Modify CREATE DATABASE to enforce that the source database's encoding setting

must be used for the new database, except when copying from template0.
This is the same rule that we now enforce for locale settings, and it has
the same motivation: databases other than template0 might contain data that
would be invalid according to a different setting.  This represents another
step in a continuing process of locking down ways in which encoding violations
could occur inside the backend.  Per discussion of a few days ago.

In passing, fix pre-existing breakage of mbregress.sh, and fix up a couple
of ereport() calls in dbcommands.c that failed to specify sqlstate codes.

3 files changed, 33 insertions, 15 deletions

diff --git a/src/backend/commands/dbcommands.c b/src/backend/commands/dbcommands.c
index cf6e7400985..8d5972dfa51 100644
--- a/src/backend/commands/dbcommands.c
+++ b/src/backend/commands/dbcommands.c
@@ -13,7 +13,7 @@
  *
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/commands/dbcommands.c,v 1.223 2009/05/05 23:39:55 tgl Exp $
+ *	  $PostgreSQL: pgsql/src/backend/commands/dbcommands.c,v 1.224 2009/05/06 16:15:21 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -361,7 +361,8 @@ createdb(const CreatedbStmt *stmt)
 #endif
 		  (encoding == PG_SQL_ASCII && superuser())))
 		ereport(ERROR,
-				(errmsg("encoding %s does not match locale %s",
+				(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
+				 errmsg("encoding %s does not match locale %s",
 						pg_encoding_to_char(encoding),
 						dbctype),
 			 errdetail("The chosen LC_CTYPE setting requires encoding %s.",
@@ -374,29 +375,45 @@ createdb(const CreatedbStmt *stmt)
 #endif
 		  (encoding == PG_SQL_ASCII && superuser())))
 		ereport(ERROR,
-				(errmsg("encoding %s does not match locale %s",
+				(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
+				 errmsg("encoding %s does not match locale %s",
 						pg_encoding_to_char(encoding),
 						dbcollate),
 			 errdetail("The chosen LC_COLLATE setting requires encoding %s.",
 					   pg_encoding_to_char(collate_encoding))));
 
 	/*
-	 * Check that the new locale is compatible with the source database.
+	 * Check that the new encoding and locale settings match the source
+	 * database.  We insist on this because we simply copy the source data ---
+	 * any non-ASCII data would be wrongly encoded, and any indexes sorted
+	 * according to the source locale would be wrong.
 	 *
-	 * We know that template0 doesn't contain any indexes that depend on
-	 * collation or ctype, so template0 can be used as template for
-	 * any locale.
+	 * However, we assume that template0 doesn't contain any non-ASCII data
+	 * nor any indexes that depend on collation or ctype, so template0 can be
+	 * used as template for creating a database with any encoding or locale.
 	 */
 	if (strcmp(dbtemplate, "template0") != 0)
 	{
+		if (encoding != src_encoding)
+			ereport(ERROR,
+					(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
+					 errmsg("new encoding (%s) is incompatible with the encoding of the template database (%s)",
+							pg_encoding_to_char(encoding),
+							pg_encoding_to_char(src_encoding)),
+					 errhint("Use the same encoding as in the template database, or use template0 as template.")));
+
 		if (strcmp(dbcollate, src_collate) != 0)
 			ereport(ERROR,
-					(errmsg("new collation is incompatible with the collation of the template database (%s)", src_collate),
+					(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
+					 errmsg("new collation (%s) is incompatible with the collation of the template database (%s)",
+							dbcollate, src_collate),
 					 errhint("Use the same collation as in the template database, or use template0 as template.")));
 
 		if (strcmp(dbctype, src_ctype) != 0)
 			ereport(ERROR,
-					(errmsg("new LC_CTYPE is incompatible with LC_CTYPE of the template database (%s)", src_ctype),
+					(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
+					 errmsg("new LC_CTYPE (%s) is incompatible with the LC_CTYPE of the template database (%s)",
+							dbctype, src_ctype),
 					 errhint("Use the same LC_CTYPE as in the template database, or use template0 as template.")));
 	}
 
@@ -1099,7 +1116,8 @@ movedb(const char *dbname, const char *tblspcname)
 				continue;
 
 			ereport(ERROR,
-					(errmsg("some relations of database \"%s\" are already in tablespace \"%s\"",
+					(errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
+					 errmsg("some relations of database \"%s\" are already in tablespace \"%s\"",
 							dbname, tblspcname),
 					 errhint("You must move them back to the database's default tablespace before using this command.")));
 		}
diff --git a/src/test/mb/README b/src/test/mb/README
index c11452f8a91..e7bd757dbd8 100644
--- a/src/test/mb/README
+++ b/src/test/mb/README
@@ -1,4 +1,4 @@
-$PostgreSQL: pgsql/src/test/mb/README,v 1.3 2008/03/21 13:23:29 momjian Exp $
+$PostgreSQL: pgsql/src/test/mb/README,v 1.4 2009/05/06 16:15:21 tgl Exp $
 
 README for multibyte regression test
 							1998/7/22
@@ -7,4 +7,4 @@ README for multibyte regression test
 This directory contains a set of tests for multibyte supporting
 extentions for PostgreSQL. To run the test, simply type:
 
-% mbregress.sh
+% sh mbregress.sh
diff --git a/src/test/mb/mbregress.sh b/src/test/mb/mbregress.sh
index eb9821284b1..8a2aca6267b 100644
--- a/src/test/mb/mbregress.sh
+++ b/src/test/mb/mbregress.sh
@@ -1,5 +1,5 @@
 #! /bin/sh
-# $PostgreSQL: pgsql/src/test/mb/mbregress.sh,v 1.9 2005/06/24 15:11:59 ishii Exp $
+# $PostgreSQL: pgsql/src/test/mb/mbregress.sh,v 1.10 2009/05/06 16:15:21 tgl Exp $
 
 if echo '\c' | grep -s c >/dev/null 2>&1
 then
@@ -15,7 +15,7 @@ if [ ! -d results ];then
 fi
 
 dropdb utf8
-createdb -E UTF8 utf8
+createdb -T template0 -l C -E UTF8 utf8
 
 PSQL="psql -n -e -q"
 tests="euc_jp sjis euc_kr euc_cn euc_tw big5 utf8 mule_internal"
@@ -36,7 +36,7 @@ do
 		unset PGCLIENTENCODING
 	else
 		dropdb $i >/dev/null 2>&1
-		createdb -E `echo $i | tr 'abcdefghijklmnopqrstuvwxyz' 'ABCDEFGHIJKLMNOPQRSTUVWXYZ'` $i >/dev/null
+		createdb -T template0 -l C -E `echo $i | tr 'abcdefghijklmnopqrstuvwxyz' 'ABCDEFGHIJKLMNOPQRSTUVWXYZ'` $i >/dev/null
 		$PSQL $i < sql/${i}.sql > results/${i}.out 2>&1
 	fi