update.

[chise/xemacs-chise.git] / src / char-ucs.h

diff --git a/src/char-ucs.h b/src/char-ucs.h
index 6c51a89..d51083c 100644 (file)
--- a/src/char-ucs.h
+++ b/src/char-ucs.h
@@ -45,6 +45,23 @@ struct Lisp_Char_Byte_Table
   Lisp_Object property[256];
 };
 
+
+DECLARE_LRECORD (char_code_table, struct Lisp_Char_Code_Table);
+#define XCHAR_CODE_TABLE(x) \
+  XRECORD (x, char_code_table, struct Lisp_Char_Code_Table)
+#define XSETCHAR_CODE_TABLE(x, p) XSETRECORD (x, p, char_code_table)
+#define CHAR_CODE_TABLE_P(x) RECORDP (x, char_code_table)
+#define GC_CHAR_CODE_TABLE_P(x) GC_RECORDP (x, char_code_table)
+/* #define CHECK_CHAR_CODE_TABLE(x) CHECK_RECORD (x, char_code_table)
+   char table entries should never escape to Lisp */
+
+struct Lisp_Char_Code_Table
+{
+  struct lcrecord_header header;
+
+  Lisp_Object table;
+};
+
 Lisp_Object get_char_code_table (Emchar ch, Lisp_Object table);
 
 
@@ -88,11 +105,15 @@ typedef int Charset_ID;
 /* Big5 Level 2                        2/4 2/{(8),9,10,11} 4/0 '1' */
 #define LEADING_BYTE_CHINESE_BIG5_2    (CHARSET_ID_OFFSET - 7)
 
-#define LEADING_BYTE_HIRAGANA_JISX0208 (CHARSET_ID_OFFSET - 8)
-#define LEADING_BYTE_KATAKANA_JISX0208 (CHARSET_ID_OFFSET - 9)
+#define LEADING_BYTE_ETHIOPIC_UCS      (CHARSET_ID_OFFSET - 8)
+
+#define LEADING_BYTE_DAIKANWA          (CHARSET_ID_OFFSET - 9)
+
+/* Japanese JIS X0208-1990     2/4 2/{(8),9,10,11} 4/2 (B) */
+#define LEADING_BYTE_JAPANESE_JISX0208_1990 (CHARSET_ID_OFFSET - 10)
 
 #define MIN_LEADING_BYTE_PRIVATE       MIN_LEADING_BYTE
-#define MAX_LEADING_BYTE_PRIVATE       (CHARSET_ID_OFFSET - 10)
+#define MAX_LEADING_BYTE_PRIVATE       (CHARSET_ID_OFFSET - 11)
 
 
 /* #define CHARSET_ID_OFFSET_94                (CHARSET_ID_OFFSET - '0') */
@@ -370,7 +391,12 @@ CHARSET_BY_LEADING_BYTE (Charset_ID lb)
 #define MAX_CHAR_HALFWIDTH_KATAKANA    0xFF9F
 
 #define MIN_CHAR_OBS_94x94     0xE00000
-#define MAX_CHAR_OBS_94x94     (0xE00000 + 94 * 94 * 14 - 1)
+#define MIN_CHAR_JIS_X0208_1990        0xE04508
+#define MAX_CHAR_JIS_X0208_1990        0XE0678B
+#define MAX_CHAR_OBS_94x94     0XE1E337
+
+#define MIN_CHAR_DAIKANWA      0xE50000
+#define MAX_CHAR_DAIKANWA      0xE5FFFF
 
 #define MIN_CHAR_94            0xE90940
 #define MAX_CHAR_94            (MIN_CHAR_94 + 94 * 80 - 1)
@@ -465,6 +491,7 @@ MAKE_CHAR (Lisp_Object charset, int c1, int c2)
 
 extern Lisp_Object Vcharacter_attribute_table;
 
+Lisp_Object split_builtin_char (Emchar c);
 Lisp_Object range_charset_code_point (Lisp_Object charset, Emchar ch);
 Lisp_Object charset_code_point (Lisp_Object charset, Emchar ch);
 
@@ -488,8 +515,9 @@ SPLIT_CHAR (Emchar c)
 
          if (!EQ (charset, Qnil))
            {
-             if (!EQ (field = Fcdr (Fassq (charset, cdef)), Qnil) ||
-                 !EQ (field = range_charset_code_point (charset, c), Qnil))
+             if (!NILP (field = Fassq (charset, cdef)))
+               return field;
+             else if (!NILP (field = range_charset_code_point (charset, c)))
                return Fcons (charset, field);
            }
          charsets = Fcdr (charsets);         
@@ -497,97 +525,7 @@ SPLIT_CHAR (Emchar c)
     }
   
   /* otherwise --- maybe for bootstrap */
-  if (c < MIN_CHAR_OBS_94x94)
-    {
-      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));
-       }
-    }
-  else if (c <= MAX_CHAR_OBS_94x94)
-    {
-      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));
-    }
-  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));
-    }
-  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));
-    }
-  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));
-    }
-  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));
-    }
-  else
-    {
-      return Qnil;
-    }
+  return split_builtin_char (c);
 }
 
 INLINE void breakup_char_1 (Emchar c, Lisp_Object *charset, int *c1, int *c2);