/* Functions to handle multilingual characters.
Copyright (C) 1992, 1995 Free Software Foundation, Inc.
Copyright (C) 1995 Sun Microsystems, Inc.
- Copyright (C) 1999,2000,2001,2002,2003,2004,2008 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;
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;
Qlatin_jisx0201,
Qcyrillic_iso8859_5,
Qlatin_iso8859_9,
- Qrep_jis_x0208_1978,
+/* Qrep_jis_x0208_1978, */
Qrep_gb2312,
Qrep_gb12345,
Qrep_jis_x0208_1983,
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,
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;
}
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 )
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.
(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;
{
#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);
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, partial);
if (!NILP (ccl_program))
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),
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 (&Qlatin_jisx0201, "latin-jisx0201");
defsymbol (&Qcyrillic_iso8859_5, "cyrillic-iso8859-5");
defsymbol (&Qlatin_iso8859_9, "latin-iso8859-9");
- defsymbol (&Qrep_jis_x0208_1978, "=jis-x0208@1978");
+ /* defsymbol (&Qrep_jis_x0208_1978, "=jis-x0208@1978"); */
defsymbol (&Qrep_gb2312, "=gb2312");
defsymbol (&Qrep_gb12345, "=gb12345");
defsymbol (&Qrep_jis_x0208_1983, "=jis-x0208@1983");
build_string ("CHAR-ID"),
build_string ("System char-id"),
build_string (""),
+ 0,
Qnil, 0, 0x7FFFFFFF, 0, 0, Qnil, CONVERSION_IDENTICAL,
0);
staticpro (&Vcharset_ucs);
build_string ("UCS"),
build_string ("ISO/IEC 10646"),
build_string (""),
+ - LEADING_BYTE_UCS,
Qnil, 0, 0xEFFFF, 0, 0, Qnil, CONVERSION_IDENTICAL,
0);
staticpro (&Vcharset_ucs_bmp);
build_string ("ISO/IEC 10646 Group 0 Plane 0 (BMP)"),
build_string
("\\(ISO10646\\(\\.[0-9]+\\)?-[01]\\|UCS00-0\\|UNICODE[23]?-0\\)"),
+ - LEADING_BYTE_UCS_BMP,
Qnil, 0, 0xFFFF, 0, 0, Qnil, CONVERSION_IDENTICAL,
0);
staticpro (&Vcharset_ucs_smp);
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,
0);
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,
0);
build_string ("ASCII)"),
build_string ("ASCII (ISO646 IRV)"),
build_string ("\\(iso8859-[0-9]*\\|-ascii\\)"),
+ - LEADING_BYTE_ASCII,
Qnil, 0, 0x7F, 0, 0, Qnil, CONVERSION_IDENTICAL,
0);
staticpro (&Vcharset_control_1);
build_string ("Control characters"),
build_string ("Control characters 128-191"),
build_string (""),
+ - LEADING_BYTE_CONTROL_1,
Qnil, 0x80, 0x9F, 0x80, 0, Qnil, CONVERSION_IDENTICAL,
0);
staticpro (&Vcharset_latin_iso8859_1);
build_string ("ISO8859-1 (Latin-1)"),
build_string ("ISO8859-1 (Latin-1)"),
build_string ("iso8859-1"),
+ - LEADING_BYTE_LATIN_ISO8859_1,
Qnil, 0, 0, 0, 32, Qnil, CONVERSION_IDENTICAL,
0);
staticpro (&Vcharset_latin_iso8859_2);
build_string ("ISO8859-2 (Latin-2)"),
build_string ("ISO8859-2 (Latin-2)"),
build_string ("iso8859-2"),
+ - LEADING_BYTE_LATIN_ISO8859_2,
Qnil, 0, 0, 0, 32, Qnil, CONVERSION_IDENTICAL,
0);
staticpro (&Vcharset_latin_iso8859_3);
build_string ("ISO8859-3 (Latin-3)"),
build_string ("ISO8859-3 (Latin-3)"),
build_string ("iso8859-3"),
+ - LEADING_BYTE_LATIN_ISO8859_3,
Qnil, 0, 0, 0, 32, Qnil, CONVERSION_IDENTICAL,
0);
staticpro (&Vcharset_latin_iso8859_4);
build_string ("ISO8859-4 (Latin-4)"),
build_string ("ISO8859-4 (Latin-4)"),
build_string ("iso8859-4"),
+ - LEADING_BYTE_LATIN_ISO8859_4,
Qnil, 0, 0, 0, 32, Qnil, CONVERSION_IDENTICAL,
0);
staticpro (&Vcharset_thai_tis620);
build_string ("TIS620 (Thai)"),
build_string ("TIS620.2529 (Thai)"),
build_string ("tis620"),
+ - LEADING_BYTE_THAI_TIS620,
Qnil, 0, 0, 0, 32, Qnil, CONVERSION_IDENTICAL,
0);
staticpro (&Vcharset_greek_iso8859_7);
build_string ("ISO8859-7 (Greek)"),
build_string ("ISO8859-7 (Greek)"),
build_string ("iso8859-7"),
+ - LEADING_BYTE_GREEK_ISO8859_7,
Qnil, 0, 0, 0, 32, Qnil, CONVERSION_IDENTICAL,
0);
staticpro (&Vcharset_arabic_iso8859_6);
build_string ("ISO8859-6 (Arabic)"),
build_string ("ISO8859-6 (Arabic)"),
build_string ("iso8859-6"),
+ - LEADING_BYTE_ARABIC_ISO8859_6,
Qnil, 0, 0, 0, 32, Qnil, CONVERSION_IDENTICAL,
0);
staticpro (&Vcharset_hebrew_iso8859_8);
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,
build_string ("JISX0201.1976 (Japanese Kana)"),
build_string ("JISX0201.1976 Japanese Kana"),
build_string ("jisx0201\\.1976"),
+ - LEADING_BYTE_KATAKANA_JISX0201,
Qnil, 0, 0, 0, 33, Qnil, CONVERSION_IDENTICAL,
0);
staticpro (&Vcharset_latin_jisx0201);
build_string ("JISX0201.1976 (Japanese Roman)"),
build_string ("JISX0201.1976 Japanese Roman"),
build_string ("jisx0201\\.1976"),
+ - LEADING_BYTE_LATIN_JISX0201,
Qnil, 0, 0, 0, 33, Qnil, CONVERSION_IDENTICAL,
0);
staticpro (&Vcharset_cyrillic_iso8859_5);
build_string ("ISO8859-5 (Cyrillic)"),
build_string ("ISO8859-5 (Cyrillic)"),
build_string ("iso8859-5"),
+ - LEADING_BYTE_CYRILLIC_ISO8859_5,
Qnil, 0, 0, 0, 32, Qnil, CONVERSION_IDENTICAL,
0);
staticpro (&Vcharset_latin_iso8859_9);
build_string ("ISO8859-9 (Latin-5)"),
build_string ("ISO8859-9 (Latin-5)"),
build_string ("iso8859-9"),
+ - LEADING_BYTE_LATIN_ISO8859_9,
Qnil, 0, 0, 0, 32, Qnil, CONVERSION_IDENTICAL,
0);
#ifdef UTF2000
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,
1);
#endif
+#if 0
staticpro (&Vcharset_japanese_jisx0208_1978);
Vcharset_japanese_jisx0208_1978 =
make_charset (LEADING_BYTE_JAPANESE_JISX0208_1978,
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,
#endif
CONVERSION_IDENTICAL,
0);
+#endif
staticpro (&Vcharset_chinese_gb2312);
Vcharset_chinese_gb2312 =
make_charset (LEADING_BYTE_CHINESE_GB2312, Qrep_gb2312, 94, 2,
build_string ("GB2312)"),
build_string ("GB2312 Chinese simplified"),
build_string ("gb2312"),
+ - LEADING_BYTE_CHINESE_GB2312,
Qnil, 0, 0, 0, 33, Qnil, CONVERSION_IDENTICAL,
0);
staticpro (&Vcharset_chinese_gb12345);
build_string ("GB 12345)"),
build_string ("GB 12345-1990"),
build_string ("GB12345\\(\\.1990\\)?-0"),
+ 0,
Qnil, 0, 0, 0, 33, Qnil, CONVERSION_IDENTICAL,
0);
staticpro (&Vcharset_japanese_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,
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 */,
build_string ("KSC5601 (Korean"),
build_string ("KSC5601 Korean Hangul and Hanja"),
build_string ("ksc5601"),
+ - LEADING_BYTE_KOREAN_KSC5601,
Qnil, 0, 0, 0, 33, Qnil, CONVERSION_IDENTICAL,
0);
staticpro (&Vcharset_japanese_jisx0212);
build_string ("JISX0212 (Japanese)"),
build_string ("JISX0212 Japanese Supplement"),
build_string ("jisx0212"),
+ - LEADING_BYTE_JAPANESE_JISX0212,
Qnil, 0, 0, 0, 33, Qnil, CONVERSION_IDENTICAL,
0);
build_string
("CNS 11643 Plane 1 Chinese traditional"),
build_string (CHINESE_CNS_PLANE_RE("1")),
+ - LEADING_BYTE_CHINESE_CNS11643_1,
Qnil, 0, 0, 0, 33, Qnil, CONVERSION_IDENTICAL,
0);
staticpro (&Vcharset_chinese_cns11643_2);
build_string
("CNS 11643 Plane 2 Chinese traditional"),
build_string (CHINESE_CNS_PLANE_RE("2")),
+ - LEADING_BYTE_CHINESE_CNS11643_2,
Qnil, 0, 0, 0, 33, Qnil, CONVERSION_IDENTICAL,
0);
#ifdef UTF2000
build_string ("TCVN 5712 (VSCII-2)"),
build_string ("Vietnamese TCVN 5712:1983 (VSCII-2)"),
build_string ("tcvn5712\\(\\.1993\\)?-1"),
+ - LEADING_BYTE_LATIN_TCVN5712,
Qnil, 0, 0, 0, 32, Qnil, CONVERSION_IDENTICAL,
0);
staticpro (&Vcharset_latin_viscii_lower);
build_string ("VISCII lower (Vietnamese)"),
build_string ("VISCII lower (Vietnamese)"),
build_string ("MULEVISCII-LOWER"),
+ 0,
Qnil, 0, 0, 0, 32, Qnil, CONVERSION_IDENTICAL,
0);
staticpro (&Vcharset_latin_viscii_upper);
build_string ("VISCII upper (Vietnamese)"),
build_string ("VISCII upper (Vietnamese)"),
build_string ("MULEVISCII-UPPER"),
+ 0,
Qnil, 0, 0, 0, 32, Qnil, CONVERSION_IDENTICAL,
0);
staticpro (&Vcharset_latin_viscii);
build_string ("VISCII 1.1 (Vietnamese)"),
build_string ("VISCII 1.1 (Vietnamese)"),
build_string ("VISCII1\\.1"),
+ 0,
Qnil, 0, 0, 0, 0, Qnil, CONVERSION_IDENTICAL,
0);
staticpro (&Vcharset_chinese_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,
build_string ("Ethiopic (UCS)"),
build_string ("Ethiopic of UCS"),
build_string ("Ethiopic-Unicode"),
+ 0,
Qnil, 0x1200, 0x137F, 0, 0,
Qnil, CONVERSION_IDENTICAL,
0);
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,
0);
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,
0);
projects / chise / xemacs-chise.git.1 / blobdiff