#if 0
int
detect_coding_emacs_mule (src, src_end)
unsigned char *src, *src_end;
{
...
}
#endif
#if 0
decode_coding_XXX (coding, source, destination, src_bytes, dst_bytes)
struct coding_system *coding;
unsigned char *source, *destination;
int src_bytes, dst_bytes;
{
...
}
#endif
#if 0
encode_coding_XXX (coding, source, destination, src_bytes, dst_bytes)
struct coding_system *coding;
unsigned char *source, *destination;
int src_bytes, dst_bytes;
{
...
}
#endif
#define ONE_MORE_BYTE(c1) \
do { \
if (src < src_end) \
c1 = *src++; \
else \
goto label_end_of_loop; \
} while (0)
#define TWO_MORE_BYTES(c1, c2) \
do { \
if (src + 1 < src_end) \
c1 = *src++, c2 = *src++; \
else \
goto label_end_of_loop; \
} while (0)
#define THREE_MORE_BYTES(c1, c2, c3) \
do { \
if (src + 2 < src_end) \
c1 = *src++, c2 = *src++, c3 = *src++; \
else \
goto label_end_of_loop; \
} while (0)
#define DECODE_CHARACTER_ASCII(c) \
do { \
if (COMPOSING_P (coding->composing)) \
{ \
*dst++ = 0xA0, *dst++ = (c) | 0x80; \
coding->composed_chars++; \
if (((c) | 0x80) < 0xA0) \
coding->fake_multibyte = 1; \
} \
else \
{ \
\
*dst++ = (c) & 0x7F; \
coding->produced_char++; \
} \
} while (0)
#define DECODE_CHARACTER_DIMENSION1(charset, c) \
do { \
unsigned char leading_code = CHARSET_LEADING_CODE_BASE (charset); \
if (COMPOSING_P (coding->composing)) \
{ \
*dst++ = leading_code + 0x20; \
coding->composed_chars++; \
} \
else \
{ \
*dst++ = leading_code; \
coding->produced_char++; \
} \
if (leading_code = CHARSET_LEADING_CODE_EXT (charset)) \
*dst++ = leading_code; \
*dst++ = (c) | 0x80; \
if (((c) | 0x80) < 0xA0) \
coding->fake_multibyte = 1; \
} while (0)
#define DECODE_CHARACTER_DIMENSION2(charset, c1, c2) \
do { \
DECODE_CHARACTER_DIMENSION1 (charset, c1); \
*dst++ = (c2) | 0x80; \
if (((c2) | 0x80) < 0xA0) \
coding->fake_multibyte = 1; \
} while (0)
#include <stdio.h>
#ifdef emacs
#include <config.h>
#include "lisp.h"
#include "buffer.h"
#include "charset.h"
#include "ccl.h"
#include "coding.h"
#include "window.h"
#else
#include "mulelib.h"
#endif
Lisp_Object Qcoding_system, Qeol_type;
Lisp_Object Qbuffer_file_coding_system;
Lisp_Object Qpost_read_conversion, Qpre_write_conversion;
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 Qstart_process, Qopen_network_stream;
Lisp_Object Qtarget_idx;
Lisp_Object Vselect_safe_coding_system_function;
Lisp_Object eol_mnemonic_unix, eol_mnemonic_dos, eol_mnemonic_mac;
Lisp_Object eol_mnemonic_undecided;
int system_eol_type;
#ifdef emacs
Lisp_Object Vcoding_system_list, Vcoding_system_alist;
Lisp_Object Qcoding_system_p, Qcoding_system_error;
Lisp_Object Qemacs_mule, Qraw_text;
Lisp_Object Vcoding_system_for_read;
Lisp_Object Vcoding_system_for_write;
Lisp_Object Vlast_coding_system_used;
Lisp_Object Vlatin_extra_code_table;
int inhibit_eol_conversion;
int inherit_process_coding_system;
struct coding_system terminal_coding;
struct coding_system safe_terminal_coding;
struct coding_system keyboard_coding;
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;
#endif
Lisp_Object Qcoding_category, Qcoding_category_index;
Lisp_Object Vcoding_category_list;
Lisp_Object Vcoding_category_table;
char *coding_category_name[CODING_CATEGORY_IDX_MAX] = {
"coding-category-emacs-mule",
"coding-category-sjis",
"coding-category-iso-7",
"coding-category-iso-7-tight",
"coding-category-iso-8-1",
"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"
};
struct coding_system *coding_system_table[CODING_CATEGORY_IDX_MAX];
static
int coding_priorities[CODING_CATEGORY_IDX_MAX];
Lisp_Object Venable_character_translation;
Lisp_Object Vstandard_translation_table_for_decode;
Lisp_Object Vstandard_translation_table_for_encode;
Lisp_Object Qtranslation_table;
Lisp_Object Qtranslation_table_id;
Lisp_Object Qtranslation_table_for_decode;
Lisp_Object Qtranslation_table_for_encode;
Lisp_Object Vcharset_revision_alist;
Lisp_Object Vdefault_process_coding_system;
enum emacs_code_class_type emacs_code_class[256];
#define CHECK_CODE_RANGE_A0_FF \
do { \
if (src >= src_end) \
goto label_end_of_switch; \
else if (*src++ < 0xA0) \
return 0; \
} while (0)
int
detect_coding_emacs_mule (src, src_end)
unsigned char *src, *src_end;
{
unsigned char c;
int composing = 0;
while (src < src_end)
{
c = *src++;
if (composing)
{
if (c < 0xA0)
composing = 0;
else
c -= 0x20;
}
switch (emacs_code_class[c])
{
case EMACS_ascii_code:
case EMACS_linefeed_code:
break;
case EMACS_control_code:
if (c == ISO_CODE_ESC || c == ISO_CODE_SI || c == ISO_CODE_SO)
return 0;
break;
case EMACS_invalid_code:
return 0;
case EMACS_leading_code_composition:
if (composing)
CHECK_CODE_RANGE_A0_FF;
else
composing = 1;
break;
case EMACS_leading_code_4:
CHECK_CODE_RANGE_A0_FF;
case EMACS_leading_code_3:
CHECK_CODE_RANGE_A0_FF;
case EMACS_leading_code_2:
CHECK_CODE_RANGE_A0_FF;
break;
default:
label_end_of_switch:
break;
}
}
return CODING_CATEGORY_MASK_EMACS_MULE;
}
enum iso_code_class_type iso_code_class[256];
#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
detect_coding_iso2022 (src, src_end)
unsigned char *src, *src_end;
{
int mask = CODING_CATEGORY_MASK_ISO;
int mask_found = 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;
while (mask && src < src_end)
{
c = *src++;
switch (c)
{
case ISO_CODE_ESC:
single_shifting = 0;
if (src >= src_end)
break;
c = *src++;
if (c >= '(' && c <= '/')
{
if (src >= src_end)
break;
c1 = *src++;
if (c1 < ' ' || c1 >= 0x80
|| (charset = iso_charset_table[0][c >= ','][c1]) < 0)
break;
reg[(c - '(') % 4] = charset;
}
else if (c == '$')
{
if (src >= src_end)
break;
c = *src++;
if (c >= '@' && c <= 'B')
reg[0] = charset = iso_charset_table[1][0][c];
else if (c >= '(' && c <= '/')
{
if (src >= src_end)
break;
c1 = *src++;
if (c1 < ' ' || c1 >= 0x80
|| (charset = iso_charset_table[1][c >= ','][c1]) < 0)
break;
reg[(c - '(') % 4] = charset;
}
else
break;
}
else if (c == 'N' || c == 'O')
{
mask &= CODING_CATEGORY_MASK_ISO_7_ELSE;
break;
}
else if (c == '0' || c == '1' || c == '2')
break;
else
break;
mask &= ~CODING_CATEGORY_MASK_ISO_8BIT;
if (CHARSET_OK (CODING_CATEGORY_IDX_ISO_7, charset))
mask_found |= CODING_CATEGORY_MASK_ISO_7;
else
mask &= ~CODING_CATEGORY_MASK_ISO_7;
if (CHARSET_OK (CODING_CATEGORY_IDX_ISO_7_TIGHT, charset))
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))
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))
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)
|| SHIFT_OUT_OK (CODING_CATEGORY_IDX_ISO_8_ELSE)))
{
mask &= ~CODING_CATEGORY_MASK_ISO_7BIT;
mask_found |= CODING_CATEGORY_MASK_ISO_SHIFT;
}
break;
case ISO_CODE_SI:
single_shifting = 0;
if (shift_out == 1)
{
mask &= ~CODING_CATEGORY_MASK_ISO_7BIT;
mask_found |= CODING_CATEGORY_MASK_ISO_SHIFT;
}
break;
case ISO_CODE_CSI:
single_shifting = 0;
case ISO_CODE_SS2:
case ISO_CODE_SS3:
{
int newmask = CODING_CATEGORY_MASK_ISO_8_ELSE;
if (c != ISO_CODE_CSI)
{
if (coding_system_table[CODING_CATEGORY_IDX_ISO_8_1]->flags
& CODING_FLAG_ISO_SINGLE_SHIFT)
newmask |= CODING_CATEGORY_MASK_ISO_8_1;
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]))
{
if (coding_system_table[CODING_CATEGORY_IDX_ISO_8_1]->flags
& CODING_FLAG_ISO_LATIN_EXTRA)
newmask |= CODING_CATEGORY_MASK_ISO_8_1;
if (coding_system_table[CODING_CATEGORY_IDX_ISO_8_2]->flags
& CODING_FLAG_ISO_LATIN_EXTRA)
newmask |= CODING_CATEGORY_MASK_ISO_8_2;
}
mask &= newmask;
mask_found |= newmask;
}
break;
default:
if (c < 0x80)
{
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]))
{
int newmask = 0;
if (coding_system_table[CODING_CATEGORY_IDX_ISO_8_1]->flags
& CODING_FLAG_ISO_LATIN_EXTRA)
newmask |= CODING_CATEGORY_MASK_ISO_8_1;
if (coding_system_table[CODING_CATEGORY_IDX_ISO_8_2]->flags
& CODING_FLAG_ISO_LATIN_EXTRA)
newmask |= CODING_CATEGORY_MASK_ISO_8_2;
mask &= newmask;
mask_found |= newmask;
}
else
return 0;
}
else
{
unsigned char *src_begin = src;
mask &= ~(CODING_CATEGORY_MASK_ISO_7BIT
| CODING_CATEGORY_MASK_ISO_7_ELSE);
mask_found |= CODING_CATEGORY_MASK_ISO_8_1;
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;
}
}
return (mask & mask_found);
}
#define DECODE_ISO_CHARACTER(charset, c1) \
do { \
int c_alt, charset_alt = (charset); \
if (COMPOSING_HEAD_P (coding->composing)) \
{ \
*dst++ = LEADING_CODE_COMPOSITION; \
if (COMPOSING_WITH_RULE_P (coding->composing)) \
\
*dst++ = 0xFF; \
coding->composing += 2; \
} \
if (charset_alt >= 0) \
{ \
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--; \
charset_alt = CHARSET_ASCII; \
} \
} \
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) \
DECODE_CHARACTER_ASCII (c1); \
else if (CHARSET_DIMENSION (charset_alt) == 1) \
DECODE_CHARACTER_DIMENSION1 (charset_alt, c1); \
else \
DECODE_CHARACTER_DIMENSION2 (charset_alt, c1, c2); \
if (COMPOSING_WITH_RULE_P (coding->composing)) \
\
coding->composing = COMPOSING_WITH_RULE_RULE; \
} while (0)
#define DECODE_DESIGNATION(reg, dimension, chars, final_char) \
do { \
int charset; \
\
if (final_char < '0' || final_char >= 128) \
goto label_invalid_code; \
charset = ISO_CHARSET_TABLE (make_number (dimension), \
make_number (chars), \
make_number (final_char)); \
if (charset >= 0 \
&& (CODING_SPEC_ISO_REQUESTED_DESIGNATION (coding, charset) == reg \
|| coding->safe_charsets[charset])) \
{ \
if (coding->spec.iso2022.last_invalid_designation_register == 0 \
&& reg == 0 \
&& charset == CHARSET_ASCII) \
{ \
\
coding->spec.iso2022.last_invalid_designation_register = -1; \
goto label_invalid_code; \
} \
coding->spec.iso2022.last_invalid_designation_register = -1; \
if ((coding->mode & CODING_MODE_DIRECTION) \
&& CHARSET_REVERSE_CHARSET (charset) >= 0) \
charset = CHARSET_REVERSE_CHARSET (charset); \
CODING_SPEC_ISO_DESIGNATION (coding, reg) = charset; \
} \
else \
{ \
coding->spec.iso2022.last_invalid_designation_register = reg; \
goto label_invalid_code; \
} \
} while (0)
int
check_composing_code (coding, src, src_end)
struct coding_system *coding;
unsigned char *src, *src_end;
{
int charset, c, c1, dim;
while (src < src_end)
{
c = *src++;
if (c >= 0x20)
continue;
if (c != ISO_CODE_ESC || src >= src_end)
return -1;
c = *src++;
if (c == '1')
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 <= '/')
{
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 -1;
}
int
decode_coding_iso2022 (coding, source, destination, src_bytes, dst_bytes)
struct coding_system *coding;
unsigned char *source, *destination;
int src_bytes, dst_bytes;
{
unsigned char *src = source;
unsigned char *src_end = source + src_bytes;
unsigned char *dst = destination;
unsigned char *dst_end = destination + dst_bytes;
unsigned char *adjusted_dst_end = dst_end - 6;
int charset;
int charset0 = CODING_SPEC_ISO_PLANE_CHARSET (coding, 0);
int charset1 = CODING_SPEC_ISO_PLANE_CHARSET (coding, 1);
Lisp_Object translation_table
= coding->translation_table_for_decode;
int result = CODING_FINISH_NORMAL;
if (!NILP (Venable_character_translation) && NILP (translation_table))
translation_table = Vstandard_translation_table_for_decode;
coding->produced_char = 0;
coding->fake_multibyte = 0;
while (src < src_end && (dst_bytes
? (dst < adjusted_dst_end)
: (dst < src - 6)))
{
unsigned char *src_base = src;
int c1 = *src++, c2;
switch (iso_code_class [c1])
{
case ISO_0x20_or_0x7F:
if (!coding->composing
&& (charset0 < 0 || CHARSET_CHARS (charset0) == 94))
{
*dst++ = c1;
coding->produced_char++;
break;
}
case ISO_graphic_plane_0:
if (coding->composing == COMPOSING_WITH_RULE_RULE)
{
*dst++ = c1 | 0x80;
coding->composing = COMPOSING_WITH_RULE_TAIL;
}
else
DECODE_ISO_CHARACTER (charset0, c1);
break;
case ISO_0xA0_or_0xFF:
if (charset1 < 0 || CHARSET_CHARS (charset1) == 94
|| coding->flags & CODING_FLAG_ISO_SEVEN_BITS)
goto label_invalid_code;
case ISO_graphic_plane_1:
if (coding->flags & CODING_FLAG_ISO_SEVEN_BITS)
goto label_invalid_code;
else
DECODE_ISO_CHARACTER (charset1, c1);
break;
case ISO_control_code:
if (c1 == '\n'
&& (coding->mode & CODING_MODE_INHIBIT_INCONSISTENT_EOL)
&& (coding->eol_type == CODING_EOL_CR
|| coding->eol_type == CODING_EOL_CRLF))
{
result = CODING_FINISH_INCONSISTENT_EOL;
goto label_end_of_loop_2;
}
*dst++ = c1;
coding->produced_char++;
if (c1 >= 0x80)
coding->fake_multibyte = 1;
break;
case ISO_carriage_return:
if (coding->eol_type == CODING_EOL_CR)
*dst++ = '\n';
else if (coding->eol_type == CODING_EOL_CRLF)
{
ONE_MORE_BYTE (c1);
if (c1 == ISO_CODE_LF)
*dst++ = '\n';
else
{
if (coding->mode & CODING_MODE_INHIBIT_INCONSISTENT_EOL)
{
result = CODING_FINISH_INCONSISTENT_EOL;
goto label_end_of_loop_2;
}
src--;
*dst++ = '\r';
}
}
else
*dst++ = c1;
coding->produced_char++;
break;
case ISO_shift_out:
if (! (coding->flags & CODING_FLAG_ISO_LOCKING_SHIFT)
|| CODING_SPEC_ISO_DESIGNATION (coding, 1) < 0)
goto label_invalid_code;
CODING_SPEC_ISO_INVOCATION (coding, 0) = 1;
charset0 = CODING_SPEC_ISO_PLANE_CHARSET (coding, 0);
break;
case ISO_shift_in:
if (! (coding->flags & CODING_FLAG_ISO_LOCKING_SHIFT))
goto label_invalid_code;
CODING_SPEC_ISO_INVOCATION (coding, 0) = 0;
charset0 = CODING_SPEC_ISO_PLANE_CHARSET (coding, 0);
break;
case ISO_single_shift_2_7:
case ISO_single_shift_2:
if (! (coding->flags & CODING_FLAG_ISO_SINGLE_SHIFT))
goto label_invalid_code;
c1 = 'N';
goto label_escape_sequence;
case ISO_single_shift_3:
if (! (coding->flags & CODING_FLAG_ISO_SINGLE_SHIFT))
goto label_invalid_code;
c1 = 'O';
goto label_escape_sequence;
case ISO_control_sequence_introducer:
c1 = '[';
goto label_escape_sequence;
case ISO_escape:
ONE_MORE_BYTE (c1);
label_escape_sequence:
switch (c1)
{
case '&':
ONE_MORE_BYTE (c1);
if (!(c1 >= '@' && c1 <= '~'))
goto label_invalid_code;
ONE_MORE_BYTE (c1);
if (c1 != ISO_CODE_ESC)
goto label_invalid_code;
ONE_MORE_BYTE (c1);
goto label_escape_sequence;
case '$':
if (! (coding->flags & CODING_FLAG_ISO_DESIGNATION))
goto label_invalid_code;
ONE_MORE_BYTE (c1);
if (c1 >= '@' && c1 <= 'B')
{
DECODE_DESIGNATION (0, 2, 94, c1);
}
else if (c1 >= 0x28 && c1 <= 0x2B)
{
ONE_MORE_BYTE (c2);
DECODE_DESIGNATION (c1 - 0x28, 2, 94, c2);
}
else if (c1 >= 0x2C && c1 <= 0x2F)
{
ONE_MORE_BYTE (c2);
DECODE_DESIGNATION (c1 - 0x2C, 2, 96, c2);
}
else
goto label_invalid_code;
break;
case 'n':
if (! (coding->flags & CODING_FLAG_ISO_LOCKING_SHIFT)
|| CODING_SPEC_ISO_DESIGNATION (coding, 2) < 0)
goto label_invalid_code;
CODING_SPEC_ISO_INVOCATION (coding, 0) = 2;
charset0 = CODING_SPEC_ISO_PLANE_CHARSET (coding, 0);
break;
case 'o':
if (! (coding->flags & CODING_FLAG_ISO_LOCKING_SHIFT)
|| CODING_SPEC_ISO_DESIGNATION (coding, 3) < 0)
goto label_invalid_code;
CODING_SPEC_ISO_INVOCATION (coding, 0) = 3;
charset0 = CODING_SPEC_ISO_PLANE_CHARSET (coding, 0);
break;
case 'N':
if (! (coding->flags & CODING_FLAG_ISO_SINGLE_SHIFT)
|| CODING_SPEC_ISO_DESIGNATION (coding, 2) < 0)
goto label_invalid_code;
ONE_MORE_BYTE (c1);
charset = CODING_SPEC_ISO_DESIGNATION (coding, 2);
DECODE_ISO_CHARACTER (charset, c1);
break;
case 'O':
if (! (coding->flags & CODING_FLAG_ISO_SINGLE_SHIFT)
|| CODING_SPEC_ISO_DESIGNATION (coding, 3) < 0)
goto label_invalid_code;
ONE_MORE_BYTE (c1);
charset = CODING_SPEC_ISO_DESIGNATION (coding, 3);
DECODE_ISO_CHARACTER (charset, c1);
break;
case '0': case '2':
if (check_composing_code (coding, src, src_end) == 0)
{
coding->composing = (c1 == '0'
? COMPOSING_NO_RULE_HEAD
: COMPOSING_WITH_RULE_HEAD);
coding->composed_chars = 0;
}
else
{
*dst++ = ISO_CODE_ESC;
*dst++ = c1;
coding->produced_char += 2;
}
break;
case '1':
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;
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;
break;
case '[':
if (coding->flags & CODING_FLAG_ISO_NO_DIRECTION)
goto label_invalid_code;
ONE_MORE_BYTE (c1);
switch (c1)
{
case ']':
coding->mode &= ~CODING_MODE_DIRECTION;
case '0':
case '1':
ONE_MORE_BYTE (c1);
if (c1 == ']')
coding->mode &= ~CODING_MODE_DIRECTION;
else
goto label_invalid_code;
break;
case '2':
ONE_MORE_BYTE (c1);
if (c1 == ']')
coding->mode |= CODING_MODE_DIRECTION;
else
goto label_invalid_code;
break;
default:
goto label_invalid_code;
}
break;
default:
if (! (coding->flags & CODING_FLAG_ISO_DESIGNATION))
goto label_invalid_code;
if (c1 >= 0x28 && c1 <= 0x2B)
{
ONE_MORE_BYTE (c2);
DECODE_DESIGNATION (c1 - 0x28, 1, 94, c2);
}
else if (c1 >= 0x2C && c1 <= 0x2F)
{
ONE_MORE_BYTE (c2);
DECODE_DESIGNATION (c1 - 0x2C, 1, 96, c2);
}
else
{
goto label_invalid_code;
}
}
charset0 = CODING_SPEC_ISO_PLANE_CHARSET (coding, 0);
charset1 = CODING_SPEC_ISO_PLANE_CHARSET (coding, 1);
break;
label_invalid_code:
while (src_base < src)
*dst++ = *src_base++;
coding->fake_multibyte = 1;
}
continue;
label_end_of_loop:
result = CODING_FINISH_INSUFFICIENT_SRC;
label_end_of_loop_2:
src = src_base;
break;
}
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)
{
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;
coding->fake_multibyte = 1;
}
}
coding->consumed = coding->consumed_char = src - source;
coding->produced = dst - destination;
return result;
}
#define ENCODE_DESIGNATION(charset, reg, coding) \
do { \
unsigned char final_char = CHARSET_ISO_FINAL_CHAR (charset); \
char *intermediate_char_94 = "()*+"; \
char *intermediate_char_96 = ",-./"; \
int revision = CODING_SPEC_ISO_REVISION_NUMBER(coding, charset); \
if (revision < 255) \
{ \
*dst++ = ISO_CODE_ESC; \
*dst++ = '&'; \
*dst++ = '@' + revision; \
} \
*dst++ = ISO_CODE_ESC; \
if (CHARSET_DIMENSION (charset) == 1) \
{ \
if (CHARSET_CHARS (charset) == 94) \
*dst++ = (unsigned char) (intermediate_char_94[reg]); \
else \
*dst++ = (unsigned char) (intermediate_char_96[reg]); \
} \
else \
{ \
*dst++ = '$'; \
if (CHARSET_CHARS (charset) == 94) \
{ \
if (! (coding->flags & CODING_FLAG_ISO_SHORT_FORM) \
|| reg != 0 \
|| final_char < '@' || final_char > 'B') \
*dst++ = (unsigned char) (intermediate_char_94[reg]); \
} \
else \
*dst++ = (unsigned char) (intermediate_char_96[reg]); \
} \
*dst++ = final_char; \
CODING_SPEC_ISO_DESIGNATION (coding, reg) = charset; \
} while (0)
#define ENCODE_SINGLE_SHIFT_2 \
do { \
if (coding->flags & CODING_FLAG_ISO_SEVEN_BITS) \
*dst++ = ISO_CODE_ESC, *dst++ = 'N'; \
else \
{ \
*dst++ = ISO_CODE_SS2; \
coding->fake_multibyte = 1; \
} \
CODING_SPEC_ISO_SINGLE_SHIFTING (coding) = 1; \
} while (0)
#define ENCODE_SINGLE_SHIFT_3 \
do { \
if (coding->flags & CODING_FLAG_ISO_SEVEN_BITS) \
*dst++ = ISO_CODE_ESC, *dst++ = 'O'; \
else \
{ \
*dst++ = ISO_CODE_SS3; \
coding->fake_multibyte = 1; \
} \
CODING_SPEC_ISO_SINGLE_SHIFTING (coding) = 1; \
} while (0)
#define ENCODE_SHIFT_IN \
do { \
*dst++ = ISO_CODE_SI; \
CODING_SPEC_ISO_INVOCATION (coding, 0) = 0; \
} while (0)
#define ENCODE_SHIFT_OUT \
do { \
*dst++ = ISO_CODE_SO; \
CODING_SPEC_ISO_INVOCATION (coding, 0) = 1; \
} while (0)
#define ENCODE_LOCKING_SHIFT_2 \
do { \
*dst++ = ISO_CODE_ESC, *dst++ = 'n'; \
CODING_SPEC_ISO_INVOCATION (coding, 0) = 2; \
} while (0)
#define ENCODE_LOCKING_SHIFT_3 \
do { \
*dst++ = ISO_CODE_ESC, *dst++ = 'o'; \
CODING_SPEC_ISO_INVOCATION (coding, 0) = 3; \
} while (0)
#define ENCODE_ISO_CHARACTER_DIMENSION1(charset, c1) \
do { \
if (CODING_SPEC_ISO_SINGLE_SHIFTING (coding)) \
{ \
if (coding->flags & CODING_FLAG_ISO_SEVEN_BITS) \
*dst++ = c1 & 0x7F; \
else \
*dst++ = c1 | 0x80; \
CODING_SPEC_ISO_SINGLE_SHIFTING (coding) = 0; \
break; \
} \
else if (charset == CODING_SPEC_ISO_PLANE_CHARSET (coding, 0)) \
{ \
*dst++ = c1 & 0x7F; \
break; \
} \
else if (charset == CODING_SPEC_ISO_PLANE_CHARSET (coding, 1)) \
{ \
*dst++ = c1 | 0x80; \
break; \
} \
else if (coding->flags & CODING_FLAG_ISO_SAFE \
&& !coding->safe_charsets[charset]) \
{ \
\
*dst++ = CODING_INHIBIT_CHARACTER_SUBSTITUTION; \
if (CHARSET_WIDTH (charset) == 2) \
*dst++ = CODING_INHIBIT_CHARACTER_SUBSTITUTION; \
break; \
} \
else \
\
dst = encode_invocation_designation (charset, coding, dst); \
} while (1)
#define ENCODE_ISO_CHARACTER_DIMENSION2(charset, c1, c2) \
do { \
if (CODING_SPEC_ISO_SINGLE_SHIFTING (coding)) \
{ \
if (coding->flags & CODING_FLAG_ISO_SEVEN_BITS) \
*dst++ = c1 & 0x7F, *dst++ = c2 & 0x7F; \
else \
*dst++ = c1 | 0x80, *dst++ = c2 | 0x80; \
CODING_SPEC_ISO_SINGLE_SHIFTING (coding) = 0; \
break; \
} \
else if (charset == CODING_SPEC_ISO_PLANE_CHARSET (coding, 0)) \
{ \
*dst++ = c1 & 0x7F, *dst++= c2 & 0x7F; \
break; \
} \
else if (charset == CODING_SPEC_ISO_PLANE_CHARSET (coding, 1)) \
{ \
*dst++ = c1 | 0x80, *dst++= c2 | 0x80; \
break; \
} \
else if (coding->flags & CODING_FLAG_ISO_SAFE \
&& !coding->safe_charsets[charset]) \
{ \
\
*dst++ = CODING_INHIBIT_CHARACTER_SUBSTITUTION; \
if (CHARSET_WIDTH (charset) == 2) \
*dst++ = CODING_INHIBIT_CHARACTER_SUBSTITUTION; \
break; \
} \
else \
\
dst = encode_invocation_designation (charset, coding, dst); \
} while (1)
#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_DEFINED_P (charset_alt)) \
{ \
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); \
} \
} \
else \
{ \
if (coding->flags & CODING_FLAG_ISO_SEVEN_BITS) \
{ \
*dst++ = charset & 0x7f; \
*dst++ = c1 & 0x7f; \
if (c2) \
*dst++ = c2 & 0x7f; \
} \
else \
{ \
*dst++ = charset; \
*dst++ = c1; \
if (c2) \
*dst++ = c2; \
} \
} \
if (! COMPOSING_P (coding->composing)) \
coding->consumed_char++; \
} while (0)
unsigned char *
encode_invocation_designation (charset, coding, dst)
int charset;
struct coding_system *coding;
unsigned char *dst;
{
int reg;
for (reg = 0; reg < 4; reg++)
if (charset == CODING_SPEC_ISO_DESIGNATION (coding, reg))
break;
if (reg >= 4)
{
reg = CODING_SPEC_ISO_REQUESTED_DESIGNATION (coding, charset);
if (reg == CODING_SPEC_ISO_NO_REQUESTED_DESIGNATION)
reg = 0;
ENCODE_DESIGNATION (charset, reg, coding);
}
if (CODING_SPEC_ISO_INVOCATION (coding, 0) != reg
&& CODING_SPEC_ISO_INVOCATION (coding, 1) != reg)
{
switch (reg)
{
case 0:
ENCODE_SHIFT_IN;
break;
case 1:
ENCODE_SHIFT_OUT;
break;
case 2:
if (coding->flags & CODING_FLAG_ISO_SINGLE_SHIFT)
ENCODE_SINGLE_SHIFT_2;
else
ENCODE_LOCKING_SHIFT_2;
break;
case 3:
if (coding->flags & CODING_FLAG_ISO_SINGLE_SHIFT)
ENCODE_SINGLE_SHIFT_3;
else
ENCODE_LOCKING_SHIFT_3;
break;
}
}
return dst;
}
#define ENCODE_COMPOSITION_NO_RULE_START *dst++ = ISO_CODE_ESC, *dst++ = '0'
#define ENCODE_COMPOSITION_WITH_RULE_START *dst++ = ISO_CODE_ESC, *dst++ = '2'
#define ENCODE_COMPOSITION_END *dst++ = ISO_CODE_ESC, *dst++ = '1'
#define ENCODE_CONTROL_SEQUENCE_INTRODUCER \
do { \
if (coding->flags == CODING_FLAG_ISO_SEVEN_BITS) \
*dst++ = ISO_CODE_ESC, *dst++ = '['; \
else \
*dst++ = ISO_CODE_CSI; \
} while (0)
#define ENCODE_DIRECTION_R2L \
ENCODE_CONTROL_SEQUENCE_INTRODUCER, *dst++ = '2', *dst++ = ']'
#define ENCODE_DIRECTION_L2R \
ENCODE_CONTROL_SEQUENCE_INTRODUCER, *dst++ = '0', *dst++ = ']'
#define ENCODE_RESET_PLANE_AND_REGISTER \
do { \
int reg; \
if (CODING_SPEC_ISO_INVOCATION (coding, 0) != 0) \
ENCODE_SHIFT_IN; \
for (reg = 0; reg < 4; reg++) \
if (CODING_SPEC_ISO_INITIAL_DESIGNATION (coding, reg) >= 0 \
&& (CODING_SPEC_ISO_DESIGNATION (coding, reg) \
!= CODING_SPEC_ISO_INITIAL_DESIGNATION (coding, reg))) \
ENCODE_DESIGNATION \
(CODING_SPEC_ISO_INITIAL_DESIGNATION (coding, reg), reg, coding); \
} while (0)
void
encode_designation_at_bol (coding, table, src, src_end, dstp)
struct coding_system *coding;
Lisp_Object table;
unsigned char *src, *src_end, **dstp;
{
int charset, c, found = 0, reg;
int r[4];
unsigned char *dst = *dstp;
for (reg = 0; reg < 4; reg++)
r[reg] = -1;
while (src < src_end && *src != '\n' && found < 4)
{
int bytes = BYTES_BY_CHAR_HEAD (*src);
if (NILP (table))
charset = CHARSET_AT (src);
else
{
int c_alt;
unsigned char c1, c2;
SPLIT_STRING(src, bytes, charset, c1, c2);
if ((c_alt = translate_char (table, -1, charset, c1, c2)) >= 0)
charset = CHAR_CHARSET (c_alt);
}
reg = CODING_SPEC_ISO_REQUESTED_DESIGNATION (coding, charset);
if (reg != CODING_SPEC_ISO_NO_REQUESTED_DESIGNATION && r[reg] < 0)
{
found++;
r[reg] = charset;
}
src += bytes;
}
if (found)
{
for (reg = 0; reg < 4; reg++)
if (r[reg] >= 0
&& CODING_SPEC_ISO_DESIGNATION (coding, reg) != r[reg])
ENCODE_DESIGNATION (r[reg], reg, coding);
*dstp = dst;
}
}
int
encode_coding_iso2022 (coding, source, destination, src_bytes, dst_bytes)
struct coding_system *coding;
unsigned char *source, *destination;
int src_bytes, dst_bytes;
{
unsigned char *src = source;
unsigned char *src_end = source + src_bytes;
unsigned char *dst = destination;
unsigned char *dst_end = destination + dst_bytes;
unsigned char *adjusted_dst_end = dst_end - 19;
Lisp_Object translation_table
= coding->translation_table_for_encode;
int result = CODING_FINISH_NORMAL;
if (!NILP (Venable_character_translation) && NILP (translation_table))
translation_table = Vstandard_translation_table_for_encode;
coding->consumed_char = 0;
coding->fake_multibyte = 0;
while (src < src_end && (dst_bytes
? (dst < adjusted_dst_end)
: (dst < src - 19)))
{
unsigned char *src_base = src;
int charset, c1, c2, c3, c4;
if (coding->flags & CODING_FLAG_ISO_DESIGNATE_AT_BOL
&& CODING_SPEC_ISO_BOL (coding))
{
encode_designation_at_bol (coding, translation_table,
src, src_end, &dst);
CODING_SPEC_ISO_BOL (coding) = 0;
}
c1 = *src++;
if (COMPOSING_P (coding->composing))
{
if (c1 < 0xA0)
{
coding->composing = COMPOSING_NO;
ENCODE_RESET_PLANE_AND_REGISTER;
ENCODE_COMPOSITION_END;
}
else
{
if (coding->composing == COMPOSING_WITH_RULE_RULE)
{
*dst++ = c1 & 0x7F;
coding->composing = COMPOSING_WITH_RULE_HEAD;
continue;
}
else if (coding->composing == COMPOSING_WITH_RULE_HEAD)
coding->composing = COMPOSING_WITH_RULE_RULE;
if (c1 == 0xA0)
{
ONE_MORE_BYTE (c1);
c1 &= 0x7F;
}
else
c1 -= 0x20;
}
}
switch (emacs_code_class[c1])
{
case EMACS_ascii_code:
c2 = 0;
ENCODE_ISO_CHARACTER (CHARSET_ASCII, c1, c2);
break;
case EMACS_control_code:
if (coding->flags & CODING_FLAG_ISO_RESET_AT_CNTL)
ENCODE_RESET_PLANE_AND_REGISTER;
*dst++ = c1;
coding->consumed_char++;
break;
case EMACS_carriage_return_code:
if (! (coding->mode & CODING_MODE_SELECTIVE_DISPLAY))
{
if (coding->flags & CODING_FLAG_ISO_RESET_AT_CNTL)
ENCODE_RESET_PLANE_AND_REGISTER;
*dst++ = c1;
coding->consumed_char++;
break;
}
case EMACS_linefeed_code:
if (coding->flags & CODING_FLAG_ISO_RESET_AT_EOL)
ENCODE_RESET_PLANE_AND_REGISTER;
if (coding->flags & CODING_FLAG_ISO_INIT_AT_BOL)
bcopy (coding->spec.iso2022.initial_designation,
coding->spec.iso2022.current_designation,
sizeof coding->spec.iso2022.initial_designation);
if (coding->eol_type == CODING_EOL_LF
|| coding->eol_type == CODING_EOL_UNDECIDED)
*dst++ = ISO_CODE_LF;
else if (coding->eol_type == CODING_EOL_CRLF)
*dst++ = ISO_CODE_CR, *dst++ = ISO_CODE_LF;
else
*dst++ = ISO_CODE_CR;
CODING_SPEC_ISO_BOL (coding) = 1;
coding->consumed_char++;
break;
case EMACS_leading_code_2:
ONE_MORE_BYTE (c2);
c3 = 0;
if (c2 < 0xA0)
{
*dst++ = c1;
src--;
coding->consumed_char++;
}
else
ENCODE_ISO_CHARACTER (c1, c2, c3);
break;
case EMACS_leading_code_3:
TWO_MORE_BYTES (c2, c3);
c4 = 0;
if (c2 < 0xA0 || c3 < 0xA0)
{
*dst++ = c1;
src -= 2;
coding->consumed_char++;
}
else if (c1 < LEADING_CODE_PRIVATE_11)
ENCODE_ISO_CHARACTER (c1, c2, c3);
else
ENCODE_ISO_CHARACTER (c2, c3, c4);
break;
case EMACS_leading_code_4:
THREE_MORE_BYTES (c2, c3, c4);
if (c2 < 0xA0 || c3 < 0xA0 || c4 < 0xA0)
{
*dst++ = c1;
src -= 3;
coding->consumed_char++;
}
else
ENCODE_ISO_CHARACTER (c2, c3, c4);
break;
case EMACS_leading_code_composition:
ONE_MORE_BYTE (c2);
if (c2 < 0xA0)
{
*dst++ = c1;
src--;
coding->consumed_char++;
}
else if (c2 == 0xFF)
{
ENCODE_RESET_PLANE_AND_REGISTER;
coding->composing = COMPOSING_WITH_RULE_HEAD;
ENCODE_COMPOSITION_WITH_RULE_START;
coding->consumed_char++;
}
else
{
ENCODE_RESET_PLANE_AND_REGISTER;
src--;
coding->composing = COMPOSING_NO_RULE_HEAD;
ENCODE_COMPOSITION_NO_RULE_START;
coding->consumed_char++;
}
break;
case EMACS_invalid_code:
if (coding->flags & CODING_FLAG_ISO_RESET_AT_CNTL)
ENCODE_RESET_PLANE_AND_REGISTER;
*dst++ = c1;
coding->consumed_char++;
break;
}
continue;
label_end_of_loop:
result = CODING_FINISH_INSUFFICIENT_SRC;
src = src_base;
break;
}
if (src < src_end && result == CODING_FINISH_NORMAL)
result = CODING_FINISH_INSUFFICIENT_DST;
if (coding->mode & CODING_MODE_LAST_BLOCK)
{
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;
}
#define BIG5_SAME_ROW (0xFF - 0xA1 + 0x7F - 0x40)
#define DECODE_BIG5(b1, b2, charset, c1, c2) \
do { \
unsigned int temp \
= (b1 - 0xA1) * BIG5_SAME_ROW + b2 - (b2 < 0x7F ? 0x40 : 0x62); \
if (b1 < 0xC9) \
charset = charset_big5_1; \
else \
{ \
charset = charset_big5_2; \
temp -= (0xC9 - 0xA1) * BIG5_SAME_ROW; \
} \
c1 = temp / (0xFF - 0xA1) + 0x21; \
c2 = temp % (0xFF - 0xA1) + 0x21; \
} while (0)
#define ENCODE_BIG5(charset, c1, c2, b1, b2) \
do { \
unsigned int temp = (c1 - 0x21) * (0xFF - 0xA1) + (c2 - 0x21); \
if (charset == charset_big5_2) \
temp += BIG5_SAME_ROW * (0xC9 - 0xA1); \
b1 = temp / BIG5_SAME_ROW + 0xA1; \
b2 = temp % BIG5_SAME_ROW; \
b2 += b2 < 0x3F ? 0x40 : 0x62; \
} while (0)
#define DECODE_SJIS_BIG5_CHARACTER(charset, c1, c2) \
do { \
int c_alt, charset_alt = (charset); \
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); \
else if (CHARSET_DIMENSION (charset_alt) == 1) \
DECODE_CHARACTER_DIMENSION1 (charset_alt, c1); \
else \
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 (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 if (sjis_p && charset_alt == charset_latin_jisx0201) \
*dst++ = c1 & 0x7F; \
else \
{ \
*dst++ = charset_alt, *dst++ = c1; \
coding->fake_multibyte = 1; \
} \
} \
else \
{ \
c1 &= 0x7F, c2 &= 0x7F; \
if (sjis_p && (charset_alt == charset_jisx0208 \
|| charset_alt == charset_jisx0208_1978))\
{ \
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);
int
detect_coding_sjis (src, src_end)
unsigned char *src, *src_end;
{
unsigned char c;
while (src < src_end)
{
c = *src++;
if ((c >= 0x80 && c < 0xA0) || c >= 0xE0)
{
if (src < src_end && *src++ < 0x40)
return 0;
}
}
return CODING_CATEGORY_MASK_SJIS;
}
int
detect_coding_big5 (src, src_end)
unsigned char *src, *src_end;
{
unsigned char c;
while (src < src_end)
{
c = *src++;
if (c >= 0xA1)
{
if (src >= src_end)
break;
c = *src++;
if (c < 0x40 || (c >= 0x7F && c <= 0xA0))
return 0;
}
}
return CODING_CATEGORY_MASK_BIG5;
}
int
decode_coding_sjis_big5 (coding, source, destination,
src_bytes, dst_bytes, sjis_p)
struct coding_system *coding;
unsigned char *source, *destination;
int src_bytes, dst_bytes;
int sjis_p;
{
unsigned char *src = source;
unsigned char *src_end = source + src_bytes;
unsigned char *dst = destination;
unsigned char *dst_end = destination + dst_bytes;
unsigned char *adjusted_dst_end = dst_end - 3;
Lisp_Object translation_table
= coding->translation_table_for_decode;
int result = CODING_FINISH_NORMAL;
if (!NILP (Venable_character_translation) && NILP (translation_table))
translation_table = Vstandard_translation_table_for_decode;
coding->produced_char = 0;
coding->fake_multibyte = 0;
while (src < src_end && (dst_bytes
? (dst < adjusted_dst_end)
: (dst < src - 3)))
{
unsigned char *src_base = src;
unsigned char c1 = *src++, c2, c3, c4;
if (c1 < 0x20)
{
if (c1 == '\r')
{
if (coding->eol_type == CODING_EOL_CRLF)
{
ONE_MORE_BYTE (c2);
if (c2 == '\n')
*dst++ = c2;
else if (coding->mode & CODING_MODE_INHIBIT_INCONSISTENT_EOL)
{
result = CODING_FINISH_INCONSISTENT_EOL;
goto label_end_of_loop_2;
}
else
*dst++ = c1, src--;
}
else if (coding->eol_type == CODING_EOL_CR)
*dst++ = '\n';
else
*dst++ = c1;
}
else if (c1 == '\n'
&& (coding->mode & CODING_MODE_INHIBIT_INCONSISTENT_EOL)
&& (coding->eol_type == CODING_EOL_CR
|| coding->eol_type == CODING_EOL_CRLF))
{
result = CODING_FINISH_INCONSISTENT_EOL;
goto label_end_of_loop_2;
}
else
*dst++ = c1;
coding->produced_char++;
}
else if (c1 < 0x80)
{
c2 = 0;
DECODE_SJIS_BIG5_CHARACTER (charset_ascii, c1, c2);
}
else
{
if (sjis_p)
{
if (c1 < 0xA0 || (c1 >= 0xE0 && c1 < 0xF0))
{
ONE_MORE_BYTE (c2);
if (c2 >= 0x40 && c2 != 0x7F && c2 <= 0xFC)
{
DECODE_SJIS (c1, c2, c3, c4);
DECODE_SJIS_BIG5_CHARACTER (charset_jisx0208, c3, c4);
}
else
goto label_invalid_code_2;
}
else if (c1 < 0xE0)
{
c2 = 0;
DECODE_SJIS_BIG5_CHARACTER (charset_katakana_jisx0201, c1,
c2);
}
else
goto label_invalid_code_1;
}
else
{
if (c1 >= 0xA1 && c1 <= 0xFE)
{
ONE_MORE_BYTE (c2);
if ((c2 >= 0x40 && c2 <= 0x7E) || (c2 >= 0xA1 && c2 <= 0xFE))
{
int charset;
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_1;
}
}
continue;
label_invalid_code_1:
*dst++ = c1;
coding->produced_char++;
coding->fake_multibyte = 1;
continue;
label_invalid_code_2:
*dst++ = c1; *dst++= c2;
coding->produced_char += 2;
coding->fake_multibyte = 1;
continue;
label_end_of_loop:
result = CODING_FINISH_INSUFFICIENT_SRC;
label_end_of_loop_2:
src = src_base;
break;
}
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)
{
src_bytes = src_end - src;
if (dst_bytes && (dst_end - dst < src_bytes))
src_bytes = dst_end - dst;
bcopy (dst, src, src_bytes);
src += src_bytes;
dst += src_bytes;
coding->fake_multibyte = 1;
}
}
coding->consumed = coding->consumed_char = src - source;
coding->produced = dst - destination;
return result;
}
int
encode_coding_sjis_big5 (coding, source, destination,
src_bytes, dst_bytes, sjis_p)
struct coding_system *coding;
unsigned char *source, *destination;
int src_bytes, dst_bytes;
int sjis_p;
{
unsigned char *src = source;
unsigned char *src_end = source + src_bytes;
unsigned char *dst = destination;
unsigned char *dst_end = destination + dst_bytes;
unsigned char *adjusted_dst_end = dst_end - 1;
Lisp_Object translation_table
= coding->translation_table_for_encode;
int result = CODING_FINISH_NORMAL;
if (!NILP (Venable_character_translation) && NILP (translation_table))
translation_table = Vstandard_translation_table_for_encode;
coding->consumed_char = 0;
coding->fake_multibyte = 0;
while (src < src_end && (dst_bytes
? (dst < adjusted_dst_end)
: (dst < src - 1)))
{
unsigned char *src_base = src;
unsigned char c1 = *src++, c2, c3, c4;
if (coding->composing)
{
if (c1 == 0xA0)
{
ONE_MORE_BYTE (c1);
c1 &= 0x7F;
}
else if (c1 >= 0xA0)
c1 -= 0x20;
else
coding->composing = 0;
}
switch (emacs_code_class[c1])
{
case EMACS_ascii_code:
ENCODE_SJIS_BIG5_CHARACTER (charset_ascii, c1, c2);
break;
case EMACS_control_code:
*dst++ = c1;
coding->consumed_char++;
break;
case EMACS_carriage_return_code:
if (! (coding->mode & CODING_MODE_SELECTIVE_DISPLAY))
{
*dst++ = c1;
coding->consumed_char++;
break;
}
case EMACS_linefeed_code:
if (coding->eol_type == CODING_EOL_LF
|| coding->eol_type == CODING_EOL_UNDECIDED)
*dst++ = '\n';
else if (coding->eol_type == CODING_EOL_CRLF)
*dst++ = '\r', *dst++ = '\n';
else
*dst++ = '\r';
coding->consumed_char++;
break;
case EMACS_leading_code_2:
ONE_MORE_BYTE (c2);
ENCODE_SJIS_BIG5_CHARACTER (c1, c2, c3);
break;
case EMACS_leading_code_3:
TWO_MORE_BYTES (c2, c3);
ENCODE_SJIS_BIG5_CHARACTER (c1, c2, c3);
break;
case EMACS_leading_code_4:
THREE_MORE_BYTES (c2, c3, c4);
ENCODE_SJIS_BIG5_CHARACTER (c2, c3, c4);
break;
case EMACS_leading_code_composition:
coding->composing = 1;
break;
default:
*dst++ = c1;
coding->consumed_char++;
}
continue;
label_end_of_loop:
result = CODING_FINISH_INSUFFICIENT_SRC;
src = src_base;
break;
}
if (result == CODING_FINISH_NORMAL
&& src < src_end)
result = CODING_FINISH_INSUFFICIENT_DST;
coding->consumed = src - source;
coding->produced = coding->produced_char = dst - destination;
return result;
}
int
detect_coding_ccl (src, src_end)
unsigned char *src, *src_end;
{
unsigned char *valid;
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;
}
int
decode_eol (coding, source, destination, src_bytes, dst_bytes)
struct coding_system *coding;
unsigned char *source, *destination;
int src_bytes, dst_bytes;
{
unsigned char *src = source;
unsigned char *src_end = source + src_bytes;
unsigned char *dst = destination;
unsigned char *dst_end = destination + dst_bytes;
unsigned char c;
int result = CODING_FINISH_NORMAL;
coding->fake_multibyte = 0;
if (src_bytes <= 0)
{
coding->produced = coding->produced_char = 0;
coding->consumed = coding->consumed_char = 0;
return result;
}
switch (coding->eol_type)
{
case CODING_EOL_CRLF:
{
unsigned char *adjusted_dst_end = dst_end - 1;
while (src < src_end && (dst_bytes
? (dst < adjusted_dst_end)
: (dst < src - 1)))
{
unsigned char *src_base = src;
c = *src++;
if (c == '\r')
{
ONE_MORE_BYTE (c);
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;
}
}
else if (c == '\n'
&& (coding->mode & CODING_MODE_INHIBIT_INCONSISTENT_EOL))
{
result = CODING_FINISH_INCONSISTENT_EOL;
goto label_end_of_loop_2;
}
else
{
*dst++ = c;
if (BASE_LEADING_CODE_P (c))
coding->fake_multibyte = 1;
}
continue;
label_end_of_loop:
result = CODING_FINISH_INSUFFICIENT_SRC;
label_end_of_loop_2:
src = src_base;
break;
}
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)
{
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;
case CODING_EOL_CR:
if (coding->mode & CODING_MODE_INHIBIT_INCONSISTENT_EOL)
{
while (src < src_end)
{
if ((c = *src++) == '\n')
break;
if (BASE_LEADING_CODE_P (c))
coding->fake_multibyte = 1;
}
if (*--src == '\n')
{
src_bytes = src - source;
result = CODING_FINISH_INCONSISTENT_EOL;
}
}
if (dst_bytes && src_bytes > dst_bytes)
{
result = CODING_FINISH_INSUFFICIENT_DST;
src_bytes = dst_bytes;
}
if (dst_bytes)
bcopy (source, destination, src_bytes);
else
safe_bcopy (source, destination, src_bytes);
src = source + src_bytes;
while (src_bytes--) if (*dst++ == '\r') dst[-1] = '\n';
break;
default:
if (dst_bytes && src_bytes > dst_bytes)
{
result = CODING_FINISH_INSUFFICIENT_DST;
src_bytes = dst_bytes;
}
if (dst_bytes)
bcopy (source, destination, src_bytes);
else
safe_bcopy (source, destination, src_bytes);
src += src_bytes;
dst += src_bytes;
coding->fake_multibyte = 1;
break;
}
coding->consumed = coding->consumed_char = src - source;
coding->produced = coding->produced_char = dst - destination;
return result;
}
int
encode_eol (coding, source, destination, src_bytes, dst_bytes)
struct coding_system *coding;
unsigned char *source, *destination;
int src_bytes, dst_bytes;
{
unsigned char *src = source;
unsigned char *dst = destination;
int result = CODING_FINISH_NORMAL;
coding->fake_multibyte = 0;
if (coding->eol_type == CODING_EOL_CRLF)
{
unsigned char c;
unsigned char *src_end = source + src_bytes;
unsigned char *dst_end = destination + dst_bytes;
unsigned char *adjusted_dst_end = dst_end - 1;
while (src < src_end && (dst_bytes
? (dst < adjusted_dst_end)
: (dst < src - 1)))
{
c = *src++;
if (c == '\n'
|| (c == '\r' && (coding->mode & CODING_MODE_SELECTIVE_DISPLAY)))
*dst++ = '\r', *dst++ = '\n';
else
{
*dst++ = c;
if (BASE_LEADING_CODE_P (c))
coding->fake_multibyte = 1;
}
}
if (src < src_end)
result = CODING_FINISH_INSUFFICIENT_DST;
}
else
{
unsigned char c;
if (dst_bytes && src_bytes > dst_bytes)
{
src_bytes = dst_bytes;
result = CODING_FINISH_INSUFFICIENT_DST;
}
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_CR)
{
while (src_bytes--)
{
if ((c = *dst++) == '\n')
dst[-1] = '\r';
else if (BASE_LEADING_CODE_P (c))
coding->fake_multibyte = 1;
}
}
else
{
if (coding->mode & CODING_MODE_SELECTIVE_DISPLAY)
{
while (src_bytes--)
if (*dst++ == '\r') dst[-1] = '\n';
}
coding->fake_multibyte = 1;
}
src = source + dst_bytes;
dst = destination + dst_bytes;
}
coding->consumed = coding->consumed_char = src - source;
coding->produced = coding->produced_char = dst - destination;
return result;
}
int
setup_coding_system (coding_system, coding)
Lisp_Object coding_system;
struct coding_system *coding;
{
Lisp_Object coding_spec, coding_type, eol_type, plist;
Lisp_Object val;
int i;
coding->symbol = coding_system;
coding->common_flags = 0;
coding->mode = 0;
coding->heading_ascii = -1;
coding->post_read_conversion = coding->pre_write_conversion = Qnil;
if (NILP (coding_system))
goto label_invalid_coding_system;
coding_spec = Fget (coding_system, Qcoding_system);
if (!VECTORP (coding_spec)
|| XVECTOR (coding_spec)->size != 5
|| !CONSP (XVECTOR (coding_spec)->contents[3]))
goto label_invalid_coding_system;
eol_type = inhibit_eol_conversion ? Qnil : Fget (coding_system, Qeol_type);
if (VECTORP (eol_type))
{
coding->eol_type = CODING_EOL_UNDECIDED;
coding->common_flags = CODING_REQUIRE_DETECTION_MASK;
}
else if (XFASTINT (eol_type) == 1)
{
coding->eol_type = CODING_EOL_CRLF;
coding->common_flags
= CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK;
}
else if (XFASTINT (eol_type) == 2)
{
coding->eol_type = CODING_EOL_CR;
coding->common_flags
= CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK;
}
else
coding->eol_type = CODING_EOL_LF;
coding_type = XVECTOR (coding_spec)->contents[0];
if (SYMBOLP (coding_type))
{
if (EQ (coding_type, Qt))
{
coding->type = coding_type_undecided;
coding->common_flags |= CODING_REQUIRE_DETECTION_MASK;
}
else
coding->type = coding_type_no_conversion;
return 0;
}
coding->composing = 0;
coding->composed_chars = 0;
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, Qtranslation_table_for_decode);
if (SYMBOLP (val))
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, Qtranslation_table_for_encode);
coding->translation_table_for_encode = CHAR_TABLE_P (val) ? val : Qnil;
val = Fplist_get (plist, Qcoding_category);
if (!NILP (val))
{
val = Fget (val, Qcoding_category_index);
if (INTEGERP (val))
coding->category_idx = XINT (val);
else
goto label_invalid_coding_system;
}
else
goto label_invalid_coding_system;
val = Fplist_get (plist, Qsafe_charsets);
if (EQ (val, Qt))
{
for (i = 0; i <= MAX_CHARSET; i++)
coding->safe_charsets[i] = 1;
}
else
{
bzero (coding->safe_charsets, MAX_CHARSET + 1);
while (CONSP (val))
{
if ((i = get_charset_id (XCONS (val)->car)) >= 0)
coding->safe_charsets[i] = 1;
val = XCONS (val)->cdr;
}
}
switch (XFASTINT (coding_type))
{
case 0:
coding->type = coding_type_emacs_mule;
if (!NILP (coding->post_read_conversion))
coding->common_flags |= CODING_REQUIRE_DECODING_MASK;
if (!NILP (coding->pre_write_conversion))
coding->common_flags |= CODING_REQUIRE_ENCODING_MASK;
break;
case 1:
coding->type = coding_type_sjis;
coding->common_flags
|= CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK;
break;
case 2:
coding->type = coding_type_iso2022;
coding->common_flags
|= CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK;
{
Lisp_Object val, temp;
Lisp_Object *flags;
int i, charset, reg_bits = 0;
val = XVECTOR (coding_spec)->contents[4];
if (!VECTORP (val) || XVECTOR (val)->size != 32)
goto label_invalid_coding_system;
flags = XVECTOR (val)->contents;
coding->flags
= ((NILP (flags[4]) ? 0 : CODING_FLAG_ISO_SHORT_FORM)
| (NILP (flags[5]) ? 0 : CODING_FLAG_ISO_RESET_AT_EOL)
| (NILP (flags[6]) ? 0 : CODING_FLAG_ISO_RESET_AT_CNTL)
| (NILP (flags[7]) ? 0 : CODING_FLAG_ISO_SEVEN_BITS)
| (NILP (flags[8]) ? 0 : CODING_FLAG_ISO_LOCKING_SHIFT)
| (NILP (flags[9]) ? 0 : CODING_FLAG_ISO_SINGLE_SHIFT)
| (NILP (flags[10]) ? 0 : CODING_FLAG_ISO_USE_ROMAN)
| (NILP (flags[11]) ? 0 : CODING_FLAG_ISO_USE_OLDJIS)
| (NILP (flags[12]) ? 0 : CODING_FLAG_ISO_NO_DIRECTION)
| (NILP (flags[13]) ? 0 : CODING_FLAG_ISO_INIT_AT_BOL)
| (NILP (flags[14]) ? 0 : CODING_FLAG_ISO_DESIGNATE_AT_BOL)
| (NILP (flags[15]) ? 0 : CODING_FLAG_ISO_SAFE)
| (NILP (flags[16]) ? 0 : CODING_FLAG_ISO_LATIN_EXTRA)
);
CODING_SPEC_ISO_INVOCATION (coding, 0) = 0;
CODING_SPEC_ISO_INVOCATION (coding, 1)
= (coding->flags & CODING_FLAG_ISO_SEVEN_BITS ? -1 : 1);
CODING_SPEC_ISO_SINGLE_SHIFTING (coding) = 0;
CODING_SPEC_ISO_BOL (coding) = 1;
for (charset = 0; charset <= MAX_CHARSET; charset++)
CODING_SPEC_ISO_REVISION_NUMBER (coding, charset) = 255;
val = Vcharset_revision_alist;
while (CONSP (val))
{
charset = get_charset_id (Fcar_safe (XCONS (val)->car));
if (charset >= 0
&& (temp = Fcdr_safe (XCONS (val)->car), INTEGERP (temp))
&& (i = XINT (temp), (i >= 0 && (i + '@') < 128)))
CODING_SPEC_ISO_REVISION_NUMBER (coding, charset) = i;
val = XCONS (val)->cdr;
}
for (charset = 0; charset <= MAX_CHARSET; charset++)
CODING_SPEC_ISO_REQUESTED_DESIGNATION (coding, charset)
= CODING_SPEC_ISO_NO_REQUESTED_DESIGNATION;
for (i = 0; i < 4; i++)
{
if (INTEGERP (flags[i])
&& (charset = XINT (flags[i]), CHARSET_VALID_P (charset))
|| (charset = get_charset_id (flags[i])) >= 0)
{
CODING_SPEC_ISO_INITIAL_DESIGNATION (coding, i) = charset;
CODING_SPEC_ISO_REQUESTED_DESIGNATION (coding, charset) = i;
}
else if (EQ (flags[i], Qt))
{
CODING_SPEC_ISO_INITIAL_DESIGNATION (coding, i) = -1;
reg_bits |= 1 << i;
coding->flags |= CODING_FLAG_ISO_DESIGNATION;
}
else if (CONSP (flags[i]))
{
Lisp_Object tail;
tail = flags[i];
coding->flags |= CODING_FLAG_ISO_DESIGNATION;
if (INTEGERP (XCONS (tail)->car)
&& (charset = XINT (XCONS (tail)->car),
CHARSET_VALID_P (charset))
|| (charset = get_charset_id (XCONS (tail)->car)) >= 0)
{
CODING_SPEC_ISO_INITIAL_DESIGNATION (coding, i) = charset;
CODING_SPEC_ISO_REQUESTED_DESIGNATION (coding, charset) =i;
}
else
CODING_SPEC_ISO_INITIAL_DESIGNATION (coding, i) = -1;
tail = XCONS (tail)->cdr;
while (CONSP (tail))
{
if (INTEGERP (XCONS (tail)->car)
&& (charset = XINT (XCONS (tail)->car),
CHARSET_VALID_P (charset))
|| (charset = get_charset_id (XCONS (tail)->car)) >= 0)
CODING_SPEC_ISO_REQUESTED_DESIGNATION (coding, charset)
= i;
else if (EQ (XCONS (tail)->car, Qt))
reg_bits |= 1 << i;
tail = XCONS (tail)->cdr;
}
}
else
CODING_SPEC_ISO_INITIAL_DESIGNATION (coding, i) = -1;
CODING_SPEC_ISO_DESIGNATION (coding, i)
= CODING_SPEC_ISO_INITIAL_DESIGNATION (coding, i);
}
if (reg_bits && ! (coding->flags & CODING_FLAG_ISO_LOCKING_SHIFT))
{
if (coding->flags & CODING_FLAG_ISO_SEVEN_BITS)
reg_bits &= ~2;
if (! (coding->flags & CODING_FLAG_ISO_SINGLE_SHIFT))
reg_bits &= 3;
}
if (reg_bits)
for (charset = 0; charset <= MAX_CHARSET; charset++)
{
if (CHARSET_VALID_P (charset))
{
if (CHARSET_CHARS (charset) == 96)
CODING_SPEC_ISO_REQUESTED_DESIGNATION (coding, charset)
= (reg_bits & 2
? 1 : (reg_bits & 4 ? 2 : (reg_bits & 8 ? 3 : 0)));
else
CODING_SPEC_ISO_REQUESTED_DESIGNATION (coding, charset)
= (reg_bits & 1
? 0 : (reg_bits & 2 ? 1 : (reg_bits & 4 ? 2 : 3)));
}
}
}
coding->common_flags |= CODING_REQUIRE_FLUSHING_MASK;
coding->spec.iso2022.last_invalid_designation_register = -1;
break;
case 3:
coding->type = coding_type_big5;
coding->common_flags
|= CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK;
coding->flags
= (NILP (XVECTOR (coding_spec)->contents[4])
? CODING_FLAG_BIG5_HKU
: CODING_FLAG_BIG5_ETEN);
break;
case 4:
coding->type = coding_type_ccl;
coding->common_flags
|= CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK;
{
Lisp_Object val;
Lisp_Object decoder, encoder;
val = XVECTOR (coding_spec)->contents[4];
if (CONSP (val)
&& 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), 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;
case 5:
coding->type = coding_type_raw_text;
break;
default:
goto label_invalid_coding_system;
}
return 0;
label_invalid_coding_system:
coding->type = coding_type_no_conversion;
coding->category_idx = CODING_CATEGORY_IDX_BINARY;
coding->common_flags = 0;
coding->eol_type = CODING_EOL_LF;
coding->pre_write_conversion = coding->post_read_conversion = Qnil;
return -1;
}
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];
}
setup_coding_system (coding->symbol, coding);
}
return;
}
static
int ascii_skip_code[256];
static int
detect_coding_mask (source, src_bytes, priorities, skip)
unsigned char *source;
int src_bytes, *priorities, *skip;
{
register unsigned char c;
unsigned char *src = source, *src_end = source + src_bytes;
unsigned int mask;
int i;
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 && ascii_skip_code[*src]) src++;
*skip = src - source;
if (src >= src_end)
return 0;
c = *src;
if (c < 0x80)
{
mask = detect_coding_iso2022 (src, src_end);
if (mask == 0)
{
src++;
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)
goto label_return_highest_only;
}
else
{
int try;
if (c < 0xA0)
{
try = CODING_CATEGORY_MASK_SJIS | CODING_CATEGORY_MASK_EMACS_MULE;
if ((VECTORP (Vlatin_extra_code_table)
&& !NILP (XVECTOR (Vlatin_extra_code_table)->contents[c]))
|| (c == ISO_CODE_SS2 || c == ISO_CODE_SS3)
|| (c == ISO_CODE_CSI
&& (src < src_end
&& (*src == ']'
|| ((*src == '0' || *src == '1' || *src == '2')
&& src + 1 < src_end
&& src[1] == ']')))))
try |= (CODING_CATEGORY_MASK_ISO_8_ELSE
| CODING_CATEGORY_MASK_ISO_8BIT);
}
else
try = (CODING_CATEGORY_MASK_ISO_8_ELSE
| CODING_CATEGORY_MASK_ISO_8BIT
| CODING_CATEGORY_MASK_SJIS
| CODING_CATEGORY_MASK_BIG5);
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++)
{
if (priorities[i] & try & CODING_CATEGORY_MASK_ISO)
mask = detect_coding_iso2022 (src, src_end);
else if (priorities[i] & try & CODING_CATEGORY_MASK_SJIS)
mask = detect_coding_sjis (src, src_end);
else if (priorities[i] & try & CODING_CATEGORY_MASK_BIG5)
mask = detect_coding_big5 (src, src_end);
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;
}
return CODING_CATEGORY_MASK_RAW_TEXT;
}
if (try & CODING_CATEGORY_MASK_ISO)
mask |= detect_coding_iso2022 (src, src_end);
if (try & CODING_CATEGORY_MASK_SJIS)
mask |= detect_coding_sjis (src, src_end);
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);
if (try & CODING_CATEGORY_MASK_CCL)
mask |= detect_coding_ccl (src, src_end);
}
return (mask | CODING_CATEGORY_MASK_RAW_TEXT | CODING_CATEGORY_MASK_BINARY);
label_return_highest_only:
for (i = 0; i < CODING_CATEGORY_IDX_MAX; i++)
{
if (mask & priorities[i])
return priorities[i];
}
return CODING_CATEGORY_MASK_RAW_TEXT;
}
void
detect_coding (coding, src, src_bytes)
struct coding_system *coding;
unsigned char *src;
int src_bytes;
{
unsigned int idx;
int skip, mask, i;
Lisp_Object val;
val = Vcoding_category_list;
mask = detect_coding_mask (src, src_bytes, coding_priorities, &skip);
coding->heading_ascii = skip;
if (!mask) return;
idx = 0;
while (mask && ! (mask & 1)) mask >>= 1, idx++;
if (! mask)
idx = CODING_CATEGORY_IDX_RAW_TEXT;
val = XSYMBOL (XVECTOR (Vcoding_category_table)->contents[idx])->value;
if (coding->eol_type != CODING_EOL_UNDECIDED)
{
Lisp_Object tmp;
tmp = Fget (val, Qeol_type);
if (VECTORP (tmp))
val = XVECTOR (tmp)->contents[coding->eol_type];
}
setup_coding_system (val, coding);
coding->heading_ascii = skip;
}
#define MAX_EOL_CHECK_COUNT 3
static int
detect_eol_type (source, src_bytes, skip)
unsigned char *source;
int src_bytes, *skip;
{
unsigned char *src = source, *src_end = src + src_bytes;
unsigned char c;
int total = 0;
int eol_type = CODING_EOL_UNDECIDED;
int this_eol_type;
*skip = 0;
while (src < src_end && total < MAX_EOL_CHECK_COUNT)
{
c = *src++;
if (c == '\n' || c == '\r')
{
if (*skip == 0)
*skip = src - 1 - source;
total++;
if (c == '\n')
this_eol_type = CODING_EOL_LF;
else if (src >= src_end || *src != '\n')
this_eol_type = CODING_EOL_CR;
else
this_eol_type = CODING_EOL_CRLF, src++;
if (eol_type == CODING_EOL_UNDECIDED)
eol_type = this_eol_type;
else if (eol_type != this_eol_type)
{
eol_type = CODING_EOL_INCONSISTENT;
break;
}
}
}
if (*skip == 0)
*skip = src_end - source;
return eol_type;
}
void
detect_eol (coding, src, src_bytes)
struct coding_system *coding;
unsigned char *src;
int src_bytes;
{
Lisp_Object val;
int skip;
int eol_type = detect_eol_type (src, src_bytes, &skip);
if (coding->heading_ascii > skip)
coding->heading_ascii = skip;
else
skip = coding->heading_ascii;
if (eol_type == CODING_EOL_UNDECIDED)
return;
if (eol_type == CODING_EOL_INCONSISTENT)
{
#if 0
if (coding->type == coding_type_raw_text)
{
setup_coding_system (Qno_conversion, coding);
return;
}
#endif
eol_type = CODING_EOL_LF;
}
val = Fget (coding->symbol, Qeol_type);
if (VECTORP (val) && XVECTOR (val)->size == 3)
{
setup_coding_system (XVECTOR (val)->contents[eol_type], coding);
coding->heading_ascii = skip;
}
}
#define CONVERSION_BUFFER_EXTRA_ROOM 256
#define DECODING_BUFFER_MAG(coding) \
(coding->type == coding_type_iso2022 \
? 3 \
: ((coding->type == coding_type_sjis || coding->type == coding_type_big5) \
? 2 \
: (coding->type == coding_type_raw_text \
? 1 \
: (coding->type == coding_type_ccl \
? coding->spec.ccl.decoder.buf_magnification \
: 2))))
int
decoding_buffer_size (coding, src_bytes)
struct coding_system *coding;
int src_bytes;
{
return (src_bytes * DECODING_BUFFER_MAG (coding)
+ CONVERSION_BUFFER_EXTRA_ROOM);
}
int
encoding_buffer_size (coding, src_bytes)
struct coding_system *coding;
int src_bytes;
{
int magnification;
if (coding->type == coding_type_ccl)
magnification = coding->spec.ccl.encoder.buf_magnification;
else
magnification = 3;
return (src_bytes * magnification + CONVERSION_BUFFER_EXTRA_ROOM);
}
#ifndef MINIMUM_CONVERSION_BUFFER_SIZE
#define MINIMUM_CONVERSION_BUFFER_SIZE 1024
#endif
char *conversion_buffer;
int conversion_buffer_size;
char *
get_conversion_buffer (size)
int size;
{
if (size > conversion_buffer_size)
{
char *buf;
int real_size = conversion_buffer_size * 2;
while (real_size < size) real_size *= 2;
buf = (char *) xmalloc (real_size);
xfree (conversion_buffer);
conversion_buffer = buf;
conversion_buffer_size = real_size;
}
return conversion_buffer;
}
int
ccl_coding_driver (coding, source, destination, src_bytes, dst_bytes, encodep)
struct coding_system *coding;
unsigned char *source, *destination;
int src_bytes, dst_bytes, encodep;
{
struct ccl_program *ccl
= 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));
coding->produced_char
= (encodep
? coding->produced
: 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:
result = CODING_FINISH_INSUFFICIENT_SRC;
break;
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;
}
return result;
}
int
decode_coding (coding, source, destination, src_bytes, dst_bytes)
struct coding_system *coding;
unsigned char *source, *destination;
int src_bytes, dst_bytes;
{
int result;
if (src_bytes <= 0
&& coding->type != coding_type_ccl
&& ! (coding->mode & CODING_MODE_LAST_BLOCK
&& CODING_REQUIRE_FLUSHING (coding)))
{
coding->produced = coding->produced_char = 0;
coding->consumed = coding->consumed_char = 0;
coding->fake_multibyte = 0;
return CODING_FINISH_NORMAL;
}
if (coding->type == coding_type_undecided)
detect_coding (coding, source, src_bytes);
if (coding->eol_type == CODING_EOL_UNDECIDED)
detect_eol (coding, source, src_bytes);
switch (coding->type)
{
case coding_type_emacs_mule:
case coding_type_undecided:
case coding_type_raw_text:
if (coding->eol_type == CODING_EOL_LF
|| coding->eol_type == CODING_EOL_UNDECIDED)
goto label_no_conversion;
result = decode_eol (coding, source, destination, src_bytes, dst_bytes);
break;
case coding_type_sjis:
result = decode_coding_sjis_big5 (coding, source, destination,
src_bytes, dst_bytes, 1);
break;
case coding_type_iso2022:
result = decode_coding_iso2022 (coding, source, destination,
src_bytes, dst_bytes);
break;
case coding_type_big5:
result = decode_coding_sjis_big5 (coding, source, destination,
src_bytes, dst_bytes, 0);
break;
case coding_type_ccl:
result = ccl_coding_driver (coding, source, destination,
src_bytes, dst_bytes, 0);
break;
default:
label_no_conversion:
if (dst_bytes && src_bytes > dst_bytes)
{
coding->produced = dst_bytes;
result = CODING_FINISH_INSUFFICIENT_DST;
}
else
{
coding->produced = src_bytes;
result = CODING_FINISH_NORMAL;
}
if (dst_bytes)
bcopy (source, destination, coding->produced);
else
safe_bcopy (source, destination, coding->produced);
coding->fake_multibyte = 1;
coding->consumed
= coding->consumed_char = coding->produced_char = coding->produced;
break;
}
return result;
}
int
encode_coding (coding, source, destination, src_bytes, dst_bytes)
struct coding_system *coding;
unsigned char *source, *destination;
int src_bytes, dst_bytes;
{
int result;
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;
coding->fake_multibyte = 0;
return CODING_FINISH_NORMAL;
}
switch (coding->type)
{
case coding_type_emacs_mule:
case coding_type_undecided:
case coding_type_raw_text:
if (coding->eol_type == CODING_EOL_LF
|| coding->eol_type == CODING_EOL_UNDECIDED)
goto label_no_conversion;
result = encode_eol (coding, source, destination, src_bytes, dst_bytes);
break;
case coding_type_sjis:
result = encode_coding_sjis_big5 (coding, source, destination,
src_bytes, dst_bytes, 1);
break;
case coding_type_iso2022:
result = encode_coding_iso2022 (coding, source, destination,
src_bytes, dst_bytes);
break;
case coding_type_big5:
result = encode_coding_sjis_big5 (coding, source, destination,
src_bytes, dst_bytes, 0);
break;
case coding_type_ccl:
result = ccl_coding_driver (coding, source, destination,
src_bytes, dst_bytes, 1);
break;
default:
label_no_conversion:
if (dst_bytes && src_bytes > dst_bytes)
{
coding->produced = dst_bytes;
result = CODING_FINISH_INSUFFICIENT_DST;
}
else
{
coding->produced = src_bytes;
result = CODING_FINISH_NORMAL;
}
if (dst_bytes)
bcopy (source, destination, coding->produced);
else
safe_bcopy (source, destination, coding->produced);
if (coding->mode & CODING_MODE_SELECTIVE_DISPLAY)
{
unsigned char *p = destination, *pend = p + coding->produced;
while (p < pend)
if (*p++ == '\015') p[-1] = '\n';
}
coding->fake_multibyte = 1;
coding->consumed
= coding->consumed_char = coding->produced_char = coding->produced;
break;
}
return result;
}
static void
shrink_decoding_region (beg, end, coding, str)
int *beg, *end;
struct coding_system *coding;
unsigned char *str;
{
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
|| !NILP (coding->post_read_conversion))
{
return;
}
else if (coding->type == coding_type_no_conversion)
{
return;
}
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)
return;
}
eol_conversion = (coding->eol_type != CODING_EOL_LF);
if ((! eol_conversion) && (coding->heading_ascii >= 0))
*beg += coding->heading_ascii;
if (str)
{
begp_orig = begp = str + *beg;
endp_orig = endp = str + *end;
}
else
{
begp_orig = begp = BYTE_POS_ADDR (*beg);
endp_orig = endp = begp + *end - *beg;
}
switch (coding->type)
{
case coding_type_emacs_mule:
case coding_type_raw_text:
if (eol_conversion)
{
if (coding->heading_ascii < 0)
while (begp < endp && *begp != '\r' && *begp < 0x80) begp++;
while (begp < endp && endp[-1] != '\r' && endp[-1] < 0x80)
endp--;
if (begp < endp && endp < endp_orig && endp[-1] == '\r' && endp[0] == '\n')
endp++;
}
else
begp = endp;
break;
case coding_type_sjis:
case coding_type_big5:
if (coding->heading_ascii < 0)
{
if (eol_conversion)
while (begp < endp && *begp < 0x80 && *begp != '\r') begp++;
else
while (begp < endp && *begp < 0x80) begp++;
}
if (eol_conversion)
while (begp < endp && endp[-1] < 0x80 && endp[-1] != '\r') endp--;
else
while (begp < endp && endp[-1] < 0x80) endp--;
if (begp < endp && endp < endp_orig && endp[-1] == '\r' && endp[0] == '\n')
endp++;
if (begp < endp && endp < endp_orig && endp[-1] >= 0x80)
endp++;
break;
default:
if (CODING_SPEC_ISO_INITIAL_DESIGNATION (coding, 0) != CHARSET_ASCII)
break;
if (coding->heading_ascii < 0)
{
while (begp < endp && (c = *begp) < 0x80
&& c != ISO_CODE_CR && c != ISO_CODE_SO
&& c != ISO_CODE_SI && c != ISO_CODE_ESC
&& (!eol_conversion || c != ISO_CODE_LF))
begp++;
}
switch (coding->category_idx)
{
case CODING_CATEGORY_IDX_ISO_8_1:
case CODING_CATEGORY_IDX_ISO_8_2:
if (eol_conversion)
while (begp < endp && (c = endp[-1]) < 0x80 && c != '\r') endp--;
else
while (begp < endp && endp[-1] < 0x80) endp--;
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:
{
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--;
}
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')
endp = eight_bit ? eight_bit : endp + 2;
else
endp = endp_orig;
}
else if (eight_bit)
endp = eight_bit;
}
}
}
*beg += begp - begp_orig;
*end += endp - endp_orig;
return;
}
static void
shrink_encoding_region (beg, end, coding, str)
int *beg, *end;
struct coding_system *coding;
unsigned char *str;
{
unsigned char *begp_orig, *begp, *endp_orig, *endp;
int eol_conversion;
Lisp_Object translation_table;
if (coding->type == coding_type_ccl)
return;
else if (coding->type == coding_type_no_conversion)
{
*beg = *end;
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)
return;
}
if (str)
{
begp_orig = begp = str + *beg;
endp_orig = endp = str + *end;
}
else
{
begp_orig = begp = BYTE_POS_ADDR (*beg);
endp_orig = endp = begp + *end - *beg;
}
eol_conversion = (coding->eol_type == CODING_EOL_CR
|| coding->eol_type == CODING_EOL_CRLF);
switch (coding->type)
{
case coding_type_undecided:
case coding_type_emacs_mule:
case coding_type_raw_text:
if (eol_conversion)
{
while (begp < endp && *begp != '\n') begp++;
while (begp < endp && endp[-1] != '\n') endp--;
}
else
begp = endp;
break;
case coding_type_iso2022:
if (CODING_SPEC_ISO_INITIAL_DESIGNATION (coding, 0) != CHARSET_ASCII)
break;
if (coding->flags & CODING_FLAG_ISO_DESIGNATE_AT_BOL)
{
unsigned char *bol = begp;
while (begp < endp && *begp < 0x80)
{
begp++;
if (begp[-1] == '\n')
bol = begp;
}
begp = bol;
goto label_skip_tail;
}
default:
if (eol_conversion)
while (begp < endp && *begp < 0x80 && *begp != '\n') begp++;
else
while (begp < endp && *begp < 0x80) begp++;
label_skip_tail:
if (eol_conversion)
while (begp < endp && endp[-1] < 0x80 && endp[-1] != '\n') endp--;
else
while (begp < endp && *(endp - 1) < 0x80) endp--;
break;
}
*beg += begp - begp_orig;
*end += endp - endp_orig;
return;
}
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)
int
code_convert_region (from, from_byte, to, to_byte, coding, encodep, replace)
int from, from_byte, to, to_byte, encodep, replace;
struct coding_system *coding;
{
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;
int multibyte = !NILP (current_buffer->enable_multibyte_characters);
int first = 1;
int fake_multibyte = 0;
unsigned char *src, *dst;
Lisp_Object deletion;
int orig_point = PT, orig_len = len;
int prev_Z;
deletion = Qnil;
saved_coding_symbol = Qnil;
if (from < PT && PT < to)
{
TEMP_SET_PT_BOTH (from, from_byte);
orig_point = from;
}
if (replace)
{
int saved_from = from;
prepare_to_modify_buffer (from, to, &from);
if (saved_from != from)
{
to = from + len;
if (multibyte)
from_byte = CHAR_TO_BYTE (from), to_byte = CHAR_TO_BYTE (to);
else
from_byte = from, to_byte = to;
len_byte = to_byte - from_byte;
}
}
if (! encodep && CODING_REQUIRE_DETECTION (coding))
{
if (from < GPT && to > GPT)
move_gap_both (from, from_byte);
if (coding->type == coding_type_undecided)
{
detect_coding (coding, BYTE_POS_ADDR (from_byte), len_byte);
if (coding->type == coding_type_undecided)
coding->type = coding_type_emacs_mule;
}
if (coding->eol_type == CODING_EOL_UNDECIDED)
{
saved_coding_symbol = coding->symbol;
detect_eol (coding, BYTE_POS_ADDR (from_byte), len_byte);
if (coding->eol_type == CODING_EOL_UNDECIDED)
coding->eol_type = CODING_EOL_LF;
coding->mode |= CODING_MODE_INHIBIT_INCONSISTENT_EOL;
}
}
coding->consumed_char = len, coding->consumed = len_byte;
if (encodep
? ! CODING_REQUIRE_ENCODING (coding)
: ! CODING_REQUIRE_DECODING (coding))
{
coding->produced = len_byte;
if (multibyte
&& ! replace
&& coding->heading_ascii < len_byte)
{
if (from < GPT && GPT < to)
move_gap_both (to, to_byte);
len = multibyte_chars_in_text (BYTE_POS_ADDR (from_byte), len_byte);
adjust_after_insert (from, from_byte, to, to_byte, len);
coding->produced_char = len;
}
else
{
if (!replace)
adjust_after_insert (from, from_byte, to, to_byte, len_byte);
coding->produced_char = len_byte;
}
return 0;
}
if (encodep
&& ! NILP (coding->pre_write_conversion)
&& SYMBOLP (coding->pre_write_conversion)
&& ! NILP (Ffboundp (coding->pre_write_conversion)))
{
struct buffer *prev = current_buffer;
Lisp_Object new;
call2 (coding->pre_write_conversion,
make_number (from), make_number (to));
if (current_buffer != prev)
{
len = ZV - BEGV;
new = Fcurrent_buffer ();
set_buffer_internal_1 (prev);
del_range_2 (from, from_byte, to, to_byte);
TEMP_SET_PT_BOTH (from, from_byte);
insert_from_buffer (XBUFFER (new), 1, len, 0);
Fkill_buffer (new);
if (orig_point >= to)
orig_point += len - orig_len;
else if (orig_point > from)
orig_point = from;
orig_len = len;
to = from + len;
from_byte = multibyte ? CHAR_TO_BYTE (from) : from_byte;
to_byte = multibyte ? CHAR_TO_BYTE (to) : to;
len_byte = to_byte - from_byte;
TEMP_SET_PT_BOTH (from, from_byte);
}
}
if (replace)
deletion = make_buffer_string_both (from, from_byte, to, to_byte, 1);
{
int from_byte_orig = from_byte, to_byte_orig = to_byte;
if (from < GPT && GPT < to)
move_gap_both (from, from_byte);
SHRINK_CONVERSION_REGION (&from_byte, &to_byte, coding, NULL, encodep);
if (from_byte == to_byte
&& coding->type != coding_type_ccl
&& ! (coding->mode & CODING_MODE_LAST_BLOCK
&& CODING_REQUIRE_FLUSHING (coding)))
{
coding->produced = len_byte;
coding->produced_char = multibyte ? len : len_byte;
if (!replace)
adjust_after_insert (from, from_byte_orig, to, to_byte_orig, len);
return 0;
}
head_skip = from_byte - from_byte_orig;
tail_skip = to_byte_orig - to_byte;
total_skip = head_skip + tail_skip;
from += head_skip;
to -= tail_skip;
len -= total_skip; len_byte -= total_skip;
}
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;
}
require = 2000;
if (GAP_SIZE < require)
make_gap (require - GAP_SIZE);
move_gap_both (from, from_byte);
inserted = inserted_byte = 0;
src = GAP_END_ADDR, dst = GPT_ADDR;
GAP_SIZE += len_byte;
ZV -= len;
Z -= len;
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;
if (encodep)
result = encode_coding (coding, src, dst, len_byte, 0);
else
result = decode_coding (coding, src, dst, len_byte, 0);
if (coding->fake_multibyte)
fake_multibyte = 1;
if (!encodep && !multibyte)
coding->produced_char = coding->produced;
inserted += coding->produced_char;
inserted_byte += coding->produced;
len_byte -= coding->consumed;
src += coding->consumed;
dst += coding->produced;
if (result == CODING_FINISH_NORMAL)
{
src += len_byte;
break;
}
if (! encodep && result == CODING_FINISH_INCONSISTENT_EOL)
{
unsigned char *pend = dst, *p = pend - inserted_byte;
Lisp_Object eol_type;
if (coding->eol_type == CODING_EOL_CR)
{
while (p < pend) if (*p++ == '\n') p[-1] = '\r';
}
else
{
int count = 0;
while (p < pend) if (*p++ == '\n') count++;
if (src - dst < count)
{
int add = len_byte + inserted_byte;
GAP_SIZE -= add;
ZV += add; Z += add; ZV_BYTE += add; Z_BYTE += add;
GPT += inserted_byte; GPT_BYTE += inserted_byte;
make_gap (count - GAP_SIZE);
GAP_SIZE += add;
ZV -= add; Z -= add; ZV_BYTE -= add; Z_BYTE -= add;
GPT -= inserted_byte; GPT_BYTE -= inserted_byte;
src = GAP_END_ADDR - len_byte;
dst = GPT_ADDR + inserted_byte;
pend = dst;
}
inserted += count;
inserted_byte += count;
coding->produced += count;
p = dst = pend + count;
while (count)
{
*--p = *--pend;
if (*p == '\n') count--, *--p = '\r';
}
}
coding->eol_type = CODING_EOL_LF;
eol_type = Fget (saved_coding_symbol, Qeol_type);
if (VECTORP (eol_type)
&& XVECTOR (eol_type)->size == 3
&& SYMBOLP (XVECTOR (eol_type)->contents[CODING_EOL_LF]))
coding->symbol = XVECTOR (eol_type)->contents[CODING_EOL_LF];
else
coding->symbol = saved_coding_symbol;
continue;
}
if (len_byte <= 0)
{
if (coding->type != coding_type_ccl
|| coding->mode & CODING_MODE_LAST_BLOCK)
break;
coding->mode |= CODING_MODE_LAST_BLOCK;
continue;
}
if (result == CODING_FINISH_INSUFFICIENT_SRC)
{
inserted += len_byte;
inserted_byte += len_byte;
while (len_byte--)
*dst++ = *src++;
fake_multibyte = 1;
break;
}
if (result == CODING_FINISH_INTERRUPT)
{
fake_multibyte = 1;
break;
}
if (coding->consumed < 1)
{
fake_multibyte = 1;
break;
}
if (first)
{
float ratio = coding->produced - coding->consumed;
ratio /= coding->consumed;
require = len_byte * ratio;
first = 0;
}
if ((src - dst) < (require + 2000))
{
int add = len_byte + inserted_byte;
GAP_SIZE -= add;
ZV += add; Z += add; ZV_BYTE += add; Z_BYTE += add;
GPT += inserted_byte; GPT_BYTE += inserted_byte;
make_gap (require + 2000);
GAP_SIZE += add;
ZV -= add; Z -= add; ZV_BYTE -= add; Z_BYTE -= add;
GPT -= inserted_byte; GPT_BYTE -= inserted_byte;
src = GAP_END_ADDR - len_byte;
dst = GPT_ADDR + inserted_byte;
}
}
if (src - dst > 0) *dst = 0;
if (multibyte
&& (encodep
|| fake_multibyte
|| (to - from) != (to_byte - from_byte)))
inserted = multibyte_chars_in_text (GPT_ADDR, inserted_byte);
if (total_skip > 0)
{
if (tail_skip > 0)
safe_bcopy (GAP_END_ADDR, GPT_ADDR + inserted_byte, tail_skip);
inserted += total_skip; inserted_byte += total_skip;
GAP_SIZE += total_skip;
GPT -= head_skip; GPT_BYTE -= head_skip;
ZV -= total_skip; ZV_BYTE -= total_skip;
Z -= total_skip; Z_BYTE -= total_skip;
from -= head_skip; from_byte -= head_skip;
to += tail_skip; to_byte += tail_skip;
}
prev_Z = Z;
adjust_after_replace (from, from_byte, deletion, inserted, inserted_byte);
inserted = Z - prev_Z;
if (! encodep && ! NILP (coding->post_read_conversion))
{
Lisp_Object val;
if (from != PT)
TEMP_SET_PT_BOTH (from, from_byte);
prev_Z = Z;
val = call1 (coding->post_read_conversion, make_number (inserted));
CHECK_NUMBER (val, 0);
inserted += Z - prev_Z;
}
if (orig_point >= from)
{
if (orig_point >= from + orig_len)
orig_point += inserted - orig_len;
else
orig_point = from;
TEMP_SET_PT (orig_point);
}
signal_after_change (from, to - from, inserted);
{
coding->consumed = to_byte - from_byte;
coding->consumed_char = to - from;
coding->produced = inserted_byte;
coding->produced_char = inserted;
}
return 0;
}
Lisp_Object
code_convert_string (str, coding, encodep, nocopy)
Lisp_Object str;
struct coding_system *coding;
int encodep, nocopy;
{
int len;
char *buf;
int from = 0, to = XSTRING (str)->size;
int to_byte = STRING_BYTES (XSTRING (str));
struct gcpro gcpro1;
Lisp_Object saved_coding_symbol;
int result;
saved_coding_symbol = Qnil;
if (encodep && !NILP (coding->pre_write_conversion)
|| !encodep && !NILP (coding->post_read_conversion))
{
int count = specpdl_ptr - specpdl;
struct buffer *prev = current_buffer;
record_unwind_protect (Fset_buffer, Fcurrent_buffer ());
GCPRO1 (str);
temp_output_buffer_setup (" *code-converting-work*");
UNGCPRO;
set_buffer_internal (XBUFFER (Vstandard_output));
if (encodep)
insert_from_string (str, 0, 0, to, to_byte, 0);
else
{
current_buffer->enable_multibyte_characters = Qnil;
insert_from_string (str, 0, 0, to_byte, to_byte, 0);
current_buffer->enable_multibyte_characters = Qt;
}
code_convert_region (BEGV, BEGV_BYTE, ZV, ZV_BYTE, coding, encodep, 1);
if (encodep)
current_buffer->enable_multibyte_characters = Qnil;
str = make_buffer_string (BEGV, ZV, 0);
set_buffer_internal (prev);
return unbind_to (count, str);
}
if (! encodep && CODING_REQUIRE_DETECTION (coding))
{
if (coding->type == coding_type_undecided)
{
detect_coding (coding, XSTRING (str)->data, to_byte);
if (coding->type == coding_type_undecided)
coding->type = coding_type_emacs_mule;
}
if (coding->eol_type == CODING_EOL_UNDECIDED)
{
saved_coding_symbol = coding->symbol;
detect_eol (coding, XSTRING (str)->data, to_byte);
if (coding->eol_type == CODING_EOL_UNDECIDED)
coding->eol_type = CODING_EOL_LF;
coding->mode |= CODING_MODE_INHIBIT_INCONSISTENT_EOL;
}
}
if (encodep
? ! CODING_REQUIRE_ENCODING (coding)
: ! CODING_REQUIRE_DECODING (coding))
from = to_byte;
else
{
SHRINK_CONVERSION_REGION (&from, &to_byte, coding, XSTRING (str)->data,
encodep);
}
if (from == to_byte
&& coding->type != coding_type_ccl)
return (nocopy ? str : Fcopy_sequence (str));
if (encodep)
len = encoding_buffer_size (coding, to_byte - from);
else
len = decoding_buffer_size (coding, to_byte - from);
len += from + STRING_BYTES (XSTRING (str)) - to_byte;
GCPRO1 (str);
buf = get_conversion_buffer (len);
UNGCPRO;
if (from > 0)
bcopy (XSTRING (str)->data, buf, from);
result = (encodep
? encode_coding (coding, XSTRING (str)->data + from,
buf + from, to_byte - from, len)
: decode_coding (coding, XSTRING (str)->data + from,
buf + from, to_byte - from, len));
if (! encodep && result == CODING_FINISH_INCONSISTENT_EOL)
{
coding->eol_type = CODING_EOL_LF;
coding->symbol = saved_coding_symbol;
return code_convert_string (str, coding, encodep, nocopy);
}
bcopy (XSTRING (str)->data + to_byte, buf + from + coding->produced,
STRING_BYTES (XSTRING (str)) - to_byte);
len = from + STRING_BYTES (XSTRING (str)) - to_byte;
if (encodep)
str = make_unibyte_string (buf, len + coding->produced);
else
{
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;
}
#ifdef emacs
DEFUN ("coding-system-p", Fcoding_system_p, Scoding_system_p, 1, 1, 0,
"Return t if OBJECT is nil or a coding-system.\n\
See the documentation of `make-coding-system' for information\n\
about coding-system objects.")
(obj)
Lisp_Object obj;
{
if (NILP (obj))
return Qt;
if (!SYMBOLP (obj))
return Qnil;
obj = Fget (obj, Qcoding_system);
return ((VECTORP (obj) && XVECTOR (obj)->size == 5)
? Qt : Qnil);
}
DEFUN ("read-non-nil-coding-system", Fread_non_nil_coding_system,
Sread_non_nil_coding_system, 1, 1, 0,
"Read a coding system from the minibuffer, prompting with string PROMPT.")
(prompt)
Lisp_Object prompt;
{
Lisp_Object val;
do
{
val = Fcompleting_read (prompt, Vcoding_system_alist, Qnil,
Qt, Qnil, Qcoding_system_history, Qnil, Qnil);
}
while (XSTRING (val)->size == 0);
return (Fintern (val, Qnil));
}
DEFUN ("read-coding-system", Fread_coding_system, Sread_coding_system, 1, 2, 0,
"Read a coding system from the minibuffer, prompting with string PROMPT.\n\
If the user enters null input, return second argument DEFAULT-CODING-SYSTEM.")
(prompt, default_coding_system)
Lisp_Object prompt, default_coding_system;
{
Lisp_Object val;
if (SYMBOLP (default_coding_system))
XSETSTRING (default_coding_system, XSYMBOL (default_coding_system)->name);
val = Fcompleting_read (prompt, Vcoding_system_alist, Qnil,
Qt, Qnil, Qcoding_system_history,
default_coding_system, Qnil);
return (XSTRING (val)->size == 0 ? Qnil : Fintern (val, Qnil));
}
DEFUN ("check-coding-system", Fcheck_coding_system, Scheck_coding_system,
1, 1, 0,
"Check validity of CODING-SYSTEM.\n\
If valid, return CODING-SYSTEM, else signal a `coding-system-error' error.\n\
It is valid if it is a symbol with a non-nil `coding-system' property.\n\
The value of property should be a vector of length 5.")
(coding_system)
Lisp_Object coding_system;
{
CHECK_SYMBOL (coding_system, 0);
if (!NILP (Fcoding_system_p (coding_system)))
return coding_system;
while (1)
Fsignal (Qcoding_system_error, Fcons (coding_system, Qnil));
}
Lisp_Object
detect_coding_system (src, src_bytes, highest)
unsigned char *src;
int src_bytes, highest;
{
int coding_mask, eol_type;
Lisp_Object val, tmp;
int dummy;
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;
if (!coding_mask)
{
val = Qundecided;
if (eol_type != CODING_EOL_UNDECIDED)
{
Lisp_Object val2;
val2 = Fget (Qundecided, Qeol_type);
if (VECTORP (val2))
val = XVECTOR (val2)->contents[eol_type];
}
return (highest ? val : Fcons (val, Qnil));
}
val = Qnil;
for (tmp = Vcoding_category_list; !NILP (tmp); tmp = XCONS (tmp)->cdr)
{
int idx
= XFASTINT (Fget (XCONS (tmp)->car, Qcoding_category_index));
if (coding_mask & (1 << idx))
{
val = Fcons (Fsymbol_value (XCONS (tmp)->car), val);
if (highest)
break;
}
}
if (!highest)
val = Fnreverse (val);
for (tmp = val; !NILP (tmp); tmp = XCONS (tmp)->cdr)
{
if (eol_type != CODING_EOL_UNDECIDED
&& eol_type != CODING_EOL_INCONSISTENT)
{
Lisp_Object eol;
eol = Fget (XCONS (tmp)->car, Qeol_type);
if (VECTORP (eol))
XCONS (tmp)->car = XVECTOR (eol)->contents[eol_type];
}
}
return (highest ? XCONS (val)->car : val);
}
DEFUN ("detect-coding-region", Fdetect_coding_region, Sdetect_coding_region,
2, 3, 0,
"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 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.")
(start, end, highest)
Lisp_Object start, end, highest;
{
int from, to;
int from_byte, to_byte;
CHECK_NUMBER_COERCE_MARKER (start, 0);
CHECK_NUMBER_COERCE_MARKER (end, 1);
validate_region (&start, &end);
from = XINT (start), to = XINT (end);
from_byte = CHAR_TO_BYTE (from);
to_byte = CHAR_TO_BYTE (to);
if (from < GPT && to >= GPT)
move_gap_both (to, to_byte);
return detect_coding_system (BYTE_POS_ADDR (from_byte),
to_byte - from_byte,
!NILP (highest));
}
DEFUN ("detect-coding-string", Fdetect_coding_string, Sdetect_coding_string,
1, 2, 0,
"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 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.")
(string, highest)
Lisp_Object string, highest;
{
CHECK_STRING (string, 0);
return detect_coding_system (XSTRING (string)->data,
STRING_BYTES (XSTRING (string)),
!NILP (highest));
}
Lisp_Object
code_convert_region1 (start, end, coding_system, encodep)
Lisp_Object start, end, coding_system;
int encodep;
{
struct coding_system coding;
int from, to, len;
CHECK_NUMBER_COERCE_MARKER (start, 0);
CHECK_NUMBER_COERCE_MARKER (end, 1);
CHECK_SYMBOL (coding_system, 2);
validate_region (&start, &end);
from = XFASTINT (start);
to = XFASTINT (end);
if (NILP (coding_system))
return make_number (to - from);
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;
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);
}
DEFUN ("decode-coding-region", Fdecode_coding_region, Sdecode_coding_region,
3, 3, "r\nzCoding system: ",
"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\
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;
{
return code_convert_region1 (start, end, coding_system, 0);
}
DEFUN ("encode-coding-region", Fencode_coding_region, Sencode_coding_region,
3, 3, "r\nzCoding 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\
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;
{
return code_convert_region1 (start, end, coding_system, 1);
}
Lisp_Object
code_convert_string1 (string, coding_system, nocopy, encodep)
Lisp_Object string, coding_system, nocopy;
int encodep;
{
struct coding_system coding;
CHECK_STRING (string, 0);
CHECK_SYMBOL (coding_system, 1);
if (NILP (coding_system))
return (NILP (nocopy) ? Fcopy_sequence (string) : 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;
Vlast_coding_system_used = coding.symbol;
return code_convert_string (string, &coding, encodep, !NILP (nocopy));
}
DEFUN ("decode-coding-string", Fdecode_coding_string, Sdecode_coding_string,
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.\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);
}
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.\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);
}
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);
}
DEFUN ("decode-sjis-char", Fdecode_sjis_char, Sdecode_sjis_char, 1, 1, 0,
"Decode a Japanese character which has CODE in shift_jis encoding.\n\
Return the corresponding character.")
(code)
Lisp_Object code;
{
unsigned char c1, c2, s1, s2;
Lisp_Object val;
CHECK_NUMBER (code, 0);
s1 = (XFASTINT (code)) >> 8, s2 = (XFASTINT (code)) & 0xFF;
if (s1 == 0)
{
if (s2 < 0x80)
XSETFASTINT (val, s2);
else if (s2 >= 0xA0 || s2 <= 0xDF)
XSETFASTINT (val,
MAKE_NON_ASCII_CHAR (charset_katakana_jisx0201, s2, 0));
else
error ("Invalid Shift JIS code: %x", XFASTINT (code));
}
else
{
if ((s1 < 0x80 || s1 > 0x9F && s1 < 0xE0 || s1 > 0xEF)
|| (s2 < 0x40 || s2 == 0x7F || s2 > 0xFC))
error ("Invalid Shift JIS code: %x", XFASTINT (code));
DECODE_SJIS (s1, s2, c1, c2);
XSETFASTINT (val, MAKE_NON_ASCII_CHAR (charset_jisx0208, c1, c2));
}
return val;
}
DEFUN ("encode-sjis-char", Fencode_sjis_char, Sencode_sjis_char, 1, 1, 0,
"Encode a Japanese character CHAR to shift_jis encoding.\n\
Return the corresponding code in SJIS.")
(ch)
Lisp_Object ch;
{
int charset, c1, c2, s1, s2;
Lisp_Object val;
CHECK_NUMBER (ch, 0);
SPLIT_CHAR (XFASTINT (ch), charset, c1, c2);
if (charset == CHARSET_ASCII)
{
val = ch;
}
else if (charset == charset_jisx0208
&& c1 > 0x20 && c1 < 0x7F && c2 > 0x20 && c2 < 0x7F)
{
ENCODE_SJIS (c1, c2, s1, s2);
XSETFASTINT (val, (s1 << 8) | s2);
}
else if (charset == charset_katakana_jisx0201
&& c1 > 0x20 && c2 < 0xE0)
{
XSETFASTINT (val, c1 | 0x80);
}
else
error ("Can't encode to shift_jis: %d", XFASTINT (ch));
return val;
}
DEFUN ("decode-big5-char", Fdecode_big5_char, Sdecode_big5_char, 1, 1, 0,
"Decode a Big5 character which has CODE in BIG5 coding system.\n\
Return the corresponding character.")
(code)
Lisp_Object code;
{
int charset;
unsigned char b1, b2, c1, c2;
Lisp_Object val;
CHECK_NUMBER (code, 0);
b1 = (XFASTINT (code)) >> 8, b2 = (XFASTINT (code)) & 0xFF;
if (b1 == 0)
{
if (b2 >= 0x80)
error ("Invalid BIG5 code: %x", XFASTINT (code));
val = code;
}
else
{
if ((b1 < 0xA1 || b1 > 0xFE)
|| (b2 < 0x40 || (b2 > 0x7E && b2 < 0xA1) || b2 > 0xFE))
error ("Invalid BIG5 code: %x", XFASTINT (code));
DECODE_BIG5 (b1, b2, charset, c1, c2);
XSETFASTINT (val, MAKE_NON_ASCII_CHAR (charset, c1, c2));
}
return val;
}
DEFUN ("encode-big5-char", Fencode_big5_char, Sencode_big5_char, 1, 1, 0,
"Encode the Big5 character CHAR to BIG5 coding system.\n\
Return the corresponding character code in Big5.")
(ch)
Lisp_Object ch;
{
int charset, c1, c2, b1, b2;
Lisp_Object val;
CHECK_NUMBER (ch, 0);
SPLIT_CHAR (XFASTINT (ch), charset, c1, c2);
if (charset == CHARSET_ASCII)
{
val = ch;
}
else if ((charset == charset_big5_1
&& (XFASTINT (ch) >= 0x250a1 && XFASTINT (ch) <= 0x271ec))
|| (charset == charset_big5_2
&& XFASTINT (ch) >= 0x290a1 && XFASTINT (ch) <= 0x2bdb2))
{
ENCODE_BIG5 (charset, c1, c2, b1, b2);
XSETFASTINT (val, (b1 << 8) | b2);
}
else
error ("Can't encode to Big5: %d", XFASTINT (ch));
return val;
}
DEFUN ("set-terminal-coding-system-internal",
Fset_terminal_coding_system_internal,
Sset_terminal_coding_system_internal, 1, 1, 0, "")
(coding_system)
Lisp_Object coding_system;
{
CHECK_SYMBOL (coding_system, 0);
setup_coding_system (Fcheck_coding_system (coding_system), &terminal_coding);
terminal_coding.flags |= CODING_FLAG_ISO_SAFE;
return Qnil;
}
DEFUN ("set-safe-terminal-coding-system-internal",
Fset_safe_terminal_coding_system_internal,
Sset_safe_terminal_coding_system_internal, 1, 1, 0, "")
(coding_system)
Lisp_Object coding_system;
{
CHECK_SYMBOL (coding_system, 0);
setup_coding_system (Fcheck_coding_system (coding_system),
&safe_terminal_coding);
return Qnil;
}
DEFUN ("terminal-coding-system",
Fterminal_coding_system, Sterminal_coding_system, 0, 0, 0,
"Return coding system specified for terminal output.")
()
{
return terminal_coding.symbol;
}
DEFUN ("set-keyboard-coding-system-internal",
Fset_keyboard_coding_system_internal,
Sset_keyboard_coding_system_internal, 1, 1, 0, "")
(coding_system)
Lisp_Object coding_system;
{
CHECK_SYMBOL (coding_system, 0);
setup_coding_system (Fcheck_coding_system (coding_system), &keyboard_coding);
return Qnil;
}
DEFUN ("keyboard-coding-system",
Fkeyboard_coding_system, Skeyboard_coding_system, 0, 0, 0,
"Return coding system specified for decoding keyboard input.")
()
{
return keyboard_coding.symbol;
}
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\
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\
\n\
The first argument OPERATION specifies an I/O primitive:\n\
For file I/O, `insert-file-contents' or `write-region'.\n\
For process I/O, `call-process', `call-process-region', or `start-process'.\n\
For network I/O, `open-network-stream'.\n\
\n\
The remaining arguments should be the same arguments that were passed\n\
to the primitive. Depending on which primitive, one of those arguments\n\
is selected as the TARGET. For example, if OPERATION does file I/O,\n\
whichever argument specifies the file name is TARGET.\n\
\n\
TARGET has a meaning which depends on OPERATION:\n\
For file I/O, TARGET is a file name.\n\
For process I/O, TARGET is a process name.\n\
For network I/O, TARGET is a service name or a port number\n\
\n\
This function looks up what specified for TARGET in,\n\
`file-coding-system-alist', `process-coding-system-alist',\n\
or `network-coding-system-alist' depending on OPERATION.\n\
They may specify a coding system, a cons of coding systems,\n\
or a function symbol to call.\n\
In the last case, we call the function with one argument,\n\
which is a list of all the arguments given to this function.")
(nargs, args)
int nargs;
Lisp_Object *args;
{
Lisp_Object operation, target_idx, target, val;
register Lisp_Object chain;
if (nargs < 2)
error ("Too few arguments");
operation = args[0];
if (!SYMBOLP (operation)
|| !INTEGERP (target_idx = Fget (operation, Qtarget_idx)))
error ("Invalid first arguement");
if (nargs < 1 + XINT (target_idx))
error ("Too few arguments for operation: %s",
XSYMBOL (operation)->name->data);
target = args[XINT (target_idx) + 1];
if (!(STRINGP (target)
|| (EQ (operation, Qopen_network_stream) && INTEGERP (target))))
error ("Invalid %dth argument", XINT (target_idx) + 1);
chain = ((EQ (operation, Qinsert_file_contents)
|| EQ (operation, Qwrite_region))
? Vfile_coding_system_alist
: (EQ (operation, Qopen_network_stream)
? Vnetwork_coding_system_alist
: Vprocess_coding_system_alist));
if (NILP (chain))
return Qnil;
for (; CONSP (chain); chain = XCONS (chain)->cdr)
{
Lisp_Object elt;
elt = XCONS (chain)->car;
if (CONSP (elt)
&& ((STRINGP (target)
&& STRINGP (XCONS (elt)->car)
&& fast_string_match (XCONS (elt)->car, target) >= 0)
|| (INTEGERP (target) && EQ (target, XCONS (elt)->car))))
{
val = XCONS (elt)->cdr;
if (CONSP (val))
return val;
if (! SYMBOLP (val))
return Qnil;
if (! NILP (Fcoding_system_p (val)))
return Fcons (val, val);
if (! NILP (Ffboundp (val)))
{
val = call1 (val, Flist (nargs, args));
if (CONSP (val))
return val;
if (SYMBOLP (val) && ! NILP (Fcoding_system_p (val)))
return Fcons (val, val);
}
return Qnil;
}
}
return Qnil;
}
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,\n\
coding-category-ccl")
()
{
int i;
for (i = CODING_CATEGORY_IDX_ISO_7; i <= CODING_CATEGORY_IDX_CCL; 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;
}
while (i < CODING_CATEGORY_IDX_MAX)
coding_priorities[i++] = CODING_CATEGORY_MASK_RAW_TEXT;
return Qnil;
}
#endif
void
init_coding ()
{
conversion_buffer = (char *) xmalloc (MINIMUM_CONVERSION_BUFFER_SIZE);
}
void
init_coding_once ()
{
int i;
for (i = 0; i <= 0x20; i++)
emacs_code_class[i] = EMACS_control_code;
emacs_code_class[0x0A] = EMACS_linefeed_code;
emacs_code_class[0x0D] = EMACS_carriage_return_code;
for (i = 0x21 ; i < 0x7F; i++)
emacs_code_class[i] = EMACS_ascii_code;
emacs_code_class[0x7F] = EMACS_control_code;
emacs_code_class[0x80] = EMACS_leading_code_composition;
for (i = 0x81; i < 0xFF; i++)
emacs_code_class[i] = EMACS_invalid_code;
emacs_code_class[LEADING_CODE_PRIVATE_11] = EMACS_leading_code_3;
emacs_code_class[LEADING_CODE_PRIVATE_12] = EMACS_leading_code_3;
emacs_code_class[LEADING_CODE_PRIVATE_21] = EMACS_leading_code_4;
emacs_code_class[LEADING_CODE_PRIVATE_22] = EMACS_leading_code_4;
for (i = 0; i < 0x20; i++)
iso_code_class[i] = ISO_control_code;
for (i = 0x21; i < 0x7F; i++)
iso_code_class[i] = ISO_graphic_plane_0;
for (i = 0x80; i < 0xA0; i++)
iso_code_class[i] = ISO_control_code;
for (i = 0xA1; i < 0xFF; i++)
iso_code_class[i] = ISO_graphic_plane_1;
iso_code_class[0x20] = iso_code_class[0x7F] = ISO_0x20_or_0x7F;
iso_code_class[0xA0] = iso_code_class[0xFF] = ISO_0xA0_or_0xFF;
iso_code_class[ISO_CODE_CR] = ISO_carriage_return;
iso_code_class[ISO_CODE_SO] = ISO_shift_out;
iso_code_class[ISO_CODE_SI] = ISO_shift_in;
iso_code_class[ISO_CODE_SS2_7] = ISO_single_shift_2_7;
iso_code_class[ISO_CODE_ESC] = ISO_escape;
iso_code_class[ISO_CODE_SS2] = ISO_single_shift_2;
iso_code_class[ISO_CODE_SS3] = ISO_single_shift_3;
iso_code_class[ISO_CODE_CSI] = ISO_control_sequence_introducer;
conversion_buffer_size = 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
system_eol_type = CODING_EOL_LF;
#endif
}
#ifdef emacs
void
syms_of_coding ()
{
Qtarget_idx = intern ("target-idx");
staticpro (&Qtarget_idx);
Qcoding_system_history = intern ("coding-system-history");
staticpro (&Qcoding_system_history);
Fset (Qcoding_system_history, Qnil);
Fput (Qinsert_file_contents, Qtarget_idx, make_number (0));
Fput (Qwrite_region, Qtarget_idx, make_number (2));
Qcall_process = intern ("call-process");
staticpro (&Qcall_process);
Fput (Qcall_process, Qtarget_idx, make_number (0));
Qcall_process_region = intern ("call-process-region");
staticpro (&Qcall_process_region);
Fput (Qcall_process_region, Qtarget_idx, make_number (2));
Qstart_process = intern ("start-process");
staticpro (&Qstart_process);
Fput (Qstart_process, Qtarget_idx, make_number (2));
Qopen_network_stream = intern ("open-network-stream");
staticpro (&Qopen_network_stream);
Fput (Qopen_network_stream, Qtarget_idx, make_number (3));
Qcoding_system = intern ("coding-system");
staticpro (&Qcoding_system);
Qeol_type = intern ("eol-type");
staticpro (&Qeol_type);
Qbuffer_file_coding_system = intern ("buffer-file-coding-system");
staticpro (&Qbuffer_file_coding_system);
Qpost_read_conversion = intern ("post-read-conversion");
staticpro (&Qpost_read_conversion);
Qpre_write_conversion = intern ("pre-write-conversion");
staticpro (&Qpre_write_conversion);
Qno_conversion = intern ("no-conversion");
staticpro (&Qno_conversion);
Qundecided = intern ("undecided");
staticpro (&Qundecided);
Qcoding_system_p = intern ("coding-system-p");
staticpro (&Qcoding_system_p);
Qcoding_system_error = intern ("coding-system-error");
staticpro (&Qcoding_system_error);
Fput (Qcoding_system_error, Qerror_conditions,
Fcons (Qcoding_system_error, Fcons (Qerror, Qnil)));
Fput (Qcoding_system_error, Qerror_message,
build_string ("Invalid coding system"));
Qcoding_category = intern ("coding-category");
staticpro (&Qcoding_category);
Qcoding_category_index = intern ("coding-category-index");
staticpro (&Qcoding_category_index);
Vcoding_category_table
= Fmake_vector (make_number (CODING_CATEGORY_IDX_MAX), Qnil);
staticpro (&Vcoding_category_table);
{
int i;
for (i = 0; i < CODING_CATEGORY_IDX_MAX; i++)
{
XVECTOR (Vcoding_category_table)->contents[i]
= intern (coding_category_name[i]);
Fput (XVECTOR (Vcoding_category_table)->contents[i],
Qcoding_category_index, make_number (i));
}
}
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);
Qtranslation_table_for_decode = intern ("translation-table-for-decode");
staticpro (&Qtranslation_table_for_decode);
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);
Qraw_text = intern ("raw-text");
staticpro (&Qraw_text);
defsubr (&Scoding_system_p);
defsubr (&Sread_coding_system);
defsubr (&Sread_non_nil_coding_system);
defsubr (&Scheck_coding_system);
defsubr (&Sdetect_coding_region);
defsubr (&Sdetect_coding_string);
defsubr (&Sdecode_coding_region);
defsubr (&Sencode_coding_region);
defsubr (&Sdecode_coding_string);
defsubr (&Sencode_coding_string);
defsubr (&Sdecode_sjis_char);
defsubr (&Sencode_sjis_char);
defsubr (&Sdecode_big5_char);
defsubr (&Sencode_big5_char);
defsubr (&Sset_terminal_coding_system_internal);
defsubr (&Sset_safe_terminal_coding_system_internal);
defsubr (&Sterminal_coding_system);
defsubr (&Sset_keyboard_coding_system_internal);
defsubr (&Skeyboard_coding_system);
defsubr (&Sfind_operation_coding_system);
defsubr (&Supdate_coding_systems_internal);
defsubr (&Sset_coding_priority_internal);
DEFVAR_LISP ("coding-system-list", &Vcoding_system_list,
"List of coding systems.\n\
\n\
Do not alter the value of this variable manually. This variable should be\n\
updated by the functions `make-coding-system' and\n\
`define-coding-system-alias'.");
Vcoding_system_list = Qnil;
DEFVAR_LISP ("coding-system-alist", &Vcoding_system_alist,
"Alist of coding system names.\n\
Each element is one element list of coding system name.\n\
This variable is given to `completing-read' as TABLE argument.\n\
\n\
Do not alter the value of this variable manually. This variable should be\n\
updated by the functions `make-coding-system' and\n\
`define-coding-system-alias'.");
Vcoding_system_alist = Qnil;
DEFVAR_LISP ("coding-category-list", &Vcoding_category_list,
"List of coding-categories (symbols) ordered by priority.");
{
int i;
Vcoding_category_list = Qnil;
for (i = CODING_CATEGORY_IDX_MAX - 1; i >= 0; i--)
Vcoding_category_list
= Fcons (XVECTOR (Vcoding_category_table)->contents[i],
Vcoding_category_list);
}
DEFVAR_LISP ("coding-system-for-read", &Vcoding_system_for_read,
"Specify the coding system for read operations.\n\
It is useful to bind this variable with `let', but do not set it globally.\n\
If the value is a coding system, it is used for decoding on read operation.\n\
If not, an appropriate element is used from one of the coding system alists:\n\
There are three such tables, `file-coding-system-alist',\n\
`process-coding-system-alist', and `network-coding-system-alist'.");
Vcoding_system_for_read = Qnil;
DEFVAR_LISP ("coding-system-for-write", &Vcoding_system_for_write,
"Specify the coding system for write operations.\n\
Programs bind this variable with `let', but you should not set it globally.\n\
If the value is a coding system, it is used for encoding of output,\n\
when writing it to a file and when sending it to a file or subprocess.\n\
\n\
If this does not specify a coding system, an appropriate element\n\
is used from one of the coding system alists:\n\
There are three such tables, `file-coding-system-alist',\n\
`process-coding-system-alist', and `network-coding-system-alist'.\n\
For output to files, if the above procedure does not specify a coding system,\n\
the value of `buffer-file-coding-system' is used.");
Vcoding_system_for_write = Qnil;
DEFVAR_LISP ("last-coding-system-used", &Vlast_coding_system_used,
"Coding system used in the latest file or process I/O.");
Vlast_coding_system_used = Qnil;
DEFVAR_BOOL ("inhibit-eol-conversion", &inhibit_eol_conversion,
"*Non-nil means always inhibit code conversion of end-of-line format.\n\
See info node `Coding Systems' and info node `Text and Binary' concerning\n\
such conversion.");
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\
where PATTERN is a regular expression matching a file name,\n\
VAL is a coding system, a cons of coding systems, or a function symbol.\n\
If VAL is a coding system, it is used for both decoding and encoding\n\
the file contents.\n\
If VAL is a cons of coding systems, the car part is used for decoding,\n\
and the cdr part is used for encoding.\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'\n\
and the variable `auto-coding-alist'.");
Vfile_coding_system_alist = Qnil;
DEFVAR_LISP ("process-coding-system-alist", &Vprocess_coding_system_alist,
"Alist to decide a coding system to use for a process I/O operation.\n\
The format is ((PATTERN . VAL) ...),\n\
where PATTERN is a regular expression matching a program name,\n\
VAL is a coding system, a cons of coding systems, or a function symbol.\n\
If VAL is a coding system, it is used for both decoding what received\n\
from the program and encoding what sent to the program.\n\
If VAL is a cons of coding systems, the car part is used for decoding,\n\
and the cdr part is used for encoding.\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'.");
Vprocess_coding_system_alist = Qnil;
DEFVAR_LISP ("network-coding-system-alist", &Vnetwork_coding_system_alist,
"Alist to decide a coding system to use for a network I/O operation.\n\
The format is ((PATTERN . VAL) ...),\n\
where PATTERN is a regular expression matching a network service name\n\
or is a port number to connect to,\n\
VAL is a coding system, a cons of coding systems, or a function symbol.\n\
If VAL is a coding system, it is used for both decoding what received\n\
from the network stream and encoding what sent to the network stream.\n\
If VAL is a cons of coding systems, the car part is used for decoding,\n\
and the cdr part is used for encoding.\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'.");
Vnetwork_coding_system_alist = Qnil;
DEFVAR_LISP ("eol-mnemonic-unix", &eol_mnemonic_unix,
"*String displayed in mode line for UNIX-like (LF) end-of-line format.");
eol_mnemonic_unix = build_string (":");
DEFVAR_LISP ("eol-mnemonic-dos", &eol_mnemonic_dos,
"*String displayed in mode line for DOS-like (CRLF) end-of-line format.");
eol_mnemonic_dos = build_string ("\\");
DEFVAR_LISP ("eol-mnemonic-mac", &eol_mnemonic_mac,
"*String displayed in mode line for MAC-like (CR) end-of-line format.");
eol_mnemonic_mac = build_string ("/");
DEFVAR_LISP ("eol-mnemonic-undecided", &eol_mnemonic_undecided,
"*String displayed in mode line when end-of-line format is not yet determined.");
eol_mnemonic_undecided = build_string (":");
DEFVAR_LISP ("enable-character-translation", &Venable_character_translation,
"*Non-nil enables character translation while encoding and decoding.");
Venable_character_translation = Qt;
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-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\
While encoding, if a charset (car part of an element) is found,\n\
designate it with the escape sequence identifing revision (cdr part of the element).");
Vcharset_revision_alist = Qnil;
DEFVAR_LISP ("default-process-coding-system",
&Vdefault_process_coding_system,
"Cons of coding systems used for process I/O by default.\n\
The car part is used for decoding a process output,\n\
the cdr part is used for encoding a text to be sent to a process.");
Vdefault_process_coding_system = Qnil;
DEFVAR_LISP ("latin-extra-code-table", &Vlatin_extra_code_table,
"Table of extra Latin codes in the range 128..159 (inclusive).\n\
This is a vector of length 256.\n\
If Nth element is non-nil, the existence of code N in a file\n\
\(or output of subprocess) doesn't prevent it to be detected as\n\
a coding system of ISO 2022 variant which has a flag\n\
`accept-latin-extra-code' t (e.g. iso-latin-1) on reading a file\n\
or reading output of a subprocess.\n\
Only 128th through 159th elements has a meaning.");
Vlatin_extra_code_table = Fmake_vector (make_number (256), Qnil);
DEFVAR_LISP ("select-safe-coding-system-function",
&Vselect_safe_coding_system_function,
"Function to call to select safe coding system for encoding a text.\n\
\n\
If set, this function is called to force a user to select a proper\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-coding-system' (which see).");
Vselect_safe_coding_system_function = Qnil;
}
#endif