X-Git-Url: http://git.chise.org/gitweb/?a=blobdiff_plain;f=src%2Fchar-ucs.h;h=42d98ef5e639a48092e49b1fe0d3311bd175fbf8;hb=83672a528db7fe9cace421905b7efd06c11b7c98;hp=d45683a9d3b4f0fbf693f2fcd9a45e164fe4be86;hpb=333b7317418f97a7ff16338e8eb8b98f6c7dbe47;p=chise%2Fxemacs-chise.git

diff --git a/src/char-ucs.h b/src/char-ucs.h
index d45683a..42d98ef 100644
--- a/src/char-ucs.h
+++ b/src/char-ucs.h
@@ -60,6 +60,8 @@ typedef int Charset_ID;
 
 #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
@@ -216,7 +218,7 @@ struct Lisp_Charset
   unsigned int graphic;
 
   /* Byte->character mapping table */
-  Emchar* decoding_table;
+  Lisp_Object decoding_table;
 
   /* Character->byte mapping table */
   Emchar_to_byte_table* to_byte1_table;
@@ -225,8 +227,11 @@ struct Lisp_Charset
   /* Range of character code */
   Emchar ucs_min, ucs_max;
 
-  /* Offset for external representation */
+  /* Offset for external code */
   Emchar code_offset;
+
+  /* Offset for each byte */
+  Emchar byte_offset;
 };
 
 DECLARE_LRECORD (charset, struct Lisp_Charset);
@@ -270,6 +275,7 @@ DECLARE_LRECORD (charset, struct Lisp_Charset);
 #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))
@@ -291,6 +297,10 @@ DECLARE_LRECORD (charset, struct Lisp_Charset);
 #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];
@@ -340,7 +350,13 @@ CHARSET_BY_LEADING_BYTE (Charset_ID lb)
 #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
@@ -361,19 +377,37 @@ INLINE Emchar MAKE_CHAR (Lisp_Object charset, int c1, int c2);
 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)];
+  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 (CHARSET_UCS_MAX (XCHARSET (charset)))
-    return c1 - CHARSET_CODE_OFFSET (XCHARSET (charset))
-      + CHARSET_UCS_MIN (XCHARSET (charset));
+  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))
@@ -416,7 +450,7 @@ 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 < MIN_CHAR_GREEK)
+  if (c < MIN_CHAR_94)
     {
       Lisp_Object charsets = Vdefault_coded_charset_priority_list;
       while (!EQ (charsets, Qnil))
@@ -430,7 +464,7 @@ breakup_char_1 (Emchar c, Lisp_Object *charset, int *c1, int *c2)
 	    }
 	  charsets = Fcdr (charsets);	      
 	}
-      /* otherwise */
+      /* otherwise --- maybe for bootstrap */
       if (c <= MAX_CHAR_BASIC_LATIN)
 	{
 	  *charset = Vcharset_ascii;
@@ -449,6 +483,37 @@ breakup_char_1 (Emchar c, Lisp_Object *charset, int *c1, int *c2)
 	  *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 + 33;
+	  *c2 = 0;
+	}
       else
 	{
 	  *charset = Vcharset_ucs_bmp;
@@ -456,73 +521,6 @@ breakup_char_1 (Emchar c, Lisp_Object *charset, int *c1, int *c2)
 	  *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_coded_charset_priority_list;
-      while (!EQ (charsets, Qnil))
-	{
-	  *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);	      
-	}
-      /* 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)
     {
       *charset