;
+ mask = detect_coding_mask (src, src_bytes, coding_priorities, &skip);
coding->heading_ascii = skip;
if (!mask) return;
if (coding->eol_type != CODING_EOL_UNDECIDED)
{
- Lisp_Object tmp = Fget (val, Qeol_type);
+ Lisp_Object tmp;
+ tmp = Fget (val, Qeol_type);
if (VECTORP (tmp))
val = XVECTOR (tmp)->contents[coding->eol_type];
}
= encodep ? &coding->spec.ccl.encoder : &coding->spec.ccl.decoder;
int result;
+ ccl->last_block = coding->mode & CODING_MODE_LAST_BLOCK;
+
coding->produced = ccl_driver (ccl, source, destination,
src_bytes, dst_bytes, &(coding->consumed));
- if (encodep)
- {
- coding->produced_char = coding->produced;
- coding->consumed_char
- = multibyte_chars_in_text (source, coding->consumed);
- }
- else
- {
- coding->produced_char
- = multibyte_chars_in_text (destination, coding->produced);
- coding->consumed_char = coding->consumed;
- }
+ coding->produced_char
+ = multibyte_chars_in_text (destination, coding->produced);
+ coding->consumed_char
+ = multibyte_chars_in_text (source, coding->consumed);
+
switch (ccl->status)
{
case CCL_STAT_SUSPEND_BY_SRC:
case CCL_STAT_SUSPEND_BY_DST:
result = CODING_FINISH_INSUFFICIENT_DST;
break;
+ case CCL_STAT_QUIT:
+ case CCL_STAT_INVALID_CMD:
+ result = CODING_FINISH_INTERRUPT;
+ break;
default:
result = CODING_FINISH_NORMAL;
break;
{
int result;
- if (src_bytes <= 0)
+ if (src_bytes <= 0
+ && ! (coding->mode & CODING_MODE_LAST_BLOCK
+ && CODING_REQUIRE_FLUSHING (coding)))
{
coding->produced = coding->produced_char = 0;
coding->consumed = coding->consumed_char = 0;
{
int result;
- if (src_bytes <= 0)
+ if (src_bytes <= 0
+ && ! (coding->mode & CODING_MODE_LAST_BLOCK
+ && CODING_REQUIRE_FLUSHING (coding)))
{
coding->produced = coding->produced_char = 0;
coding->consumed = coding->consumed_char = 0;
{
unsigned char *begp_orig, *begp, *endp_orig, *endp, c;
int eol_conversion;
+ Lisp_Object translation_table;
if (coding->type == coding_type_ccl
|| coding->type == coding_type_undecided
return;
}
- if (coding->heading_ascii >= 0)
+ translation_table = coding->translation_table_for_decode;
+ if (NILP (translation_table) && !NILP (Venable_character_translation))
+ translation_table = Vstandard_translation_table_for_decode;
+ if (CHAR_TABLE_P (translation_table))
+ {
+ int i;
+ for (i = 0; i < 128; i++)
+ if (!NILP (CHAR_TABLE_REF (translation_table, i)))
+ break;
+ if (i < 128)
+ /* Some ASCII character should be tranlsated. We give up
+ shrinking. */
+ return;
+ }
+
+ eol_conversion = (coding->eol_type != CODING_EOL_LF);
+
+ if ((! eol_conversion) && (coding->heading_ascii >= 0))
/* Detection routine has already found how much we can skip at the
head. */
*beg += coding->heading_ascii;
endp_orig = endp = begp + *end - *beg;
}
- eol_conversion = (coding->eol_type != CODING_EOL_LF);
-
switch (coding->type)
{
case coding_type_emacs_mule:
{
if (coding->heading_ascii < 0)
while (begp < endp && *begp != '\r' && *begp < 0x80) begp++;
- while (begp < endp && *(endp - 1) != '\r' && *(endp - 1) < 0x80)
+ while (begp < endp && endp[-1] != '\r' && endp[-1] < 0x80)
endp--;
+ /* Do not consider LF as ascii if preceded by CR, since that
+ confuses eol decoding. */
+ if (begp < endp && endp < endp_orig && endp[-1] == '\r' && endp[0] == '\n')
+ endp++;
}
else
begp = endp;
while (begp < endp && endp[-1] < 0x80 && endp[-1] != '\r') endp--;
else
while (begp < endp && endp[-1] < 0x80) endp--;
+ /* Do not consider LF as ascii if preceded by CR, since that
+ confuses eol decoding. */
+ if (begp < endp && endp < endp_orig && endp[-1] == '\r' && endp[0] == '\n')
+ endp++;
if (begp < endp && endp < endp_orig && endp[-1] >= 0x80)
endp++;
break;
while (begp < endp && (c = endp[-1]) < 0x80 && c != '\r') endp--;
else
while (begp < endp && endp[-1] < 0x80) endp--;
+ /* Do not consider LF as ascii if preceded by CR, since that
+ confuses eol decoding. */
+ if (begp < endp && endp < endp_orig && endp[-1] == '\r' && endp[0] == '\n')
+ endp++;
break;
case CODING_CATEGORY_IDX_ISO_7:
case CODING_CATEGORY_IDX_ISO_7_TIGHT:
- /* We can skip all charactes at the tail except for ESC and
- the following 2-byte at the tail. */
- if (eol_conversion)
- while (begp < endp
- && (c = endp[-1]) < 0x80 && c != ISO_CODE_ESC && c != '\r')
- endp--;
- else
- while (begp < endp
- && (c = endp[-1]) < 0x80 && c != ISO_CODE_ESC)
- endp--;
- if (begp < endp && endp[-1] == ISO_CODE_ESC)
- {
- if (endp + 1 < endp_orig && end[0] == '(' && end[1] == 'B')
- /* This is an ASCII designation sequence. We can
- surely skip the tail. */
- endp += 2;
- else
- /* Hmmm, we can't skip the tail. */
- endp = endp_orig;
- }
+ {
+ /* We can skip all charactes at the tail except for 8-bit
+ codes and ESC and the following 2-byte at the tail. */
+ unsigned char *eight_bit = NULL;
+
+ if (eol_conversion)
+ while (begp < endp
+ && (c = endp[-1]) != ISO_CODE_ESC && c != '\r')
+ {
+ if (!eight_bit && c & 0x80) eight_bit = endp;
+ endp--;
+ }
+ else
+ while (begp < endp
+ && (c = endp[-1]) != ISO_CODE_ESC)
+ {
+ if (!eight_bit && c & 0x80) eight_bit = endp;
+ endp--;
+ }
+ /* Do not consider LF as ascii if preceded by CR, since that
+ confuses eol decoding. */
+ if (begp < endp && endp < endp_orig
+ && endp[-1] == '\r' && endp[0] == '\n')
+ endp++;
+ if (begp < endp && endp[-1] == ISO_CODE_ESC)
+ {
+ if (endp + 1 < endp_orig && end[0] == '(' && end[1] == 'B')
+ /* This is an ASCII designation sequence. We can
+ surely skip the tail. But, if we have
+ encountered an 8-bit code, skip only the codes
+ after that. */
+ endp = eight_bit ? eight_bit : endp + 2;
+ else
+ /* Hmmm, we can't skip the tail. */
+ endp = endp_orig;
+ }
+ else if (eight_bit)
+ endp = eight_bit;
+ }
}
}
*beg += begp - begp_orig;
{
unsigned char *begp_orig, *begp, *endp_orig, *endp;
int eol_conversion;
+ Lisp_Object translation_table;
if (coding->type == coding_type_ccl)
/* We can't skip any data. */
return;
}
+ translation_table = coding->translation_table_for_encode;
+ if (NILP (translation_table) && !NILP (Venable_character_translation))
+ translation_table = Vstandard_translation_table_for_encode;
+ if (CHAR_TABLE_P (translation_table))
+ {
+ int i;
+ for (i = 0; i < 128; i++)
+ if (!NILP (CHAR_TABLE_REF (translation_table, i)))
+ break;
+ if (i < 128)
+ /* Some ASCII character should be tranlsated. We give up
+ shrinking. */
+ return;
+ }
+
if (str)
{
begp_orig = begp = str + *beg;
return;
}
+/* As shrinking conversion region requires some overhead, we don't try
+ shrinking if the length of conversion region is less than this
+ value. */
+static int shrink_conversion_region_threshhold = 1024;
+
+#define SHRINK_CONVERSION_REGION(beg, end, coding, str, encodep) \
+ do { \
+ if (*(end) - *(beg) > shrink_conversion_region_threshhold) \
+ { \
+ if (encodep) shrink_encoding_region (beg, end, coding, str); \
+ else shrink_decoding_region (beg, end, coding, str); \
+ } \
+ } while (0)
+
/* Decode (if ENCODEP is zero) or encode (if ENCODEP is nonzero) the
text from FROM to TO (byte positions are FROM_BYTE and TO_BYTE) by
coding system CODING, and return the status code of code conversion
int len = to - from, len_byte = to_byte - from_byte;
int require, inserted, inserted_byte;
int head_skip, tail_skip, total_skip;
- Lisp_Object saved_coding_symbol = Qnil;
+ Lisp_Object saved_coding_symbol;
int multibyte = !NILP (current_buffer->enable_multibyte_characters);
int first = 1;
int fake_multibyte = 0;
unsigned char *src, *dst;
- Lisp_Object deletion = Qnil;
+ Lisp_Object deletion;
+
+ deletion = Qnil;
+ saved_coding_symbol = Qnil;
+
+ if (from < PT && PT < to)
+ SET_PT_BOTH (from, from_byte);
if (replace)
{
coding->produced_char = len;
}
else
- coding->produced_char = len_byte;
+ {
+ if (!replace)
+ adjust_after_insert (from, from_byte, to, to_byte, len_byte);
+ coding->produced_char = len_byte;
+ }
return 0;
}
new buffer. */
struct buffer *prev = current_buffer, *new;
- call2 (coding->pre_write_conversion, from, to);
+ call2 (coding->pre_write_conversion,
+ make_number (from), make_number (to));
if (current_buffer != prev)
{
len = ZV - BEGV;
if (from < GPT && GPT < to)
move_gap_both (from, from_byte);
- if (encodep)
- shrink_encoding_region (&from_byte, &to_byte, coding, NULL);
- else
- shrink_decoding_region (&from_byte, &to_byte, coding, NULL);
- if (from_byte == to_byte)
+ SHRINK_CONVERSION_REGION (&from_byte, &to_byte, coding, NULL, encodep);
+ if (from_byte == to_byte
+ && ! (coding->mode & CODING_MODE_LAST_BLOCK
+ && CODING_REQUIRE_FLUSHING (coding)))
{
coding->produced = len_byte;
coding->produced_char = multibyte ? len : len_byte;
len -= total_skip; len_byte -= total_skip;
}
+ /* The code conversion routine can not preserve text properties for
+ now. So, we must remove all text properties in the region.
+ Here, we must suppress all modification hooks. */
+ if (replace)
+ {
+ int saved_inhibit_modification_hooks = inhibit_modification_hooks;
+ inhibit_modification_hooks = 1;
+ Fset_text_properties (make_number (from), make_number (to), Qnil, Qnil);
+ inhibit_modification_hooks = saved_inhibit_modification_hooks;
+ }
+
/* For converion, we must put the gap before the text in addition to
making the gap larger for efficient decoding. The required gap
size starts from 2000 which is the magic number used in make_gap.
make_gap (require - GAP_SIZE);
move_gap_both (from, from_byte);
- if (GPT - BEG < beg_unchanged)
- beg_unchanged = GPT - BEG;
- if (Z - GPT < end_unchanged)
- end_unchanged = Z - GPT;
-
inserted = inserted_byte = 0;
src = GAP_END_ADDR, dst = GPT_ADDR;
ZV_BYTE -= len_byte;
Z_BYTE -= len_byte;
+ if (GPT - BEG < beg_unchanged)
+ beg_unchanged = GPT - BEG;
+ if (Z - GPT < end_unchanged)
+ end_unchanged = Z - GPT;
+
for (;;)
{
int result;
src += coding->consumed;
dst += inserted_byte;
+ if (result == CODING_FINISH_NORMAL)
+ {
+ src += len_byte;
+ break;
+ }
if (! encodep && result == CODING_FINISH_INCONSISTENT_EOL)
{
unsigned char *pend = dst, *p = pend - inserted_byte;
inserted += len_byte;
inserted_byte += len_byte;
while (len_byte--)
- *src++ = *dst++;
+ *dst++ = *src++;
+ fake_multibyte = 1;
+ break;
+ }
+ if (result == CODING_FINISH_INTERRUPT)
+ {
+ /* The conversion procedure was interrupted by a user. */
+ fake_multibyte = 1;
+ break;
+ }
+ /* Now RESULT == CODING_FINISH_INSUFFICIENT_DST */
+ if (coding->consumed < 1)
+ {
+ /* It's quite strange to require more memory without
+ consuming any bytes. Perhaps CCL program bug. */
fake_multibyte = 1;
break;
}
if (src - dst > 0) *dst = 0; /* Put an anchor. */
if (multibyte
- && (fake_multibyte
- || !encodep && (to - from) != (to_byte - from_byte)))
+ && (encodep
+ || fake_multibyte
+ || (to - from) != (to_byte - from_byte)))
inserted = multibyte_chars_in_text (GPT_ADDR, inserted_byte);
/* If we have shrinked the conversion area, adjust it now. */
int from = 0, to = XSTRING (str)->size;
int to_byte = STRING_BYTES (XSTRING (str));
struct gcpro gcpro1;
- Lisp_Object saved_coding_symbol = Qnil;
+ Lisp_Object saved_coding_symbol;
int result;
+ saved_coding_symbol = Qnil;
if (encodep && !NILP (coding->pre_write_conversion)
|| !encodep && !NILP (coding->post_read_conversion))
{
else
{
/* Try to skip the heading and tailing ASCIIs. */
- if (encodep)
- shrink_encoding_region (&from, &to_byte, coding, XSTRING (str)->data);
- else
- shrink_decoding_region (&from, &to_byte, coding, XSTRING (str)->data);
+ SHRINK_CONVERSION_REGION (&from, &to_byte, coding, XSTRING (str)->data,
+ encodep);
}
if (from == to_byte)
return (nocopy ? str : Fcopy_sequence (str));
if (encodep)
str = make_unibyte_string (buf, len + coding->produced);
else
- str = make_string_from_bytes (buf, len + coding->produced_char,
- len + coding->produced);
+ {
+ int chars= (coding->fake_multibyte
+ ? multibyte_chars_in_text (buf + from, coding->produced)
+ : coding->produced_char);
+ str = make_multibyte_string (buf, len + chars, len + coding->produced);
+ }
+
return str;
}
\f
#ifdef emacs
-/*** 7. Emacs Lisp library functions ***/
+/*** 8. Emacs Lisp library functions ***/
DEFUN ("coding-system-p", Fcoding_system_p, Scoding_system_p, 1, 1, 0,
"Return t if OBJECT is nil or a coding-system.\n\
coding_mask = detect_coding_mask (src, src_bytes, NULL, &dummy);
eol_type = detect_eol_type (src, src_bytes, &dummy);
if (eol_type == CODING_EOL_INCONSISTENT)
- eol_type == CODING_EOL_UNDECIDED;
+ eol_type = CODING_EOL_UNDECIDED;
if (!coding_mask)
{
if (VECTORP (val2))
val = XVECTOR (val2)->contents[eol_type];
}
- return val;
+ return (highest ? val : Fcons (val, Qnil));
}
/* At first, gather possible coding systems in VAL. */
if (!highest)
val = Fnreverse (val);
- /* Then, substitute the elements by subsidiary coding systems. */
+ /* Then, replace the elements with subsidiary coding systems. */
for (tmp = val; !NILP (tmp); tmp = XCONS (tmp)->cdr)
{
- if (eol_type != CODING_EOL_UNDECIDED)
+ if (eol_type != CODING_EOL_UNDECIDED
+ && eol_type != CODING_EOL_INCONSISTENT)
{
Lisp_Object eol;
eol = Fget (XCONS (tmp)->car, Qeol_type);
"Detect coding system of the text in the region between START and END.\n\
Return a list of possible coding systems ordered by priority.\n\
\n\
-If only ASCII characters are found, it returns `undecided'\n\
-or its subsidiary coding system according to a detected end-of-line format.\n\
+If only ASCII characters are found, it returns a list of single element\n\
+`undecided' or its subsidiary coding system according to a detected\n\
+end-of-line format.\n\
\n\
If optional argument HIGHEST is non-nil, return the coding system of\n\
highest priority.")
"Detect coding system of the text in STRING.\n\
Return a list of possible coding systems ordered by priority.\n\
\n\
-If only ASCII characters are found, it returns `undecided'\n\
-or its subsidiary coding system according to a detected end-of-line format.\n\
+If only ASCII characters are found, it returns a list of single element\n\
+`undecided' or its subsidiary coding system according to a detected\n\
+end-of-line format.\n\
\n\
If optional argument HIGHEST is non-nil, return the coding system of\n\
highest priority.")
coding.mode |= CODING_MODE_LAST_BLOCK;
code_convert_region (from, CHAR_TO_BYTE (from), to, CHAR_TO_BYTE (to),
&coding, encodep, 1);
+ Vlast_coding_system_used = coding.symbol;
return make_number (coding.produced_char);
}
"Decode the current region by specified coding system.\n\
When called from a program, takes three arguments:\n\
START, END, and CODING-SYSTEM. START and END are buffer positions.\n\
-Return length of decoded text.")
+This function sets `last-coding-system-used' to the precise coding system\n\
+used (which may be different from CODING-SYSTEM if CODING-SYSTEM is\n\
+not fully specified.)\n\
+It returns the length of the decoded text.")
(start, end, coding_system)
Lisp_Object start, end, coding_system;
{
"Encode the current region by specified coding system.\n\
When called from a program, takes three arguments:\n\
START, END, and CODING-SYSTEM. START and END are buffer positions.\n\
-Return length of encoded text.")
+This function sets `last-coding-system-used' to the precise coding system\n\
+used (which may be different from CODING-SYSTEM if CODING-SYSTEM is\n\
+not fully specified.)\n\
+It returns the length of the encoded text.")
(start, end, coding_system)
Lisp_Object start, end, coding_system;
{
error ("Invalid coding system: %s", XSYMBOL (coding_system)->name->data);
coding.mode |= CODING_MODE_LAST_BLOCK;
+ Vlast_coding_system_used = coding.symbol;
return code_convert_string (string, &coding, encodep, !NILP (nocopy));
}
2, 3, 0,
"Decode STRING which is encoded in CODING-SYSTEM, and return the result.\n\
Optional arg NOCOPY non-nil means it is ok to return STRING itself\n\
-if the decoding operation is trivial.")
+if the decoding operation is trivial.\n\
+This function sets `last-coding-system-used' to the precise coding system\n\
+used (which may be different from CODING-SYSTEM if CODING-SYSTEM is\n\
+not fully specified.)")
(string, coding_system, nocopy)
Lisp_Object string, coding_system, nocopy;
{
- return code_convert_string1(string, coding_system, nocopy, 0);
+ return code_convert_string1 (string, coding_system, nocopy, 0);
}
DEFUN ("encode-coding-string", Fencode_coding_string, Sencode_coding_string,
2, 3, 0,
"Encode STRING to CODING-SYSTEM, and return the result.\n\
Optional arg NOCOPY non-nil means it is ok to return STRING itself\n\
-if the encoding operation is trivial.")
+if the encoding operation is trivial.\n\
+This function sets `last-coding-system-used' to the precise coding system\n\
+used (which may be different from CODING-SYSTEM if CODING-SYSTEM is\n\
+not fully specified.)")
(string, coding_system, nocopy)
Lisp_Object string, coding_system, nocopy;
{
- return code_convert_string1(string, coding_system, nocopy, 1);
+ return code_convert_string1 (string, coding_system, nocopy, 1);
}
+/* Encode or decode STRING according to CODING_SYSTEM.
+ Do not set Vlast_coding_system_used. */
+
+Lisp_Object
+code_convert_string_norecord (string, coding_system, encodep)
+ Lisp_Object string, coding_system;
+ int encodep;
+{
+ struct coding_system coding;
+
+ CHECK_STRING (string, 0);
+ CHECK_SYMBOL (coding_system, 1);
+
+ if (NILP (coding_system))
+ return string;
+
+ if (setup_coding_system (Fcheck_coding_system (coding_system), &coding) < 0)
+ error ("Invalid coding system: %s", XSYMBOL (coding_system)->name->data);
+
+ coding.mode |= CODING_MODE_LAST_BLOCK;
+ return code_convert_string (string, &coding, encodep, Qt);
+}
\f
DEFUN ("decode-sjis-char", Fdecode_sjis_char, Sdecode_sjis_char, 1, 1, 0,
"Decode a JISX0208 character of shift-jis encoding.\n\
DEFUN ("find-operation-coding-system", Ffind_operation_coding_system,
Sfind_operation_coding_system, 1, MANY, 0,
"Choose a coding system for an operation based on the target name.\n\
-The value names a pair of coding systems: (DECODING-SYSTEM ENCODING-SYSTEM).\n\
+The value names a pair of coding systems: (DECODING-SYSTEM . ENCODING-SYSTEM).\n\
DECODING-SYSTEM is the coding system to use for decoding\n\
\(in case OPERATION does decoding), and ENCODING-SYSTEM is the coding system\n\
for encoding (in case OPERATION does encoding).\n\
return Qnil;
}
-DEFUN ("update-iso-coding-systems", Fupdate_iso_coding_systems,
- Supdate_iso_coding_systems, 0, 0, 0,
- "Update internal database for ISO2022 based coding systems.\n\
+DEFUN ("update-coding-systems-internal", Fupdate_coding_systems_internal,
+ Supdate_coding_systems_internal, 0, 0, 0,
+ "Update internal database for ISO2022 and CCL based coding systems.\n\
When values of the following coding categories are changed, you must\n\
call this function:\n\
coding-category-iso-7, coding-category-iso-7-tight,\n\
coding-category-iso-8-1, coding-category-iso-8-2,\n\
- coding-category-iso-7-else, coding-category-iso-8-else")
+ coding-category-iso-7-else, coding-category-iso-8-else,\n\
+ coding-category-ccl")
()
{
int i;
- for (i = CODING_CATEGORY_IDX_ISO_7; i <= CODING_CATEGORY_IDX_ISO_8_ELSE;
- i++)
+ for (i = CODING_CATEGORY_IDX_ISO_7; i <= CODING_CATEGORY_IDX_CCL; i++)
{
- if (! coding_system_table[i])
- coding_system_table[i]
- = (struct coding_system *) xmalloc (sizeof (struct coding_system));
- setup_coding_system
- (XSYMBOL (XVECTOR (Vcoding_category_table)->contents[i])->value,
- coding_system_table[i]);
+ Lisp_Object val;
+
+ val = XSYMBOL (XVECTOR (Vcoding_category_table)->contents[i])->value;
+ if (!NILP (val))
+ {
+ if (! coding_system_table[i])
+ coding_system_table[i] = ((struct coding_system *)
+ xmalloc (sizeof (struct coding_system)));
+ setup_coding_system (val, coding_system_table[i]);
+ }
+ else if (coding_system_table[i])
+ {
+ xfree (coding_system_table[i]);
+ coding_system_table[i] = NULL;
+ }
}
+
+ return Qnil;
+}
+
+DEFUN ("set-coding-priority-internal", Fset_coding_priority_internal,
+ Sset_coding_priority_internal, 0, 0, 0,
+ "Update internal database for the current value of `coding-category-list'.\n\
+This function is internal use only.")
+ ()
+{
+ int i = 0, idx;
+ Lisp_Object val;
+
+ val = Vcoding_category_list;
+
+ while (CONSP (val) && i < CODING_CATEGORY_IDX_MAX)
+ {
+ if (! SYMBOLP (XCONS (val)->car))
+ break;
+ idx = XFASTINT (Fget (XCONS (val)->car, Qcoding_category_index));
+ if (idx >= CODING_CATEGORY_IDX_MAX)
+ break;
+ coding_priorities[i++] = (1 << idx);
+ val = XCONS (val)->cdr;
+ }
+ /* If coding-category-list is valid and contains all coding
+ categories, `i' should be CODING_CATEGORY_IDX_MAX now. If not,
+ the following code saves Emacs from craching. */
+ while (i < CODING_CATEGORY_IDX_MAX)
+ coding_priorities[i++] = CODING_CATEGORY_MASK_RAW_TEXT;
+
return Qnil;
}
#endif /* emacs */
\f
-/*** 8. Post-amble ***/
+/*** 9. Post-amble ***/
+void
+init_coding ()
+{
+ conversion_buffer = (char *) xmalloc (MINIMUM_CONVERSION_BUFFER_SIZE);
+}
+
+void
init_coding_once ()
{
int i;
iso_code_class[ISO_CODE_CSI] = ISO_control_sequence_introducer;
conversion_buffer_size = MINIMUM_CONVERSION_BUFFER_SIZE;
- conversion_buffer = (char *) xmalloc (MINIMUM_CONVERSION_BUFFER_SIZE);
setup_coding_system (Qnil, &keyboard_coding);
setup_coding_system (Qnil, &terminal_coding);
setup_coding_system (Qnil, &safe_terminal_coding);
+ setup_coding_system (Qnil, &default_buffer_file_coding);
bzero (coding_system_table, sizeof coding_system_table);
+ bzero (ascii_skip_code, sizeof ascii_skip_code);
+ for (i = 0; i < 128; i++)
+ ascii_skip_code[i] = 1;
+
#if defined (MSDOS) || defined (WINDOWSNT)
system_eol_type = CODING_EOL_CRLF;
#else
#ifdef emacs
+void
syms_of_coding ()
{
Qtarget_idx = intern ("target-idx");
}
}
- Qcharacter_unification_table = intern ("character-unification-table");
- staticpro (&Qcharacter_unification_table);
- Fput (Qcharacter_unification_table, Qchar_table_extra_slots,
- make_number (0));
+ Qtranslation_table = intern ("translation-table");
+ staticpro (&Qtranslation_table);
+ Fput (Qtranslation_table, Qchar_table_extra_slots, make_number (1));
+
+ Qtranslation_table_id = intern ("translation-table-id");
+ staticpro (&Qtranslation_table_id);
- Qcharacter_unification_table_for_decode
- = intern ("character-unification-table-for-decode");
- staticpro (&Qcharacter_unification_table_for_decode);
+ Qtranslation_table_for_decode = intern ("translation-table-for-decode");
+ staticpro (&Qtranslation_table_for_decode);
- Qcharacter_unification_table_for_encode
- = intern ("character-unification-table-for-encode");
- staticpro (&Qcharacter_unification_table_for_encode);
+ Qtranslation_table_for_encode = intern ("translation-table-for-encode");
+ staticpro (&Qtranslation_table_for_encode);
Qsafe_charsets = intern ("safe-charsets");
staticpro (&Qsafe_charsets);
+ Qvalid_codes = intern ("valid-codes");
+ staticpro (&Qvalid_codes);
+
Qemacs_mule = intern ("emacs-mule");
staticpro (&Qemacs_mule);
defsubr (&Sset_keyboard_coding_system_internal);
defsubr (&Skeyboard_coding_system);
defsubr (&Sfind_operation_coding_system);
- defsubr (&Supdate_iso_coding_systems);
+ defsubr (&Supdate_coding_systems_internal);
+ defsubr (&Sset_coding_priority_internal);
DEFVAR_LISP ("coding-system-list", &Vcoding_system_list,
"List of coding systems.\n\
"*Non-nil inhibit code conversion of end-of-line format in any cases.");
inhibit_eol_conversion = 0;
+ DEFVAR_BOOL ("inherit-process-coding-system", &inherit_process_coding_system,
+ "Non-nil means process buffer inherits coding system of process output.\n\
+Bind it to t if the process output is to be treated as if it were a file\n\
+read from some filesystem.");
+ inherit_process_coding_system = 0;
+
DEFVAR_LISP ("file-coding-system-alist", &Vfile_coding_system_alist,
"Alist to decide a coding system to use for a file I/O operation.\n\
The format is ((PATTERN . VAL) ...),\n\
If VAL is a function symbol, the function must return a coding system\n\
or a cons of coding systems which are used as above.\n\
\n\
-See also the function `find-operation-coding-system'.");
+See also the function `find-operation-coding-system'\n\
+and the variable `auto-coding-alist'.");
Vfile_coding_system_alist = Qnil;
DEFVAR_LISP ("process-coding-system-alist", &Vprocess_coding_system_alist,
"Mnemonic character indicating end-of-line format is not yet decided.");
eol_mnemonic_undecided = ':';
- DEFVAR_LISP ("enable-character-unification", &Venable_character_unification,
- "Non-nil means ISO 2022 encoder/decoder do character unification.");
- Venable_character_unification = Qt;
+ DEFVAR_LISP ("enable-character-translation", &Venable_character_translation,
+ "*Non-nil enables character translation while encoding and decoding.");
+ Venable_character_translation = Qt;
- DEFVAR_LISP ("standard-character-unification-table-for-decode",
- &Vstandard_character_unification_table_for_decode,
- "Table for unifying characters when reading.");
- Vstandard_character_unification_table_for_decode = Qnil;
+ DEFVAR_LISP ("standard-translation-table-for-decode",
+ &Vstandard_translation_table_for_decode,
+ "Table for translating characters while decoding.");
+ Vstandard_translation_table_for_decode = Qnil;
- DEFVAR_LISP ("standard-character-unification-table-for-encode",
- &Vstandard_character_unification_table_for_encode,
- "Table for unifying characters when writing.");
- Vstandard_character_unification_table_for_encode = Qnil;
+ DEFVAR_LISP ("standard-translation-table-for-encode",
+ &Vstandard_translation_table_for_encode,
+ "Table for translationg characters while encoding.");
+ Vstandard_translation_table_for_encode = Qnil;
DEFVAR_LISP ("charset-revision-table", &Vcharset_revision_alist,
"Alist of charsets vs revision numbers.\n\
coding system which can encode the text in the case that a default\n\
coding system used in each operation can't encode the text.\n\
\n\
-The default value is `select-safe-codign-system' (which see).");
+The default value is `select-safe-coding-system' (which see).");
Vselect_safe_coding_system_function = Qnil;
}
HCoop / bpt / emacs.git / blobdiff