#include "lisp.h"
#include "buffer.h"
-#include "mule-charset.h"
+#include "character.h"
#include "mule-ccl.h"
#include "file-coding.h"
r[7] = LOWER_BYTE (SJIS (Y, Z) */
/* Terminate CCL program successfully. */
-#define CCL_SUCCESS \
-do { \
- ccl->status = CCL_STAT_SUCCESS; \
+#define CCL_SUCCESS \
+ do { \
+ ccl->status = CCL_STAT_SUCCESS; \
/* The "if (1)" inhibits the warning \
"end-of loop code not reached" */ \
if (1) goto ccl_finish; \
-} while (0)
+ } while (0)
/* Suspend CCL program because of reading from empty input buffer or
writing to full output buffer. When this program is resumed, the
same I/O command is executed. */
-#define CCL_SUSPEND(stat) \
-do { \
- ic--; \
+#define CCL_SUSPEND(stat) \
+ do { \
+ ic--; \
ccl->status = (stat); \
/* The "if (1)" inhibits the warning \
"end-of loop code not reached" */ \
if (1) goto ccl_finish; \
-} while (0)
+ } while (0)
/* Terminate CCL program because of invalid command. Should not occur
in the normal case. */
-#define CCL_INVALID_CMD \
-do { \
- ccl->status = CCL_STAT_INVALID_CMD; \
+#define CCL_INVALID_CMD \
+ do { \
+ ccl->status = CCL_STAT_INVALID_CMD; \
/* The "if (1)" inhibits the warning \
"end-of loop code not reached" */ \
if (1) goto ccl_error_handler; \
-} while (0)
+ } while (0)
/* Encode one character CH to multibyte form and write to the current
output buffer. At encoding time, if CH is less than 256, CH is
} \
} while (0)
+#define POSSIBLE_LEADING_BYTE_P(leading_byte) \
+ ((leading_byte > MIN_LEADING_BYTE) && \
+ (leading_byte - MIN_LEADING_BYTE) < NUM_LEADING_BYTES)
/* Set C to the character code made from CHARSET and CODE. This is
like MAKE_CHAR but check the validity of CHARSET and CODE. If they
case CCL_Extension:
switch (EXCMD)
{
+#ifndef UTF2000
case CCL_ReadMultibyteChar2:
if (!src)
CCL_INVALID_CMD;
- if (src >= src_end)
- {
- src++;
- goto ccl_read_multibyte_character_suspend;
- }
-
- i = *src++;
- if (i < 0x80)
- {
- /* ASCII */
- reg[rrr] = i;
- reg[RRR] = LEADING_BYTE_ASCII;
- }
- else if (i <= MAX_LEADING_BYTE_OFFICIAL_1)
- {
- if (src >= src_end)
- goto ccl_read_multibyte_character_suspend;
- reg[RRR] = i;
- reg[rrr] = (*src++ & 0x7F);
- }
- else if (i <= MAX_LEADING_BYTE_OFFICIAL_2)
- {
- if ((src + 1) >= src_end)
- goto ccl_read_multibyte_character_suspend;
- reg[RRR] = i;
- i = (*src++ & 0x7F);
- reg[rrr] = ((i << 7) | (*src & 0x7F));
- src++;
- }
- else if (i == PRE_LEADING_BYTE_PRIVATE_1)
- {
- if ((src + 1) >= src_end)
- goto ccl_read_multibyte_character_suspend;
- reg[RRR] = *src++;
- reg[rrr] = (*src++ & 0x7F);
- }
- else if (i == PRE_LEADING_BYTE_PRIVATE_2)
- {
- if ((src + 2) >= src_end)
+ if (src >= src_end)
+ {
+ src++;
goto ccl_read_multibyte_character_suspend;
- reg[RRR] = *src++;
- i = (*src++ & 0x7F);
- reg[rrr] = ((i << 7) | (*src & 0x7F));
- src++;
- }
- else
- {
- /* INVALID CODE. Return a single byte character. */
- reg[RRR] = LEADING_BYTE_ASCII;
- reg[rrr] = i;
- }
+ }
+
+ i = *src++;
+ if (i < 0x80)
+ {
+ /* ASCII */
+ reg[rrr] = i;
+ reg[RRR] = LEADING_BYTE_ASCII;
+ }
+ /* Previously, these next two elses were reversed in order,
+ which should have worked fine, but is more fragile than
+ this order. */
+ else if (LEADING_BYTE_CONTROL_1 == i)
+ {
+ if (src >= src_end)
+ goto ccl_read_multibyte_character_suspend;
+ reg[RRR] = i;
+ reg[rrr] = (*src++ - 0xA0);
+ }
+ else if (i <= MAX_LEADING_BYTE_OFFICIAL_1)
+ {
+ if (src >= src_end)
+ goto ccl_read_multibyte_character_suspend;
+ reg[RRR] = i;
+ reg[rrr] = (*src++ & 0x7F);
+ }
+ else if (LEADING_BYTE_CONTROL_1 == i)
+ {
+ if (src >= src_end)
+ goto ccl_read_multibyte_character_suspend;
+ reg[RRR] = i;
+ reg[rrr] = (*src++ - 0xA0);
+ }
+ else if (i <= MAX_LEADING_BYTE_OFFICIAL_2)
+ {
+ if ((src + 1) >= src_end)
+ goto ccl_read_multibyte_character_suspend;
+ reg[RRR] = i;
+ i = (*src++ & 0x7F);
+ reg[rrr] = ((i << 7) | (*src & 0x7F));
+ src++;
+ }
+ else if (i == PRE_LEADING_BYTE_PRIVATE_1)
+ {
+ if ((src + 1) >= src_end)
+ goto ccl_read_multibyte_character_suspend;
+ reg[RRR] = *src++;
+ reg[rrr] = (*src++ & 0x7F);
+ }
+ else if (i == PRE_LEADING_BYTE_PRIVATE_2)
+ {
+ if ((src + 2) >= src_end)
+ goto ccl_read_multibyte_character_suspend;
+ reg[RRR] = *src++;
+ i = (*src++ & 0x7F);
+ reg[rrr] = ((i << 7) | (*src & 0x7F));
+ src++;
+ }
+ else
+ {
+ /* INVALID CODE. Return a single byte character. */
+ reg[RRR] = LEADING_BYTE_ASCII;
+ reg[rrr] = i;
+ }
break;
ccl_read_multibyte_character_suspend:
CCL_SUSPEND (CCL_STAT_SUSPEND_BY_SRC);
break;
+#endif
+#ifndef UTF2000
case CCL_WriteMultibyteChar2:
i = reg[RRR]; /* charset */
- if (i == LEADING_BYTE_ASCII)
+ if (i == LEADING_BYTE_ASCII)
i = reg[rrr] & 0xFF;
- else if (XCHARSET_DIMENSION (CHARSET_BY_LEADING_BYTE (i)) == 1)
- i = (((i - FIELD2_TO_OFFICIAL_LEADING_BYTE) << 7)
- | (reg[rrr] & 0x7F));
- else if (i < MAX_LEADING_BYTE_OFFICIAL_2)
- i = ((i - FIELD1_TO_OFFICIAL_LEADING_BYTE) << 14) | reg[rrr];
- else
- i = ((i - FIELD1_TO_PRIVATE_LEADING_BYTE) << 14) | reg[rrr];
+ else if (LEADING_BYTE_CONTROL_1 == i)
+ i = ((reg[rrr] & 0xFF) - 0xA0);
+ else if (POSSIBLE_LEADING_BYTE_P(i) &&
+ !NILP(CHARSET_BY_LEADING_BYTE(i)))
+ {
+ if (XCHARSET_DIMENSION (CHARSET_BY_LEADING_BYTE (i)) == 1)
+ i = (((i - FIELD2_TO_OFFICIAL_LEADING_BYTE) << 7)
+ | (reg[rrr] & 0x7F));
+ else if (i <= MAX_LEADING_BYTE_OFFICIAL_2)
+ i = ((i - FIELD1_TO_OFFICIAL_LEADING_BYTE) << 14)
+ | reg[rrr];
+ else
+ i = ((i - FIELD1_TO_PRIVATE_LEADING_BYTE) << 14) | reg[rrr];
+ }
+ else
+ {
+ /* No charset we know about; use U+3012 GETA MARK */
+ i = MAKE_CHAR
+ (CHARSET_BY_LEADING_BYTE(LEADING_BYTE_JAPANESE_JISX0208),
+ 34, 46);
+ }
CCL_WRITE_CHAR (i);
break;
+#endif
case CCL_TranslateCharacter:
#if 0
for (;i < j;i++)
{
-
size = XVECTOR (Vcode_conversion_map_vector)->size;
point = XINT (ccl_prog[ic++]);
if (point >= size) continue;