bug#9318: 23.3.50; The first call of encode-coding-region() returns wrong result

[Kazuhiro Ito <kzhr@d1.dion.ne.jp>]

> > SUMMARY OF THE PROBLEM:
> > In encode_coding_XXX(), calling encode_char() could cause relocation
> > of buffers.  char_charset(), ENCODE_ISO_CHARACTER and ENCODE_CHAR
> > could also cause relocation because they could call encode_char().
> > After using of them, coding->destination, dst, dst_end should be
> > updated as needed.
> 
> I noticed CHAR_CHARSET_P macro slipped out of my check.
> CHAR_CHARSET_P could also cause relocation of buffers.

Here is the patch for the code, which contains Andreas' patch.  In my
environment, problems are fixed.  I think it would be better that the
interface of encode_designation_at_bol() is changed.

=== modified file 'src/coding.c'
--- src/coding.c	2011-05-09 09:59:23 +0000
+++ src/coding.c	2011-08-28 07:33:54 +0000
@@ -1026,6 +1026,54 @@
       }									     \
   } while (0)
 
+#define CODING_ENCODE_CHAR(coding, dst, dst_end, charset, c, code)	\
+  do {									\
+    charset_map_loaded = 0;						\
+    code = ENCODE_CHAR (charset, c);					\
+    if (charset_map_loaded)						\
+      {									\
+	const unsigned char *orig = coding->destination;		\
+	EMACS_INT offset;						\
+									\
+	coding_set_destination (coding);				\
+	offset = coding->destination - orig;				\
+	dst += offset;							\
+	dst_end += offset;						\
+      }									\
+  } while (0)
+
+#define CODING_CHAR_CHARSET(coding, dst, dst_end, c, charset_list, code_return, charset) \
+  do {									\
+    charset_map_loaded = 0;						\
+    charset = char_charset (c, charset_list, code_return);		\
+    if (charset_map_loaded)						\
+      {									\
+	const unsigned char *orig = coding->destination;		\
+	EMACS_INT offset;						\
+									\
+	coding_set_destination (coding);				\
+	offset = coding->destination - orig;				\
+	dst += offset;							\
+	dst_end += offset;						\
+      }									\
+  } while (0)
+
+#define CODING_CHAR_CHARSET_P(coding, dst, dst_end, c, charset, result) \
+  do {									\
+    charset_map_loaded = 0;						\
+    result = CHAR_CHARSET_P(c, charset);				\
+    if (charset_map_loaded)						\
+      {									\
+	const unsigned char *orig = coding->destination;		\
+	EMACS_INT offset;						\
+									\
+	coding_set_destination (coding);				\
+	offset = coding->destination - orig;				\
+	dst += offset;							\
+	dst_end += offset;						\
+      }									\
+  } while (0)
+
 
 /* If there are at least BYTES length of room at dst, allocate memory
    for coding->destination and update dst and dst_end.  We don't have
@@ -2778,14 +2826,19 @@
 
 	  if (preferred_charset_id >= 0)
 	    {
+	      int result;
+
 	      charset = CHARSET_FROM_ID (preferred_charset_id);
-	      if (CHAR_CHARSET_P (c, charset))
+	      CODING_CHAR_CHARSET_P (coding, dst, dst_end, c, charset, result);
+	      if (result)
 		code = ENCODE_CHAR (charset, c);
 	      else
-		charset = char_charset (c, charset_list, &code);
+		CODING_CHAR_CHARSET(coding, dst, dst_end, c, charset_list,
+				    &code, charset);
 	    }
 	  else
-	    charset = char_charset (c, charset_list, &code);
+	    CODING_CHAR_CHARSET(coding, dst, dst_end, c, charset_list,
+				&code, charset);
 	  if (! charset)
 	    {
 	      c = coding->default_char;
@@ -2794,7 +2847,8 @@
 		  EMIT_ONE_ASCII_BYTE (c);
 		  continue;
 		}
-	      charset = char_charset (c, charset_list, &code);
+	      CODING_CHAR_CHARSET(coding, dst, dst_end, c, charset_list,
+				  &code, charset);
 	    }
 	  dimension = CHARSET_DIMENSION (charset);
 	  emacs_mule_id = CHARSET_EMACS_MULE_ID (charset);
@@ -4317,8 +4371,9 @@
 
 #define ENCODE_ISO_CHARACTER(charset, c)				   \
   do {									   \
-    int code = ENCODE_CHAR ((charset),(c));				   \
-									   \
+    int code;								   \
+    CODING_ENCODE_CHAR (coding, dst, dst_end, (charset), (c), code);	   \
+    									   \
     if (CHARSET_DIMENSION (charset) == 1)				   \
       ENCODE_ISO_CHARACTER_DIMENSION1 ((charset), code);		   \
     else								   \
@@ -4476,7 +4531,17 @@
       c = *charbuf++;
       if (c == '\n')
 	break;
+
+      charset_map_loaded = 0;
       charset = char_charset (c, charset_list, NULL);
+      if (charset_map_loaded)
+	{
+	  const unsigned char *orig = coding->destination;
+
+	  coding_set_destination (coding);
+	  dst += coding->destination - orig;
+	}
+
       id = CHARSET_ID (charset);
       reg = CODING_ISO_REQUEST (coding, id);
       if (reg >= 0 && r[reg] < 0)
@@ -4543,6 +4608,12 @@
 
 	  /* We have to produce designation sequences if any now.  */
 	  dst = encode_designation_at_bol (coding, charbuf, charbuf_end, dst);
+	  if (charset_map_loaded)
+	    {
+	      EMACS_INT offset = coding->destination + coding->dst_bytes - dst_end;
+	      dst_end += offset;
+	      dst_prev += offset;
+	    }
 	  bol_designation = 0;
 	  /* We are sure that designation sequences are all ASCII bytes.  */
 	  produced_chars += dst - dst_prev;
@@ -4616,12 +4687,17 @@
 
 	  if (preferred_charset_id >= 0)
 	    {
+	      int result;
+
 	      charset = CHARSET_FROM_ID (preferred_charset_id);
-	      if (! CHAR_CHARSET_P (c, charset))
-		charset = char_charset (c, charset_list, NULL);
+	      CODING_CHAR_CHARSET_P (coding, dst, dst_end, c, charset, result);
+	      if (! result)
+		CODING_CHAR_CHARSET(coding, dst, dst_end, c, charset_list,
+				    NULL, charset);
 	    }
 	  else
-	    charset = char_charset (c, charset_list, NULL);
+	    CODING_CHAR_CHARSET(coding, dst, dst_end, c, charset_list,
+				NULL, charset);
 	  if (!charset)
 	    {
 	      if (coding->mode & CODING_MODE_SAFE_ENCODING)
@@ -4632,7 +4708,8 @@
 	      else
 		{
 		  c = coding->default_char;
-		  charset = char_charset (c, charset_list, NULL);
+		  CODING_CHAR_CHARSET(coding, dst, dst_end, c,
+				      charset_list, NULL, charset);
 		}
 	    }
 	  ENCODE_ISO_CHARACTER (charset, c);
@@ -5064,7 +5141,9 @@
       else
 	{
 	  unsigned code;
-	  struct charset *charset = char_charset (c, charset_list, &code);
+	  struct charset *charset;
+	  CODING_CHAR_CHARSET(coding, dst, dst_end, c, charset_list,
+			      &code, charset);
 
 	  if (!charset)
 	    {
@@ -5076,7 +5155,8 @@
 	      else
 		{
 		  c = coding->default_char;
-		  charset = char_charset (c, charset_list, &code);
+		  CODING_CHAR_CHARSET(coding, dst, dst_end, c,
+				      charset_list, &code, charset);
 		}
 	    }
 	  if (code == CHARSET_INVALID_CODE (charset))
@@ -5153,7 +5233,9 @@
       else
 	{
 	  unsigned code;
-	  struct charset *charset = char_charset (c, charset_list, &code);
+	  struct charset *charset;
+	  CODING_CHAR_CHARSET(coding, dst, dst_end, c, charset_list,
+			      &code, charset);
 
 	  if (! charset)
 	    {
@@ -5165,7 +5247,8 @@
 	      else
 		{
 		  c = coding->default_char;
-		  charset = char_charset (c, charset_list, &code);
+		  CODING_CHAR_CHARSET(coding, dst, dst_end, c,
+				      charset_list, &code, charset);
 		}
 	    }
 	  if (code == CHARSET_INVALID_CODE (charset))
@@ -5747,7 +5831,9 @@
 	}
       else
 	{
-	  charset = char_charset (c, charset_list, &code);
+	  CODING_CHAR_CHARSET(coding, dst, dst_end, c, charset_list,
+			      &code, charset);
+
 	  if (charset)
 	    {
 	      if (CHARSET_DIMENSION (charset) == 1)


-- 
Kazuhiro Ito