Change the backend to reject strings containing invalidly-encoded multibyte

characters in all cases.  Formerly we mostly just threw warnings for invalid
input, and failed to detect it at all if no encoding conversion was required.
The tighter check is needed to defend against SQL-injection attacks as per
CVE-2006-2313 (further details will be published after release).  Embedded
zero (null) bytes will be rejected as well.  The checks are applied during
input to the backend (receipt from client or COPY IN), so it no longer seems
necessary to check in textin() and related routines; any string arriving at
those functions will already have been validated.  Conversion failure
reporting (for characters with no equivalent in the destination encoding)
has been cleaned up and made consistent while at it.

Also, fix a few longstanding errors in little-used encoding conversion
routines: win1251_to_iso, win866_to_iso, euc_tw_to_big5, euc_tw_to_mic,
mic_to_euc_tw were all broken to varying extents.

Patches by Tatsuo Ishii and Tom Lane.  Thanks to Akio Ishida and Yasuo Ohgaki
for identifying the security issues.

Author: tglsfdc

src/backend/commands/copy.c

@@ -8,7 +8,7 @@
  *
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/commands/copy.c,v 1.263 2006/04/05 22:11:54 tgl Exp $
+ *	  $PostgreSQL: pgsql/src/backend/commands/copy.c,v 1.264 2006/05/21 20:05:19 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -1023,9 +1023,15 @@ DoCopy(const CopyStmt *stmt)
 	cstate->raw_buf_index = cstate->raw_buf_len = 0;
 	cstate->processed = 0;
 
-	/* Set up encoding conversion info */
+	/*
+	 * Set up encoding conversion info.  Even if the client and server
+	 * encodings are the same, we must apply pg_client_to_server() to
+	 * validate data in multibyte encodings.
+	 */
 	cstate->client_encoding = pg_get_client_encoding();
-	cstate->need_transcoding = (cstate->client_encoding != GetDatabaseEncoding());
+	cstate->need_transcoding =
+		(cstate->client_encoding != GetDatabaseEncoding() ||
+		 pg_database_encoding_max_length() > 1);
 	/* See Multibyte encoding comment above */
 	cstate->encoding_embeds_ascii = PG_ENCODING_IS_CLIENT_ONLY(cstate->client_encoding);
 

src/backend/utils/adt/name.c

@@ -14,7 +14,7 @@
  *
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/utils/adt/name.c,v 1.57 2006/03/05 15:58:43 momjian Exp $
+ *	  $PostgreSQL: pgsql/src/backend/utils/adt/name.c,v 1.58 2006/05/21 20:05:19 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -49,10 +49,7 @@ namein(PG_FUNCTION_ARGS)
 	NameData   *result;
 	int			len;
 
-	/* verify encoding */
 	len = strlen(s);
-	pg_verifymbstr(s, len, false);
-
 	len = pg_mbcliplen(s, len, NAMEDATALEN - 1);
 
 	result = (NameData *) palloc0(NAMEDATALEN);

src/backend/utils/adt/varchar.c

@@ -8,7 +8,7 @@
  *
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/utils/adt/varchar.c,v 1.115 2006/03/05 15:58:44 momjian Exp $
+ *	  $PostgreSQL: pgsql/src/backend/utils/adt/varchar.c,v 1.116 2006/05/21 20:05:19 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -73,9 +73,6 @@ bpchar_input(const char *s, size_t len, int32 atttypmod)
 	char	   *r;
 	size_t		maxlen;
 
-	/* verify encoding */
-	pg_verifymbstr(s, len, false);
-
 	/* If typmod is -1 (or invalid), use the actual string length */
 	if (atttypmod < (int32) VARHDRSZ)
 		maxlen = len;
@@ -393,9 +390,6 @@ varchar_input(const char *s, size_t len, int32 atttypmod)
 	VarChar    *result;
 	size_t		maxlen;
 
-	/* verify encoding */
-	pg_verifymbstr(s, len, false);
-
 	maxlen = atttypmod - VARHDRSZ;
 
 	if (atttypmod >= (int32) VARHDRSZ && len > maxlen)

src/backend/utils/adt/varlena.c

@@ -8,7 +8,7 @@
  *
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/utils/adt/varlena.c,v 1.146 2006/04/04 19:35:36 tgl Exp $
+ *	  $PostgreSQL: pgsql/src/backend/utils/adt/varlena.c,v 1.147 2006/05/21 20:05:19 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -256,10 +256,7 @@ textin(PG_FUNCTION_ARGS)
 	text	   *result;
 	int			len;
 
-	/* verify encoding */
 	len = strlen(inputText);
-	pg_verifymbstr(inputText, len, false);
-
 	result = (text *) palloc(len + VARHDRSZ);
 	VARATT_SIZEP(result) = len + VARHDRSZ;
 
@@ -299,9 +296,6 @@ textrecv(PG_FUNCTION_ARGS)
 
 	str = pq_getmsgtext(buf, buf->len - buf->cursor, &nbytes);
 
-	/* verify encoding */
-	pg_verifymbstr(str, nbytes, false);
-
 	result = (text *) palloc(nbytes + VARHDRSZ);
 	VARATT_SIZEP(result) = nbytes + VARHDRSZ;
 	memcpy(VARDATA(result), str, nbytes);