#include "lstream.h"
#include "device.h"
#include "faces.h"
+#include "mule-ccl.h"
/* The various pre-defined charsets. */
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;
+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;
#endif /* ENABLE_COMPOSITE_CHARS */
/* Table of charsets indexed by leading byte. */
-Lisp_Object charset_by_leading_byte[128];
+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
indexed by the first byte of that representation.
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
/* 0x80 - 0x8f are for Dimension-1 official charsets */
+#ifdef CHAR_IS_UCS4
2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3,
+#else
+ 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
+#endif
/* 0x90 - 0x9d are for Dimension-2 official charsets */
/* 0x9e is for Dimension-1 private charsets */
/* 0x9f is for Dimension-2 private charsets */
3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 4
};
+#endif
+
+#ifdef UTF2000
+static Lisp_Object
+mark_char_byte_table (Lisp_Object obj, void (*markobj) (Lisp_Object))
+{
+ struct Lisp_Char_Byte_Table *cte = XCHAR_BYTE_TABLE (obj);
+ int i;
+
+ for (i = 0; i < 256; i++)
+ {
+ markobj (cte->property[i]);
+ }
+ return Qnil;
+}
+
+static int
+char_byte_table_equal (Lisp_Object obj1, Lisp_Object obj2, int depth)
+{
+ struct Lisp_Char_Byte_Table *cte1 = XCHAR_BYTE_TABLE (obj1);
+ struct Lisp_Char_Byte_Table *cte2 = XCHAR_BYTE_TABLE (obj2);
+ int i;
+
+ for (i = 0; i < 256; i++)
+ if (CHAR_BYTE_TABLE_P (cte1->property[i]))
+ {
+ if (CHAR_BYTE_TABLE_P (cte2->property[i]))
+ {
+ if (!char_byte_table_equal (cte1->property[i],
+ cte2->property[i], depth + 1))
+ return 0;
+ }
+ else
+ return 0;
+ }
+ else
+ if (!internal_equal (cte1->property[i], cte2->property[i], depth + 1))
+ return 0;
+ return 1;
+}
+
+static unsigned long
+char_byte_table_hash (Lisp_Object obj, int depth)
+{
+ struct Lisp_Char_Byte_Table *cte = XCHAR_BYTE_TABLE (obj);
+
+ return internal_array_hash (cte->property, 256, depth);
+}
+
+static const struct lrecord_description char_byte_table_description[] = {
+ { XD_LISP_OBJECT, offsetof(struct Lisp_Char_Byte_Table, property), 256 },
+ { XD_END }
+};
+
+DEFINE_LRECORD_IMPLEMENTATION ("char-code-table", char_byte_table,
+ mark_char_byte_table,
+ internal_object_printer,
+ 0, char_byte_table_equal,
+ char_byte_table_hash,
+ char_byte_table_description,
+ struct Lisp_Char_Byte_Table);
+
+
+static Lisp_Object
+make_char_byte_table (Lisp_Object initval)
+{
+ Lisp_Object obj;
+ int i;
+ struct Lisp_Char_Byte_Table *cte =
+ alloc_lcrecord_type (struct Lisp_Char_Byte_Table,
+ &lrecord_char_byte_table);
+
+ for (i = 0; i < 256; i++)
+ cte->property[i] = initval;
+
+ XSETCHAR_BYTE_TABLE (obj, cte);
+ return obj;
+}
+
+static Lisp_Object
+copy_char_byte_table (Lisp_Object entry)
+{
+ struct Lisp_Char_Byte_Table *cte = XCHAR_BYTE_TABLE (entry);
+ Lisp_Object obj;
+ int i;
+ struct Lisp_Char_Byte_Table *ctenew =
+ alloc_lcrecord_type (struct Lisp_Char_Byte_Table,
+ &lrecord_char_byte_table);
+
+ for (i = 0; i < 256; i++)
+ {
+ Lisp_Object new = cte->property[i];
+ if (CHAR_BYTE_TABLE_P (new))
+ ctenew->property[i] = copy_char_byte_table (new);
+ else
+ ctenew->property[i] = new;
+ }
+
+ XSETCHAR_BYTE_TABLE (obj, ctenew);
+ return obj;
+}
+
+#define make_char_code_table(initval) make_char_byte_table(initval)
+
+Lisp_Object
+get_char_code_table (Emchar ch, Lisp_Object table)
+{
+ struct Lisp_Char_Byte_Table* cpt = XCHAR_BYTE_TABLE (table);
+ Lisp_Object ret = cpt->property [ch >> 24];
+
+ if (CHAR_BYTE_TABLE_P (ret))
+ cpt = XCHAR_BYTE_TABLE (ret);
+ else
+ return ret;
+
+ ret = cpt->property [(unsigned char) (ch >> 16)];
+ if (CHAR_BYTE_TABLE_P (ret))
+ cpt = XCHAR_BYTE_TABLE (ret);
+ else
+ return ret;
+
+ ret = cpt->property [(unsigned char) (ch >> 8)];
+ if (CHAR_BYTE_TABLE_P (ret))
+ cpt = XCHAR_BYTE_TABLE (ret);
+ else
+ return ret;
+
+ return cpt->property [(unsigned char) ch];
+}
+
+void
+put_char_code_table (Emchar ch, Lisp_Object value, Lisp_Object table)
+{
+ struct Lisp_Char_Byte_Table* cpt1 = XCHAR_BYTE_TABLE (table);
+ Lisp_Object ret = cpt1->property[ch >> 24];
+
+ if (CHAR_BYTE_TABLE_P (ret))
+ {
+ struct Lisp_Char_Byte_Table* cpt2 = XCHAR_BYTE_TABLE (ret);
+
+ ret = cpt2->property[(unsigned char)(ch >> 16)];
+ if (CHAR_BYTE_TABLE_P (ret))
+ {
+ struct Lisp_Char_Byte_Table* cpt3 = XCHAR_BYTE_TABLE (ret);
+
+ ret = cpt3->property[(unsigned char)(ch >> 8)];
+ if (CHAR_BYTE_TABLE_P (ret))
+ {
+ struct Lisp_Char_Byte_Table* cpt4
+ = XCHAR_BYTE_TABLE (ret);
+
+ cpt4->property[(unsigned char)ch] = value;
+ }
+ else if (!EQ (ret, value))
+ {
+ Lisp_Object cpt4 = make_char_byte_table (ret);
+
+ XCHAR_BYTE_TABLE(cpt4)->property[(unsigned char)ch] = value;
+ cpt3->property[(unsigned char)(ch >> 8)] = cpt4;
+ }
+ }
+ else if (!EQ (ret, value))
+ {
+ Lisp_Object cpt3 = make_char_byte_table (ret);
+ Lisp_Object cpt4 = make_char_byte_table (ret);
+
+ XCHAR_BYTE_TABLE(cpt4)->property[(unsigned char)ch] = value;
+ XCHAR_BYTE_TABLE(cpt3)->property[(unsigned char)(ch >> 8)]
+ = cpt4;
+ cpt2->property[(unsigned char)(ch >> 16)] = cpt3;
+ }
+ }
+ else if (!EQ (ret, value))
+ {
+ Lisp_Object cpt2 = make_char_byte_table (ret);
+ Lisp_Object cpt3 = make_char_byte_table (ret);
+ Lisp_Object cpt4 = make_char_byte_table (ret);
+
+ XCHAR_BYTE_TABLE(cpt4)->property[(unsigned char)ch] = value;
+ XCHAR_BYTE_TABLE(cpt3)->property[(unsigned char)(ch >> 8)] = cpt4;
+ XCHAR_BYTE_TABLE(cpt2)->property[(unsigned char)(ch >> 16)] = cpt3;
+ cpt1->property[(unsigned char)(ch >> 24)] = cpt2;
+ }
+}
+
+
+Lisp_Object Vcharacter_attribute_table;
+
+DEFUN ("char-attribute-alist", Fchar_attribute_alist, 1, 1, 0, /*
+Return the alist of attributes of CHARACTER.
+*/
+ (character))
+{
+ return get_char_code_table (XCHAR (character), Vcharacter_attribute_table);
+}
+
+DEFUN ("get-char-attribute", Fget_char_attribute, 2, 2, 0, /*
+Return the value of CHARACTER's ATTRIBUTE.
+*/
+ (character, attribute))
+{
+ Lisp_Object ret
+ = get_char_code_table (XCHAR (character), Vcharacter_attribute_table);
+ Lisp_Object ccs;
+
+ if (EQ (ret, Qnil))
+ return Qnil;
+
+ if (!NILP (ccs = Ffind_charset (attribute)))
+ attribute = ccs;
+
+ return Fcdr (Fassq (attribute, ret));
+}
+
+Lisp_Object
+put_char_attribute (Lisp_Object character, Lisp_Object attribute,
+ Lisp_Object value)
+{
+ Emchar char_code = XCHAR (character);
+ Lisp_Object ret
+ = get_char_code_table (char_code, Vcharacter_attribute_table);
+ Lisp_Object cell;
+
+ cell = Fassq (attribute, ret);
+
+ if (NILP (cell))
+ {
+ ret = Fcons (Fcons (attribute, value), ret);
+ }
+ else if (!EQ (Fcdr (cell), value))
+ {
+ Fsetcdr (cell, value);
+ }
+ put_char_code_table (char_code, ret, Vcharacter_attribute_table);
+ return ret;
+}
+
+DEFUN ("put-char-attribute", Fput_char_attribute, 3, 3, 0, /*
+Store CHARACTER's ATTRIBUTE with VALUE.
+*/
+ (character, attribute, value))
+{
+ Lisp_Object ccs;
+
+ ccs = Ffind_charset (attribute);
+ if (!NILP (ccs))
+ {
+ Lisp_Object rest;
+ Lisp_Object v = XCHARSET_DECODING_TABLE (ccs);
+ Lisp_Object nv;
+ int i = -1;
+ int ccs_len;
+
+ /* ad-hoc method for `ascii' */
+ if ((XCHARSET_CHARS (ccs) == 94) &&
+ (XCHARSET_BYTE_OFFSET (ccs) != 33))
+ ccs_len = 128 - XCHARSET_BYTE_OFFSET (ccs);
+ else
+ ccs_len = XCHARSET_CHARS (ccs);
+
+ if (!CONSP (value))
+ signal_simple_error ("Invalid value for coded-charset",
+ value);
+
+ attribute = ccs;
+ rest = Fget_char_attribute (character, attribute);
+ if (VECTORP (v))
+ {
+ if (!NILP (rest))
+ {
+ while (!NILP (rest))
+ {
+ Lisp_Object ei = Fcar (rest);
+
+ i = XINT (ei) - XCHARSET_BYTE_OFFSET (ccs);
+ nv = XVECTOR_DATA(v)[i];
+ if (!VECTORP (nv))
+ break;
+ v = nv;
+ rest = Fcdr (rest);
+ }
+ if (i >= 0)
+ XVECTOR_DATA(v)[i] = Qnil;
+ v = XCHARSET_DECODING_TABLE (ccs);
+ }
+ }
+ else
+ {
+ XCHARSET_DECODING_TABLE (ccs) = v = make_vector (ccs_len, Qnil);
+ }
+
+ rest = value;
+ i = -1;
+ while (CONSP (rest))
+ {
+ Lisp_Object ei = Fcar (rest);
+
+ if (!INTP (ei))
+ signal_simple_error ("Invalid value for coded-charset",
+ value);
+ i = XINT (ei) - XCHARSET_BYTE_OFFSET (ccs);
+ nv = XVECTOR_DATA(v)[i];
+ rest = Fcdr (rest);
+ if (CONSP (rest))
+ {
+ if (!VECTORP (nv))
+ {
+ nv = (XVECTOR_DATA(v)[i] = make_vector (ccs_len, Qnil));
+ }
+ v = nv;
+ }
+ else
+ break;
+ }
+ XVECTOR_DATA(v)[i] = character;
+ }
+ return put_char_attribute (character, attribute, value);
+}
+
+Lisp_Object Qucs;
+
+DEFUN ("define-char", Fdefine_char, 1, 1, 0, /*
+Store character's ATTRIBUTES.
+*/
+ (attributes))
+{
+ Lisp_Object rest = attributes;
+ Lisp_Object code = Fcdr (Fassq (Qucs, attributes));
+ Lisp_Object character;
+
+ if (NILP (code))
+ {
+ while (CONSP (rest))
+ {
+ Lisp_Object cell = Fcar (rest);
+ Lisp_Object ccs;
+
+ if (!LISTP (cell))
+ signal_simple_error ("Invalid argument", attributes);
+ if (!NILP (ccs = Ffind_charset (Fcar (cell)))
+ && XCHARSET_FINAL (ccs))
+ {
+ Emchar code;
+
+ if (XCHARSET_DIMENSION (ccs) == 1)
+ {
+ Lisp_Object eb1 = Fcar (Fcdr (cell));
+ int b1;
+
+ if (!INTP (eb1))
+ signal_simple_error ("Invalid argument", attributes);
+ b1 = XINT (eb1);
+ switch (XCHARSET_CHARS (ccs))
+ {
+ case 94:
+ code = MIN_CHAR_94
+ + (XCHARSET_FINAL (ccs) - '0') * 94 + (b1 - 33);
+ break;
+ case 96:
+ code = MIN_CHAR_96
+ + (XCHARSET_FINAL (ccs) - '0') * 96 + (b1 - 32);
+ break;
+ default:
+ abort ();
+ }
+ }
+ else if (XCHARSET_DIMENSION (ccs) == 2)
+ {
+ Lisp_Object eb1 = Fcar (Fcdr (cell));
+ Lisp_Object eb2 = Fcar (Fcdr (Fcdr (cell)));
+ int b1, b2;
+
+ if (!INTP (eb1))
+ signal_simple_error ("Invalid argument", attributes);
+ b1 = XINT (eb1);
+ if (!INTP (eb2))
+ signal_simple_error ("Invalid argument", attributes);
+ b2 = XINT (eb2);
+ switch (XCHARSET_CHARS (ccs))
+ {
+ case 94:
+ code = MIN_CHAR_94x94
+ + (XCHARSET_FINAL (ccs) - '0') * 94 * 94
+ + (b1 - 33) * 94 + (b2 - 33);
+ break;
+ case 96:
+ code = MIN_CHAR_96x96
+ + (XCHARSET_FINAL (ccs) - '0') * 96 * 96
+ + (b1 - 32) * 96 + (b2 - 32);
+ break;
+ default:
+ abort ();
+ }
+ }
+ else
+ {
+ rest = Fcdr (rest);
+ continue;
+ }
+ character = make_char (code);
+ goto setup_attributes;
+ }
+ rest = Fcdr (rest);
+ }
+ return Qnil;
+ }
+ else if (!INTP (code))
+ signal_simple_error ("Invalid argument", attributes);
+ else
+ character = make_char (XINT (code));
+
+ setup_attributes:
+ rest = attributes;
+ while (CONSP (rest))
+ {
+ Lisp_Object cell = Fcar (rest);
+
+ if (!LISTP (cell))
+ signal_simple_error ("Invalid argument", attributes);
+ Fput_char_attribute (character, Fcar (cell), Fcdr (cell));
+ rest = Fcdr (rest);
+ }
+ return
+ get_char_code_table (XCHAR (character), Vcharacter_attribute_table);
+}
Lisp_Object Vutf_2000_version;
+#endif
+#ifndef UTF2000
int leading_code_private_11;
+#endif
Lisp_Object Qcharsetp;
Lisp_Object Qregistry, Qfinal, Qgraphic;
Lisp_Object Qdirection;
Lisp_Object Qreverse_direction_charset;
-Lisp_Object Qccl_program;
Lisp_Object Qleading_byte;
Lisp_Object Qshort_name, Qlong_name;
Qjapanese_jisx0212,
Qchinese_cns11643_1,
Qchinese_cns11643_2,
+#ifdef UTF2000
+ Qucs_bmp,
+ Qlatin_viscii,
+ 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;
+#ifdef UTF2000
+static Charset_ID next_allocated_leading_byte;
+#else
+static Charset_ID next_allocated_1_byte_leading_byte;
+static Charset_ID next_allocated_2_byte_leading_byte;
+#endif
/* 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;
}
write_c_string (buf, printcharfun);
}
+static const struct lrecord_description charset_description[] = {
+ { XD_LISP_OBJECT, offsetof(struct Lisp_Charset, name), 7 },
+#ifdef UTF2000
+ { XD_LISP_OBJECT, offsetof(struct Lisp_Charset, decoding_table), 2 },
+#endif
+ { XD_END }
+};
+
DEFINE_LRECORD_IMPLEMENTATION ("charset", charset,
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) = Qnil;
+ 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
- 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;
+ switch (CHARSET_TYPE (cs))
+ {
+ case CHARSET_TYPE_94:
+ CHARSET_DIMENSION (cs) = 1;
+ CHARSET_CHARS (cs) = 94;
+ break;
+ case CHARSET_TYPE_96:
+ CHARSET_DIMENSION (cs) = 1;
+ CHARSET_CHARS (cs) = 96;
+ break;
+ case CHARSET_TYPE_94X94:
+ CHARSET_DIMENSION (cs) = 2;
+ CHARSET_CHARS (cs) = 94;
+ break;
+ case CHARSET_TYPE_96X96:
+ CHARSET_DIMENSION (cs) = 2;
+ CHARSET_CHARS (cs) = 96;
+ break;
+#ifdef UTF2000
+ case CHARSET_TYPE_128:
+ CHARSET_DIMENSION (cs) = 1;
+ CHARSET_CHARS (cs) = 128;
+ break;
+ case CHARSET_TYPE_128X128:
+ CHARSET_DIMENSION (cs) = 2;
+ CHARSET_CHARS (cs) = 128;
+ break;
+ case CHARSET_TYPE_256:
+ CHARSET_DIMENSION (cs) = 1;
+ CHARSET_CHARS (cs) = 256;
+ break;
+ case CHARSET_TYPE_256X256:
+ CHARSET_DIMENSION (cs) = 2;
+ CHARSET_CHARS (cs) = 256;
+ break;
+#endif
+ }
+#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 - 128]));
- charset_by_leading_byte[id - 128] = obj;
+ assert (NILP (charset_by_leading_byte[id - MIN_LEADING_BYTE]));
+ charset_by_leading_byte[id - MIN_LEADING_BYTE] = obj;
+#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
all except in the leading-byte table. */
static int
get_unallocated_leading_byte (int dimension)
{
- int lb;
+ Charset_ID lb;
+#ifdef UTF2000
+ if (next_allocated_leading_byte > MAX_LEADING_BYTE_PRIVATE)
+ lb = 0;
+ else
+ lb = next_allocated_leading_byte++;
+#else
if (dimension == 1)
{
if (next_allocated_1_byte_leading_byte > MAX_LEADING_BYTE_PRIVATE_1)
else
lb = next_allocated_2_byte_leading_byte++;
}
+#endif
if (!lb)
signal_simple_error
return lb;
}
+#ifdef UTF2000
+Lisp_Object
+range_charset_code_point (Lisp_Object charset, Emchar ch)
+{
+ int d;
+
+ if ((XCHARSET_UCS_MIN (charset) <= ch)
+ && (ch <= XCHARSET_UCS_MAX (charset)))
+ {
+ d = ch - XCHARSET_UCS_MIN (charset) + XCHARSET_CODE_OFFSET (charset);
+
+ if (XCHARSET_DIMENSION (charset) == 1)
+ return list1 (make_int (d + XCHARSET_BYTE_OFFSET (charset)));
+ else if (XCHARSET_DIMENSION (charset) == 2)
+ return list2 (make_int (d / XCHARSET_CHARS (charset)
+ + XCHARSET_BYTE_OFFSET (charset)),
+ make_int (d % XCHARSET_CHARS (charset)
+ + XCHARSET_BYTE_OFFSET (charset)));
+ else if (XCHARSET_DIMENSION (charset) == 3)
+ return list3 (make_int (d / (XCHARSET_CHARS (charset)
+ * XCHARSET_CHARS (charset))
+ + XCHARSET_BYTE_OFFSET (charset)),
+ make_int (d / XCHARSET_CHARS (charset)
+ % XCHARSET_CHARS (charset)
+ + XCHARSET_BYTE_OFFSET (charset)),
+ make_int (d % XCHARSET_CHARS (charset)
+ + XCHARSET_BYTE_OFFSET (charset)));
+ else /* if (XCHARSET_DIMENSION (charset) == 4) */
+ return list4 (make_int (d / (XCHARSET_CHARS (charset)
+ * XCHARSET_CHARS (charset)
+ * XCHARSET_CHARS (charset))
+ + XCHARSET_BYTE_OFFSET (charset)),
+ make_int (d / (XCHARSET_CHARS (charset)
+ * XCHARSET_CHARS (charset))
+ % XCHARSET_CHARS (charset)
+ + XCHARSET_BYTE_OFFSET (charset)),
+ make_int (d / XCHARSET_CHARS (charset)
+ % XCHARSET_CHARS (charset)
+ + XCHARSET_BYTE_OFFSET (charset)),
+ make_int (d % 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 list1 (make_int (d + 33));
+ }
+ else if (XCHARSET_CHARS (charset) == 96)
+ {
+ if (((d = ch - (MIN_CHAR_96
+ + (XCHARSET_FINAL (charset) - '0') * 96)) >= 0)
+ && (d < 96))
+ return list1 (make_int (d + 32));
+ }
+ else
+ return Qnil;
+ }
+ 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 list2 ((d / 94) + 33, 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 list2 ((d / 96) + 32, d % 96 + 32);
+ }
+ }
+ }
+ return Qnil;
+}
+
+Lisp_Object
+charset_code_point (Lisp_Object charset, Emchar ch)
+{
+ Lisp_Object cdef = get_char_code_table (ch, Vcharacter_attribute_table);
+
+ if (!EQ (cdef, Qnil))
+ {
+ Lisp_Object field = Fassq (charset, cdef);
+
+ if (!EQ (field, Qnil))
+ return Fcdr (field);
+ }
+ return range_charset_code_point (charset, ch);
+}
+
+Lisp_Object Vdefault_coded_charset_priority_list;
+#endif
+
\f
/************************************************************************/
/* Basic charset Lisp functions */
Lisp_Object rest, keyword, value;
Lisp_Object ccl_program = Qnil;
Lisp_Object short_name = Qnil, long_name = Qnil;
+ unsigned char byte_offset = 0;
CHECK_SYMBOL (name);
if (!NILP (doc_string))
{
CHECK_INT (value);
graphic = XINT (value);
+#ifdef UTF2000
+ if (graphic < 0 || graphic > 2)
+#else
if (graphic < 0 || graphic > 1)
+#endif
signal_simple_error ("Invalid value for 'graphic", value);
}
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, byte_offset);
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;
+ Lisp_Object old_table;
+ size_t i;
+
+ charset = Fget_charset (charset);
+ cs = XCHARSET (charset);
+
+ if (EQ (table, Qnil))
+ {
+ CHARSET_DECODING_TABLE(cs) = table;
+ return table;
+ }
+ else if (VECTORP (table))
+ {
+ if (XVECTOR_LENGTH (table) > CHARSET_CHARS (cs))
+ args_out_of_range (table, make_int (CHARSET_CHARS (cs)));
+ old_table = CHARSET_DECODING_TABLE(cs);
+ CHARSET_DECODING_TABLE(cs) = table;
+ }
+ else
+ signal_error (Qwrong_type_argument,
+ list2 (build_translated_string ("vector-or-nil-p"),
+ table));
+ /* signal_simple_error ("Wrong type argument: vector-or-nil-p", table); */
+
+ switch (CHARSET_DIMENSION (cs))
+ {
+ case 1:
+ for (i = 0; i < XVECTOR_LENGTH (table); i++)
+ {
+ Lisp_Object c = XVECTOR_DATA(table)[i];
+
+ if (CHARP (c))
+ put_char_attribute
+ (c, charset,
+ list1 (make_int (i + CHARSET_BYTE_OFFSET (cs))));
+ }
+ break;
+ case 2:
+ for (i = 0; i < XVECTOR_LENGTH (table); i++)
+ {
+ Lisp_Object v = XVECTOR_DATA(table)[i];
+
+ if (VECTORP (v))
+ {
+ size_t j;
+
+ if (XVECTOR_LENGTH (v) > CHARSET_CHARS (cs))
+ {
+ CHARSET_DECODING_TABLE(cs) = old_table;
+ args_out_of_range (v, make_int (CHARSET_CHARS (cs)));
+ }
+ for (j = 0; j < XVECTOR_LENGTH (v); j++)
+ {
+ Lisp_Object c = XVECTOR_DATA(v)[j];
+
+ if (CHARP (c))
+ put_char_attribute (c, charset,
+ list2
+ (make_int
+ (i + CHARSET_BYTE_OFFSET (cs)),
+ make_int
+ (j + CHARSET_BYTE_OFFSET (cs))));
+ }
+ }
+ else if (CHARP (v))
+ put_char_attribute (v, charset,
+ list1
+ (make_int (i + CHARSET_BYTE_OFFSET (cs))));
+ }
+ break;
+ }
+ 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 ("char-octet", Fchar_octet, 1, 2, 0, /*
-Return the octet numbered N (should be 0 or 1) of char CH.
-N defaults to 0 if omitted.
+DEFUN ("split-char", Fsplit_char, 1, 1, 0, /*
+Return list of charset and one or two position-codes of CHAR.
*/
- (ch, n))
+ (character))
{
- Lisp_Object charset;
- int c1, c2, int_n;
+ /* This function can GC */
+ struct gcpro gcpro1, gcpro2;
+ Lisp_Object charset = Qnil;
+ Lisp_Object rc = Qnil;
+ int c1, c2;
- CHECK_CHAR_COERCE_INT (ch);
- if (NILP (n))
- int_n = 0;
+ GCPRO2 (charset, rc);
+ CHECK_CHAR_COERCE_INT (character);
+
+ BREAKUP_CHAR (XCHAR (character), charset, c1, c2);
+
+ if (XCHARSET_DIMENSION (Fget_charset (charset)) == 2)
+ {
+ rc = list3 (XCHARSET_NAME (charset), make_int (c1), make_int (c2));
+ }
else
{
- CHECK_INT (n);
- int_n = XINT (n);
- if (int_n != 0 && int_n != 1)
- signal_simple_error ("Octet number must be 0 or 1", n);
+ rc = list2 (XCHARSET_NAME (charset), make_int (c1));
}
- BREAKUP_CHAR (XCHAR (ch), charset, c1, c2);
- return make_int (int_n == 0 ? c1 : c2);
+ UNGCPRO;
+
+ return rc;
}
\f
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 (Fchar_attribute_alist);
+ DEFSUBR (Fget_char_attribute);
+ DEFSUBR (Fput_char_attribute);
+ DEFSUBR (Fdefine_char);
+ DEFSUBR (Fcharset_mapping_table);
+ DEFSUBR (Fset_charset_mapping_table);
+#endif
DEFSUBR (Fmake_char);
DEFSUBR (Fchar_charset);
- DEFSUBR (Fchar_octet);
+ DEFSUBR (Fsplit_char);
#ifdef ENABLE_COMPOSITE_CHARS
DEFSUBR (Fmake_composite_char);
defsymbol (&Qgraphic, "graphic");
defsymbol (&Qdirection, "direction");
defsymbol (&Qreverse_direction_charset, "reverse-direction-charset");
- defsymbol (&Qccl_program, "ccl-program");
defsymbol (&Qshort_name, "short-name");
defsymbol (&Qlong_name, "long-name");
defsymbol (&Qjapanese_jisx0212, "japanese-jisx0212");
defsymbol (&Qchinese_cns11643_1, "chinese-cns11643-1");
defsymbol (&Qchinese_cns11643_2, "chinese-cns11643-2");
+#ifdef UTF2000
+ defsymbol (&Qucs, "ucs");
+ defsymbol (&Qucs_bmp, "ucs-bmp");
+ defsymbol (&Qlatin_viscii, "latin-viscii");
+ 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("0.2 (JR NAMBA)");
- DEFVAR_LISP ("utf-2000-version", &Vutf_2000_version /*
-Version number of UTF-2000.
-*/ );
-#endif
-
- 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;
}
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
+#ifdef UTF2000
+ next_allocated_leading_byte = MIN_LEADING_BYTE_PRIVATE;
+#else
next_allocated_1_byte_leading_byte = MIN_LEADING_BYTE_PRIVATE_1;
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("0.11 (Shiki)");
+ DEFVAR_LISP ("utf-2000-version", &Vutf_2000_version /*
+Version number of UTF-2000.
+*/ );
+
+ staticpro (&Vcharacter_attribute_table);
+ Vcharacter_attribute_table = make_char_code_table (Qnil);
+
+ Vdefault_coded_charset_priority_list = Qnil;
+ DEFVAR_LISP ("default-coded-charset-priority-list",
+ &Vdefault_coded_charset_priority_list /*
+Default order of preferred coded-character-sets.
+*/ );
+#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, 2, 0,
+ CHARSET_LEFT_TO_RIGHT,
+ build_string ("BMP"),
+ build_string ("BMP"),
+ build_string ("ISO/IEC 10646 Group 0 Plane 0 (BMP)"),
+ build_string ("\\(ISO10646.*-1\\|UNICODE[23]?-0\\)"),
+ 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 ("MULEVISCII-LOWER"),
+ 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 ("MULEVISCII-UPPER"),
+ Qnil, 0, 0, 0, 32);
+ Vcharset_latin_viscii =
+ make_charset (LEADING_BYTE_LATIN_VISCII, Qlatin_viscii,
+ CHARSET_TYPE_256, 1, 2, 0,
+ CHARSET_LEFT_TO_RIGHT,
+ build_string ("VISCII"),
+ build_string ("VISCII 1.1 (Vietnamese)"),
+ build_string ("VISCII 1.1 (Vietnamese)"),
+ build_string ("VISCII1\\.1"),
+ Qnil, 0, 0, 0, 0);
+ 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"),