/* Functions to handle multilingual characters.
Copyright (C) 1992, 1995 Free Software Foundation, Inc.
Copyright (C) 1995 Sun Microsystems, Inc.
- Copyright (C) 1999,2000,2001,2002,2003,2004 MORIOKA Tomohiko
+ Copyright (C) 1999, 2000, 2001, 2002, 2003, 2004, 2008, 2009, 2011, 2013, 2016
+ MORIOKA Tomohiko
This file is part of XEmacs.
Lisp_Object Vcharset_latin_jisx0201;
Lisp_Object Vcharset_cyrillic_iso8859_5;
Lisp_Object Vcharset_latin_iso8859_9;
-Lisp_Object Vcharset_japanese_jisx0208_1978;
+/* Lisp_Object Vcharset_japanese_jisx0208_1978; */
Lisp_Object Vcharset_chinese_gb2312;
Lisp_Object Vcharset_chinese_gb12345;
Lisp_Object Vcharset_japanese_jisx0208;
return 0;
}
+void
+decoding_table_put_char (Lisp_Object ccs,
+ int code_point, Lisp_Object character)
+{
+#if 1
+ Lisp_Object table1 = XCHARSET_DECODING_TABLE (ccs);
+ int dim = XCHARSET_DIMENSION (ccs);
+
+ if (dim == 1)
+ XCHARSET_DECODING_TABLE (ccs)
+ = put_ccs_octet_table (table1, ccs, code_point, character);
+ else if (dim == 2)
+ {
+ Lisp_Object table2
+ = get_ccs_octet_table (table1, ccs, (unsigned char)(code_point >> 8));
+
+ table2 = put_ccs_octet_table (table2, ccs,
+ (unsigned char)code_point, character);
+ XCHARSET_DECODING_TABLE (ccs)
+ = put_ccs_octet_table (table1, ccs,
+ (unsigned char)(code_point >> 8), table2);
+ }
+ else if (dim == 3)
+ {
+ Lisp_Object table2
+ = get_ccs_octet_table (table1, ccs, (unsigned char)(code_point >> 16));
+ Lisp_Object table3
+ = get_ccs_octet_table (table2, ccs, (unsigned char)(code_point >> 8));
+
+ table3 = put_ccs_octet_table (table3, ccs,
+ (unsigned char)code_point, character);
+ table2 = put_ccs_octet_table (table2, ccs,
+ (unsigned char)(code_point >> 8), table3);
+ XCHARSET_DECODING_TABLE (ccs)
+ = put_ccs_octet_table (table1, ccs,
+ (unsigned char)(code_point >> 16), table2);
+ }
+ else /* if (dim == 4) */
+ {
+ Lisp_Object table2
+ = get_ccs_octet_table (table1, ccs, (unsigned char)(code_point >> 24));
+ Lisp_Object table3
+ = get_ccs_octet_table (table2, ccs, (unsigned char)(code_point >> 16));
+ Lisp_Object table4
+ = get_ccs_octet_table (table3, ccs, (unsigned char)(code_point >> 8));
+
+ table4 = put_ccs_octet_table (table4, ccs,
+ (unsigned char)code_point, character);
+ table3 = put_ccs_octet_table (table3, ccs,
+ (unsigned char)(code_point >> 8), table4);
+ table2 = put_ccs_octet_table (table2, ccs,
+ (unsigned char)(code_point >> 16), table3);
+ XCHARSET_DECODING_TABLE (ccs)
+ = put_ccs_octet_table (table1, ccs,
+ (unsigned char)(code_point >> 24), table2);
+ }
+#else
+ Lisp_Object v = XCHARSET_DECODING_TABLE (ccs);
+ int dim = XCHARSET_DIMENSION (ccs);
+ int byte_offset = XCHARSET_BYTE_OFFSET (ccs);
+ int i = -1;
+ Lisp_Object nv;
+ int ccs_len = XVECTOR_LENGTH (v);
+
+ while (dim > 0)
+ {
+ dim--;
+ i = ((code_point >> (8 * dim)) & 255) - byte_offset;
+ nv = XVECTOR_DATA(v)[i];
+ if (dim > 0)
+ {
+ if (!VECTORP (nv))
+ {
+ if (EQ (nv, character))
+ return;
+ else
+ nv = (XVECTOR_DATA(v)[i] = make_vector (ccs_len, Qnil));
+ }
+ v = nv;
+ }
+ else
+ break;
+ }
+ XVECTOR_DATA(v)[i] = character;
+#endif
+}
+
Lisp_Object
put_char_ccs_code_point (Lisp_Object character,
Lisp_Object ccs, Lisp_Object value)
{
- if ( !( EQ (XCHARSET_NAME (ccs), Qmap_ucs)
+ if ( !( EQ (XCHARSET_NAME (ccs), Qrep_ucs)
&& INTP (value) && (XINT (value) < 0xF0000)
&& XCHAR (character) == XINT (value) )
|| !INTP (value) )
Lisp_Object Qshort_name, Qlong_name;
Lisp_Object Qiso_ir;
#ifdef UTF2000
+Lisp_Object Qto_iso_ir;
+Lisp_Object Qpartial;
Lisp_Object Qmin_code, Qmax_code, Qcode_offset;
Lisp_Object Qmother, Qconversion, Q94x60, Q94x94x60, Qbig5_1, Qbig5_2;
#endif
Qlatin_jisx0201,
Qcyrillic_iso8859_5,
Qlatin_iso8859_9,
- Qmap_jis_x0208_1978,
- Qmap_gb2312,
- Qmap_gb12345,
- Qmap_jis_x0208_1983,
- Qmap_ks_x1001,
- Qmap_jis_x0212,
- Qmap_cns11643_1,
- Qmap_cns11643_2,
+/* Qrep_jis_x0208_1978, */
+ Qrep_gb2312,
+ Qrep_gb12345,
+ Qrep_jis_x0208_1983,
+ Qrep_ks_x1001,
+ Qrep_jis_x0212,
+ Qrep_cns11643_1,
+ Qrep_cns11643_2,
#ifdef UTF2000
Qsystem_char_id,
- Qmap_ucs, Qucs,
+ Qrep_ucs, Qucs,
Qucs_bmp,
Qucs_smp,
Qucs_sip,
Qlatin_viscii_upper,
Qvietnamese_viscii_lower,
Qvietnamese_viscii_upper,
- Qmap_jis_x0208,
- Qmap_jis_x0208_1990,
- Qmap_big5,
+ Qrep_jis_x0208,
+ Qrep_jis_x0208_1990,
+ Qrep_big5,
Qethiopic_ucs,
#endif
Qchinese_big5_1,
Bufbyte final, unsigned char direction, Lisp_Object short_name,
Lisp_Object long_name, Lisp_Object doc,
Lisp_Object reg,
+ int iso_ir,
Lisp_Object decoding_table,
Emchar min_code, Emchar max_code,
Emchar code_offset, unsigned char byte_offset,
- Lisp_Object mother, unsigned char conversion)
+ Lisp_Object mother, unsigned char conversion,
+ int partial)
{
Lisp_Object obj;
Lisp_Charset *cs = alloc_lcrecord_type (Lisp_Charset, &lrecord_charset);
CHARSET_CCL_PROGRAM (cs) = Qnil;
CHARSET_REVERSE_DIRECTION_CHARSET (cs) = Qnil;
#ifdef UTF2000
+ CHARSET_ISO_IR (cs) = iso_ir;
CHARSET_DECODING_TABLE(cs) = Qunbound;
CHARSET_MIN_CODE (cs) = min_code;
CHARSET_MAX_CODE (cs) = max_code;
unsigned char iso2022_type
= (dimension == 1 ? 0 : 2) + (chars == 94 ? 0 : 1);
#if UTF2000
- if (code_offset == 0)
+ if ( ( !partial ) && ( code_offset == 0 ) )
{
assert (NILP (chlook->charset_by_attributes[iso2022_type][final]));
chlook->charset_by_attributes[iso2022_type][final] = obj;
#else
if (dimension == 1)
{
- if (chlook->next_allocated_1_byte_leading_byte > MAX_LEADING_BYTE_PRIVATE_1)
+ if (chlook->next_allocated_1_byte_leading_byte >
+ MAX_LEADING_BYTE_PRIVATE_1)
lb = 0;
else
lb = chlook->next_allocated_1_byte_leading_byte++;
}
else
{
- if (chlook->next_allocated_2_byte_leading_byte > MAX_LEADING_BYTE_PRIVATE_2)
- lb = 0;
+ /* awfully fragile, but correct */
+#if MAX_LEADING_BYTE_PRIVATE_2 == 255
+ if (chlook->next_allocated_2_byte_leading_byte == 0)
+#else
+ if (chlook->next_allocated_2_byte_leading_byte >
+ MAX_LEADING_BYTE_PRIVATE_2)
+#endif
+ lb = 0;
else
lb = chlook->next_allocated_2_byte_leading_byte++;
}
}
int
-charset_code_point (Lisp_Object charset, Emchar ch, int defined_only)
+charset_code_point (Lisp_Object charset, Emchar ch, int accepted_mode)
{
- Lisp_Object encoding_table = XCHARSET_ENCODING_TABLE (charset);
Lisp_Object ret;
- if ( CHAR_TABLEP (encoding_table)
- && INTP (ret = get_char_id_table (XCHAR_TABLE(encoding_table),
- ch)) )
- return XINT (ret);
- else
+ if ( accepted_mode >= 0 )
+ {
+ Lisp_Object encoding_table = XCHARSET_ENCODING_TABLE (charset);
+
+ if ( CHAR_TABLEP (encoding_table)
+#ifdef USE_CONCORD_OBJECT_SYSTEM
+ && !UNBOUNDP (ret = get_char_id_table_ce (XCHAR_TABLE
+ (encoding_table),
+ ch))
+#else
+ && !UNBOUNDP (ret = get_char_id_table (XCHAR_TABLE(encoding_table),
+ ch))
+#endif
+ )
+ if ( INTP (ret) )
+ return XINT (ret);
+ else
+ return -1;
+ }
{
Lisp_Object mother = XCHARSET_MOTHER (charset);
int min = XCHARSET_MIN_CODE (charset);
int max = XCHARSET_MAX_CODE (charset);
int code = -1;
- if ( CHARSETP (mother) )
- {
- if (XCHARSET_FINAL (charset) >= '0')
- code = charset_code_point (mother, ch, 1);
- else
- code = charset_code_point (mother, ch, defined_only);
- }
- else if (defined_only)
+ if ( CHARSETP (mother) && ( accepted_mode >= 0)
+ && ( XCHARSET_FINAL (charset) >= '0' )
+ )
+ code = charset_code_point (mother, ch, CHAR_DEFINED_ONLY);
+ else if ( CHARSETP (mother)
+ && ( XCHARSET_FINAL (charset) < '0' )
+ )
+ code = charset_code_point (mother, ch, accepted_mode);
+ else if ( accepted_mode == CHAR_DEFINED_ONLY )
return -1;
else if ( ((max == 0) && CHARSETP (mother)
&& (XCHARSET_FINAL (charset) == 0))
|| ((min <= ch) && (ch <= max)) )
code = ch;
+
if ( ((max == 0) && CHARSETP (mother) && (code >= 0))
|| ((min <= code) && (code <= max)) )
{
exit (-1);
}
}
- else if (defined_only)
+ else if ( accepted_mode == CHAR_DEFINED_ONLY )
return -1;
else if ( ( XCHARSET_FINAL (charset) >= '0' ) &&
( XCHARSET_MIN_CODE (charset) == 0 )
}
int
+encode_char_2 (Emchar ch, Lisp_Object* charset)
+{
+ Lisp_Object charsets = Vdefault_coded_charset_priority_list;
+ int code_point;
+
+ while (!NILP (charsets))
+ {
+ *charset = Ffind_charset (Fcar (charsets));
+ if ( !NILP (*charset)
+ && (XCHARSET_DIMENSION (*charset) <= 2) )
+ {
+ code_point = charset_code_point (*charset, ch, 0);
+ if (code_point >= 0)
+ return code_point;
+
+ if ( !NILP (Vdisplay_coded_charset_priority_use_inheritance) &&
+ NILP (Vdisplay_coded_charset_priority_use_hierarchy_order) )
+ {
+ code_point = encode_char_2_search_children (ch, charset);
+ if (code_point >= 0)
+ return code_point;
+ }
+ }
+ charsets = Fcdr (charsets);
+ }
+
+ if ( !NILP (Vdisplay_coded_charset_priority_use_inheritance) &&
+ !NILP (Vdisplay_coded_charset_priority_use_hierarchy_order) )
+ {
+ charsets = Vdefault_coded_charset_priority_list;
+ while (!NILP (charsets))
+ {
+ *charset = Ffind_charset (Fcar (charsets));
+ if ( !NILP (*charset)
+ && (XCHARSET_DIMENSION (*charset) <= 2) )
+ {
+ code_point = encode_char_2_search_children (ch, charset);
+ if (code_point >= 0)
+ return code_point;
+ }
+ charsets = Fcdr (charsets);
+ }
+ }
+
+ /* otherwise --- maybe for bootstrap */
+ return encode_builtin_char_1 (ch, charset);
+}
+
+int
encode_builtin_char_1 (Emchar c, Lisp_Object* charset)
{
if (c <= MAX_CHAR_BASIC_LATIN)
}
Lisp_Object Vdefault_coded_charset_priority_list;
+Lisp_Object Vdisplay_coded_charset_priority_use_inheritance;
+Lisp_Object Vdisplay_coded_charset_priority_use_hierarchy_order;
#endif
\f
is passed the octets of the character, with the high
bit cleared and set depending upon whether the value
of the 'graphic property is 0 or 1.
+'iso-ir ISO-IR number (for representative coded-charset).
+'=>iso-ir [UTF-2000 only] Corresponding ISO-IR number.
'mother [UTF-2000 only] Base coded-charset.
'code-min [UTF-2000 only] Minimum code-point of a base coded-charset.
'code-max [UTF-2000 only] Maximum code-point of a base coded-charset.
coded-charset.
'conversion [UTF-2000 only] Conversion for a code-point of a base
coded-charset (94x60, 94x94x60, big5-1 or big5-2).
+'partial [UTF-2000 only] If t, specify as a partial coded-charset.
*/
(name, doc_string, props))
{
int id = 0, dimension = 1, chars = 94, graphic = 0, final = 0, columns = -1;
+ int iso_ir = 0;
int direction = CHARSET_LEFT_TO_RIGHT;
Lisp_Object registry = Qnil;
Lisp_Object charset;
Lisp_Object ccl_program = Qnil;
Lisp_Object short_name = Qnil, long_name = Qnil;
Lisp_Object mother = Qnil;
+ int partial = 0;
int min_code = 0, max_code = 0, code_offset = 0;
int byte_offset = -1;
int conversion = 0;
{
#ifdef UTF2000
CHECK_INT (value);
- id = - XINT (value);
+ iso_ir = XINT (value);
+ id = - iso_ir;
#endif
}
+#ifdef UTF2000
+ else if (EQ (keyword, Qto_iso_ir))
+ {
+ CHECK_INT (value);
+ iso_ir = XINT (value);
+ }
+#endif
+
else if (EQ (keyword, Qdimension))
{
CHECK_INT (value);
}
#ifdef UTF2000
+ else if (EQ (keyword, Qpartial))
+ {
+ partial = !NILP (value);
+ }
+
else if (EQ (keyword, Qmother))
{
mother = Fget_charset (value);
byte_offset = 0;
}
+ if ( (conversion == 0) && NILP (mother) && (min_code > 0) )
+ {
+ switch (chars)
+ {
+ case 94:
+ switch (dimension)
+ {
+ case 1:
+ conversion = CONVERSION_94;
+ break;
+ case 2:
+ conversion = CONVERSION_94x94;
+ break;
+ case 3:
+ conversion = CONVERSION_94x94x94;
+ break;
+ case 4:
+ conversion = CONVERSION_94x94x94x94;
+ break;
+ }
+ break;
+ case 96:
+ switch (dimension)
+ {
+ case 1:
+ conversion = CONVERSION_96;
+ break;
+ case 2:
+ conversion = CONVERSION_96x96;
+ break;
+ case 3:
+ conversion = CONVERSION_96x96x96;
+ break;
+ case 4:
+ conversion = CONVERSION_96x96x96x96;
+ break;
+ }
+ break;
+ }
+ }
+
charset = make_charset (id, name, chars, dimension, columns, graphic,
final, direction, short_name, long_name,
- doc_string, registry,
+ doc_string, registry, iso_ir,
Qnil, min_code, max_code, code_offset, byte_offset,
- mother, conversion);
+ mother, conversion, partial);
if (!NILP (ccl_program))
XCHARSET_CCL_PROGRAM (charset) = ccl_program;
return charset;
graphic, final, direction, short_name, long_name,
doc_string, registry,
#ifdef UTF2000
+ CHARSET_ISO_IR(cs),
CHARSET_DECODING_TABLE(cs),
CHARSET_MIN_CODE(cs),
CHARSET_MAX_CODE(cs),
#else
Qnil, 0, 0, 0, 0, Qnil, 0
#endif
-);
+ , 0);
CHARSET_REVERSE_DIRECTION_CHARSET (cs) = new_charset;
XCHARSET_REVERSE_DIRECTION_CHARSET (new_charset) = charset;
return CHARSETP (obj) ? XCHARSET_NAME (obj) : obj;
}
#ifdef UTF2000
+ if (EQ (prop, Qiso_ir)||
+ EQ (prop, Qto_iso_ir))
+ {
+ if ( CHARSET_ISO_IR (cs) > 0 )
+ return make_int (CHARSET_ISO_IR (cs));
+ else
+ return Qnil;
+ }
if (EQ (prop, Qmother))
return CHARSET_MOTHER (cs);
if (EQ (prop, Qmin_code))
= chise_ds_decode_char (default_chise_data_source,
XSTRING_DATA(Fsymbol_name (XCHARSET_NAME(ccs))),
code_point);
+#if 0
if (char_id >= 0)
decoding_table_put_char (ccs, code_point, make_char (char_id));
else
decoding_table_put_char (ccs, code_point, Qnil);
+#endif
/* chise_ccst_close (dt_ccs); */
return char_id;
charset = Fget_charset (charset);
CHECK_INT (code);
c = XINT (code);
- if (XCHARSET_GRAPHIC (charset) == 1)
+ if ( (XCHARSET_GRAPHIC (charset) == 0) ||
+ (XCHARSET_GRAPHIC (charset) == 1) )
c &= 0x7F7F7F7F;
if (NILP (defined_only))
c = DECODE_CHAR (charset, c, !NILP (without_inheritance));
defsymbol (&Qlong_name, "long-name");
defsymbol (&Qiso_ir, "iso-ir");
#ifdef UTF2000
+ defsymbol (&Qto_iso_ir, "=>iso-ir");
+ defsymbol (&Qpartial, "partial");
defsymbol (&Qmother, "mother");
defsymbol (&Qmin_code, "min-code");
defsymbol (&Qmax_code, "max-code");
defsymbol (&Qlatin_jisx0201, "latin-jisx0201");
defsymbol (&Qcyrillic_iso8859_5, "cyrillic-iso8859-5");
defsymbol (&Qlatin_iso8859_9, "latin-iso8859-9");
- defsymbol (&Qmap_jis_x0208_1978, "=jis-x0208@1978");
- defsymbol (&Qmap_gb2312, "=gb2312");
- defsymbol (&Qmap_gb12345, "=gb12345");
- defsymbol (&Qmap_jis_x0208_1983, "=jis-x0208@1983");
- defsymbol (&Qmap_ks_x1001, "=ks-x1001");
- defsymbol (&Qmap_jis_x0212, "=jis-x0212");
- defsymbol (&Qmap_cns11643_1, "=cns11643-1");
- defsymbol (&Qmap_cns11643_2, "=cns11643-2");
+ /* defsymbol (&Qrep_jis_x0208_1978, "=jis-x0208@1978"); */
+ defsymbol (&Qrep_gb2312, "=gb2312");
+ defsymbol (&Qrep_gb12345, "=gb12345");
+ defsymbol (&Qrep_jis_x0208_1983, "=jis-x0208@1983");
+ defsymbol (&Qrep_ks_x1001, "=ks-x1001");
+ defsymbol (&Qrep_jis_x0212, "=jis-x0212");
+ defsymbol (&Qrep_cns11643_1, "=cns11643-1");
+ defsymbol (&Qrep_cns11643_2, "=cns11643-2");
#ifdef UTF2000
defsymbol (&Qsystem_char_id, "system-char-id");
- defsymbol (&Qmap_ucs, "=ucs");
+ defsymbol (&Qrep_ucs, "=ucs");
defsymbol (&Qucs, "ucs");
defsymbol (&Qucs_bmp, "ucs-bmp");
defsymbol (&Qucs_smp, "ucs-smp");
defsymbol (&Qlatin_viscii_upper, "latin-viscii-upper");
defsymbol (&Qvietnamese_viscii_lower, "vietnamese-viscii-lower");
defsymbol (&Qvietnamese_viscii_upper, "vietnamese-viscii-upper");
- defsymbol (&Qmap_jis_x0208, "=jis-x0208");
- defsymbol (&Qmap_jis_x0208_1990, "=jis-x0208@1990");
- defsymbol (&Qmap_big5, "=big5");
+ defsymbol (&Qrep_jis_x0208, "=jis-x0208");
+ defsymbol (&Qrep_jis_x0208_1990, "=jis-x0208@1990");
+ defsymbol (&Qrep_big5, "=big5");
defsymbol (&Qethiopic_ucs, "ethiopic-ucs");
#endif
defsymbol (&Qchinese_big5_1, "chinese-big5-1");
&Vdefault_coded_charset_priority_list /*
Default order of preferred coded-character-sets.
*/ );
+ Vdisplay_coded_charset_priority_use_inheritance = Qt;
+ DEFVAR_LISP ("display-coded-charset-priority-use-inheritance",
+ &Vdisplay_coded_charset_priority_use_inheritance /*
+If non-nil, use character inheritance.
+*/ );
+ Vdisplay_coded_charset_priority_use_hierarchy_order = Qt;
+ DEFVAR_LISP ("display-coded-charset-priority-use-hierarchy-order",
+ &Vdisplay_coded_charset_priority_use_hierarchy_order /*
+If non-nil, prefer nearest character in hierarchy order.
+*/ );
#endif
}
build_string ("CHAR-ID"),
build_string ("System char-id"),
build_string (""),
- Qnil, 0, 0x7FFFFFFF, 0, 0, Qnil, CONVERSION_IDENTICAL);
+ 0,
+ Qnil, 0, 0x7FFFFFFF, 0, 0, Qnil, CONVERSION_IDENTICAL,
+ 0);
staticpro (&Vcharset_ucs);
Vcharset_ucs =
- make_charset (LEADING_BYTE_UCS, Qmap_ucs, 256, 4,
+ make_charset (LEADING_BYTE_UCS, Qrep_ucs, 256, 4,
1, 2, 0, CHARSET_LEFT_TO_RIGHT,
build_string ("UCS"),
build_string ("UCS"),
build_string ("ISO/IEC 10646"),
build_string (""),
- Qnil, 0, 0xEFFFF, 0, 0, Qnil, CONVERSION_IDENTICAL);
+ - LEADING_BYTE_UCS,
+ Qnil, 0, 0xEFFFF, 0, 0, Qnil, CONVERSION_IDENTICAL,
+ 0);
staticpro (&Vcharset_ucs_bmp);
Vcharset_ucs_bmp =
make_charset (LEADING_BYTE_UCS_BMP, Qucs_bmp, 256, 2,
build_string ("ISO/IEC 10646 Group 0 Plane 0 (BMP)"),
build_string
("\\(ISO10646\\(\\.[0-9]+\\)?-[01]\\|UCS00-0\\|UNICODE[23]?-0\\)"),
- Qnil, 0, 0xFFFF, 0, 0, Qnil, CONVERSION_IDENTICAL);
+ - LEADING_BYTE_UCS_BMP,
+ Qnil, 0, 0xFFFF, 0, 0, Qnil, CONVERSION_IDENTICAL,
+ 0);
staticpro (&Vcharset_ucs_smp);
Vcharset_ucs_smp =
make_charset (LEADING_BYTE_UCS_SMP, Qucs_smp, 256, 2,
build_string ("UCS-SMP"),
build_string ("ISO/IEC 10646 Group 0 Plane 1 (SMP)"),
build_string ("UCS00-1"),
+ 0,
Qnil, MIN_CHAR_SMP, MAX_CHAR_SMP,
- MIN_CHAR_SMP, 0, Qnil, CONVERSION_IDENTICAL);
+ MIN_CHAR_SMP, 0, Qnil, CONVERSION_IDENTICAL,
+ 0);
staticpro (&Vcharset_ucs_sip);
Vcharset_ucs_sip =
make_charset (LEADING_BYTE_UCS_SIP, Qucs_sip, 256, 2,
build_string ("UCS-SIP"),
build_string ("ISO/IEC 10646 Group 0 Plane 2 (SIP)"),
build_string ("\\(ISO10646.*-2\\|UCS00-2\\)"),
+ 0,
Qnil, MIN_CHAR_SIP, MAX_CHAR_SIP,
- MIN_CHAR_SIP, 0, Qnil, CONVERSION_IDENTICAL);
+ MIN_CHAR_SIP, 0, Qnil, CONVERSION_IDENTICAL,
+ 0);
#else
# define MIN_CHAR_THAI 0
# define MAX_CHAR_THAI 0
build_string ("ASCII)"),
build_string ("ASCII (ISO646 IRV)"),
build_string ("\\(iso8859-[0-9]*\\|-ascii\\)"),
- Qnil, 0, 0x7F, 0, 0, Qnil, CONVERSION_IDENTICAL);
+ - LEADING_BYTE_ASCII,
+ Qnil, 0, 0x7F, 0, 0, Qnil, CONVERSION_IDENTICAL,
+ 0);
staticpro (&Vcharset_control_1);
Vcharset_control_1 =
make_charset (LEADING_BYTE_CONTROL_1, Qcontrol_1, 94, 1,
build_string ("Control characters"),
build_string ("Control characters 128-191"),
build_string (""),
- Qnil, 0x80, 0x9F, 0x80, 0, Qnil, CONVERSION_IDENTICAL);
+ - LEADING_BYTE_CONTROL_1,
+ Qnil, 0x80, 0x9F, 0x80, 0, Qnil, CONVERSION_IDENTICAL,
+ 0);
staticpro (&Vcharset_latin_iso8859_1);
Vcharset_latin_iso8859_1 =
make_charset (LEADING_BYTE_LATIN_ISO8859_1, Qlatin_iso8859_1, 96, 1,
build_string ("ISO8859-1 (Latin-1)"),
build_string ("ISO8859-1 (Latin-1)"),
build_string ("iso8859-1"),
- Qnil, 0, 0, 0, 32, Qnil, CONVERSION_IDENTICAL);
+ - LEADING_BYTE_LATIN_ISO8859_1,
+ Qnil, 0, 0, 0, 32, Qnil, CONVERSION_IDENTICAL,
+ 0);
staticpro (&Vcharset_latin_iso8859_2);
Vcharset_latin_iso8859_2 =
make_charset (LEADING_BYTE_LATIN_ISO8859_2, Qlatin_iso8859_2, 96, 1,
build_string ("ISO8859-2 (Latin-2)"),
build_string ("ISO8859-2 (Latin-2)"),
build_string ("iso8859-2"),
- Qnil, 0, 0, 0, 32, Qnil, CONVERSION_IDENTICAL);
+ - LEADING_BYTE_LATIN_ISO8859_2,
+ Qnil, 0, 0, 0, 32, Qnil, CONVERSION_IDENTICAL,
+ 0);
staticpro (&Vcharset_latin_iso8859_3);
Vcharset_latin_iso8859_3 =
make_charset (LEADING_BYTE_LATIN_ISO8859_3, Qlatin_iso8859_3, 96, 1,
build_string ("ISO8859-3 (Latin-3)"),
build_string ("ISO8859-3 (Latin-3)"),
build_string ("iso8859-3"),
- Qnil, 0, 0, 0, 32, Qnil, CONVERSION_IDENTICAL);
+ - LEADING_BYTE_LATIN_ISO8859_3,
+ Qnil, 0, 0, 0, 32, Qnil, CONVERSION_IDENTICAL,
+ 0);
staticpro (&Vcharset_latin_iso8859_4);
Vcharset_latin_iso8859_4 =
make_charset (LEADING_BYTE_LATIN_ISO8859_4, Qlatin_iso8859_4, 96, 1,
build_string ("ISO8859-4 (Latin-4)"),
build_string ("ISO8859-4 (Latin-4)"),
build_string ("iso8859-4"),
- Qnil, 0, 0, 0, 32, Qnil, CONVERSION_IDENTICAL);
+ - LEADING_BYTE_LATIN_ISO8859_4,
+ Qnil, 0, 0, 0, 32, Qnil, CONVERSION_IDENTICAL,
+ 0);
staticpro (&Vcharset_thai_tis620);
Vcharset_thai_tis620 =
make_charset (LEADING_BYTE_THAI_TIS620, Qthai_tis620, 96, 1,
build_string ("TIS620 (Thai)"),
build_string ("TIS620.2529 (Thai)"),
build_string ("tis620"),
- Qnil, 0, 0, 0, 32, Qnil, CONVERSION_IDENTICAL);
+ - LEADING_BYTE_THAI_TIS620,
+ Qnil, 0, 0, 0, 32, Qnil, CONVERSION_IDENTICAL,
+ 0);
staticpro (&Vcharset_greek_iso8859_7);
Vcharset_greek_iso8859_7 =
make_charset (LEADING_BYTE_GREEK_ISO8859_7, Qgreek_iso8859_7, 96, 1,
build_string ("ISO8859-7 (Greek)"),
build_string ("ISO8859-7 (Greek)"),
build_string ("iso8859-7"),
- Qnil, 0, 0, 0, 32, Qnil, CONVERSION_IDENTICAL);
+ - LEADING_BYTE_GREEK_ISO8859_7,
+ Qnil, 0, 0, 0, 32, Qnil, CONVERSION_IDENTICAL,
+ 0);
staticpro (&Vcharset_arabic_iso8859_6);
Vcharset_arabic_iso8859_6 =
make_charset (LEADING_BYTE_ARABIC_ISO8859_6, Qarabic_iso8859_6, 96, 1,
build_string ("ISO8859-6 (Arabic)"),
build_string ("ISO8859-6 (Arabic)"),
build_string ("iso8859-6"),
- Qnil, 0, 0, 0, 32, Qnil, CONVERSION_IDENTICAL);
+ - LEADING_BYTE_ARABIC_ISO8859_6,
+ Qnil, 0, 0, 0, 32, Qnil, CONVERSION_IDENTICAL,
+ 0);
staticpro (&Vcharset_hebrew_iso8859_8);
Vcharset_hebrew_iso8859_8 =
make_charset (LEADING_BYTE_HEBREW_ISO8859_8, Qhebrew_iso8859_8, 96, 1,
build_string ("ISO8859-8 (Hebrew)"),
build_string ("ISO8859-8 (Hebrew)"),
build_string ("iso8859-8"),
+ - LEADING_BYTE_HEBREW_ISO8859_8,
Qnil,
0 /* MIN_CHAR_HEBREW */,
0 /* MAX_CHAR_HEBREW */, 0, 32,
- Qnil, CONVERSION_IDENTICAL);
+ Qnil, CONVERSION_IDENTICAL,
+ 0);
staticpro (&Vcharset_katakana_jisx0201);
Vcharset_katakana_jisx0201 =
make_charset (LEADING_BYTE_KATAKANA_JISX0201, Qkatakana_jisx0201, 94, 1,
build_string ("JISX0201.1976 (Japanese Kana)"),
build_string ("JISX0201.1976 Japanese Kana"),
build_string ("jisx0201\\.1976"),
- Qnil, 0, 0, 0, 33, Qnil, CONVERSION_IDENTICAL);
+ - LEADING_BYTE_KATAKANA_JISX0201,
+ Qnil, 0, 0, 0, 33, Qnil, CONVERSION_IDENTICAL,
+ 0);
staticpro (&Vcharset_latin_jisx0201);
Vcharset_latin_jisx0201 =
make_charset (LEADING_BYTE_LATIN_JISX0201, Qlatin_jisx0201, 94, 1,
build_string ("JISX0201.1976 (Japanese Roman)"),
build_string ("JISX0201.1976 Japanese Roman"),
build_string ("jisx0201\\.1976"),
- Qnil, 0, 0, 0, 33, Qnil, CONVERSION_IDENTICAL);
+ - LEADING_BYTE_LATIN_JISX0201,
+ Qnil, 0, 0, 0, 33, Qnil, CONVERSION_IDENTICAL,
+ 0);
staticpro (&Vcharset_cyrillic_iso8859_5);
Vcharset_cyrillic_iso8859_5 =
make_charset (LEADING_BYTE_CYRILLIC_ISO8859_5, Qcyrillic_iso8859_5, 96, 1,
build_string ("ISO8859-5 (Cyrillic)"),
build_string ("ISO8859-5 (Cyrillic)"),
build_string ("iso8859-5"),
- Qnil, 0, 0, 0, 32, Qnil, CONVERSION_IDENTICAL);
+ - LEADING_BYTE_CYRILLIC_ISO8859_5,
+ Qnil, 0, 0, 0, 32, Qnil, CONVERSION_IDENTICAL,
+ 0);
staticpro (&Vcharset_latin_iso8859_9);
Vcharset_latin_iso8859_9 =
make_charset (LEADING_BYTE_LATIN_ISO8859_9, Qlatin_iso8859_9, 96, 1,
build_string ("ISO8859-9 (Latin-5)"),
build_string ("ISO8859-9 (Latin-5)"),
build_string ("iso8859-9"),
- Qnil, 0, 0, 0, 32, Qnil, CONVERSION_IDENTICAL);
+ - LEADING_BYTE_LATIN_ISO8859_9,
+ Qnil, 0, 0, 0, 32, Qnil, CONVERSION_IDENTICAL,
+ 0);
#ifdef UTF2000
staticpro (&Vcharset_jis_x0208);
Vcharset_jis_x0208 =
make_charset (LEADING_BYTE_JIS_X0208,
- Qmap_jis_x0208, 94, 2,
+ Qrep_jis_x0208, 94, 2,
2, 0, 'B', CHARSET_LEFT_TO_RIGHT,
build_string ("JIS X0208"),
build_string ("JIS X0208 Common"),
build_string ("JIS X0208 Common part"),
- build_string ("jisx0208\\.1990"),
+ build_string ("jisx0208"),
+ - LEADING_BYTE_JAPANESE_JISX0208_1978,
Qnil,
MIN_CHAR_JIS_X0208_1990,
MAX_CHAR_JIS_X0208_1990, MIN_CHAR_JIS_X0208_1990, 33,
- Qnil, CONVERSION_94x94);
+ Qnil, CONVERSION_94x94,
+ 1);
#endif
+#if 0
staticpro (&Vcharset_japanese_jisx0208_1978);
Vcharset_japanese_jisx0208_1978 =
make_charset (LEADING_BYTE_JAPANESE_JISX0208_1978,
- Qmap_jis_x0208_1978, 94, 2,
+ Qrep_jis_x0208_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"),
+ - LEADING_BYTE_JAPANESE_JISX0208_1978,
Qnil, 0, 0, 0, 33,
#ifdef UTF2000
Vcharset_jis_x0208,
#else
Qnil,
#endif
- CONVERSION_IDENTICAL);
+ CONVERSION_IDENTICAL,
+ 0);
+#endif
staticpro (&Vcharset_chinese_gb2312);
Vcharset_chinese_gb2312 =
- make_charset (LEADING_BYTE_CHINESE_GB2312, Qmap_gb2312, 94, 2,
+ make_charset (LEADING_BYTE_CHINESE_GB2312, Qrep_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, Qnil, CONVERSION_IDENTICAL);
+ - LEADING_BYTE_CHINESE_GB2312,
+ Qnil, 0, 0, 0, 33, Qnil, CONVERSION_IDENTICAL,
+ 0);
staticpro (&Vcharset_chinese_gb12345);
Vcharset_chinese_gb12345 =
- make_charset (LEADING_BYTE_CHINESE_GB12345, Qmap_gb12345, 94, 2,
+ make_charset (LEADING_BYTE_CHINESE_GB12345, Qrep_gb12345, 94, 2,
2, 0, 0, CHARSET_LEFT_TO_RIGHT,
build_string ("G1"),
build_string ("GB 12345)"),
build_string ("GB 12345-1990"),
build_string ("GB12345\\(\\.1990\\)?-0"),
- Qnil, 0, 0, 0, 33, Qnil, CONVERSION_IDENTICAL);
+ 0,
+ Qnil, 0, 0, 0, 33, Qnil, CONVERSION_IDENTICAL,
+ 0);
staticpro (&Vcharset_japanese_jisx0208);
Vcharset_japanese_jisx0208 =
- make_charset (LEADING_BYTE_JAPANESE_JISX0208, Qmap_jis_x0208_1983, 94, 2,
+ make_charset (LEADING_BYTE_JAPANESE_JISX0208, Qrep_jis_x0208_1983, 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"),
+ - LEADING_BYTE_JAPANESE_JISX0208,
Qnil, 0, 0, 0, 33,
#ifdef UTF2000
Vcharset_jis_x0208,
#else
Qnil,
#endif
- CONVERSION_IDENTICAL);
+ CONVERSION_IDENTICAL,
+ 0);
#ifdef UTF2000
staticpro (&Vcharset_japanese_jisx0208_1990);
Vcharset_japanese_jisx0208_1990 =
make_charset (LEADING_BYTE_JAPANESE_JISX0208_1990,
- Qmap_jis_x0208_1990, 94, 2,
+ Qrep_jis_x0208_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"),
+ - LEADING_BYTE_JAPANESE_JISX0208_1990,
Qnil,
0x2121 /* MIN_CHAR_JIS_X0208_1990 */,
0x7426 /* MAX_CHAR_JIS_X0208_1990 */,
0 /* MIN_CHAR_JIS_X0208_1990 */, 33,
Vcharset_jis_x0208 /* Qnil */,
- CONVERSION_IDENTICAL /* CONVERSION_94x94 */);
+ CONVERSION_IDENTICAL /* CONVERSION_94x94 */,
+ 0);
#endif
staticpro (&Vcharset_korean_ksc5601);
Vcharset_korean_ksc5601 =
- make_charset (LEADING_BYTE_KOREAN_KSC5601, Qmap_ks_x1001, 94, 2,
+ make_charset (LEADING_BYTE_KOREAN_KSC5601, Qrep_ks_x1001, 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, Qnil, CONVERSION_IDENTICAL);
+ - LEADING_BYTE_KOREAN_KSC5601,
+ Qnil, 0, 0, 0, 33, Qnil, CONVERSION_IDENTICAL,
+ 0);
staticpro (&Vcharset_japanese_jisx0212);
Vcharset_japanese_jisx0212 =
- make_charset (LEADING_BYTE_JAPANESE_JISX0212, Qmap_jis_x0212, 94, 2,
+ make_charset (LEADING_BYTE_JAPANESE_JISX0212, Qrep_jis_x0212, 94, 2,
2, 0, 'D', CHARSET_LEFT_TO_RIGHT,
build_string ("JISX0212"),
build_string ("JISX0212 (Japanese)"),
build_string ("JISX0212 Japanese Supplement"),
build_string ("jisx0212"),
- Qnil, 0, 0, 0, 33, Qnil, CONVERSION_IDENTICAL);
+ - LEADING_BYTE_JAPANESE_JISX0212,
+ Qnil, 0, 0, 0, 33, Qnil, CONVERSION_IDENTICAL,
+ 0);
#define CHINESE_CNS_PLANE_RE(n) "cns11643[.-]\\(.*[.-]\\)?" n "$"
staticpro (&Vcharset_chinese_cns11643_1);
Vcharset_chinese_cns11643_1 =
- make_charset (LEADING_BYTE_CHINESE_CNS11643_1, Qmap_cns11643_1, 94, 2,
+ make_charset (LEADING_BYTE_CHINESE_CNS11643_1, Qrep_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, Qnil, CONVERSION_IDENTICAL);
+ - LEADING_BYTE_CHINESE_CNS11643_1,
+ Qnil, 0, 0, 0, 33, Qnil, CONVERSION_IDENTICAL,
+ 0);
staticpro (&Vcharset_chinese_cns11643_2);
Vcharset_chinese_cns11643_2 =
- make_charset (LEADING_BYTE_CHINESE_CNS11643_2, Qmap_cns11643_2, 94, 2,
+ make_charset (LEADING_BYTE_CHINESE_CNS11643_2, Qrep_cns11643_2, 94, 2,
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")),
- Qnil, 0, 0, 0, 33, Qnil, CONVERSION_IDENTICAL);
+ - LEADING_BYTE_CHINESE_CNS11643_2,
+ Qnil, 0, 0, 0, 33, Qnil, CONVERSION_IDENTICAL,
+ 0);
#ifdef UTF2000
staticpro (&Vcharset_latin_tcvn5712);
Vcharset_latin_tcvn5712 =
build_string ("TCVN 5712 (VSCII-2)"),
build_string ("Vietnamese TCVN 5712:1983 (VSCII-2)"),
build_string ("tcvn5712\\(\\.1993\\)?-1"),
- Qnil, 0, 0, 0, 32, Qnil, CONVERSION_IDENTICAL);
+ - LEADING_BYTE_LATIN_TCVN5712,
+ Qnil, 0, 0, 0, 32, Qnil, CONVERSION_IDENTICAL,
+ 0);
staticpro (&Vcharset_latin_viscii_lower);
Vcharset_latin_viscii_lower =
make_charset (LEADING_BYTE_LATIN_VISCII_LOWER, Qlatin_viscii_lower, 96, 1,
build_string ("VISCII lower (Vietnamese)"),
build_string ("VISCII lower (Vietnamese)"),
build_string ("MULEVISCII-LOWER"),
- Qnil, 0, 0, 0, 32, Qnil, CONVERSION_IDENTICAL);
+ 0,
+ Qnil, 0, 0, 0, 32, Qnil, CONVERSION_IDENTICAL,
+ 0);
staticpro (&Vcharset_latin_viscii_upper);
Vcharset_latin_viscii_upper =
make_charset (LEADING_BYTE_LATIN_VISCII_UPPER, Qlatin_viscii_upper, 96, 1,
build_string ("VISCII upper (Vietnamese)"),
build_string ("VISCII upper (Vietnamese)"),
build_string ("MULEVISCII-UPPER"),
- Qnil, 0, 0, 0, 32, Qnil, CONVERSION_IDENTICAL);
+ 0,
+ Qnil, 0, 0, 0, 32, Qnil, CONVERSION_IDENTICAL,
+ 0);
staticpro (&Vcharset_latin_viscii);
Vcharset_latin_viscii =
make_charset (LEADING_BYTE_LATIN_VISCII, Qlatin_viscii, 256, 1,
build_string ("VISCII 1.1 (Vietnamese)"),
build_string ("VISCII 1.1 (Vietnamese)"),
build_string ("VISCII1\\.1"),
- Qnil, 0, 0, 0, 0, Qnil, CONVERSION_IDENTICAL);
+ 0,
+ Qnil, 0, 0, 0, 0, Qnil, CONVERSION_IDENTICAL,
+ 0);
staticpro (&Vcharset_chinese_big5);
Vcharset_chinese_big5 =
- make_charset (LEADING_BYTE_CHINESE_BIG5, Qmap_big5, 256, 2,
+ make_charset (LEADING_BYTE_CHINESE_BIG5, Qrep_big5, 256, 2,
2, 2, 0, CHARSET_LEFT_TO_RIGHT,
build_string ("Big5"),
build_string ("Big5"),
build_string ("Big5 Chinese traditional"),
build_string ("big5-0"),
+ 0,
Qnil,
MIN_CHAR_BIG5_CDP, MAX_CHAR_BIG5_CDP,
- MIN_CHAR_BIG5_CDP, 0, Qnil, CONVERSION_IDENTICAL);
+ MIN_CHAR_BIG5_CDP, 0, Qnil, CONVERSION_IDENTICAL,
+ 0);
staticpro (&Vcharset_ethiopic_ucs);
Vcharset_ethiopic_ucs =
build_string ("Ethiopic (UCS)"),
build_string ("Ethiopic of UCS"),
build_string ("Ethiopic-Unicode"),
+ 0,
Qnil, 0x1200, 0x137F, 0, 0,
- Qnil, CONVERSION_IDENTICAL);
+ Qnil, CONVERSION_IDENTICAL,
+ 0);
#endif
staticpro (&Vcharset_chinese_big5_1);
Vcharset_chinese_big5_1 =
build_string
("Big5 Level-1 Chinese traditional"),
build_string ("big5"),
+ 0,
Qnil, 0, 0, 0, 33, /* Qnil, CONVERSION_IDENTICAL */
- Vcharset_chinese_big5, CONVERSION_BIG5_1);
+ Vcharset_chinese_big5, CONVERSION_BIG5_1,
+ 0);
staticpro (&Vcharset_chinese_big5_2);
Vcharset_chinese_big5_2 =
make_charset (LEADING_BYTE_CHINESE_BIG5_2, Qchinese_big5_2, 94, 2,
build_string
("Big5 Level-2 Chinese traditional"),
build_string ("big5"),
+ 0,
Qnil, 0, 0, 0, 33, /* Qnil, CONVERSION_IDENTICAL */
- Vcharset_chinese_big5, CONVERSION_BIG5_2);
+ Vcharset_chinese_big5, CONVERSION_BIG5_2,
+ 0);
#ifdef ENABLE_COMPOSITE_CHARS
/* #### For simplicity, we put composite chars into a 96x96 charset.