I wrote:
> Peter Eisentraut <[email protected]> writes:
>> AFAIR, the only reason that we haven't disallowed this sort of stuff
>> years and years ago is that people use it; the Japanese in particular.
>> I don't see what is different now.
> What's different now is that 8.4 has already established the principle
> that you have to clone template0 if you want to change the locale of a
> database. I think this is a good time to establish the same principle
> for encodings. (Or in other words, if we don't fix it now, when will
> be a better time?)
Attached is a proposed patch (without documentation changes as yet)
for this. Since the code is already enforcing exact locale match when
cloning a non-template0 database, I just made it act the same for
encoding, without any strange exceptions for SQL_ASCII.
I found that mbregress.sh was already broken by the existing
restrictions, if you try to use it in a database whose default
locale isn't C. The patch adds switches to fix that.
The patch also incidentally fixes a few ereport's that were missing
errcode values.
Last chance for objections ...
regards, tom lane
Index: src/backend/commands/dbcommands.c
===================================================================
RCS file: /cvsroot/pgsql/src/backend/commands/dbcommands.c,v
retrieving revision 1.223
diff -c -r1.223 dbcommands.c
*** src/backend/commands/dbcommands.c 5 May 2009 23:39:55 -0000 1.223
--- src/backend/commands/dbcommands.c 6 May 2009 00:30:59 -0000
***************
*** 361,367 ****
#endif
(encoding == PG_SQL_ASCII && superuser())))
ereport(ERROR,
! (errmsg("encoding %s does not match locale %s",
pg_encoding_to_char(encoding),
dbctype),
errdetail("The chosen LC_CTYPE setting requires
encoding %s.",
--- 361,368 ----
#endif
(encoding == PG_SQL_ASCII && superuser())))
ereport(ERROR,
! (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.",
***************
*** 374,402 ****
#endif
(encoding == PG_SQL_ASCII && superuser())))
ereport(ERROR,
! (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.
*
! * 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.
*/
if (strcmp(dbtemplate, "template0") != 0)
{
if (strcmp(dbcollate, src_collate) != 0)
ereport(ERROR,
! (errmsg("new collation is incompatible
with the collation of the template database (%s)", 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),
errhint("Use the same LC_CTYPE as in
the template database, or use template0 as template.")));
}
--- 375,419 ----
#endif
(encoding == PG_SQL_ASCII && superuser())))
ereport(ERROR,
! (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 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.
*
! * 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,
!
(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,
!
(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.")));
}
***************
*** 1099,1105 ****
continue;
ereport(ERROR,
! (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.")));
}
--- 1116,1123 ----
continue;
ereport(ERROR,
!
(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.")));
}
Index: src/test/mb/mbregress.sh
===================================================================
RCS file: /cvsroot/pgsql/src/test/mb/mbregress.sh,v
retrieving revision 1.9
diff -c -r1.9 mbregress.sh
*** src/test/mb/mbregress.sh 24 Jun 2005 15:11:59 -0000 1.9
--- src/test/mb/mbregress.sh 6 May 2009 00:30:59 -0000
***************
*** 15,21 ****
fi
dropdb utf8
! createdb -E UTF8 utf8
PSQL="psql -n -e -q"
tests="euc_jp sjis euc_kr euc_cn euc_tw big5 utf8 mule_internal"
--- 15,21 ----
fi
dropdb 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"
***************
*** 36,42 ****
unset PGCLIENTENCODING
else
dropdb $i >/dev/null 2>&1
! createdb -E `echo $i | tr 'abcdefghijklmnopqrstuvwxyz'
'ABCDEFGHIJKLMNOPQRSTUVWXYZ'` $i >/dev/null
$PSQL $i < sql/${i}.sql > results/${i}.out 2>&1
fi
--- 36,42 ----
unset PGCLIENTENCODING
else
dropdb $i >/dev/null 2>&1
! 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
--
Sent via pgsql-hackers mailing list ([email protected])
To make changes to your subscription:
http://www.postgresql.org/mailpref/pgsql-hackers
