#define LEADING_BYTE_UCS_BMP 0x80
#define LEADING_BYTE_CONTROL_1 0x81 /* represent normal 80-9F */
+#define LEADING_BYTE_HIRAGANA_JISX0208 0x82
+#define LEADING_BYTE_KATAKANA_JISX0208 0x83
#define CHARSET_ID_OFFSET_94 0x55
/* Which half of font to be used to display this character set */
unsigned int graphic;
- /* byte->character mapping table */
- Emchar* decoding_table;
+ /* Byte->character mapping table */
+ Lisp_Object decoding_table;
- /* character->byte mapping table */
+ /* Character->byte mapping table */
Emchar_to_byte_table* to_byte1_table;
Emchar_to_byte_table* to_byte2_table;
+
+ /* Range of character code */
+ Emchar ucs_min, ucs_max;
+
+ /* Offset for external code */
+ Emchar code_offset;
+
+ /* Offset for each byte */
+ Emchar byte_offset;
};
DECLARE_LRECORD (charset, struct Lisp_Charset);
#define CHARSET_DECODING_TABLE(cs) ((cs)->decoding_table)
#define CHARSET_TO_BYTE1_TABLE(cs) ((cs)->to_byte1_table)
#define CHARSET_TO_BYTE2_TABLE(cs) ((cs)->to_byte2_table)
+#define CHARSET_UCS_MIN(cs) ((cs)->ucs_min)
+#define CHARSET_UCS_MAX(cs) ((cs)->ucs_max)
+#define CHARSET_CODE_OFFSET(cs) ((cs)->code_offset)
+#define CHARSET_BYTE_OFFSET(cs) ((cs)->byte_offset)
#define XCHARSET_ID(cs) CHARSET_ID (XCHARSET (cs))
#define XCHARSET_DECODING_TABLE(cs) CHARSET_DECODING_TABLE(XCHARSET(cs))
#define XCHARSET_TO_BYTE1_TABLE(cs) CHARSET_TO_BYTE1_TABLE(XCHARSET(cs))
#define XCHARSET_TO_BYTE2_TABLE(cs) CHARSET_TO_BYTE2_TABLE(XCHARSET(cs))
+#define XCHARSET_UCS_MIN(cs) CHARSET_UCS_MIN(XCHARSET(cs))
+#define XCHARSET_UCS_MAX(cs) CHARSET_UCS_MAX(XCHARSET(cs))
+#define XCHARSET_CODE_OFFSET(cs) CHARSET_CODE_OFFSET(XCHARSET(cs))
+#define XCHARSET_BYTE_OFFSET(cs) CHARSET_BYTE_OFFSET(XCHARSET(cs))
/* Table of charsets indexed by (leading byte - 128). */
extern Lisp_Object charset_by_leading_byte[NUM_LEADING_BYTES];
#define MIN_CHAR_THAI 0x0E00
#define MAX_CHAR_THAI 0x0E5F
-#define MIN_CHAR_HALFWIDTH_KATAKANA 0xFF60
+#define MIN_CHAR_HIRAGANA 0x3041
+#define MAX_CHAR_HIRAGANA 0x3093
+
+#define MIN_CHAR_KATAKANA 0x30A1
+#define MAX_CHAR_KATAKANA 0x30F6
+
+#define MIN_CHAR_HALFWIDTH_KATAKANA 0xFF61
#define MAX_CHAR_HALFWIDTH_KATAKANA 0xFF9F
#define MIN_CHAR_94 0xE90940
INLINE Emchar
MAKE_CHAR (Lisp_Object charset, int c1, int c2)
{
- Emchar* decoding_table;
-
- if ((decoding_table = XCHARSET_DECODING_TABLE (charset)) != NULL)
- return decoding_table[c1 - (XCHARSET_CHARS (charset) == 94 ? 33 : 32)];
- else if (EQ (charset, Vcharset_ascii))
- return c1;
- else if (EQ (charset, Vcharset_control_1))
- return c1 | 0x80;
- else if (EQ (charset, Vcharset_ucs_bmp))
- return (c1 << 8) | c2;
- else if (EQ (charset, Vcharset_latin_iso8859_1))
- return c1 | 0x80;
- else if (EQ (charset, Vcharset_cyrillic_iso8859_5))
- return c1 + MIN_CHAR_CYRILLIC - 0x20;
- else if (EQ (charset, Vcharset_greek_iso8859_7))
- return c1 + MIN_CHAR_GREEK - 0x20;
- else if (EQ (charset, Vcharset_hebrew_iso8859_8))
- return c1 + MIN_CHAR_HEBREW - 0x20;
- else if (EQ (charset, Vcharset_thai_tis620))
- return c1 + MIN_CHAR_THAI - 0x20;
+ Lisp_Object decoding_table = XCHARSET_DECODING_TABLE (charset);
+ int idx;
+ Lisp_Object ch;
+
+ if (!EQ (decoding_table, Qnil)
+ && (0 <= (idx = c1 - (XCHARSET_CHARS (charset) == 94 ? 33 : 32)))
+ && (idx < XVECTOR_LENGTH (decoding_table))
+ && !EQ (ch = XVECTOR_DATA(decoding_table)[idx], Qnil))
+ return XCHAR (ch);
else if (EQ (charset, Vcharset_katakana_jisx0201))
if (c1 < 0x60)
- return c1 + MIN_CHAR_HALFWIDTH_KATAKANA - 0x20;
+ return c1 + MIN_CHAR_HALFWIDTH_KATAKANA - 33;
else
/* return MIN_CHAR_94 + ('I' - '0') * 94 + (c1 - 33); */
return ' ';
+ else 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))
}
}
-extern Charset_ID latin_a_char_to_charset[128];
-extern unsigned char latin_a_char_to_byte1[128];
-extern unsigned char latin_a_char_to_byte2[128];
-
unsigned char charset_get_byte1 (Lisp_Object charset, Emchar ch);
unsigned char charset_get_byte2 (Lisp_Object charset, Emchar ch);
-extern Lisp_Object Vdefault_preferred_coded_charset_list;
+extern Lisp_Object Vdefault_coded_charset_priority_list;
EXFUN (Ffind_charset, 1);
INLINE void breakup_char_1 (Emchar c, Lisp_Object *charset, int *c1, int *c2);
INLINE void
breakup_char_1 (Emchar c, Lisp_Object *charset, int *c1, int *c2)
{
- if (c < 0x100)
+ if (c < MIN_CHAR_94)
{
- Lisp_Object charsets = Vdefault_preferred_coded_charset_list;
+ Lisp_Object charsets = Vdefault_coded_charset_priority_list;
while (!EQ (charsets, Qnil))
{
*charset = Ffind_charset (Fcar (charsets));
}
charsets = Fcdr (charsets);
}
- /* otherwise */
+ /* otherwise --- maybe for bootstrap */
if (c <= MAX_CHAR_BASIC_LATIN)
{
*charset = Vcharset_ascii;
*c1 = charset_get_byte1 (*charset, c);
*c2 = charset_get_byte2 (*charset, c);
}
- else
+ else if ((MIN_CHAR_GREEK <= c) && (c <= MAX_CHAR_GREEK))
{
- *charset = Vcharset_ucs_bmp;
- *c1 = c >> 8;
- *c2 = c & 0xff;
+ *charset = Vcharset_greek_iso8859_7;
+ *c1 = c - MIN_CHAR_GREEK + 0x20;
+ *c2 = 0;
}
- }
- else if (c <= 0x17f)
- {
- *charset
- = CHARSET_BY_LEADING_BYTE (latin_a_char_to_charset[c - 0x100]);
- if (XCHARSET_TO_BYTE1_TABLE (*charset) != NULL)
+ else if ((MIN_CHAR_CYRILLIC <= c) && (c <= MAX_CHAR_CYRILLIC))
{
- *c1 = charset_get_byte1 (*charset, c);
- *c2 = charset_get_byte2 (*charset, c);
+ *charset = Vcharset_cyrillic_iso8859_5;
+ *c1 = c - MIN_CHAR_CYRILLIC + 0x20;
+ *c2 = 0;
}
- else
+ else if ((MIN_CHAR_HEBREW <= c) && (c <= MAX_CHAR_HEBREW))
{
- *c1 = latin_a_char_to_byte1[c - 0x100];
- *c2 = latin_a_char_to_byte2[c - 0x100];
+ *charset = Vcharset_hebrew_iso8859_8;
+ *c1 = c - MIN_CHAR_HEBREW + 0x20;
+ *c2 = 0;
}
- }
- else if (c < MIN_CHAR_GREEK)
- {
- Lisp_Object charsets = Vdefault_preferred_coded_charset_list;
- while (!EQ (charsets, Qnil))
+ else if ((MIN_CHAR_THAI <= c) && (c <= MAX_CHAR_THAI))
{
- *charset = Ffind_charset (Fcar (charsets));
- if (!EQ (*charset, Qnil)
- && (*c1 = charset_get_byte1 (*charset, c)) )
- {
- *c2 = charset_get_byte2 (*charset, c);
- return;
- }
- charsets = Fcdr (charsets);
+ *charset = Vcharset_thai_tis620;
+ *c1 = c - MIN_CHAR_THAI + 0x20;
+ *c2 = 0;
}
- /* otherwise */
- *charset = Vcharset_ucs_bmp;
- *c1 = c >> 8;
- *c2 = c & 0xff;
- }
- else if (c <= MAX_CHAR_GREEK)
- {
- *charset = Vcharset_greek_iso8859_7;
- *c1 = c - MIN_CHAR_GREEK + 0x20;
- *c2 = 0;
- }
- else if (c < MIN_CHAR_CYRILLIC)
- {
- *charset = Vcharset_ucs_bmp;
- *c1 = c >> 8;
- *c2 = c & 0xff;
- }
- else if (c <= MAX_CHAR_CYRILLIC)
- {
- *charset = Vcharset_cyrillic_iso8859_5;
- *c1 = c - MIN_CHAR_CYRILLIC + 0x20;
- *c2 = 0;
- }
- else if (c < MIN_CHAR_HEBREW)
- {
- *charset = Vcharset_ucs_bmp;
- *c1 = c >> 8;
- *c2 = c & 0xff;
- }
- else if (c <= MAX_CHAR_HEBREW)
- {
- *charset = Vcharset_hebrew_iso8859_8;
- *c1 = c - MIN_CHAR_HEBREW + 0x20;
- *c2 = 0;
- }
- else if (c < MIN_CHAR_THAI)
- {
- *charset = Vcharset_ucs_bmp;
- *c1 = c >> 8;
- *c2 = c & 0xff;
- }
- else if (c <= MAX_CHAR_THAI)
- {
- *charset = Vcharset_thai_tis620;
- *c1 = c - MIN_CHAR_THAI + 0x20;
- *c2 = 0;
- }
- else if (c < MIN_CHAR_HALFWIDTH_KATAKANA)
- {
- Lisp_Object charsets = Vdefault_preferred_coded_charset_list;
- while (!EQ (charsets, Qnil))
+ else if ((MIN_CHAR_HALFWIDTH_KATAKANA <= c)
+ && (c <= MAX_CHAR_HALFWIDTH_KATAKANA))
{
- *charset = Ffind_charset (Fcar (charsets));
- if (!EQ (*charset, Qnil)
- && (*c1 = charset_get_byte1 (*charset, c)) )
- {
- *c2 = charset_get_byte2 (*charset, c);
- return;
- }
- charsets = Fcdr (charsets);
+ *charset = Vcharset_katakana_jisx0201;
+ *c1 = c - MIN_CHAR_HALFWIDTH_KATAKANA + 33;
+ *c2 = 0;
+ }
+ else
+ {
+ *charset = Vcharset_ucs_bmp;
+ *c1 = c >> 8;
+ *c2 = c & 0xff;
}
- /* otherwise */
- *charset = Vcharset_ucs_bmp;
- *c1 = c >> 8;
- *c2 = c & 0xff;
- }
- else if (c <= MAX_CHAR_HALFWIDTH_KATAKANA)
- {
- *charset = Vcharset_katakana_jisx0201;
- *c1 = c - MIN_CHAR_HALFWIDTH_KATAKANA + 0x20;
- *c2 = 0;
}
else if (c <= MAX_CHAR_94)
{
projects / chise / xemacs-chise.git / blobdiff