X-Git-Url: http://git.chise.org/gitweb/?a=blobdiff_plain;f=src%2Fchar-ucs.h;h=56b72bfda66a1182d46e37ef5acc326366e970f6;hb=7c00b553ec1c85f4eff517d08a87be98e6158119;hp=93fe8c6e491fda48c02be0015fd15f2a579f1466;hpb=31c757f1f48c650ddfd7ec317dc62f763256114e;p=chise%2Fxemacs-chise.git-

diff --git a/src/char-ucs.h b/src/char-ucs.h
index 93fe8c6..56b72bf 100644
--- a/src/char-ucs.h
+++ b/src/char-ucs.h
@@ -215,12 +215,18 @@ struct Lisp_Charset
   /* Which half of font to be used to display this character set */
   unsigned int graphic;
 
-  /* byte->character mapping table */
+  /* Byte->character mapping table */
   Emchar* 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 representation */
+  Emchar code_offset;
 };
 
 DECLARE_LRECORD (charset, struct Lisp_Charset);
@@ -261,6 +267,9 @@ 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 XCHARSET_ID(cs)		  CHARSET_ID           (XCHARSET (cs))
@@ -356,28 +365,15 @@ MAKE_CHAR (Lisp_Object charset, int c1, int c2)
   
   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;
   else if (EQ (charset, Vcharset_katakana_jisx0201))
     if (c1 < 0x60)
       return c1 + MIN_CHAR_HALFWIDTH_KATAKANA - 0x20;
     else
       /* return MIN_CHAR_94 + ('I' - '0') * 94 + (c1 - 33); */
       return ' ';
+  else if (CHARSET_UCS_MAX (XCHARSET (charset)))
+    return c1 - CHARSET_CODE_OFFSET (XCHARSET (charset))
+      + CHARSET_UCS_MIN (XCHARSET (charset));
   else if (XCHARSET_DIMENSION (charset) == 1)
     {
       switch (XCHARSET_CHARS (charset))
@@ -410,56 +406,19 @@ MAKE_CHAR (Lisp_Object charset, int c1, int c2)
     }
 }
 
-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 <= MAX_CHAR_BASIC_LATIN)
-    {
-      *charset = Vcharset_ascii;
-      *c1 = charset_get_byte1 (*charset, c);
-      *c2 = charset_get_byte2 (*charset, c);
-    }
-  else if (c < 0xA0)
-    {
-      *charset = Vcharset_control_1;
-      *c1 = charset_get_byte1 (*charset, c);
-      *c2 = charset_get_byte2 (*charset, c);
-    }
-  else if (c <= 0xff)
-    {
-      *charset = Vcharset_latin_iso8859_1;
-      *c1 = charset_get_byte1 (*charset, c);
-      *c2 = charset_get_byte2 (*charset, c);
-    }
-  else if (c <= 0x17f)
-    {
-      *charset
-	= CHARSET_BY_LEADING_BYTE (latin_a_char_to_charset[c - 0x100]);
-      if (XCHARSET_TO_BYTE1_TABLE (*charset) != NULL)
-	{
-	  *c1 = charset_get_byte1 (*charset, c);
-	  *c2 = charset_get_byte2 (*charset, c);
-	}
-      else
-	{
-	  *c1 = latin_a_char_to_byte1[c - 0x100];
-	  *c2 = latin_a_char_to_byte2[c - 0x100];
-	}
-    }
-  else if (c < MIN_CHAR_GREEK)
+  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));
@@ -471,77 +430,62 @@ breakup_char_1 (Emchar c, Lisp_Object *charset, int *c1, int *c2)
 	    }
 	  charsets = Fcdr (charsets);	      
 	}
-      /* 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))
+      /* otherwise --- maybe for bootstrap */
+      if (c <= MAX_CHAR_BASIC_LATIN)
 	{
-	  *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_ascii;
+	  *c1 = charset_get_byte1 (*charset, c);
+	  *c2 = charset_get_byte2 (*charset, c);
+	}
+      else if (c < 0xA0)
+	{
+	  *charset = Vcharset_control_1;
+	  *c1 = charset_get_byte1 (*charset, c);
+	  *c2 = charset_get_byte2 (*charset, c);
+	}
+      else if (c <= 0xff)
+	{
+	  *charset = Vcharset_latin_iso8859_1;
+	  *c1 = charset_get_byte1 (*charset, c);
+	  *c2 = charset_get_byte2 (*charset, c);
+	}
+      else if ((MIN_CHAR_GREEK <= c) && (c <= MAX_CHAR_GREEK))
+	{
+	  *charset = Vcharset_greek_iso8859_7;
+	  *c1 = c - MIN_CHAR_GREEK + 0x20;
+	  *c2 = 0;
+	}
+      else if ((MIN_CHAR_CYRILLIC <= c) && (c <= MAX_CHAR_CYRILLIC))
+	{
+	  *charset = Vcharset_cyrillic_iso8859_5;
+	  *c1 = c - MIN_CHAR_CYRILLIC + 0x20;
+	  *c2 = 0;
+	}
+      else if ((MIN_CHAR_HEBREW <= c) && (c <= MAX_CHAR_HEBREW))
+	{
+	  *charset = Vcharset_hebrew_iso8859_8;
+	  *c1 = c - MIN_CHAR_HEBREW + 0x20;
+	  *c2 = 0;
+	}
+      else if ((MIN_CHAR_THAI <= c) && (c <= MAX_CHAR_THAI))
+	{
+	  *charset = Vcharset_thai_tis620;
+	  *c1 = c - MIN_CHAR_THAI + 0x20;
+	  *c2 = 0;
+	}
+      else if ((MIN_CHAR_HALFWIDTH_KATAKANA <= c)
+	       && (c <= MAX_CHAR_HALFWIDTH_KATAKANA))
+	{
+	  *charset = Vcharset_katakana_jisx0201;
+	  *c1 = c - MIN_CHAR_HALFWIDTH_KATAKANA + 0x20;
+	  *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)
     {