/* Functions to handle multilingual characters.
Copyright (C) 1992, 1995 Free Software Foundation, Inc.
Copyright (C) 1995 Sun Microsystems, Inc.
+ Copyright (C) 1999,2000 MORIOKA Tomohiko
This file is part of XEmacs.
Lisp_Object Vcharset_japanese_jisx0208_1978;
Lisp_Object Vcharset_chinese_gb2312;
Lisp_Object Vcharset_japanese_jisx0208;
+Lisp_Object Vcharset_japanese_jisx0208_1990;
Lisp_Object Vcharset_korean_ksc5601;
Lisp_Object Vcharset_japanese_jisx0212;
Lisp_Object Vcharset_chinese_cns11643_1;
Lisp_Object Vcharset_chinese_cns11643_2;
#ifdef UTF2000
+Lisp_Object Vcharset_ucs;
Lisp_Object Vcharset_ucs_bmp;
Lisp_Object Vcharset_latin_viscii;
+Lisp_Object Vcharset_latin_tcvn5712;
Lisp_Object Vcharset_latin_viscii_lower;
Lisp_Object Vcharset_latin_viscii_upper;
+Lisp_Object Vcharset_ideograph_daikanwa;
+Lisp_Object Vcharset_mojikyo;
+Lisp_Object Vcharset_mojikyo_pj_1;
+Lisp_Object Vcharset_mojikyo_pj_2;
+Lisp_Object Vcharset_mojikyo_pj_3;
+Lisp_Object Vcharset_mojikyo_pj_4;
+Lisp_Object Vcharset_mojikyo_pj_5;
+Lisp_Object Vcharset_mojikyo_pj_6;
+Lisp_Object Vcharset_mojikyo_pj_7;
+Lisp_Object Vcharset_mojikyo_pj_8;
+Lisp_Object Vcharset_mojikyo_pj_9;
+Lisp_Object Vcharset_mojikyo_pj_10;
+Lisp_Object Vcharset_mojikyo_pj_11;
+Lisp_Object Vcharset_mojikyo_pj_12;
+Lisp_Object Vcharset_mojikyo_pj_13;
+Lisp_Object Vcharset_mojikyo_pj_14;
+Lisp_Object Vcharset_mojikyo_pj_15;
+Lisp_Object Vcharset_mojikyo_pj_16;
+Lisp_Object Vcharset_mojikyo_pj_17;
+Lisp_Object Vcharset_mojikyo_pj_18;
+Lisp_Object Vcharset_mojikyo_pj_19;
+Lisp_Object Vcharset_mojikyo_pj_20;
+Lisp_Object Vcharset_mojikyo_pj_21;
Lisp_Object Vcharset_ethiopic_ucs;
-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[NUM_LEADING_BYTES];
+struct charset_lookup *chlook;
-/* Table of charsets indexed by type/final-byte/direction. */
+static const struct lrecord_description charset_lookup_description_1[] = {
+ { XD_LISP_OBJECT, offsetof(struct charset_lookup, charset_by_leading_byte),
#ifdef UTF2000
-Lisp_Object charset_by_attributes[4][128];
+ 128+4*128
#else
-Lisp_Object charset_by_attributes[4][128][2];
+ 128+4*128*2
#endif
+ }, { XD_END }
+};
+
+static const struct struct_description charset_lookup_description = {
+ sizeof(struct charset_lookup),
+ charset_lookup_description_1
+};
#ifndef UTF2000
/* Table of number of bytes in the string representation of a character
rep_bytes_by_first_byte(c) is more efficient than the equivalent
canonical computation:
- (BYTE_ASCII_P (c) ? 1 : XCHARSET_REP_BYTES (CHARSET_BY_LEADING_BYTE (c))) */
+ XCHARSET_REP_BYTES (CHARSET_BY_LEADING_BYTE (c)) */
-Bytecount rep_bytes_by_first_byte[0xA0] =
+const Bytecount rep_bytes_by_first_byte[0xA0] =
{ /* 0x00 - 0x7f are for straight ASCII */
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,
#ifdef UTF2000
static Lisp_Object
-mark_char_byte_table (Lisp_Object obj, void (*markobj) (Lisp_Object))
+mark_char_byte_table (Lisp_Object obj)
{
struct Lisp_Char_Byte_Table *cte = XCHAR_BYTE_TABLE (obj);
int i;
for (i = 0; i < 256; i++)
{
- markobj (cte->property[i]);
+ mark_object (cte->property[i]);
}
return Qnil;
}
static Lisp_Object
-mark_char_code_table (Lisp_Object obj, void (*markobj) (Lisp_Object))
+mark_char_code_table (Lisp_Object obj)
{
struct Lisp_Char_Code_Table *cte = XCHAR_CODE_TABLE (obj);
Lisp_Object Q_decomposition;
Lisp_Object Q_ucs;
Lisp_Object Qcompat;
+Lisp_Object Qisolated;
+Lisp_Object Qinitial;
+Lisp_Object Qmedial;
+Lisp_Object Qfinal;
+Lisp_Object Qvertical;
Lisp_Object QnoBreak;
Lisp_Object Qfraction;
Lisp_Object Qsuper;
Lisp_Object Qsub;
Lisp_Object Qcircle;
+Lisp_Object Qsquare;
Lisp_Object Qwide;
Lisp_Object Qnarrow;
+Lisp_Object Qsmall;
Lisp_Object Qfont;
Emchar
return XCHAR (v);
else if (EQ (v, Qcompat))
return -1;
- else if (EQ (v, QnoBreak))
+ else if (EQ (v, Qisolated))
return -2;
- else if (EQ (v, Qfraction))
+ else if (EQ (v, Qinitial))
return -3;
- else if (EQ (v, Qsuper))
+ else if (EQ (v, Qmedial))
return -4;
- else if (EQ (v, Qsub))
+ else if (EQ (v, Qfinal))
return -5;
- else if (EQ (v, Qcircle))
+ else if (EQ (v, Qvertical))
return -6;
- else if (EQ (v, Qwide))
+ else if (EQ (v, QnoBreak))
return -7;
- else if (EQ (v, Qnarrow))
+ else if (EQ (v, Qfraction))
return -8;
- else if (EQ (v, Qfont))
+ else if (EQ (v, Qsuper))
return -9;
+ else if (EQ (v, Qsub))
+ return -10;
+ else if (EQ (v, Qcircle))
+ return -11;
+ else if (EQ (v, Qsquare))
+ return -12;
+ else if (EQ (v, Qwide))
+ return -13;
+ else if (EQ (v, Qnarrow))
+ return -14;
+ else if (EQ (v, Qsmall))
+ return -15;
+ else if (EQ (v, Qfont))
+ return -16;
else
signal_simple_error (err_msg, err_arg);
}
*/
(character, attribute))
{
- Lisp_Object ret
- = get_char_code_table (XCHAR (character), Vcharacter_attribute_table);
+ Lisp_Object ret;
Lisp_Object ccs;
+ CHECK_CHAR (character);
+ ret = get_char_code_table (XCHAR (character),
+ Vcharacter_attribute_table);
if (EQ (ret, Qnil))
return Qnil;
put_char_code_table (char_code, ret, Vcharacter_attribute_table);
return ret;
}
-
+
+Lisp_Object
+remove_char_attribute (Lisp_Object character, Lisp_Object attribute)
+{
+ Emchar char_code = XCHAR (character);
+ Lisp_Object alist
+ = get_char_code_table (char_code, Vcharacter_attribute_table);
+
+ if (EQ (attribute, Fcar (Fcar (alist))))
+ {
+ alist = Fcdr (alist);
+ }
+ else
+ {
+ Lisp_Object pr = alist;
+ Lisp_Object r = Fcdr (alist);
+
+ while (!NILP (r))
+ {
+ if (EQ (attribute, Fcar (Fcar (r))))
+ {
+ XCDR (pr) = Fcdr (r);
+ break;
+ }
+ pr = r;
+ r = Fcdr (r);
+ }
+ }
+ put_char_code_table (char_code, alist, Vcharacter_attribute_table);
+ return alist;
+}
+
+Lisp_Object Qucs;
+
DEFUN ("put-char-attribute", Fput_char_attribute, 3, 3, 0, /*
Store CHARACTER's ATTRIBUTE with VALUE.
*/
{
Lisp_Object ccs;
+ CHECK_CHAR (character);
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 (!EQ (XCHARSET_NAME (ccs), Qucs)
+ || (XCHAR (character) != XINT (value)))
{
- if (!NILP (rest))
+ Lisp_Object cpos, rest;
+ Lisp_Object v = XCHARSET_DECODING_TABLE (ccs);
+ Lisp_Object nv;
+ int i = -1;
+ int ccs_len;
+ int dim;
+ int code_point;
+
+ /* 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))
{
+ Lisp_Object ret = Fcar (value);
+
+ if (!INTP (ret))
+ signal_simple_error ("Invalid value for coded-charset", value);
+ code_point = XINT (ret);
+ if (XCHARSET_GRAPHIC (ccs) == 1)
+ code_point &= 0x7F;
+ rest = Fcdr (value);
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;
+ int i;
+
+ if (!CONSP (rest))
+ signal_simple_error ("Invalid value for coded-charset",
+ value);
+ ret = Fcar (rest);
+ if (!INTP (ret))
+ signal_simple_error ("Invalid value for coded-charset",
+ value);
+ i = XINT (ret);
+ if (XCHARSET_GRAPHIC (ccs) == 1)
+ i &= 0x7F;
+ code_point = (code_point << 8) | i;
rest = Fcdr (rest);
}
- if (i >= 0)
- XVECTOR_DATA(v)[i] = Qnil;
- v = XCHARSET_DECODING_TABLE (ccs);
+ value = make_int (code_point);
}
- }
- else
- {
- XCHARSET_DECODING_TABLE (ccs) = v = make_vector (ccs_len, Qnil);
- }
-
- if (XCHARSET_GRAPHIC (ccs) == 1)
- value = Fcopy_list (value);
- 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);
- if ((i < 0) || (255 < i))
- signal_simple_error ("Invalid value for coded-charset", value);
- if (XCHARSET_GRAPHIC (ccs) == 1)
+ else if (INTP (value))
{
- i &= 0x7F;
- Fsetcar (rest, make_int (i));
+ if (XCHARSET_GRAPHIC (ccs) == 1)
+ value = make_int (XINT (value) & 0x7F7F7F7F);
}
- i -= XCHARSET_BYTE_OFFSET (ccs);
- nv = XVECTOR_DATA(v)[i];
- rest = Fcdr (rest);
- if (CONSP (rest))
+ else
+ signal_simple_error ("Invalid value for coded-charset", value);
+
+ attribute = ccs;
+ cpos = Fget_char_attribute (character, attribute);
+ if (VECTORP (v))
{
- if (!VECTORP (nv))
+ if (!NILP (cpos))
{
- nv = (XVECTOR_DATA(v)[i] = make_vector (ccs_len, Qnil));
+ dim = XCHARSET_DIMENSION (ccs);
+ code_point = XINT (cpos);
+ while (dim > 0)
+ {
+ dim--;
+ i = ((code_point >> (8 * dim)) & 255)
+ - XCHARSET_BYTE_OFFSET (ccs);
+ nv = XVECTOR_DATA(v)[i];
+ if (!VECTORP (nv))
+ break;
+ v = nv;
+ }
+ if (i >= 0)
+ XVECTOR_DATA(v)[i] = Qnil;
+ v = XCHARSET_DECODING_TABLE (ccs);
}
- v = nv;
}
else
- break;
+ {
+ XCHARSET_DECODING_TABLE (ccs) = v = make_vector (ccs_len, Qnil);
+ }
+
+ dim = XCHARSET_DIMENSION (ccs);
+ code_point = XINT (value);
+ i = -1;
+ while (dim > 0)
+ {
+ dim--;
+ i = ((code_point >> (8 * dim)) & 255)
+ - XCHARSET_BYTE_OFFSET (ccs);
+ nv = XVECTOR_DATA(v)[i];
+ if (dim > 0)
+ {
+ if (!VECTORP (nv))
+ nv = (XVECTOR_DATA(v)[i] = make_vector (ccs_len, Qnil));
+ v = nv;
+ }
+ else
+ break;
+ }
+ XVECTOR_DATA(v)[i] = character;
}
- XVECTOR_DATA(v)[i] = character;
+ else
+ attribute = ccs;
}
else if (EQ (attribute, Q_decomposition))
{
- Lisp_Object rest = value;
- Lisp_Object table = Vcharacter_composition_table;
-
if (!CONSP (value))
signal_simple_error ("Invalid value for ->decomposition",
value);
- while (CONSP (rest))
+ if (CONSP (Fcdr (value)))
{
- Lisp_Object v = Fcar (rest);
- Lisp_Object ntable;
- Emchar c
- = to_char_code (v, "Invalid value for ->decomposition", value);
+ Lisp_Object rest = value;
+ Lisp_Object table = Vcharacter_composition_table;
- rest = Fcdr (rest);
- if (!CONSP (rest))
+ while (CONSP (rest))
{
- put_char_code_table (c, character, table);
- break;
+ Lisp_Object v = Fcar (rest);
+ Lisp_Object ntable;
+ Emchar c
+ = to_char_code (v,
+ "Invalid value for ->decomposition", value);
+
+ rest = Fcdr (rest);
+ if (!CONSP (rest))
+ {
+ put_char_code_table (c, character, table);
+ break;
+ }
+ else
+ {
+ ntable = get_char_code_table (c, table);
+ if (!CHAR_CODE_TABLE_P (ntable))
+ {
+ ntable = make_char_code_table (Qnil);
+ put_char_code_table (c, ntable, table);
+ }
+ table = ntable;
+ }
}
- else
+ }
+ else
+ {
+ Lisp_Object v = Fcar (value);
+
+ if (INTP (v))
{
- ntable = get_char_code_table (c, table);
- if (!CHAR_CODE_TABLE_P (ntable))
+ Emchar c = XINT (v);
+ Lisp_Object ret
+ = get_char_code_table (c, Vcharacter_variant_table);
+
+ if (NILP (Fmemq (v, ret)))
{
- ntable = make_char_code_table (Qnil);
- put_char_code_table (c, ntable, table);
+ put_char_code_table (c, Fcons (character, ret),
+ Vcharacter_variant_table);
}
- table = ntable;
}
}
}
}
return put_char_attribute (character, attribute, value);
}
+
+DEFUN ("remove-char-attribute", Fremove_char_attribute, 2, 2, 0, /*
+Remove CHARACTER's ATTRIBUTE.
+*/
+ (character, attribute))
+{
+ Lisp_Object ccs;
-Lisp_Object Qucs;
+ CHECK_CHAR (character);
+ ccs = Ffind_charset (attribute);
+ if (!NILP (ccs))
+ {
+ Lisp_Object cpos;
+ Lisp_Object v = XCHARSET_DECODING_TABLE (ccs);
+ Lisp_Object nv;
+ int i = -1;
+ int ccs_len;
+ int dim;
+ int code_point;
+
+ /* 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);
+
+ attribute = ccs;
+ cpos = Fget_char_attribute (character, attribute);
+ if (VECTORP (v))
+ {
+ if (!NILP (cpos))
+ {
+ dim = XCHARSET_DIMENSION (ccs);
+ code_point = XINT (cpos);
+ while (dim > 0)
+ {
+ dim--;
+ i = ((code_point >> (8 * dim)) & 255)
+ - XCHARSET_BYTE_OFFSET (ccs);
+ nv = XVECTOR_DATA(v)[i];
+ if (!VECTORP (nv))
+ break;
+ v = nv;
+ }
+ if (i >= 0)
+ XVECTOR_DATA(v)[i] = Qnil;
+ v = XCHARSET_DECODING_TABLE (ccs);
+ }
+ }
+ }
+ return remove_char_attribute (character, attribute);
+}
+
+EXFUN (Fmake_char, 3);
+EXFUN (Fdecode_char, 2);
DEFUN ("define-char", Fdefine_char, 1, 1, 0, /*
Store character's ATTRIBUTES.
if (!LISTP (cell))
signal_simple_error ("Invalid argument", attributes);
if (!NILP (ccs = Ffind_charset (Fcar (cell)))
- && XCHARSET_FINAL (ccs))
+ && ((XCHARSET_FINAL (ccs) != 0) ||
+ (XCHARSET_UCS_MAX (ccs) > 0)) )
{
- 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 ();
- }
- }
+ cell = Fcdr (cell);
+ if (CONSP (cell))
+ character = Fmake_char (ccs, Fcar (cell), Fcar (Fcdr (cell)));
else
- {
- rest = Fcdr (rest);
- continue;
- }
- character = make_char (code);
+ character = Fdecode_char (ccs, cell);
goto setup_attributes;
}
rest = Fcdr (rest);
}
+ if (!NILP (code = Fcdr (Fassq (Q_ucs, attributes))))
+ {
+ if (!INTP (code))
+ signal_simple_error ("Invalid argument", attributes);
+ else
+ character = make_char (XINT (code) + 0x100000);
+ goto setup_attributes;
+ }
return Qnil;
}
else if (!INTP (code))
Qjapanese_jisx0208_1978,
Qchinese_gb2312,
Qjapanese_jisx0208,
+ Qjapanese_jisx0208_1990,
Qkorean_ksc5601,
Qjapanese_jisx0212,
Qchinese_cns11643_1,
#ifdef UTF2000
Qucs_bmp,
Qlatin_viscii,
+ Qlatin_tcvn5712,
Qlatin_viscii_lower,
Qlatin_viscii_upper,
Qvietnamese_viscii_lower,
Qvietnamese_viscii_upper,
+ Qideograph_daikanwa,
+ Qmojikyo,
+ Qmojikyo_pj_1,
+ Qmojikyo_pj_2,
+ Qmojikyo_pj_3,
+ Qmojikyo_pj_4,
+ Qmojikyo_pj_5,
+ Qmojikyo_pj_6,
+ Qmojikyo_pj_7,
+ Qmojikyo_pj_8,
+ Qmojikyo_pj_9,
+ Qmojikyo_pj_10,
+ Qmojikyo_pj_11,
+ Qmojikyo_pj_12,
+ Qmojikyo_pj_13,
+ Qmojikyo_pj_14,
+ Qmojikyo_pj_15,
+ Qmojikyo_pj_16,
+ Qmojikyo_pj_17,
+ Qmojikyo_pj_18,
+ Qmojikyo_pj_19,
+ Qmojikyo_pj_20,
+ Qmojikyo_pj_21,
Qethiopic_ucs,
- Qhiragana_jisx0208,
- Qkatakana_jisx0208,
#endif
Qchinese_big5_1,
Qchinese_big5_2,
if (f3 < 0x20)
return 0;
- if (f3 != 0x20 && f3 != 0x7F)
+ if (f3 != 0x20 && f3 != 0x7F && !(f2 >= MIN_CHAR_FIELD2_PRIVATE &&
+ f2 <= MAX_CHAR_FIELD2_PRIVATE))
return 1;
/*
FIELD2_TO_PRIVATE_LEADING_BYTE are the same.
*/
charset = CHARSET_BY_LEADING_BYTE (f2 + FIELD2_TO_OFFICIAL_LEADING_BYTE);
+ if (EQ (charset, Qnil))
+ return 0;
return (XCHARSET_CHARS (charset) == 96);
}
else
}
#endif /* ENABLE_COMPOSITE_CHARS */
- if (f2 != 0x20 && f2 != 0x7F && f3 != 0x20 && f3 != 0x7F)
+ if (f2 != 0x20 && f2 != 0x7F && f3 != 0x20 && f3 != 0x7F
+ && !(f1 >= MIN_CHAR_FIELD1_PRIVATE && f1 <= MAX_CHAR_FIELD1_PRIVATE))
return 1;
if (f1 <= MAX_CHAR_FIELD1_OFFICIAL)
charset =
CHARSET_BY_LEADING_BYTE (f1 + FIELD1_TO_PRIVATE_LEADING_BYTE);
+ if (EQ (charset, Qnil))
+ return 0;
return (XCHARSET_CHARS (charset) == 96);
}
}
/************************************************************************/
static Lisp_Object
-mark_charset (Lisp_Object obj, void (*markobj) (Lisp_Object))
+mark_charset (Lisp_Object obj)
{
struct Lisp_Charset *cs = XCHARSET (obj);
- markobj (cs->short_name);
- markobj (cs->long_name);
- markobj (cs->doc_string);
- markobj (cs->registry);
- markobj (cs->ccl_program);
+ mark_object (cs->short_name);
+ mark_object (cs->long_name);
+ mark_object (cs->doc_string);
+ mark_object (cs->registry);
+ mark_object (cs->ccl_program);
#ifdef UTF2000
- markobj (cs->decoding_table);
+ mark_object (cs->decoding_table);
#endif
return cs->name;
}
print_internal (CHARSET_LONG_NAME (cs), printcharfun, 1);
write_c_string (" ", printcharfun);
print_internal (CHARSET_DOC_STRING (cs), printcharfun, 1);
- sprintf (buf, " %s %s cols=%d g%d final='%c' reg=",
- CHARSET_TYPE (cs) == CHARSET_TYPE_94 ? "94" :
- CHARSET_TYPE (cs) == CHARSET_TYPE_96 ? "96" :
- CHARSET_TYPE (cs) == CHARSET_TYPE_94X94 ? "94x94" :
- "96x96",
+ sprintf (buf, " %d^%d %s cols=%d g%d final='%c' reg=",
+ CHARSET_CHARS (cs),
+ CHARSET_DIMENSION (cs),
CHARSET_DIRECTION (cs) == CHARSET_LEFT_TO_RIGHT ? "l2r" : "r2l",
CHARSET_COLUMNS (cs),
CHARSET_GRAPHIC (cs),
mark_charset, print_charset, 0, 0, 0,
charset_description,
struct Lisp_Charset);
-
/* Make a new charset. */
static Lisp_Object
make_charset (Charset_ID id, Lisp_Object name,
- unsigned char type, unsigned char columns, unsigned char graphic,
+ unsigned short chars, unsigned char dimension,
+ unsigned char columns, unsigned char graphic,
Bufbyte final, unsigned char direction, Lisp_Object short_name,
Lisp_Object long_name, Lisp_Object doc,
Lisp_Object reg,
Emchar ucs_min, Emchar ucs_max,
Emchar code_offset, unsigned char byte_offset)
{
+ unsigned char type = 0;
Lisp_Object obj;
struct Lisp_Charset *cs =
alloc_lcrecord_type (struct Lisp_Charset, &lrecord_charset);
CHARSET_NAME (cs) = name;
CHARSET_SHORT_NAME (cs) = short_name;
CHARSET_LONG_NAME (cs) = long_name;
+ CHARSET_CHARS (cs) = chars;
+ CHARSET_DIMENSION (cs) = dimension;
CHARSET_DIRECTION (cs) = direction;
- CHARSET_TYPE (cs) = type;
CHARSET_COLUMNS (cs) = columns;
CHARSET_GRAPHIC (cs) = graphic;
CHARSET_FINAL (cs) = final;
CHARSET_BYTE_OFFSET(cs) = byte_offset;
#endif
- switch (CHARSET_TYPE (cs))
+ switch (CHARSET_CHARS (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;
+ case 94:
+ switch (CHARSET_DIMENSION (cs))
+ {
+ case 1:
+ type = CHARSET_TYPE_94;
+ break;
+ case 2:
+ type = CHARSET_TYPE_94X94;
+ break;
+ }
break;
- case CHARSET_TYPE_96X96:
- CHARSET_DIMENSION (cs) = 2;
- CHARSET_CHARS (cs) = 96;
+ case 96:
+ switch (CHARSET_DIMENSION (cs))
+ {
+ case 1:
+ type = CHARSET_TYPE_96;
+ break;
+ case 2:
+ type = CHARSET_TYPE_96X96;
+ break;
+ }
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;
+ case 128:
+ switch (CHARSET_DIMENSION (cs))
+ {
+ case 1:
+ type = CHARSET_TYPE_128;
+ break;
+ case 2:
+ type = CHARSET_TYPE_128X128;
+ break;
+ }
break;
- case CHARSET_TYPE_256X256:
- CHARSET_DIMENSION (cs) = 2;
- CHARSET_CHARS (cs) = 256;
+ case 256:
+ switch (CHARSET_DIMENSION (cs))
+ {
+ case 1:
+ type = CHARSET_TYPE_256;
+ break;
+ case 2:
+ type = CHARSET_TYPE_256X256;
+ break;
+ }
break;
#endif
}
+#ifndef UTF2000
+ CHARSET_TYPE (cs) = type;
+#endif
#ifndef UTF2000
if (id == LEADING_BYTE_ASCII)
else
CHARSET_REP_BYTES (cs) = CHARSET_DIMENSION (cs) + 2;
#endif
-
+
if (final)
{
/* some charsets do not have final characters. This includes
#if UTF2000
if (code_offset == 0)
{
- assert (NILP (charset_by_attributes[type][final]));
- charset_by_attributes[type][final] = obj;
+ assert (NILP (chlook->charset_by_attributes[type][final]));
+ chlook->charset_by_attributes[type][final] = obj;
}
#else
- assert (NILP (charset_by_attributes[type][final][direction]));
- charset_by_attributes[type][final][direction] = obj;
+ assert (NILP (chlook->charset_by_attributes[type][final][direction]));
+ chlook->charset_by_attributes[type][final][direction] = obj;
#endif
}
- 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] = CHARSET_REP_BYTES (cs);
-#endif
+ assert (NILP (chlook->charset_by_leading_byte[id - MIN_LEADING_BYTE]));
+ chlook->charset_by_leading_byte[id - MIN_LEADING_BYTE] = obj;
/* Some charsets are "faux" and don't have names or really exist at
all except in the leading-byte table. */
}
#ifdef UTF2000
-Lisp_Object
+Emchar
+make_builtin_char (Lisp_Object charset, int c1, int c2)
+{
+ if (XCHARSET_UCS_MAX (charset))
+ {
+ Emchar code
+ = (XCHARSET_DIMENSION (charset) == 1
+ ?
+ c1 - XCHARSET_BYTE_OFFSET (charset)
+ :
+ (c1 - XCHARSET_BYTE_OFFSET (charset)) * XCHARSET_CHARS (charset)
+ + c2 - XCHARSET_BYTE_OFFSET (charset))
+ - XCHARSET_CODE_OFFSET (charset) + XCHARSET_UCS_MIN (charset);
+ if ((code < XCHARSET_UCS_MIN (charset))
+ || (XCHARSET_UCS_MAX (charset) < code))
+ signal_simple_error ("Arguments makes invalid character",
+ make_char (code));
+ return code;
+ }
+ else if (XCHARSET_DIMENSION (charset) == 1)
+ {
+ switch (XCHARSET_CHARS (charset))
+ {
+ case 94:
+ return MIN_CHAR_94
+ + (XCHARSET_FINAL (charset) - '0') * 94 + (c1 - 33);
+ case 96:
+ return MIN_CHAR_96
+ + (XCHARSET_FINAL (charset) - '0') * 96 + (c1 - 32);
+ default:
+ abort ();
+ }
+ }
+ else
+ {
+ switch (XCHARSET_CHARS (charset))
+ {
+ case 94:
+ return MIN_CHAR_94x94
+ + (XCHARSET_FINAL (charset) - '0') * 94 * 94
+ + (c1 - 33) * 94 + (c2 - 33);
+ case 96:
+ return MIN_CHAR_96x96
+ + (XCHARSET_FINAL (charset) - '0') * 96 * 96
+ + (c1 - 32) * 96 + (c2 - 32);
+ default:
+ abort ();
+ }
+ }
+}
+
+int
range_charset_code_point (Lisp_Object charset, Emchar ch)
{
int d;
&& (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)));
+
+ if (XCHARSET_CHARS (charset) == 256)
+ return d;
+ else if (XCHARSET_DIMENSION (charset) == 1)
+ return 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)));
+ return
+ ((d / XCHARSET_CHARS (charset)
+ + XCHARSET_BYTE_OFFSET (charset)) << 8)
+ | (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)));
+ return
+ ((d / (XCHARSET_CHARS (charset) * XCHARSET_CHARS (charset))
+ + XCHARSET_BYTE_OFFSET (charset)) << 16)
+ | ((d / XCHARSET_CHARS (charset)
+ % XCHARSET_CHARS (charset)
+ + XCHARSET_BYTE_OFFSET (charset)) << 8)
+ | (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)));
+ return
+ ((d / (XCHARSET_CHARS (charset)
+ * XCHARSET_CHARS (charset) * XCHARSET_CHARS (charset))
+ + XCHARSET_BYTE_OFFSET (charset)) << 24)
+ | ((d / (XCHARSET_CHARS (charset) * XCHARSET_CHARS (charset))
+ % XCHARSET_CHARS (charset)
+ + XCHARSET_BYTE_OFFSET (charset)) << 16)
+ | ((d / XCHARSET_CHARS (charset) % XCHARSET_CHARS (charset)
+ + XCHARSET_BYTE_OFFSET (charset)) << 8)
+ | (d % XCHARSET_CHARS (charset) + XCHARSET_BYTE_OFFSET (charset));
}
else if (XCHARSET_CODE_OFFSET (charset) == 0)
{
if (((d = ch - (MIN_CHAR_94
+ (XCHARSET_FINAL (charset) - '0') * 94)) >= 0)
&& (d < 94))
- return list1 (make_int (d + 33));
+ return 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));
+ return d + 32;
}
else
- return Qnil;
+ return -1;
}
else if (XCHARSET_DIMENSION (charset) == 2)
{
+ (XCHARSET_FINAL (charset) - '0') * 94 * 94))
>= 0)
&& (d < 94 * 94))
- return list2 (make_int ((d / 94) + 33),
- make_int (d % 94 + 33));
+ return (((d / 94) + 33) << 8) | (d % 94 + 33);
}
else if (XCHARSET_CHARS (charset) == 96)
{
+ (XCHARSET_FINAL (charset) - '0') * 96 * 96))
>= 0)
&& (d < 96 * 96))
- return list2 (make_int ((d / 96) + 32),
- make_int (d % 96 + 32));
+ return (((d / 96) + 32) << 8) | (d % 96 + 32);
}
+ else
+ return -1;
}
}
- return Qnil;
+ return -1;
}
-Lisp_Object
-split_builtin_char (Emchar c)
+int
+encode_builtin_char_1 (Emchar c, Lisp_Object* charset)
{
- if (c < MIN_CHAR_OBS_94x94)
+ if (c <= MAX_CHAR_BASIC_LATIN)
{
- if (c <= MAX_CHAR_BASIC_LATIN)
- {
- return list2 (Vcharset_ascii, make_int (c));
- }
- else if (c < 0xA0)
- {
- return list2 (Vcharset_control_1, make_int (c & 0x7F));
- }
- else if (c <= 0xff)
- {
- return list2 (Vcharset_latin_iso8859_1, make_int (c & 0x7F));
- }
- else if ((MIN_CHAR_GREEK <= c) && (c <= MAX_CHAR_GREEK))
- {
- return list2 (Vcharset_greek_iso8859_7,
- make_int (c - MIN_CHAR_GREEK + 0x20));
- }
- else if ((MIN_CHAR_CYRILLIC <= c) && (c <= MAX_CHAR_CYRILLIC))
- {
- return list2 (Vcharset_cyrillic_iso8859_5,
- make_int (c - MIN_CHAR_CYRILLIC + 0x20));
- }
- else if ((MIN_CHAR_HEBREW <= c) && (c <= MAX_CHAR_HEBREW))
- {
- return list2 (Vcharset_hebrew_iso8859_8,
- make_int (c - MIN_CHAR_HEBREW + 0x20));
- }
- else if ((MIN_CHAR_THAI <= c) && (c <= MAX_CHAR_THAI))
- {
- return list2 (Vcharset_thai_tis620,
- make_int (c - MIN_CHAR_THAI + 0x20));
- }
- else if ((MIN_CHAR_HALFWIDTH_KATAKANA <= c)
- && (c <= MAX_CHAR_HALFWIDTH_KATAKANA))
- {
- return list2 (Vcharset_katakana_jisx0201,
- make_int (c - MIN_CHAR_HALFWIDTH_KATAKANA + 33));
- }
- else
- {
- return list3 (Vcharset_ucs_bmp,
- make_int (c >> 8), make_int (c & 0xff));
- }
+ *charset = Vcharset_ascii;
+ return c;
+ }
+ else if (c < 0xA0)
+ {
+ *charset = Vcharset_control_1;
+ return c & 0x7F;
}
- else if (c <= MAX_CHAR_OBS_94x94)
+ else if (c <= 0xff)
{
- return list3 (CHARSET_BY_ATTRIBUTES
- (CHARSET_TYPE_94X94,
- ((c - MIN_CHAR_OBS_94x94) / (94 * 94)) + '@',
- CHARSET_LEFT_TO_RIGHT),
- make_int ((((c - MIN_CHAR_OBS_94x94) / 94) % 94) + 33),
- make_int (((c - MIN_CHAR_OBS_94x94) % 94) + 33));
+ *charset = Vcharset_latin_iso8859_1;
+ return c & 0x7F;
+ }
+ /*
+ else if ((MIN_CHAR_GREEK <= c) && (c <= MAX_CHAR_GREEK))
+ {
+ *charset = Vcharset_greek_iso8859_7;
+ return c - MIN_CHAR_GREEK + 0x20;
+ }
+ else if ((MIN_CHAR_CYRILLIC <= c) && (c <= MAX_CHAR_CYRILLIC))
+ {
+ *charset = Vcharset_cyrillic_iso8859_5;
+ return c - MIN_CHAR_CYRILLIC + 0x20;
+ }
+ */
+ else if ((MIN_CHAR_HEBREW <= c) && (c <= MAX_CHAR_HEBREW))
+ {
+ *charset = Vcharset_hebrew_iso8859_8;
+ return c - MIN_CHAR_HEBREW + 0x20;
+ }
+ else if ((MIN_CHAR_THAI <= c) && (c <= MAX_CHAR_THAI))
+ {
+ *charset = Vcharset_thai_tis620;
+ return c - MIN_CHAR_THAI + 0x20;
+ }
+ /*
+ else if ((MIN_CHAR_HALFWIDTH_KATAKANA <= c)
+ && (c <= MAX_CHAR_HALFWIDTH_KATAKANA))
+ {
+ return list2 (Vcharset_katakana_jisx0201,
+ make_int (c - MIN_CHAR_HALFWIDTH_KATAKANA + 33));
+ }
+ */
+ else if (c <= MAX_CHAR_BMP)
+ {
+ *charset = Vcharset_ucs_bmp;
+ return c;
+ }
+ else if (c < MIN_CHAR_DAIKANWA)
+ {
+ *charset = Vcharset_ucs;
+ return c;
+ }
+ else if (c <= MAX_CHAR_DAIKANWA)
+ {
+ *charset = Vcharset_ideograph_daikanwa;
+ return c - MIN_CHAR_DAIKANWA;
+ }
+ else if (c < MIN_CHAR_94)
+ {
+ *charset = Vcharset_ucs;
+ return c;
}
else if (c <= MAX_CHAR_94)
{
- return list2 (CHARSET_BY_ATTRIBUTES (CHARSET_TYPE_94,
- ((c - MIN_CHAR_94) / 94) + '0',
- CHARSET_LEFT_TO_RIGHT),
- make_int (((c - MIN_CHAR_94) % 94) + 33));
+ *charset = CHARSET_BY_ATTRIBUTES (CHARSET_TYPE_94,
+ ((c - MIN_CHAR_94) / 94) + '0',
+ CHARSET_LEFT_TO_RIGHT);
+ if (!NILP (*charset))
+ return ((c - MIN_CHAR_94) % 94) + 33;
+ else
+ {
+ *charset = Vcharset_ucs;
+ return c;
+ }
}
else if (c <= MAX_CHAR_96)
{
- return list2 (CHARSET_BY_ATTRIBUTES (CHARSET_TYPE_96,
- ((c - MIN_CHAR_96) / 96) + '0',
- CHARSET_LEFT_TO_RIGHT),
- make_int (((c - MIN_CHAR_96) % 96) + 32));
+ *charset = CHARSET_BY_ATTRIBUTES (CHARSET_TYPE_96,
+ ((c - MIN_CHAR_96) / 96) + '0',
+ CHARSET_LEFT_TO_RIGHT);
+ if (!NILP (*charset))
+ return ((c - MIN_CHAR_96) % 96) + 32;
+ else
+ {
+ *charset = Vcharset_ucs;
+ return c;
+ }
}
else if (c <= MAX_CHAR_94x94)
{
- return list3 (CHARSET_BY_ATTRIBUTES
- (CHARSET_TYPE_94X94,
- ((c - MIN_CHAR_94x94) / (94 * 94)) + '0',
- CHARSET_LEFT_TO_RIGHT),
- make_int ((((c - MIN_CHAR_94x94) / 94) % 94) + 33),
- make_int (((c - MIN_CHAR_94x94) % 94) + 33));
+ *charset
+ = CHARSET_BY_ATTRIBUTES (CHARSET_TYPE_94X94,
+ ((c - MIN_CHAR_94x94) / (94 * 94)) + '0',
+ CHARSET_LEFT_TO_RIGHT);
+ if (!NILP (*charset))
+ return (((((c - MIN_CHAR_94x94) / 94) % 94) + 33) << 8)
+ | (((c - MIN_CHAR_94x94) % 94) + 33);
+ else
+ {
+ *charset = Vcharset_ucs;
+ return c;
+ }
}
else if (c <= MAX_CHAR_96x96)
{
- return list3 (CHARSET_BY_ATTRIBUTES
- (CHARSET_TYPE_96X96,
- ((c - MIN_CHAR_96x96) / (96 * 96)) + '0',
- CHARSET_LEFT_TO_RIGHT),
- make_int ((((c - MIN_CHAR_96x96) / 96) % 96) + 32),
- make_int (((c - MIN_CHAR_96x96) % 96) + 32));
+ *charset
+ = CHARSET_BY_ATTRIBUTES (CHARSET_TYPE_96X96,
+ ((c - MIN_CHAR_96x96) / (96 * 96)) + '0',
+ CHARSET_LEFT_TO_RIGHT);
+ if (!NILP (*charset))
+ return ((((c - MIN_CHAR_96x96) / 96) % 96) + 32) << 8
+ | (((c - MIN_CHAR_96x96) % 96) + 32);
+ else
+ {
+ *charset = Vcharset_ucs;
+ return c;
+ }
}
else
{
- return Qnil;
+ *charset = Vcharset_ucs;
+ return c;
}
}
-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
byte_offset = 0;
}
- charset = make_charset (id, name, type, columns, graphic,
+ charset = make_charset (id, name, chars, dimension, columns, graphic,
final, direction, short_name, long_name,
doc_string, registry,
Qnil, 0, 0, 0, byte_offset);
(charset, new_name))
{
Lisp_Object new_charset = Qnil;
- int id, dimension, columns, graphic, final;
- int direction, type;
+ int id, chars, dimension, columns, graphic, final;
+ int direction;
Lisp_Object registry, doc_string, short_name, long_name;
struct Lisp_Charset *cs;
cs = XCHARSET (charset);
- type = CHARSET_TYPE (cs);
- columns = CHARSET_COLUMNS (cs);
+ chars = CHARSET_CHARS (cs);
dimension = CHARSET_DIMENSION (cs);
+ columns = CHARSET_COLUMNS (cs);
id = get_unallocated_leading_byte (dimension);
graphic = CHARSET_GRAPHIC (cs);
long_name = CHARSET_LONG_NAME (cs);
registry = CHARSET_REGISTRY (cs);
- new_charset = make_charset (id, new_name, type, columns,
+ new_charset = make_charset (id, new_name, chars, dimension, columns,
graphic, final, direction, short_name, long_name,
doc_string, registry,
#ifdef UTF2000
if (CHARP (c))
put_char_attribute
(c, charset,
- list1 (make_int (i + CHARSET_BYTE_OFFSET (cs))));
+ make_int (i + CHARSET_BYTE_OFFSET (cs)));
}
break;
case 2:
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))));
+ put_char_attribute
+ (c, charset,
+ make_int ( ((i + CHARSET_BYTE_OFFSET (cs)) << 8)
+ | (j + CHARSET_BYTE_OFFSET (cs)) ));
}
}
else if (CHARP (v))
put_char_attribute (v, charset,
- list1
- (make_int (i + CHARSET_BYTE_OFFSET (cs))));
+ make_int (i + CHARSET_BYTE_OFFSET (cs)));
}
break;
}
/* Lisp primitives for working with characters */
/************************************************************************/
+#ifdef UTF2000
+DEFUN ("decode-char", Fdecode_char, 2, 2, 0, /*
+Make a character from CHARSET and code-point CODE.
+*/
+ (charset, code))
+{
+ int c;
+
+ charset = Fget_charset (charset);
+ CHECK_INT (code);
+ c = XINT (code);
+ if (XCHARSET_GRAPHIC (charset) == 1)
+ c &= 0x7F7F7F7F;
+ return make_char (DECODE_CHAR (charset, c));
+}
+#endif
+
DEFUN ("make-char", Fmake_char, 2, 3, 0, /*
Make a character from CHARSET and octets ARG1 and ARG2.
ARG2 is required only for characters from two-dimensional charsets.
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.
+*/
+ (ch, n))
+{
+ Lisp_Object charset;
+ int octet0, octet1;
+
+ CHECK_CHAR_COERCE_INT (ch);
+
+ BREAKUP_CHAR (XCHAR (ch), charset, octet0, octet1);
+
+ if (NILP (n) || EQ (n, Qzero))
+ return make_int (octet0);
+ else if (EQ (n, make_int (1)))
+ return make_int (octet1);
+ else
+ signal_simple_error ("Octet number must be 0 or 1", n);
+}
+
DEFUN ("split-char", Fsplit_char, 1, 1, 0, /*
Return list of charset and one or two position-codes of CHAR.
*/
struct gcpro gcpro1, gcpro2;
Lisp_Object charset = Qnil;
Lisp_Object rc = Qnil;
+#ifdef UTF2000
+ int code_point;
+ int dimension;
+#else
int c1, c2;
+#endif
GCPRO2 (charset, rc);
CHECK_CHAR_COERCE_INT (character);
+#ifdef UTF2000
+ code_point = ENCODE_CHAR (XCHAR (character), charset);
+ dimension = XCHARSET_DIMENSION (charset);
+ while (dimension > 0)
+ {
+ rc = Fcons (make_int (code_point & 255), rc);
+ code_point >>= 8;
+ dimension--;
+ }
+ rc = Fcons (XCHARSET_NAME (charset), rc);
+#else
BREAKUP_CHAR (XCHAR (character), charset, c1, c2);
if (XCHARSET_DIMENSION (Fget_charset (charset)) == 2)
{
rc = list2 (XCHARSET_NAME (charset), make_int (c1));
}
+#endif
UNGCPRO;
return rc;
DEFSUBR (Fchar_attribute_alist);
DEFSUBR (Fget_char_attribute);
DEFSUBR (Fput_char_attribute);
+ DEFSUBR (Fremove_char_attribute);
DEFSUBR (Fdefine_char);
DEFSUBR (Fchar_variants);
DEFSUBR (Fget_composite_char);
DEFSUBR (Fset_charset_mapping_table);
#endif
+#ifdef UTF2000
+ DEFSUBR (Fdecode_char);
+#endif
DEFSUBR (Fmake_char);
DEFSUBR (Fchar_charset);
+ DEFSUBR (Fchar_octet);
DEFSUBR (Fsplit_char);
#ifdef ENABLE_COMPOSITE_CHARS
defsymbol (&Qjapanese_jisx0208_1978, "japanese-jisx0208-1978");
defsymbol (&Qchinese_gb2312, "chinese-gb2312");
defsymbol (&Qjapanese_jisx0208, "japanese-jisx0208");
+ defsymbol (&Qjapanese_jisx0208_1990, "japanese-jisx0208-1990");
defsymbol (&Qkorean_ksc5601, "korean-ksc5601");
defsymbol (&Qjapanese_jisx0212, "japanese-jisx0212");
defsymbol (&Qchinese_cns11643_1, "chinese-cns11643-1");
defsymbol (&Q_ucs, "->ucs");
defsymbol (&Q_decomposition, "->decomposition");
defsymbol (&Qcompat, "compat");
+ defsymbol (&Qisolated, "isolated");
+ defsymbol (&Qinitial, "initial");
+ defsymbol (&Qmedial, "medial");
+ defsymbol (&Qfinal, "final");
+ defsymbol (&Qvertical, "vertical");
defsymbol (&QnoBreak, "noBreak");
defsymbol (&Qfraction, "fraction");
defsymbol (&Qsuper, "super");
defsymbol (&Qsub, "sub");
defsymbol (&Qcircle, "circle");
+ defsymbol (&Qsquare, "square");
defsymbol (&Qwide, "wide");
defsymbol (&Qnarrow, "narrow");
+ defsymbol (&Qsmall, "small");
defsymbol (&Qfont, "font");
defsymbol (&Qucs, "ucs");
defsymbol (&Qucs_bmp, "ucs-bmp");
defsymbol (&Qlatin_viscii, "latin-viscii");
+ defsymbol (&Qlatin_tcvn5712, "latin-tcvn5712");
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 (&Qideograph_daikanwa, "ideograph-daikanwa");
+ defsymbol (&Qmojikyo, "mojikyo");
+ defsymbol (&Qmojikyo_pj_1, "mojikyo-pj-1");
+ defsymbol (&Qmojikyo_pj_2, "mojikyo-pj-2");
+ defsymbol (&Qmojikyo_pj_3, "mojikyo-pj-3");
+ defsymbol (&Qmojikyo_pj_4, "mojikyo-pj-4");
+ defsymbol (&Qmojikyo_pj_5, "mojikyo-pj-5");
+ defsymbol (&Qmojikyo_pj_6, "mojikyo-pj-6");
+ defsymbol (&Qmojikyo_pj_7, "mojikyo-pj-7");
+ defsymbol (&Qmojikyo_pj_8, "mojikyo-pj-8");
+ defsymbol (&Qmojikyo_pj_9, "mojikyo-pj-9");
+ defsymbol (&Qmojikyo_pj_10, "mojikyo-pj-10");
+ defsymbol (&Qmojikyo_pj_11, "mojikyo-pj-11");
+ defsymbol (&Qmojikyo_pj_12, "mojikyo-pj-12");
+ defsymbol (&Qmojikyo_pj_13, "mojikyo-pj-13");
+ defsymbol (&Qmojikyo_pj_14, "mojikyo-pj-14");
+ defsymbol (&Qmojikyo_pj_15, "mojikyo-pj-15");
+ defsymbol (&Qmojikyo_pj_16, "mojikyo-pj-16");
+ defsymbol (&Qmojikyo_pj_17, "mojikyo-pj-17");
+ defsymbol (&Qmojikyo_pj_18, "mojikyo-pj-18");
+ defsymbol (&Qmojikyo_pj_19, "mojikyo-pj-19");
+ defsymbol (&Qmojikyo_pj_20, "mojikyo-pj-20");
+ defsymbol (&Qmojikyo_pj_21, "mojikyo-pj-21");
defsymbol (&Qethiopic_ucs, "ethiopic-ucs");
- 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");
int k;
#endif
+ chlook = xnew (struct charset_lookup);
+ dumpstruct (&chlook, &charset_lookup_description);
+
/* Table of charsets indexed by leading byte. */
- for (i = 0; i < countof (charset_by_leading_byte); i++)
- charset_by_leading_byte[i] = Qnil;
+ for (i = 0; i < countof (chlook->charset_by_leading_byte); i++)
+ chlook->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;
+ for (i = 0; i < countof (chlook->charset_by_attributes); i++)
+ for (j = 0; j < countof (chlook->charset_by_attributes[0]); j++)
+ chlook->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;
+ for (i = 0; i < countof (chlook->charset_by_attributes); i++)
+ for (j = 0; j < countof (chlook->charset_by_attributes[0]); j++)
+ for (k = 0; k < countof (chlook->charset_by_attributes[0][0]); k++)
+ chlook->charset_by_attributes[i][j][k] = Qnil;
#endif
#ifdef UTF2000
#endif
#ifdef UTF2000
- Vutf_2000_version = build_string("0.12 (Kashiwara)");
+ Vutf_2000_version = build_string("0.14 (Kawachi-Katakami)");
DEFVAR_LISP ("utf-2000-version", &Vutf_2000_version /*
Version number of UTF-2000.
*/ );
ease of access. */
#ifdef UTF2000
+ staticpro (&Vcharset_ucs);
+ Vcharset_ucs =
+ make_charset (LEADING_BYTE_UCS, Qucs, 256, 4,
+ 1, 2, 0, CHARSET_LEFT_TO_RIGHT,
+ build_string ("UCS"),
+ build_string ("UCS"),
+ build_string ("ISO/IEC 10646"),
+ build_string (""),
+ Qnil, 0, 0xFFFFFFF, 0, 0);
+ staticpro (&Vcharset_ucs_bmp);
Vcharset_ucs_bmp =
- make_charset (LEADING_BYTE_UCS_BMP, Qucs_bmp,
- CHARSET_TYPE_256X256, 1, 2, 0,
- CHARSET_LEFT_TO_RIGHT,
+ make_charset (LEADING_BYTE_UCS_BMP, Qucs_bmp, 256, 2,
+ 1, 2, 0, CHARSET_LEFT_TO_RIGHT,
build_string ("BMP"),
build_string ("BMP"),
build_string ("ISO/IEC 10646 Group 0 Plane 0 (BMP)"),
#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
+ staticpro (&Vcharset_ascii);
Vcharset_ascii =
- make_charset (LEADING_BYTE_ASCII, Qascii,
- CHARSET_TYPE_94, 1, 0, 'B',
- CHARSET_LEFT_TO_RIGHT,
+ make_charset (LEADING_BYTE_ASCII, Qascii, 94, 1,
+ 1, 0, 'B', CHARSET_LEFT_TO_RIGHT,
build_string ("ASCII"),
build_string ("ASCII)"),
build_string ("ASCII (ISO646 IRV)"),
build_string ("\\(iso8859-[0-9]*\\|-ascii\\)"),
Qnil, 0, 0x7F, 0, 0);
+ staticpro (&Vcharset_control_1);
Vcharset_control_1 =
- make_charset (LEADING_BYTE_CONTROL_1, Qcontrol_1,
- CHARSET_TYPE_94, 1, 1, 0,
- CHARSET_LEFT_TO_RIGHT,
+ make_charset (LEADING_BYTE_CONTROL_1, Qcontrol_1, 94, 1,
+ 1, 1, 0, CHARSET_LEFT_TO_RIGHT,
build_string ("C1"),
build_string ("Control characters"),
build_string ("Control characters 128-191"),
build_string (""),
Qnil, 0x80, 0x9F, 0, 0);
+ staticpro (&Vcharset_latin_iso8859_1);
Vcharset_latin_iso8859_1 =
- make_charset (LEADING_BYTE_LATIN_ISO8859_1, Qlatin_iso8859_1,
- CHARSET_TYPE_96, 1, 1, 'A',
- CHARSET_LEFT_TO_RIGHT,
+ make_charset (LEADING_BYTE_LATIN_ISO8859_1, Qlatin_iso8859_1, 96, 1,
+ 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"),
Qnil, 0xA0, 0xFF, 0, 32);
+ staticpro (&Vcharset_latin_iso8859_2);
Vcharset_latin_iso8859_2 =
- make_charset (LEADING_BYTE_LATIN_ISO8859_2, Qlatin_iso8859_2,
- CHARSET_TYPE_96, 1, 1, 'B',
- CHARSET_LEFT_TO_RIGHT,
+ make_charset (LEADING_BYTE_LATIN_ISO8859_2, Qlatin_iso8859_2, 96, 1,
+ 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"),
Qnil, 0, 0, 0, 32);
+ staticpro (&Vcharset_latin_iso8859_3);
Vcharset_latin_iso8859_3 =
- make_charset (LEADING_BYTE_LATIN_ISO8859_3, Qlatin_iso8859_3,
- CHARSET_TYPE_96, 1, 1, 'C',
- CHARSET_LEFT_TO_RIGHT,
+ make_charset (LEADING_BYTE_LATIN_ISO8859_3, Qlatin_iso8859_3, 96, 1,
+ 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"),
Qnil, 0, 0, 0, 32);
+ staticpro (&Vcharset_latin_iso8859_4);
Vcharset_latin_iso8859_4 =
- make_charset (LEADING_BYTE_LATIN_ISO8859_4, Qlatin_iso8859_4,
- CHARSET_TYPE_96, 1, 1, 'D',
- CHARSET_LEFT_TO_RIGHT,
+ make_charset (LEADING_BYTE_LATIN_ISO8859_4, Qlatin_iso8859_4, 96, 1,
+ 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"),
Qnil, 0, 0, 0, 32);
+ staticpro (&Vcharset_thai_tis620);
Vcharset_thai_tis620 =
- make_charset (LEADING_BYTE_THAI_TIS620, Qthai_tis620,
- CHARSET_TYPE_96, 1, 1, 'T',
- CHARSET_LEFT_TO_RIGHT,
+ make_charset (LEADING_BYTE_THAI_TIS620, Qthai_tis620, 96, 1,
+ 1, 1, 'T', CHARSET_LEFT_TO_RIGHT,
build_string ("TIS620"),
build_string ("TIS620 (Thai)"),
build_string ("TIS620.2529 (Thai)"),
build_string ("tis620"),
Qnil, MIN_CHAR_THAI, MAX_CHAR_THAI, 0, 32);
+ staticpro (&Vcharset_greek_iso8859_7);
Vcharset_greek_iso8859_7 =
- make_charset (LEADING_BYTE_GREEK_ISO8859_7, Qgreek_iso8859_7,
- CHARSET_TYPE_96, 1, 1, 'F',
- CHARSET_LEFT_TO_RIGHT,
+ make_charset (LEADING_BYTE_GREEK_ISO8859_7, Qgreek_iso8859_7, 96, 1,
+ 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"),
- Qnil, MIN_CHAR_GREEK, MAX_CHAR_GREEK, 0, 32);
+ Qnil,
+ 0 /* MIN_CHAR_GREEK */,
+ 0 /* MAX_CHAR_GREEK */, 0, 32);
+ staticpro (&Vcharset_arabic_iso8859_6);
Vcharset_arabic_iso8859_6 =
- make_charset (LEADING_BYTE_ARABIC_ISO8859_6, Qarabic_iso8859_6,
- CHARSET_TYPE_96, 1, 1, 'G',
- CHARSET_RIGHT_TO_LEFT,
+ make_charset (LEADING_BYTE_ARABIC_ISO8859_6, Qarabic_iso8859_6, 96, 1,
+ 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"),
Qnil, 0, 0, 0, 32);
+ staticpro (&Vcharset_hebrew_iso8859_8);
Vcharset_hebrew_iso8859_8 =
- make_charset (LEADING_BYTE_HEBREW_ISO8859_8, Qhebrew_iso8859_8,
- CHARSET_TYPE_96, 1, 1, 'H',
- CHARSET_RIGHT_TO_LEFT,
+ make_charset (LEADING_BYTE_HEBREW_ISO8859_8, Qhebrew_iso8859_8, 96, 1,
+ 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"),
Qnil, MIN_CHAR_HEBREW, MAX_CHAR_HEBREW, 0, 32);
+ staticpro (&Vcharset_katakana_jisx0201);
Vcharset_katakana_jisx0201 =
- make_charset (LEADING_BYTE_KATAKANA_JISX0201, Qkatakana_jisx0201,
- CHARSET_TYPE_94, 1, 1, 'I',
- CHARSET_LEFT_TO_RIGHT,
+ make_charset (LEADING_BYTE_KATAKANA_JISX0201, Qkatakana_jisx0201, 94, 1,
+ 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"),
- Qnil,
- MIN_CHAR_HALFWIDTH_KATAKANA,
- MAX_CHAR_HALFWIDTH_KATAKANA, 0, 33);
+ Qnil, 0, 0, 0, 33);
+ staticpro (&Vcharset_latin_jisx0201);
Vcharset_latin_jisx0201 =
- make_charset (LEADING_BYTE_LATIN_JISX0201, Qlatin_jisx0201,
- CHARSET_TYPE_94, 1, 0, 'J',
- CHARSET_LEFT_TO_RIGHT,
+ make_charset (LEADING_BYTE_LATIN_JISX0201, Qlatin_jisx0201, 94, 1,
+ 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"),
Qnil, 0, 0, 0, 33);
+ staticpro (&Vcharset_cyrillic_iso8859_5);
Vcharset_cyrillic_iso8859_5 =
- make_charset (LEADING_BYTE_CYRILLIC_ISO8859_5, Qcyrillic_iso8859_5,
- CHARSET_TYPE_96, 1, 1, 'L',
- CHARSET_LEFT_TO_RIGHT,
+ make_charset (LEADING_BYTE_CYRILLIC_ISO8859_5, Qcyrillic_iso8859_5, 96, 1,
+ 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"),
- Qnil, MIN_CHAR_CYRILLIC, MAX_CHAR_CYRILLIC, 0, 32);
+ Qnil,
+ 0 /* MIN_CHAR_CYRILLIC */,
+ 0 /* MAX_CHAR_CYRILLIC */, 0, 32);
+ staticpro (&Vcharset_latin_iso8859_9);
Vcharset_latin_iso8859_9 =
- make_charset (LEADING_BYTE_LATIN_ISO8859_9, Qlatin_iso8859_9,
- CHARSET_TYPE_96, 1, 1, 'M',
- CHARSET_LEFT_TO_RIGHT,
+ make_charset (LEADING_BYTE_LATIN_ISO8859_9, Qlatin_iso8859_9, 96, 1,
+ 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"),
Qnil, 0, 0, 0, 32);
+ staticpro (&Vcharset_japanese_jisx0208_1978);
Vcharset_japanese_jisx0208_1978 =
- make_charset (LEADING_BYTE_JAPANESE_JISX0208_1978, Qjapanese_jisx0208_1978,
- CHARSET_TYPE_94X94, 2, 0, '@',
- CHARSET_LEFT_TO_RIGHT,
+ make_charset (LEADING_BYTE_JAPANESE_JISX0208_1978,
+ Qjapanese_jisx0208_1978, 94, 2,
+ 2, 0, '@', CHARSET_LEFT_TO_RIGHT,
build_string ("JIS X0208:1978"),
build_string ("JIS X0208:1978 (Japanese)"),
build_string
("JIS X0208:1978 Japanese Kanji (so called \"old JIS\")"),
build_string ("\\(jisx0208\\|jisc6226\\)\\.1978"),
Qnil, 0, 0, 0, 33);
+ staticpro (&Vcharset_chinese_gb2312);
Vcharset_chinese_gb2312 =
- make_charset (LEADING_BYTE_CHINESE_GB2312, Qchinese_gb2312,
- CHARSET_TYPE_94X94, 2, 0, 'A',
- CHARSET_LEFT_TO_RIGHT,
+ make_charset (LEADING_BYTE_CHINESE_GB2312, Qchinese_gb2312, 94, 2,
+ 2, 0, 'A', CHARSET_LEFT_TO_RIGHT,
build_string ("GB2312"),
build_string ("GB2312)"),
build_string ("GB2312 Chinese simplified"),
build_string ("gb2312"),
Qnil, 0, 0, 0, 33);
+ staticpro (&Vcharset_japanese_jisx0208);
Vcharset_japanese_jisx0208 =
- make_charset (LEADING_BYTE_JAPANESE_JISX0208, Qjapanese_jisx0208,
- CHARSET_TYPE_94X94, 2, 0, 'B',
- CHARSET_LEFT_TO_RIGHT,
+ make_charset (LEADING_BYTE_JAPANESE_JISX0208, Qjapanese_jisx0208, 94, 2,
+ 2, 0, 'B', CHARSET_LEFT_TO_RIGHT,
build_string ("JISX0208"),
build_string ("JIS X0208:1983 (Japanese)"),
build_string ("JIS X0208:1983 Japanese Kanji"),
build_string ("jisx0208\\.1983"),
Qnil, 0, 0, 0, 33);
+#ifdef UTF2000
+ staticpro (&Vcharset_japanese_jisx0208_1990);
+ Vcharset_japanese_jisx0208_1990 =
+ make_charset (LEADING_BYTE_JAPANESE_JISX0208_1990,
+ Qjapanese_jisx0208_1990, 94, 2,
+ 2, 0, 0, CHARSET_LEFT_TO_RIGHT,
+ build_string ("JISX0208-1990"),
+ build_string ("JIS X0208:1990 (Japanese)"),
+ build_string ("JIS X0208:1990 Japanese Kanji"),
+ build_string ("jisx0208\\.1990"),
+ Qnil,
+ MIN_CHAR_JIS_X0208_1990,
+ MAX_CHAR_JIS_X0208_1990, 0, 33);
+#endif
+ staticpro (&Vcharset_korean_ksc5601);
Vcharset_korean_ksc5601 =
- make_charset (LEADING_BYTE_KOREAN_KSC5601, Qkorean_ksc5601,
- CHARSET_TYPE_94X94, 2, 0, 'C',
- CHARSET_LEFT_TO_RIGHT,
+ make_charset (LEADING_BYTE_KOREAN_KSC5601, Qkorean_ksc5601, 94, 2,
+ 2, 0, 'C', CHARSET_LEFT_TO_RIGHT,
build_string ("KSC5601"),
build_string ("KSC5601 (Korean"),
build_string ("KSC5601 Korean Hangul and Hanja"),
build_string ("ksc5601"),
Qnil, 0, 0, 0, 33);
+ staticpro (&Vcharset_japanese_jisx0212);
Vcharset_japanese_jisx0212 =
- make_charset (LEADING_BYTE_JAPANESE_JISX0212, Qjapanese_jisx0212,
- CHARSET_TYPE_94X94, 2, 0, 'D',
- CHARSET_LEFT_TO_RIGHT,
+ make_charset (LEADING_BYTE_JAPANESE_JISX0212, Qjapanese_jisx0212, 94, 2,
+ 2, 0, 'D', CHARSET_LEFT_TO_RIGHT,
build_string ("JISX0212"),
build_string ("JISX0212 (Japanese)"),
build_string ("JISX0212 Japanese Supplement"),
Qnil, 0, 0, 0, 33);
#define CHINESE_CNS_PLANE_RE(n) "cns11643[.-]\\(.*[.-]\\)?" n "$"
+ staticpro (&Vcharset_chinese_cns11643_1);
Vcharset_chinese_cns11643_1 =
- make_charset (LEADING_BYTE_CHINESE_CNS11643_1, Qchinese_cns11643_1,
- CHARSET_TYPE_94X94, 2, 0, 'G',
- CHARSET_LEFT_TO_RIGHT,
+ make_charset (LEADING_BYTE_CHINESE_CNS11643_1, Qchinese_cns11643_1, 94, 2,
+ 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")),
Qnil, 0, 0, 0, 33);
+ staticpro (&Vcharset_chinese_cns11643_2);
Vcharset_chinese_cns11643_2 =
- make_charset (LEADING_BYTE_CHINESE_CNS11643_2, Qchinese_cns11643_2,
- CHARSET_TYPE_94X94, 2, 0, 'H',
- CHARSET_LEFT_TO_RIGHT,
+ make_charset (LEADING_BYTE_CHINESE_CNS11643_2, Qchinese_cns11643_2, 94, 2,
+ 2, 0, 'H', CHARSET_LEFT_TO_RIGHT,
build_string ("CNS11643-2"),
build_string ("CNS11643-2 (Chinese traditional)"),
build_string
build_string (CHINESE_CNS_PLANE_RE("2")),
Qnil, 0, 0, 0, 33);
#ifdef UTF2000
+ staticpro (&Vcharset_latin_tcvn5712);
+ Vcharset_latin_tcvn5712 =
+ make_charset (LEADING_BYTE_LATIN_TCVN5712, Qlatin_tcvn5712, 96, 1,
+ 1, 1, 'Z', CHARSET_LEFT_TO_RIGHT,
+ build_string ("TCVN 5712"),
+ build_string ("TCVN 5712 (VSCII-2)"),
+ build_string ("Vietnamese TCVN 5712:1983 (VSCII-2)"),
+ build_string ("tcvn5712-1"),
+ Qnil, 0, 0, 0, 32);
+ staticpro (&Vcharset_latin_viscii_lower);
Vcharset_latin_viscii_lower =
- make_charset (LEADING_BYTE_LATIN_VISCII_LOWER, Qlatin_viscii_lower,
- CHARSET_TYPE_96, 1, 1, '1',
- CHARSET_LEFT_TO_RIGHT,
+ make_charset (LEADING_BYTE_LATIN_VISCII_LOWER, Qlatin_viscii_lower, 96, 1,
+ 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);
+ staticpro (&Vcharset_latin_viscii_upper);
Vcharset_latin_viscii_upper =
- make_charset (LEADING_BYTE_LATIN_VISCII_UPPER, Qlatin_viscii_upper,
- CHARSET_TYPE_96, 1, 1, '2',
- CHARSET_LEFT_TO_RIGHT,
+ make_charset (LEADING_BYTE_LATIN_VISCII_UPPER, Qlatin_viscii_upper, 96, 1,
+ 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);
+ staticpro (&Vcharset_latin_viscii);
Vcharset_latin_viscii =
- make_charset (LEADING_BYTE_LATIN_VISCII, Qlatin_viscii,
- CHARSET_TYPE_256, 1, 2, 0,
- CHARSET_LEFT_TO_RIGHT,
+ make_charset (LEADING_BYTE_LATIN_VISCII, Qlatin_viscii, 256, 1,
+ 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);
+ staticpro (&Vcharset_ideograph_daikanwa);
+ Vcharset_ideograph_daikanwa =
+ make_charset (LEADING_BYTE_DAIKANWA, Qideograph_daikanwa, 256, 2,
+ 2, 2, 0, CHARSET_LEFT_TO_RIGHT,
+ build_string ("Daikanwa"),
+ build_string ("Morohashi's Daikanwa"),
+ build_string ("Daikanwa dictionary by MOROHASHI Tetsuji"),
+ build_string ("Daikanwa"),
+ Qnil, MIN_CHAR_DAIKANWA, MAX_CHAR_DAIKANWA, 0, 0);
+ staticpro (&Vcharset_mojikyo);
+ Vcharset_mojikyo =
+ make_charset (LEADING_BYTE_MOJIKYO, Qmojikyo, 256, 3,
+ 2, 2, 0, CHARSET_LEFT_TO_RIGHT,
+ build_string ("Mojikyo"),
+ build_string ("Mojikyo"),
+ build_string ("Konjaku-Mojikyo"),
+ build_string (""),
+ Qnil, MIN_CHAR_MOJIKYO, MAX_CHAR_MOJIKYO, 0, 0);
+ staticpro (&Vcharset_mojikyo_pj_1);
+ Vcharset_mojikyo_pj_1 =
+ make_charset (LEADING_BYTE_MOJIKYO_PJ_1, Qmojikyo_pj_1, 94, 2,
+ 2, 0, 0, CHARSET_LEFT_TO_RIGHT,
+ build_string ("Mojikyo-PJ-1"),
+ build_string ("Mojikyo (pseudo JIS encoding) part 1"),
+ build_string
+ ("Konjaku-Mojikyo (pseudo JIS encoding) part 1"),
+ build_string ("jisx0208\\.Mojikyo-1$"),
+ Qnil, 0, 0, 0, 33);
+ staticpro (&Vcharset_mojikyo_pj_2);
+ Vcharset_mojikyo_pj_2 =
+ make_charset (LEADING_BYTE_MOJIKYO_PJ_2, Qmojikyo_pj_2, 94, 2,
+ 2, 0, 0, CHARSET_LEFT_TO_RIGHT,
+ build_string ("Mojikyo-PJ-2"),
+ build_string ("Mojikyo (pseudo JIS encoding) part 2"),
+ build_string
+ ("Konjaku-Mojikyo (pseudo JIS encoding) part 2"),
+ build_string ("jisx0208\\.Mojikyo-2$"),
+ Qnil, 0, 0, 0, 33);
+ staticpro (&Vcharset_mojikyo_pj_3);
+ Vcharset_mojikyo_pj_3 =
+ make_charset (LEADING_BYTE_MOJIKYO_PJ_3, Qmojikyo_pj_3, 94, 2,
+ 2, 0, 0, CHARSET_LEFT_TO_RIGHT,
+ build_string ("Mojikyo-PJ-3"),
+ build_string ("Mojikyo (pseudo JIS encoding) part 3"),
+ build_string
+ ("Konjaku-Mojikyo (pseudo JIS encoding) part 3"),
+ build_string ("jisx0208\\.Mojikyo-3$"),
+ Qnil, 0, 0, 0, 33);
+ staticpro (&Vcharset_mojikyo_pj_4);
+ Vcharset_mojikyo_pj_4 =
+ make_charset (LEADING_BYTE_MOJIKYO_PJ_4, Qmojikyo_pj_4, 94, 2,
+ 2, 0, 0, CHARSET_LEFT_TO_RIGHT,
+ build_string ("Mojikyo-PJ-4"),
+ build_string ("Mojikyo (pseudo JIS encoding) part 4"),
+ build_string
+ ("Konjaku-Mojikyo (pseudo JIS encoding) part 4"),
+ build_string ("jisx0208\\.Mojikyo-4$"),
+ Qnil, 0, 0, 0, 33);
+ staticpro (&Vcharset_mojikyo_pj_5);
+ Vcharset_mojikyo_pj_5 =
+ make_charset (LEADING_BYTE_MOJIKYO_PJ_5, Qmojikyo_pj_5, 94, 2,
+ 2, 0, 0, CHARSET_LEFT_TO_RIGHT,
+ build_string ("Mojikyo-PJ-5"),
+ build_string ("Mojikyo (pseudo JIS encoding) part 5"),
+ build_string
+ ("Konjaku-Mojikyo (pseudo JIS encoding) part 5"),
+ build_string ("jisx0208\\.Mojikyo-5$"),
+ Qnil, 0, 0, 0, 33);
+ staticpro (&Vcharset_mojikyo_pj_6);
+ Vcharset_mojikyo_pj_6 =
+ make_charset (LEADING_BYTE_MOJIKYO_PJ_6, Qmojikyo_pj_6, 94, 2,
+ 2, 0, 0, CHARSET_LEFT_TO_RIGHT,
+ build_string ("Mojikyo-PJ-6"),
+ build_string ("Mojikyo (pseudo JIS encoding) part 6"),
+ build_string
+ ("Konjaku-Mojikyo (pseudo JIS encoding) part 6"),
+ build_string ("jisx0208\\.Mojikyo-6$"),
+ Qnil, 0, 0, 0, 33);
+ staticpro (&Vcharset_mojikyo_pj_7);
+ Vcharset_mojikyo_pj_7 =
+ make_charset (LEADING_BYTE_MOJIKYO_PJ_7, Qmojikyo_pj_7, 94, 2,
+ 2, 0, 0, CHARSET_LEFT_TO_RIGHT,
+ build_string ("Mojikyo-PJ-7"),
+ build_string ("Mojikyo (pseudo JIS encoding) part 7"),
+ build_string
+ ("Konjaku-Mojikyo (pseudo JIS encoding) part 7"),
+ build_string ("jisx0208\\.Mojikyo-7$"),
+ Qnil, 0, 0, 0, 33);
+ staticpro (&Vcharset_mojikyo_pj_8);
+ Vcharset_mojikyo_pj_8 =
+ make_charset (LEADING_BYTE_MOJIKYO_PJ_8, Qmojikyo_pj_8, 94, 2,
+ 2, 0, 0, CHARSET_LEFT_TO_RIGHT,
+ build_string ("Mojikyo-PJ-8"),
+ build_string ("Mojikyo (pseudo JIS encoding) part 8"),
+ build_string
+ ("Konjaku-Mojikyo (pseudo JIS encoding) part 8"),
+ build_string ("jisx0208\\.Mojikyo-8$"),
+ Qnil, 0, 0, 0, 33);
+ staticpro (&Vcharset_mojikyo_pj_9);
+ Vcharset_mojikyo_pj_9 =
+ make_charset (LEADING_BYTE_MOJIKYO_PJ_9, Qmojikyo_pj_9, 94, 2,
+ 2, 0, 0, CHARSET_LEFT_TO_RIGHT,
+ build_string ("Mojikyo-PJ-9"),
+ build_string ("Mojikyo (pseudo JIS encoding) part 9"),
+ build_string
+ ("Konjaku-Mojikyo (pseudo JIS encoding) part 9"),
+ build_string ("jisx0208\\.Mojikyo-9$"),
+ Qnil, 0, 0, 0, 33);
+ staticpro (&Vcharset_mojikyo_pj_10);
+ Vcharset_mojikyo_pj_10 =
+ make_charset (LEADING_BYTE_MOJIKYO_PJ_10, Qmojikyo_pj_10, 94, 2,
+ 2, 0, 0, CHARSET_LEFT_TO_RIGHT,
+ build_string ("Mojikyo-PJ-10"),
+ build_string ("Mojikyo (pseudo JIS encoding) part 10"),
+ build_string
+ ("Konjaku-Mojikyo (pseudo JIS encoding) part 10"),
+ build_string ("jisx0208\\.Mojikyo-10$"),
+ Qnil, 0, 0, 0, 33);
+ staticpro (&Vcharset_mojikyo_pj_11);
+ Vcharset_mojikyo_pj_11 =
+ make_charset (LEADING_BYTE_MOJIKYO_PJ_11, Qmojikyo_pj_11, 94, 2,
+ 2, 0, 0, CHARSET_LEFT_TO_RIGHT,
+ build_string ("Mojikyo-PJ-11"),
+ build_string ("Mojikyo (pseudo JIS encoding) part 11"),
+ build_string
+ ("Konjaku-Mojikyo (pseudo JIS encoding) part 11"),
+ build_string ("jisx0208\\.Mojikyo-11$"),
+ Qnil, 0, 0, 0, 33);
+ staticpro (&Vcharset_mojikyo_pj_12);
+ Vcharset_mojikyo_pj_12 =
+ make_charset (LEADING_BYTE_MOJIKYO_PJ_12, Qmojikyo_pj_12, 94, 2,
+ 2, 0, 0, CHARSET_LEFT_TO_RIGHT,
+ build_string ("Mojikyo-PJ-12"),
+ build_string ("Mojikyo (pseudo JIS encoding) part 12"),
+ build_string
+ ("Konjaku-Mojikyo (pseudo JIS encoding) part 12"),
+ build_string ("jisx0208\\.Mojikyo-12$"),
+ Qnil, 0, 0, 0, 33);
+ staticpro (&Vcharset_mojikyo_pj_13);
+ Vcharset_mojikyo_pj_13 =
+ make_charset (LEADING_BYTE_MOJIKYO_PJ_13, Qmojikyo_pj_13, 94, 2,
+ 2, 0, 0, CHARSET_LEFT_TO_RIGHT,
+ build_string ("Mojikyo-PJ-13"),
+ build_string ("Mojikyo (pseudo JIS encoding) part 13"),
+ build_string
+ ("Konjaku-Mojikyo (pseudo JIS encoding) part 13"),
+ build_string ("jisx0208\\.Mojikyo-13$"),
+ Qnil, 0, 0, 0, 33);
+ staticpro (&Vcharset_mojikyo_pj_14);
+ Vcharset_mojikyo_pj_14 =
+ make_charset (LEADING_BYTE_MOJIKYO_PJ_14, Qmojikyo_pj_14, 94, 2,
+ 2, 0, 0, CHARSET_LEFT_TO_RIGHT,
+ build_string ("Mojikyo-PJ-14"),
+ build_string ("Mojikyo (pseudo JIS encoding) part 14"),
+ build_string
+ ("Konjaku-Mojikyo (pseudo JIS encoding) part 14"),
+ build_string ("jisx0208\\.Mojikyo-14$"),
+ Qnil, 0, 0, 0, 33);
+ staticpro (&Vcharset_mojikyo_pj_15);
+ Vcharset_mojikyo_pj_15 =
+ make_charset (LEADING_BYTE_MOJIKYO_PJ_15, Qmojikyo_pj_15, 94, 2,
+ 2, 0, 0, CHARSET_LEFT_TO_RIGHT,
+ build_string ("Mojikyo-PJ-15"),
+ build_string ("Mojikyo (pseudo JIS encoding) part 15"),
+ build_string
+ ("Konjaku-Mojikyo (pseudo JIS encoding) part 15"),
+ build_string ("jisx0208\\.Mojikyo-15$"),
+ Qnil, 0, 0, 0, 33);
+ staticpro (&Vcharset_mojikyo_pj_16);
+ Vcharset_mojikyo_pj_16 =
+ make_charset (LEADING_BYTE_MOJIKYO_PJ_16, Qmojikyo_pj_16, 94, 2,
+ 2, 0, 0, CHARSET_LEFT_TO_RIGHT,
+ build_string ("Mojikyo-PJ-16"),
+ build_string ("Mojikyo (pseudo JIS encoding) part 16"),
+ build_string
+ ("Konjaku-Mojikyo (pseudo JIS encoding) part 16"),
+ build_string ("jisx0208\\.Mojikyo-16$"),
+ Qnil, 0, 0, 0, 33);
+ staticpro (&Vcharset_mojikyo_pj_17);
+ Vcharset_mojikyo_pj_17 =
+ make_charset (LEADING_BYTE_MOJIKYO_PJ_17, Qmojikyo_pj_17, 94, 2,
+ 2, 0, 0, CHARSET_LEFT_TO_RIGHT,
+ build_string ("Mojikyo-PJ-17"),
+ build_string ("Mojikyo (pseudo JIS encoding) part 17"),
+ build_string
+ ("Konjaku-Mojikyo (pseudo JIS encoding) part 17"),
+ build_string ("jisx0208\\.Mojikyo-17$"),
+ Qnil, 0, 0, 0, 33);
+ staticpro (&Vcharset_mojikyo_pj_18);
+ Vcharset_mojikyo_pj_18 =
+ make_charset (LEADING_BYTE_MOJIKYO_PJ_18, Qmojikyo_pj_18, 94, 2,
+ 2, 0, 0, CHARSET_LEFT_TO_RIGHT,
+ build_string ("Mojikyo-PJ-18"),
+ build_string ("Mojikyo (pseudo JIS encoding) part 18"),
+ build_string
+ ("Konjaku-Mojikyo (pseudo JIS encoding) part 18"),
+ build_string ("jisx0208\\.Mojikyo-18$"),
+ Qnil, 0, 0, 0, 33);
+ staticpro (&Vcharset_mojikyo_pj_19);
+ Vcharset_mojikyo_pj_19 =
+ make_charset (LEADING_BYTE_MOJIKYO_PJ_19, Qmojikyo_pj_19, 94, 2,
+ 2, 0, 0, CHARSET_LEFT_TO_RIGHT,
+ build_string ("Mojikyo-PJ-19"),
+ build_string ("Mojikyo (pseudo JIS encoding) part 19"),
+ build_string
+ ("Konjaku-Mojikyo (pseudo JIS encoding) part 19"),
+ build_string ("jisx0208\\.Mojikyo-19$"),
+ Qnil, 0, 0, 0, 33);
+ staticpro (&Vcharset_mojikyo_pj_20);
+ Vcharset_mojikyo_pj_20 =
+ make_charset (LEADING_BYTE_MOJIKYO_PJ_20, Qmojikyo_pj_20, 94, 2,
+ 2, 0, 0, CHARSET_LEFT_TO_RIGHT,
+ build_string ("Mojikyo-PJ-20"),
+ build_string ("Mojikyo (pseudo JIS encoding) part 20"),
+ build_string
+ ("Konjaku-Mojikyo (pseudo JIS encoding) part 20"),
+ build_string ("jisx0208\\.Mojikyo-20$"),
+ Qnil, 0, 0, 0, 33);
+ staticpro (&Vcharset_mojikyo_pj_21);
+ Vcharset_mojikyo_pj_21 =
+ make_charset (LEADING_BYTE_MOJIKYO_PJ_21, Qmojikyo_pj_21, 94, 2,
+ 2, 0, 0, CHARSET_LEFT_TO_RIGHT,
+ build_string ("Mojikyo-PJ-21"),
+ build_string ("Mojikyo (pseudo JIS encoding) part 21"),
+ build_string
+ ("Konjaku-Mojikyo (pseudo JIS encoding) part 21"),
+ build_string ("jisx0208\\.Mojikyo-21$"),
+ Qnil, 0, 0, 0, 33);
+ staticpro (&Vcharset_ethiopic_ucs);
Vcharset_ethiopic_ucs =
- make_charset (LEADING_BYTE_ETHIOPIC_UCS, Qethiopic_ucs,
- CHARSET_TYPE_256X256, 2, 2, 0,
- CHARSET_LEFT_TO_RIGHT,
+ make_charset (LEADING_BYTE_ETHIOPIC_UCS, Qethiopic_ucs, 256, 2,
+ 2, 2, 0, CHARSET_LEFT_TO_RIGHT,
build_string ("Ethiopic (UCS)"),
build_string ("Ethiopic (UCS)"),
build_string ("Ethiopic of UCS"),
build_string ("Ethiopic-Unicode"),
Qnil, 0x1200, 0x137F, 0x1200, 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
+ staticpro (&Vcharset_chinese_big5_1);
Vcharset_chinese_big5_1 =
- make_charset (LEADING_BYTE_CHINESE_BIG5_1, Qchinese_big5_1,
- CHARSET_TYPE_94X94, 2, 0, '0',
- CHARSET_LEFT_TO_RIGHT,
+ make_charset (LEADING_BYTE_CHINESE_BIG5_1, Qchinese_big5_1, 94, 2,
+ 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"),
Qnil, 0, 0, 0, 33);
+ staticpro (&Vcharset_chinese_big5_2);
Vcharset_chinese_big5_2 =
- make_charset (LEADING_BYTE_CHINESE_BIG5_2, Qchinese_big5_2,
- CHARSET_TYPE_94X94, 2, 0, '1',
- CHARSET_LEFT_TO_RIGHT,
+ make_charset (LEADING_BYTE_CHINESE_BIG5_2, Qchinese_big5_2, 94, 2,
+ 2, 0, '1', CHARSET_LEFT_TO_RIGHT,
build_string ("Big5"),
build_string ("Big5 (Level-2)"),
build_string
/* #### 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. */
+ staticpro (&Vcharset_composite);
Vcharset_composite =
- make_charset (LEADING_BYTE_COMPOSITE, Qcomposite,
- CHARSET_TYPE_96X96, 2, 0, 0,
- CHARSET_LEFT_TO_RIGHT,
+ make_charset (LEADING_BYTE_COMPOSITE, Qcomposite, 96, 2,
+ 2, 0, 0, CHARSET_LEFT_TO_RIGHT,
build_string ("Composite"),
build_string ("Composite characters"),
build_string ("Composite characters"),
build_string (""));
+ /* #### not dumped properly */
composite_char_row_next = 32;
composite_char_col_next = 32;