Lisp_Object Vcharset_japanese_jisx0212;
Lisp_Object Vcharset_chinese_cns11643_1;
Lisp_Object Vcharset_chinese_cns11643_2;
+#ifdef UTF2000
+Lisp_Object Vcharset_ucs_bmp;
+Lisp_Object Vcharset_latin_viscii_lower;
+Lisp_Object Vcharset_latin_viscii_upper;
+Lisp_Object Vcharset_hiragana_jisx0208;
+Lisp_Object Vcharset_katakana_jisx0208;
+#endif
Lisp_Object Vcharset_chinese_big5_1;
Lisp_Object Vcharset_chinese_big5_2;
Lisp_Object charset_by_leading_byte[NUM_LEADING_BYTES];
/* Table of charsets indexed by type/final-byte/direction. */
+#ifdef UTF2000
+Lisp_Object charset_by_attributes[4][128];
+#else
Lisp_Object charset_by_attributes[4][128][2];
+#endif
#ifndef UTF2000
/* Table of number of bytes in the string representation of a character
};
#endif
+#ifdef UTF2000
+Emchar_to_byte_table*
+make_byte_from_character_table ()
+{
+ Emchar_to_byte_table* table
+ = (Emchar_to_byte_table*) xmalloc (sizeof (Emchar_to_byte_table));
+
+ table->base = NULL;
+ return table;
+}
+
+#define destroy_byte_from_character_table(table) xfree(table)
+
+void
+put_byte_from_character_table (Emchar ch, unsigned char val,
+ Emchar_to_byte_table* table)
+{
+ if (table->base == NULL)
+ {
+ table->base = xmalloc (256);
+ table->offset = ch - (ch % 256);
+ table->size = 256;
+ table->base[ch - table->offset] = val;
+ }
+ else
+ {
+ int i = ch - table->offset;
+
+ if (i < 0)
+ {
+ size_t new_size = table->size - i;
+ size_t j;
+
+ new_size += 256 - (new_size % 256);
+ table->base = xrealloc (table->base, new_size);
+ memmove (table->base + (new_size - table->size), table->base,
+ table->size);
+ for (j = 0; j < (new_size - table->size); j++)
+ table->base[j] = 0;
+ table->offset -= (new_size - table->size);
+ table->base[ch - table->offset] = val;
+ table->size = new_size;
+ }
+ else if (i >= table->size)
+ {
+ size_t new_size = i + 1;
+ size_t j;
+
+ new_size += 256 - (new_size % 256);
+ table->base = xrealloc (table->base, new_size);
+ for (j = table->size; j < new_size; j++)
+ table->base[j] = 0;
+ table->base[i] = val;
+ table->size = new_size;
+ }
+ else
+ {
+ table->base[i] = val;
+ }
+ }
+}
+
+unsigned char
+get_byte_from_character_table (Emchar ch, Emchar_to_byte_table* table)
+{
+ size_t i = ch - table->offset;
+ if (i < table->size)
+ return table->base[i];
+ else
+ return 0;
+}
+
+
Lisp_Object Vutf_2000_version;
+#endif
+#ifndef UTF2000
int leading_code_private_11;
+#endif
Lisp_Object Qcharsetp;
Qjapanese_jisx0212,
Qchinese_cns11643_1,
Qchinese_cns11643_2,
+#ifdef UTF2000
+ Qucs_bmp,
+ Qlatin_viscii_lower,
+ Qlatin_viscii_upper,
+ Qvietnamese_viscii_lower,
+ Qvietnamese_viscii_upper,
+ Qhiragana_jisx0208,
+ Qkatakana_jisx0208,
+#endif
Qchinese_big5_1,
Qchinese_big5_2,
Qcomposite;
Lisp_Object Vcharset_hash_table;
-static Bufbyte next_allocated_1_byte_leading_byte;
-static Bufbyte next_allocated_2_byte_leading_byte;
+static Charset_ID next_allocated_1_byte_leading_byte;
+static Charset_ID next_allocated_2_byte_leading_byte;
/* Composite characters are characters constructed by overstriking two
or more regular characters.
{
Bufbyte *p;
#ifndef UTF2000
- Bufbyte lb;
+ Charset_ID lb;
int c1, c2;
Lisp_Object charset;
#endif
markobj (cs->doc_string);
markobj (cs->registry);
markobj (cs->ccl_program);
+#ifdef UTF2000
+ markobj (cs->decoding_table);
+#endif
return cs->name;
}
};
DEFINE_LRECORD_IMPLEMENTATION ("charset", charset,
- mark_charset, print_charset, 0, 0, 0, charset_description,
+ mark_charset, print_charset, 0, 0, 0,
+ charset_description,
struct Lisp_Charset);
/* Make a new charset. */
static Lisp_Object
-make_charset (int id, Lisp_Object name, unsigned char rep_bytes,
+make_charset (Charset_ID id, Lisp_Object name,
unsigned char type, unsigned char columns, unsigned char graphic,
- Bufbyte final, unsigned char direction, Lisp_Object short_name,
+ Bufbyte final, unsigned char direction, Lisp_Object short_name,
Lisp_Object long_name, Lisp_Object doc,
- Lisp_Object reg)
+ Lisp_Object reg,
+ Lisp_Object decoding_table,
+ Emchar ucs_min, Emchar ucs_max,
+ Emchar code_offset, unsigned char byte_offset)
{
Lisp_Object obj;
struct Lisp_Charset *cs =
CHARSET_NAME (cs) = name;
CHARSET_SHORT_NAME (cs) = short_name;
CHARSET_LONG_NAME (cs) = long_name;
- CHARSET_REP_BYTES (cs) = rep_bytes;
CHARSET_DIRECTION (cs) = direction;
CHARSET_TYPE (cs) = type;
CHARSET_COLUMNS (cs) = columns;
CHARSET_REGISTRY (cs) = reg;
CHARSET_CCL_PROGRAM (cs) = Qnil;
CHARSET_REVERSE_DIRECTION_CHARSET (cs) = Qnil;
+#ifdef UTF2000
+ CHARSET_DECODING_TABLE(cs) = decoding_table;
+ CHARSET_UCS_MIN(cs) = ucs_min;
+ CHARSET_UCS_MAX(cs) = ucs_max;
+ CHARSET_CODE_OFFSET(cs) = code_offset;
+ CHARSET_BYTE_OFFSET(cs) = byte_offset;
+#endif
+
+ switch ( CHARSET_TYPE (cs) )
+ {
+ case CHARSET_TYPE_94:
+ CHARSET_DIMENSION (cs) = 1;
+ CHARSET_CHARS (cs) = 94;
+#ifdef UTF2000
+ if (!EQ (decoding_table, Qnil))
+ {
+ size_t i;
+ CHARSET_TO_BYTE1_TABLE(cs) = make_byte_from_character_table();
+ for (i = 0; i < 94; i++)
+ {
+ Lisp_Object c = XVECTOR_DATA(decoding_table)[i];
+
+ if (!EQ (c, Qnil))
+ put_byte_from_character_table (XCHAR (c), i + 33,
+ CHARSET_TO_BYTE1_TABLE(cs));
+ }
+ }
+ else
+ CHARSET_TO_BYTE1_TABLE(cs) = NULL;
+ CHARSET_TO_BYTE2_TABLE(cs) = NULL;
+#endif
+ break;
+ case CHARSET_TYPE_96:
+ CHARSET_DIMENSION (cs) = 1;
+ CHARSET_CHARS (cs) = 96;
+#ifdef UTF2000
+ if (!EQ (decoding_table, Qnil))
+ {
+ size_t i;
+ CHARSET_TO_BYTE1_TABLE(cs) = make_byte_from_character_table();
+ for (i = 0; i < 96; i++)
+ {
+ Lisp_Object c = XVECTOR_DATA(decoding_table)[i];
+
+ if (!EQ (c, Qnil))
+ put_byte_from_character_table (XCHAR (c), i + 32,
+ CHARSET_TO_BYTE1_TABLE(cs));
+ }
+ }
+ else
+ CHARSET_TO_BYTE1_TABLE(cs) = NULL;
+ CHARSET_TO_BYTE2_TABLE(cs) = NULL;
+#endif
+ break;
+ case CHARSET_TYPE_94X94:
+ CHARSET_DIMENSION (cs) = 2;
+ CHARSET_CHARS (cs) = 94;
+#ifdef UTF2000
+ CHARSET_TO_BYTE1_TABLE(cs) = NULL;
+ CHARSET_TO_BYTE2_TABLE(cs) = NULL;
+#endif
+ break;
+ case CHARSET_TYPE_96X96:
+ CHARSET_DIMENSION (cs) = 2;
+ CHARSET_CHARS (cs) = 96;
+#ifdef UTF2000
+ CHARSET_TO_BYTE1_TABLE(cs) = NULL;
+ CHARSET_TO_BYTE2_TABLE(cs) = NULL;
+#endif
+ break;
+#ifdef UTF2000
+ case CHARSET_TYPE_128X128:
+ CHARSET_DIMENSION (cs) = 2;
+ CHARSET_CHARS (cs) = 128;
+#ifdef UTF2000
+ CHARSET_TO_BYTE1_TABLE(cs) = NULL;
+ CHARSET_TO_BYTE2_TABLE(cs) = NULL;
+#endif
+ break;
+ case CHARSET_TYPE_256X256:
+ CHARSET_DIMENSION (cs) = 2;
+ CHARSET_CHARS (cs) = 256;
+#ifdef UTF2000
+ CHARSET_TO_BYTE1_TABLE(cs) = NULL;
+ CHARSET_TO_BYTE2_TABLE(cs) = NULL;
+#endif
+ break;
+#endif
+ }
- CHARSET_DIMENSION (cs) = (CHARSET_TYPE (cs) == CHARSET_TYPE_94 ||
- CHARSET_TYPE (cs) == CHARSET_TYPE_96) ? 1 : 2;
- CHARSET_CHARS (cs) = (CHARSET_TYPE (cs) == CHARSET_TYPE_94 ||
- CHARSET_TYPE (cs) == CHARSET_TYPE_94X94) ? 94 : 96;
-
+#ifndef UTF2000
+ if (id == LEADING_BYTE_ASCII)
+ CHARSET_REP_BYTES (cs) = 1;
+ else if (id < 0xA0)
+ CHARSET_REP_BYTES (cs) = CHARSET_DIMENSION (cs) + 1;
+ else
+ CHARSET_REP_BYTES (cs) = CHARSET_DIMENSION (cs) + 2;
+#endif
+
if (final)
{
/* some charsets do not have final characters. This includes
ASCII, Control-1, Composite, and the two faux private
charsets. */
+#if UTF2000
+ if (code_offset == 0)
+ {
+ assert (NILP (charset_by_attributes[type][final]));
+ charset_by_attributes[type][final] = obj;
+ }
+#else
assert (NILP (charset_by_attributes[type][final][direction]));
charset_by_attributes[type][final][direction] = obj;
+#endif
}
assert (NILP (charset_by_leading_byte[id - MIN_LEADING_BYTE]));
#ifndef UTF2000
if (id < 0xA0)
/* official leading byte */
- rep_bytes_by_first_byte[id] = rep_bytes;
+ rep_bytes_by_first_byte[id] = CHARSET_REP_BYTES (cs);
#endif
/* Some charsets are "faux" and don't have names or really exist at
static int
get_unallocated_leading_byte (int dimension)
{
- int lb;
+ Charset_ID lb;
if (dimension == 1)
{
return lb;
}
+#ifdef UTF2000
+unsigned char
+charset_get_byte1 (Lisp_Object charset, Emchar ch)
+{
+ Emchar_to_byte_table* table;
+ int d;
+
+ if ((table = XCHARSET_TO_BYTE1_TABLE (charset)) != NULL)
+ return get_byte_from_character_table (ch, table);
+ else if ((XCHARSET_UCS_MIN (charset) <= ch)
+ && (ch <= XCHARSET_UCS_MAX (charset)))
+ return (ch - XCHARSET_UCS_MIN (charset)
+ + XCHARSET_CODE_OFFSET (charset))
+ / (XCHARSET_DIMENSION (charset) == 1 ?
+ 1
+ :
+ XCHARSET_DIMENSION (charset) == 2 ?
+ XCHARSET_CHARS (charset)
+ :
+ XCHARSET_DIMENSION (charset) == 3 ?
+ XCHARSET_CHARS (charset) * XCHARSET_CHARS (charset)
+ :
+ XCHARSET_CHARS (charset)
+ * XCHARSET_CHARS (charset) * XCHARSET_CHARS (charset))
+ + XCHARSET_BYTE_OFFSET (charset);
+ else if (XCHARSET_CODE_OFFSET (charset) == 0)
+ {
+ if (XCHARSET_DIMENSION (charset) == 1)
+ {
+ if (XCHARSET_CHARS (charset) == 94)
+ {
+ if (((d = ch - (MIN_CHAR_94
+ + (XCHARSET_FINAL (charset) - '0') * 94)) >= 0)
+ && (d < 94))
+ return d + 33;
+ }
+ else if (XCHARSET_CHARS (charset) == 96)
+ {
+ if (((d = ch - (MIN_CHAR_96
+ + (XCHARSET_FINAL (charset) - '0') * 96)) >= 0)
+ && (d < 96))
+ return d + 32;
+ }
+ else
+ return 0;
+ }
+ else if (XCHARSET_DIMENSION (charset) == 2)
+ {
+ if (XCHARSET_CHARS (charset) == 94)
+ {
+ if (((d = ch - (MIN_CHAR_94x94
+ + (XCHARSET_FINAL (charset) - '0') * 94 * 94))
+ >= 0)
+ && (d < 94 * 94))
+ return (d / 94) + 33;
+ }
+ else if (XCHARSET_CHARS (charset) == 96)
+ {
+ if (((d = ch - (MIN_CHAR_96x96
+ + (XCHARSET_FINAL (charset) - '0') * 96 * 96))
+ >= 0)
+ && (d < 96 * 96))
+ return (d / 96) + 32;
+ }
+ }
+ }
+ return 0;
+}
+
+unsigned char
+charset_get_byte2 (Lisp_Object charset, Emchar ch)
+{
+ if (XCHARSET_DIMENSION (charset) == 1)
+ return 0;
+ else
+ {
+ Emchar_to_byte_table* table;
+
+ if ((table = XCHARSET_TO_BYTE2_TABLE (charset)) != NULL)
+ return get_byte_from_character_table (ch, table);
+ else if ((XCHARSET_UCS_MIN (charset) <= ch)
+ && (ch <= XCHARSET_UCS_MAX (charset)))
+ return ((ch - XCHARSET_UCS_MIN (charset)
+ + XCHARSET_CODE_OFFSET (charset))
+ / (XCHARSET_DIMENSION (charset) == 2 ?
+ 1
+ :
+ XCHARSET_DIMENSION (charset) == 3 ?
+ XCHARSET_CHARS (charset)
+ :
+ XCHARSET_CHARS (charset) * XCHARSET_CHARS (charset)))
+ % XCHARSET_CHARS (charset)
+ + XCHARSET_BYTE_OFFSET (charset);
+ else if (XCHARSET_CHARS (charset) == 94)
+ return (MIN_CHAR_94x94
+ + (XCHARSET_FINAL (charset) - '0') * 94 * 94 <= ch)
+ && (ch < MIN_CHAR_94x94
+ + (XCHARSET_FINAL (charset) - '0' + 1) * 94 * 94) ?
+ ((ch - MIN_CHAR_94x94) % 94) + 33 : 0;
+ else /* if (XCHARSET_CHARS (charset) == 96) */
+ return (MIN_CHAR_96x96
+ + (XCHARSET_FINAL (charset) - '0') * 96 * 96 <= ch)
+ && (ch < MIN_CHAR_96x96
+ + (XCHARSET_FINAL (charset) - '0' + 1) * 96 * 96) ?
+ ((ch - MIN_CHAR_96x96) % 96) + 32 : 0;
+ }
+}
+
+Lisp_Object Vdefault_coded_charset_priority_list;
+#endif
+
\f
/************************************************************************/
/* Basic charset Lisp functions */
error
("Character set already defined for this DIMENSION/CHARS/FINAL combo");
+#ifdef UTF2000
+ if (dimension == 1)
+ {
+ if (chars == 94)
+ {
+ /* id = CHARSET_ID_OFFSET_94 + final; */
+ id = get_unallocated_leading_byte (dimension);
+ }
+ else if (chars == 96)
+ {
+ id = get_unallocated_leading_byte (dimension);
+ }
+ else
+ {
+ abort ();
+ }
+ }
+ else if (dimension == 2)
+ {
+ if (chars == 94)
+ {
+ id = get_unallocated_leading_byte (dimension);
+ }
+ else if (chars == 96)
+ {
+ id = get_unallocated_leading_byte (dimension);
+ }
+ else
+ {
+ abort ();
+ }
+ }
+ else
+ {
+ abort ();
+ }
+#else
id = get_unallocated_leading_byte (dimension);
+#endif
if (NILP (doc_string))
doc_string = build_string ("");
if (columns == -1)
columns = dimension;
- charset = make_charset (id, name, dimension + 2, type, columns, graphic,
- final, direction, short_name, long_name, doc_string, registry);
+ charset = make_charset (id, name, type, columns, graphic,
+ final, direction, short_name, long_name,
+ doc_string, registry,
+ Qnil, 0, 0, 0, 0);
if (!NILP (ccl_program))
XCHARSET_CCL_PROGRAM (charset) = ccl_program;
return charset;
long_name = CHARSET_LONG_NAME (cs);
registry = CHARSET_REGISTRY (cs);
- new_charset = make_charset (id, new_name, dimension + 2, type, columns,
+ new_charset = make_charset (id, new_name, type, columns,
graphic, final, direction, short_name, long_name,
- doc_string, registry);
+ doc_string, registry,
+#ifdef UTF2000
+ CHARSET_DECODING_TABLE(cs),
+ CHARSET_UCS_MIN(cs),
+ CHARSET_UCS_MAX(cs),
+ CHARSET_CODE_OFFSET(cs),
+ CHARSET_BYTE_OFFSET(cs)
+#else
+ Qnil, 0, 0, 0, 0
+#endif
+);
CHARSET_REVERSE_DIRECTION_CHARSET (cs) = new_charset;
XCHARSET_REVERSE_DIRECTION_CHARSET (new_charset) = charset;
return new_charset;
}
+DEFUN ("define-charset-alias", Fdefine_charset_alias, 2, 2, 0, /*
+Define symbol ALIAS as an alias for CHARSET.
+*/
+ (alias, charset))
+{
+ CHECK_SYMBOL (alias);
+ charset = Fget_charset (charset);
+ return Fputhash (alias, charset, Vcharset_hash_table);
+}
+
/* #### Reverse direction charsets not yet implemented. */
#if 0
DEFUN ("charset-reverse-direction-charset", Fcharset_reverse_direction_charset,
}
}
-/* Japanese folks may want to (set-charset-registry 'ascii "jisx0201") */
DEFUN ("set-charset-registry", Fset_charset_registry, 2, 2, 0, /*
Set the 'registry property of CHARSET to REGISTRY.
*/
return Qnil;
}
+#ifdef UTF2000
+DEFUN ("charset-mapping-table", Fcharset_mapping_table, 1, 1, 0, /*
+Return mapping-table of CHARSET.
+*/
+ (charset))
+{
+ return XCHARSET_DECODING_TABLE (Fget_charset (charset));
+}
+
+DEFUN ("set-charset-mapping-table", Fset_charset_mapping_table, 2, 2, 0, /*
+Set mapping-table of CHARSET to TABLE.
+*/
+ (charset, table))
+{
+ struct Lisp_Charset *cs;
+ Emchar_to_byte_table* old_byte1_table;
+ Emchar_to_byte_table* old_byte2_table;
+
+ charset = Fget_charset (charset);
+ CHECK_VECTOR (table);
+
+ cs = XCHARSET (charset);
+ CHARSET_DECODING_TABLE(cs) = table;
+ old_byte1_table = CHARSET_TO_BYTE1_TABLE(cs);
+ old_byte2_table = CHARSET_TO_BYTE2_TABLE(cs);
+ switch (CHARSET_TYPE (cs))
+ {
+ case CHARSET_TYPE_94:
+ if (!EQ (table, Qnil))
+ {
+ size_t i;
+ CHARSET_TO_BYTE1_TABLE(cs) = make_byte_from_character_table();
+ for (i = 0; i < 94; i++)
+ {
+ Lisp_Object c = XVECTOR_DATA(table)[i];
+
+ if (!EQ (c, Qnil))
+ put_byte_from_character_table (XCHAR (c), i + 33,
+ CHARSET_TO_BYTE1_TABLE(cs));
+ }
+ }
+ else
+ CHARSET_TO_BYTE1_TABLE(cs) = NULL;
+ CHARSET_TO_BYTE2_TABLE(cs) = NULL;
+ break;
+ case CHARSET_TYPE_96:
+ if (!EQ (table, Qnil))
+ {
+ size_t i;
+ CHARSET_TO_BYTE1_TABLE(cs) = make_byte_from_character_table();
+ for (i = 0; i < 96; i++)
+ {
+ Lisp_Object c = XVECTOR_DATA(table)[i];
+
+ if (!EQ (c, Qnil))
+ put_byte_from_character_table (XCHAR (c), i + 32,
+ CHARSET_TO_BYTE1_TABLE(cs));
+ }
+ }
+ else
+ CHARSET_TO_BYTE1_TABLE(cs) = NULL;
+ CHARSET_TO_BYTE2_TABLE(cs) = NULL;
+ break;
+ case CHARSET_TYPE_94X94:
+ if (!EQ (table, Qnil))
+ {
+ size_t i;
+
+ CHARSET_TO_BYTE1_TABLE(cs) = make_byte_from_character_table();
+ CHARSET_TO_BYTE2_TABLE(cs) = make_byte_from_character_table();
+ for (i = 0; i < XVECTOR_LENGTH (table); i++)
+ {
+ Lisp_Object v = XVECTOR_DATA(table)[i];
+
+ if (VECTORP (v))
+ {
+ size_t j;
+
+ for (j = 0; j < XVECTOR_LENGTH (v); j++)
+ {
+ Lisp_Object c = XVECTOR_DATA(v)[j];
+
+ if (!EQ (c, Qnil))
+ {
+ put_byte_from_character_table
+ (XCHAR (c), i + 33, CHARSET_TO_BYTE1_TABLE(cs));
+ put_byte_from_character_table
+ (XCHAR (c), j + 33, CHARSET_TO_BYTE2_TABLE(cs));
+ }
+ }
+ }
+ else if (CHARP (v))
+ put_byte_from_character_table
+ (XCHAR (v), i + 33, CHARSET_TO_BYTE1_TABLE(cs));
+ }
+ }
+ else
+ {
+ CHARSET_TO_BYTE1_TABLE(cs) = NULL;
+ CHARSET_TO_BYTE2_TABLE(cs) = NULL;
+ }
+ break;
+ case CHARSET_TYPE_96X96:
+ CHARSET_TO_BYTE1_TABLE(cs) = NULL;
+ CHARSET_TO_BYTE2_TABLE(cs) = NULL;
+ break;
+ case CHARSET_TYPE_128X128:
+ CHARSET_DIMENSION (cs) = 2;
+ CHARSET_CHARS (cs) = 128;
+ CHARSET_TO_BYTE1_TABLE(cs) = NULL;
+ CHARSET_TO_BYTE2_TABLE(cs) = NULL;
+ break;
+ case CHARSET_TYPE_256X256:
+ CHARSET_DIMENSION (cs) = 2;
+ CHARSET_CHARS (cs) = 256;
+ CHARSET_TO_BYTE1_TABLE(cs) = NULL;
+ CHARSET_TO_BYTE2_TABLE(cs) = NULL;
+ break;
+ }
+ if (old_byte1_table != NULL)
+ destroy_byte_from_character_table (old_byte1_table);
+ if (old_byte2_table != NULL)
+ destroy_byte_from_character_table (old_byte2_table);
+ return table;
+}
+#endif
+
\f
/************************************************************************/
/* Lisp primitives for working with characters */
if (EQ (charset, Vcharset_ascii)) lowlim = 0, highlim = 127;
else if (EQ (charset, Vcharset_control_1)) lowlim = 0, highlim = 31;
+#ifdef UTF2000
+ else if (CHARSET_CHARS (cs) == 256) lowlim = 0, highlim = 255;
+#endif
else if (CHARSET_CHARS (cs) == 94) lowlim = 33, highlim = 126;
else /* CHARSET_CHARS (cs) == 96) */ lowlim = 32, highlim = 127;
the 8th bit off ARG1 and ARG2 becaue it allows programmers to
write (make-char 'latin-iso8859-2 CODE) where code is the actual
Latin 2 code of the character. */
- a1 = XINT (arg1) & 0x7f;
+#ifdef UTF2000
+ a1 = XINT (arg1);
+ if (highlim < 128)
+ a1 &= 0x7f;
+#else
+ a1 = XINT (arg1);
+#endif
if (a1 < lowlim || a1 > highlim)
args_out_of_range_3 (arg1, make_int (lowlim), make_int (highlim));
}
CHECK_INT (arg2);
+#ifdef UTF2000
+ a2 = XINT (arg2);
+ if (highlim < 128)
+ a2 &= 0x7f;
+#else
a2 = XINT (arg2) & 0x7f;
+#endif
if (a2 < lowlim || a2 > highlim)
args_out_of_range_3 (arg2, make_int (lowlim), make_int (highlim));
{
CHECK_CHAR_COERCE_INT (ch);
- return XCHARSET_NAME (CHARSET_BY_LEADING_BYTE
- (CHAR_LEADING_BYTE (XCHAR (ch))));
+ return XCHARSET_NAME (CHAR_CHARSET (XCHAR (ch)));
}
DEFUN ("split-char", Fsplit_char, 1, 1, 0, /*
DEFSUBR (Fmake_charset);
DEFSUBR (Fmake_reverse_direction_charset);
/* DEFSUBR (Freverse_direction_charset); */
+ DEFSUBR (Fdefine_charset_alias);
DEFSUBR (Fcharset_from_attributes);
DEFSUBR (Fcharset_short_name);
DEFSUBR (Fcharset_long_name);
DEFSUBR (Fcharset_id);
DEFSUBR (Fset_charset_ccl_program);
DEFSUBR (Fset_charset_registry);
+#ifdef UTF2000
+ DEFSUBR (Fcharset_mapping_table);
+ DEFSUBR (Fset_charset_mapping_table);
+#endif
DEFSUBR (Fmake_char);
DEFSUBR (Fchar_charset);
defsymbol (&Qjapanese_jisx0212, "japanese-jisx0212");
defsymbol (&Qchinese_cns11643_1, "chinese-cns11643-1");
defsymbol (&Qchinese_cns11643_2, "chinese-cns11643-2");
+#ifdef UTF2000
+ defsymbol (&Qucs_bmp, "ucs-bmp");
+ defsymbol (&Qlatin_viscii_lower, "latin-viscii-lower");
+ defsymbol (&Qlatin_viscii_upper, "latin-viscii-upper");
+ defsymbol (&Qvietnamese_viscii_lower, "vietnamese-viscii-lower");
+ defsymbol (&Qvietnamese_viscii_upper, "vietnamese-viscii-upper");
+ defsymbol (&Qhiragana_jisx0208, "hiragana-jisx0208");
+ defsymbol (&Qkatakana_jisx0208, "katakana-jisx0208");
+#endif
defsymbol (&Qchinese_big5_1, "chinese-big5-1");
defsymbol (&Qchinese_big5_2, "chinese-big5-2");
defsymbol (&Qcomposite, "composite");
-
-#ifdef UTF2000
- Vutf_2000_version = build_string("0.4 (Shin-Imamiya)");
- DEFVAR_LISP ("utf-2000-version", &Vutf_2000_version /*
-Version number of UTF-2000.
-*/ );
-#endif
}
void
vars_of_mule_charset (void)
{
- int i, j, k;
+ int i, j;
+#ifndef UTF2000
+ int k;
+#endif
/* Table of charsets indexed by leading byte. */
for (i = 0; i < countof (charset_by_leading_byte); i++)
charset_by_leading_byte[i] = Qnil;
+#ifdef UTF2000
+ /* Table of charsets indexed by type/final-byte. */
+ for (i = 0; i < countof (charset_by_attributes); i++)
+ for (j = 0; j < countof (charset_by_attributes[0]); j++)
+ charset_by_attributes[i][j] = Qnil;
+#else
/* Table of charsets indexed by type/final-byte/direction. */
for (i = 0; i < countof (charset_by_attributes); i++)
for (j = 0; j < countof (charset_by_attributes[0]); j++)
for (k = 0; k < countof (charset_by_attributes[0][0]); k++)
charset_by_attributes[i][j][k] = Qnil;
+#endif
next_allocated_1_byte_leading_byte = MIN_LEADING_BYTE_PRIVATE_1;
+#ifdef UTF2000
+ next_allocated_2_byte_leading_byte = LEADING_BYTE_CHINESE_BIG5_2 + 1;
+#else
next_allocated_2_byte_leading_byte = MIN_LEADING_BYTE_PRIVATE_2;
+#endif
+#ifndef UTF2000
leading_code_private_11 = PRE_LEADING_BYTE_PRIVATE_1;
DEFVAR_INT ("leading-code-private-11", &leading_code_private_11 /*
Leading-code of private TYPE9N charset of column-width 1.
*/ );
leading_code_private_11 = PRE_LEADING_BYTE_PRIVATE_1;
+#endif
+
+#ifdef UTF2000
+ Vutf_2000_version = build_string("0.8 (Kami)");
+ DEFVAR_LISP ("utf-2000-version", &Vutf_2000_version /*
+Version number of UTF-2000.
+*/ );
+
+ Vdefault_coded_charset_priority_list = Qnil;
+ DEFVAR_LISP ("default-coded-charset-priority-list",
+ &Vdefault_coded_charset_priority_list /*
+Default order of preferred coded-character-set.
+*/ );
+#endif
}
void
/* Predefined character sets. We store them into variables for
ease of access. */
+#ifdef UTF2000
+ Vcharset_ucs_bmp =
+ make_charset (LEADING_BYTE_UCS_BMP, Qucs_bmp,
+ CHARSET_TYPE_256X256, 1, 0, 0,
+ CHARSET_LEFT_TO_RIGHT,
+ build_string ("BMP"),
+ build_string ("BMP"),
+ build_string ("BMP"),
+ build_string (""),
+ Qnil, 0, 0xFFFF, 0, 0);
+#else
+# define MIN_CHAR_THAI 0
+# define MAX_CHAR_THAI 0
+# define MIN_CHAR_GREEK 0
+# define MAX_CHAR_GREEK 0
+# define MIN_CHAR_HEBREW 0
+# define MAX_CHAR_HEBREW 0
+# define MIN_CHAR_HALFWIDTH_KATAKANA 0
+# define MAX_CHAR_HALFWIDTH_KATAKANA 0
+# define MIN_CHAR_CYRILLIC 0
+# define MAX_CHAR_CYRILLIC 0
+#endif
Vcharset_ascii =
- make_charset (LEADING_BYTE_ASCII, Qascii, 1,
+ make_charset (LEADING_BYTE_ASCII, Qascii,
CHARSET_TYPE_94, 1, 0, 'B',
CHARSET_LEFT_TO_RIGHT,
build_string ("ASCII"),
build_string ("ASCII)"),
build_string ("ASCII (ISO646 IRV)"),
- build_string ("\\(iso8859-[0-9]*\\|-ascii\\)"));
+ build_string ("\\(iso8859-[0-9]*\\|-ascii\\)"),
+ Qnil, 0, 0x7F, 0, 0);
Vcharset_control_1 =
- make_charset (LEADING_BYTE_CONTROL_1, Qcontrol_1, 2,
+ make_charset (LEADING_BYTE_CONTROL_1, Qcontrol_1,
CHARSET_TYPE_94, 1, 1, 0,
CHARSET_LEFT_TO_RIGHT,
build_string ("C1"),
build_string ("Control characters"),
build_string ("Control characters 128-191"),
- build_string (""));
+ build_string (""),
+ Qnil, 0x80, 0x9F, 0, 0);
Vcharset_latin_iso8859_1 =
- make_charset (LEADING_BYTE_LATIN_ISO8859_1, Qlatin_iso8859_1, 2,
+ make_charset (LEADING_BYTE_LATIN_ISO8859_1, Qlatin_iso8859_1,
CHARSET_TYPE_96, 1, 1, 'A',
CHARSET_LEFT_TO_RIGHT,
build_string ("Latin-1"),
build_string ("ISO8859-1 (Latin-1)"),
build_string ("ISO8859-1 (Latin-1)"),
- build_string ("iso8859-1"));
+ build_string ("iso8859-1"),
+ Qnil, 0xA0, 0xFF, 0, 32);
Vcharset_latin_iso8859_2 =
- make_charset (LEADING_BYTE_LATIN_ISO8859_2, Qlatin_iso8859_2, 2,
+ make_charset (LEADING_BYTE_LATIN_ISO8859_2, Qlatin_iso8859_2,
CHARSET_TYPE_96, 1, 1, 'B',
CHARSET_LEFT_TO_RIGHT,
build_string ("Latin-2"),
build_string ("ISO8859-2 (Latin-2)"),
build_string ("ISO8859-2 (Latin-2)"),
- build_string ("iso8859-2"));
+ build_string ("iso8859-2"),
+ Qnil, 0, 0, 0, 32);
Vcharset_latin_iso8859_3 =
- make_charset (LEADING_BYTE_LATIN_ISO8859_3, Qlatin_iso8859_3, 2,
+ make_charset (LEADING_BYTE_LATIN_ISO8859_3, Qlatin_iso8859_3,
CHARSET_TYPE_96, 1, 1, 'C',
CHARSET_LEFT_TO_RIGHT,
build_string ("Latin-3"),
build_string ("ISO8859-3 (Latin-3)"),
build_string ("ISO8859-3 (Latin-3)"),
- build_string ("iso8859-3"));
+ build_string ("iso8859-3"),
+ Qnil, 0, 0, 0, 32);
Vcharset_latin_iso8859_4 =
- make_charset (LEADING_BYTE_LATIN_ISO8859_4, Qlatin_iso8859_4, 2,
+ make_charset (LEADING_BYTE_LATIN_ISO8859_4, Qlatin_iso8859_4,
CHARSET_TYPE_96, 1, 1, 'D',
CHARSET_LEFT_TO_RIGHT,
build_string ("Latin-4"),
build_string ("ISO8859-4 (Latin-4)"),
build_string ("ISO8859-4 (Latin-4)"),
- build_string ("iso8859-4"));
+ build_string ("iso8859-4"),
+ Qnil, 0, 0, 0, 32);
Vcharset_thai_tis620 =
- make_charset (LEADING_BYTE_THAI_TIS620, Qthai_tis620, 2,
+ make_charset (LEADING_BYTE_THAI_TIS620, Qthai_tis620,
CHARSET_TYPE_96, 1, 1, 'T',
CHARSET_LEFT_TO_RIGHT,
build_string ("TIS620"),
build_string ("TIS620 (Thai)"),
build_string ("TIS620.2529 (Thai)"),
- build_string ("tis620"));
+ build_string ("tis620"),
+ Qnil, MIN_CHAR_THAI, MAX_CHAR_THAI, 0, 32);
Vcharset_greek_iso8859_7 =
- make_charset (LEADING_BYTE_GREEK_ISO8859_7, Qgreek_iso8859_7, 2,
+ make_charset (LEADING_BYTE_GREEK_ISO8859_7, Qgreek_iso8859_7,
CHARSET_TYPE_96, 1, 1, 'F',
CHARSET_LEFT_TO_RIGHT,
build_string ("ISO8859-7"),
build_string ("ISO8859-7 (Greek)"),
build_string ("ISO8859-7 (Greek)"),
- build_string ("iso8859-7"));
+ build_string ("iso8859-7"),
+ Qnil, MIN_CHAR_GREEK, MAX_CHAR_GREEK, 0, 32);
Vcharset_arabic_iso8859_6 =
- make_charset (LEADING_BYTE_ARABIC_ISO8859_6, Qarabic_iso8859_6, 2,
+ make_charset (LEADING_BYTE_ARABIC_ISO8859_6, Qarabic_iso8859_6,
CHARSET_TYPE_96, 1, 1, 'G',
CHARSET_RIGHT_TO_LEFT,
build_string ("ISO8859-6"),
build_string ("ISO8859-6 (Arabic)"),
build_string ("ISO8859-6 (Arabic)"),
- build_string ("iso8859-6"));
+ build_string ("iso8859-6"),
+ Qnil, 0, 0, 0, 32);
Vcharset_hebrew_iso8859_8 =
- make_charset (LEADING_BYTE_HEBREW_ISO8859_8, Qhebrew_iso8859_8, 2,
+ make_charset (LEADING_BYTE_HEBREW_ISO8859_8, Qhebrew_iso8859_8,
CHARSET_TYPE_96, 1, 1, 'H',
CHARSET_RIGHT_TO_LEFT,
build_string ("ISO8859-8"),
build_string ("ISO8859-8 (Hebrew)"),
build_string ("ISO8859-8 (Hebrew)"),
- build_string ("iso8859-8"));
+ build_string ("iso8859-8"),
+ Qnil, MIN_CHAR_HEBREW, MAX_CHAR_HEBREW, 0, 32);
Vcharset_katakana_jisx0201 =
- make_charset (LEADING_BYTE_KATAKANA_JISX0201, Qkatakana_jisx0201, 2,
+ make_charset (LEADING_BYTE_KATAKANA_JISX0201, Qkatakana_jisx0201,
CHARSET_TYPE_94, 1, 1, 'I',
CHARSET_LEFT_TO_RIGHT,
build_string ("JISX0201 Kana"),
build_string ("JISX0201.1976 (Japanese Kana)"),
build_string ("JISX0201.1976 Japanese Kana"),
- build_string ("jisx0201.1976"));
+ build_string ("jisx0201\\.1976"),
+ Qnil,
+ MIN_CHAR_HALFWIDTH_KATAKANA,
+ MAX_CHAR_HALFWIDTH_KATAKANA, 0, 33);
Vcharset_latin_jisx0201 =
- make_charset (LEADING_BYTE_LATIN_JISX0201, Qlatin_jisx0201, 2,
+ make_charset (LEADING_BYTE_LATIN_JISX0201, Qlatin_jisx0201,
CHARSET_TYPE_94, 1, 0, 'J',
CHARSET_LEFT_TO_RIGHT,
build_string ("JISX0201 Roman"),
build_string ("JISX0201.1976 (Japanese Roman)"),
build_string ("JISX0201.1976 Japanese Roman"),
- build_string ("jisx0201.1976"));
+ build_string ("jisx0201\\.1976"),
+ Qnil, 0, 0, 0, 33);
Vcharset_cyrillic_iso8859_5 =
- make_charset (LEADING_BYTE_CYRILLIC_ISO8859_5, Qcyrillic_iso8859_5, 2,
+ make_charset (LEADING_BYTE_CYRILLIC_ISO8859_5, Qcyrillic_iso8859_5,
CHARSET_TYPE_96, 1, 1, 'L',
CHARSET_LEFT_TO_RIGHT,
build_string ("ISO8859-5"),
build_string ("ISO8859-5 (Cyrillic)"),
build_string ("ISO8859-5 (Cyrillic)"),
- build_string ("iso8859-5"));
+ build_string ("iso8859-5"),
+ Qnil, MIN_CHAR_CYRILLIC, MAX_CHAR_CYRILLIC, 0, 32);
Vcharset_latin_iso8859_9 =
- make_charset (LEADING_BYTE_LATIN_ISO8859_9, Qlatin_iso8859_9, 2,
+ make_charset (LEADING_BYTE_LATIN_ISO8859_9, Qlatin_iso8859_9,
CHARSET_TYPE_96, 1, 1, 'M',
CHARSET_LEFT_TO_RIGHT,
build_string ("Latin-5"),
build_string ("ISO8859-9 (Latin-5)"),
build_string ("ISO8859-9 (Latin-5)"),
- build_string ("iso8859-9"));
+ build_string ("iso8859-9"),
+ Qnil, 0, 0, 0, 32);
Vcharset_japanese_jisx0208_1978 =
- make_charset (LEADING_BYTE_JAPANESE_JISX0208_1978, Qjapanese_jisx0208_1978, 3,
+ make_charset (LEADING_BYTE_JAPANESE_JISX0208_1978, Qjapanese_jisx0208_1978,
CHARSET_TYPE_94X94, 2, 0, '@',
CHARSET_LEFT_TO_RIGHT,
- build_string ("JISX0208.1978"),
- build_string ("JISX0208.1978 (Japanese)"),
+ build_string ("JIS X0208:1978"),
+ build_string ("JIS X0208:1978 (Japanese)"),
build_string
- ("JISX0208.1978 Japanese Kanji (so called \"old JIS\")"),
- build_string ("\\(jisx0208\\|jisc6226\\)\\.1978"));
+ ("JIS X0208:1978 Japanese Kanji (so called \"old JIS\")"),
+ build_string ("\\(jisx0208\\|jisc6226\\)\\.1978"),
+ Qnil, 0, 0, 0, 33);
Vcharset_chinese_gb2312 =
- make_charset (LEADING_BYTE_CHINESE_GB2312, Qchinese_gb2312, 3,
+ make_charset (LEADING_BYTE_CHINESE_GB2312, Qchinese_gb2312,
CHARSET_TYPE_94X94, 2, 0, 'A',
CHARSET_LEFT_TO_RIGHT,
build_string ("GB2312"),
build_string ("GB2312)"),
build_string ("GB2312 Chinese simplified"),
- build_string ("gb2312"));
+ build_string ("gb2312"),
+ Qnil, 0, 0, 0, 33);
Vcharset_japanese_jisx0208 =
- make_charset (LEADING_BYTE_JAPANESE_JISX0208, Qjapanese_jisx0208, 3,
+ make_charset (LEADING_BYTE_JAPANESE_JISX0208, Qjapanese_jisx0208,
CHARSET_TYPE_94X94, 2, 0, 'B',
CHARSET_LEFT_TO_RIGHT,
build_string ("JISX0208"),
- build_string ("JISX0208.1983/1990 (Japanese)"),
- build_string ("JISX0208.1983/1990 Japanese Kanji"),
- build_string ("jisx0208.19\\(83\\|90\\)"));
+ build_string ("JIS X0208:1983 (Japanese)"),
+ build_string ("JIS X0208:1983 Japanese Kanji"),
+ build_string ("jisx0208\\.1983"),
+ Qnil, 0, 0, 0, 33);
Vcharset_korean_ksc5601 =
- make_charset (LEADING_BYTE_KOREAN_KSC5601, Qkorean_ksc5601, 3,
+ make_charset (LEADING_BYTE_KOREAN_KSC5601, Qkorean_ksc5601,
CHARSET_TYPE_94X94, 2, 0, 'C',
CHARSET_LEFT_TO_RIGHT,
build_string ("KSC5601"),
build_string ("KSC5601 (Korean"),
build_string ("KSC5601 Korean Hangul and Hanja"),
- build_string ("ksc5601"));
+ build_string ("ksc5601"),
+ Qnil, 0, 0, 0, 33);
Vcharset_japanese_jisx0212 =
- make_charset (LEADING_BYTE_JAPANESE_JISX0212, Qjapanese_jisx0212, 3,
+ make_charset (LEADING_BYTE_JAPANESE_JISX0212, Qjapanese_jisx0212,
CHARSET_TYPE_94X94, 2, 0, 'D',
CHARSET_LEFT_TO_RIGHT,
build_string ("JISX0212"),
build_string ("JISX0212 (Japanese)"),
build_string ("JISX0212 Japanese Supplement"),
- build_string ("jisx0212"));
+ build_string ("jisx0212"),
+ Qnil, 0, 0, 0, 33);
#define CHINESE_CNS_PLANE_RE(n) "cns11643[.-]\\(.*[.-]\\)?" n "$"
Vcharset_chinese_cns11643_1 =
- make_charset (LEADING_BYTE_CHINESE_CNS11643_1, Qchinese_cns11643_1, 3,
+ make_charset (LEADING_BYTE_CHINESE_CNS11643_1, Qchinese_cns11643_1,
CHARSET_TYPE_94X94, 2, 0, 'G',
CHARSET_LEFT_TO_RIGHT,
build_string ("CNS11643-1"),
build_string ("CNS11643-1 (Chinese traditional)"),
build_string
("CNS 11643 Plane 1 Chinese traditional"),
- build_string (CHINESE_CNS_PLANE_RE("1")));
+ build_string (CHINESE_CNS_PLANE_RE("1")),
+ Qnil, 0, 0, 0, 33);
Vcharset_chinese_cns11643_2 =
- make_charset (LEADING_BYTE_CHINESE_CNS11643_2, Qchinese_cns11643_2, 3,
+ make_charset (LEADING_BYTE_CHINESE_CNS11643_2, Qchinese_cns11643_2,
CHARSET_TYPE_94X94, 2, 0, 'H',
CHARSET_LEFT_TO_RIGHT,
build_string ("CNS11643-2"),
build_string ("CNS11643-2 (Chinese traditional)"),
build_string
("CNS 11643 Plane 2 Chinese traditional"),
- build_string (CHINESE_CNS_PLANE_RE("2")));
+ build_string (CHINESE_CNS_PLANE_RE("2")),
+ Qnil, 0, 0, 0, 33);
+#ifdef UTF2000
+ Vcharset_latin_viscii_lower =
+ make_charset (LEADING_BYTE_LATIN_VISCII_LOWER, Qlatin_viscii_lower,
+ CHARSET_TYPE_96, 1, 1, '1',
+ CHARSET_LEFT_TO_RIGHT,
+ build_string ("VISCII lower"),
+ build_string ("VISCII lower (Vietnamese)"),
+ build_string ("VISCII lower (Vietnamese)"),
+ build_string ("VISCII1\\.1"),
+ Qnil, 0, 0, 0, 32);
+ Vcharset_latin_viscii_upper =
+ make_charset (LEADING_BYTE_LATIN_VISCII_UPPER, Qlatin_viscii_upper,
+ CHARSET_TYPE_96, 1, 1, '2',
+ CHARSET_LEFT_TO_RIGHT,
+ build_string ("VISCII upper"),
+ build_string ("VISCII upper (Vietnamese)"),
+ build_string ("VISCII upper (Vietnamese)"),
+ build_string ("VISCII1\\.1"),
+ Qnil, 0, 0, 0, 32);
+ Vcharset_hiragana_jisx0208 =
+ make_charset (LEADING_BYTE_HIRAGANA_JISX0208, Qhiragana_jisx0208,
+ CHARSET_TYPE_94X94, 2, 0, 'B',
+ CHARSET_LEFT_TO_RIGHT,
+ build_string ("Hiragana"),
+ build_string ("Hiragana of JIS X0208"),
+ build_string ("Japanese Hiragana of JIS X0208"),
+ build_string ("jisx0208\\.19\\(78\\|83\\|90\\)"),
+ Qnil, MIN_CHAR_HIRAGANA, MAX_CHAR_HIRAGANA,
+ (0x24 - 33) * 94 + (0x21 - 33), 33);
+ Vcharset_katakana_jisx0208 =
+ make_charset (LEADING_BYTE_KATAKANA_JISX0208, Qkatakana_jisx0208,
+ CHARSET_TYPE_94X94, 2, 0, 'B',
+ CHARSET_LEFT_TO_RIGHT,
+ build_string ("Katakana"),
+ build_string ("Katakana of JIS X0208"),
+ build_string ("Japanese Katakana of JIS X0208"),
+ build_string ("jisx0208\\.19\\(78\\|83\\|90\\)"),
+ Qnil, MIN_CHAR_KATAKANA, MAX_CHAR_KATAKANA,
+ (0x25 - 33) * 94 + (0x21 - 33), 33);
+#endif
Vcharset_chinese_big5_1 =
- make_charset (LEADING_BYTE_CHINESE_BIG5_1, Qchinese_big5_1, 3,
+ make_charset (LEADING_BYTE_CHINESE_BIG5_1, Qchinese_big5_1,
CHARSET_TYPE_94X94, 2, 0, '0',
CHARSET_LEFT_TO_RIGHT,
build_string ("Big5"),
build_string ("Big5 (Level-1)"),
build_string
("Big5 Level-1 Chinese traditional"),
- build_string ("big5"));
+ build_string ("big5"),
+ Qnil, 0, 0, 0, 33);
Vcharset_chinese_big5_2 =
- make_charset (LEADING_BYTE_CHINESE_BIG5_2, Qchinese_big5_2, 3,
+ make_charset (LEADING_BYTE_CHINESE_BIG5_2, Qchinese_big5_2,
CHARSET_TYPE_94X94, 2, 0, '1',
CHARSET_LEFT_TO_RIGHT,
build_string ("Big5"),
build_string ("Big5 (Level-2)"),
build_string
("Big5 Level-2 Chinese traditional"),
- build_string ("big5"));
-
+ build_string ("big5"),
+ Qnil, 0, 0, 0, 33);
#ifdef ENABLE_COMPOSITE_CHARS
/* #### For simplicity, we put composite chars into a 96x96 charset.
This is going to lead to problems because you can run out of
room, esp. as we don't yet recycle numbers. */
Vcharset_composite =
- make_charset (LEADING_BYTE_COMPOSITE, Qcomposite, 3,
+ make_charset (LEADING_BYTE_COMPOSITE, Qcomposite,
CHARSET_TYPE_96X96, 2, 0, 0,
CHARSET_LEFT_TO_RIGHT,
build_string ("Composite"),