At 01:35 AM 1/6/2001 -0500, Patrick J. P. Griffin wrote:

>I've been meditating on [ Bug #127473 ] isql always ignores charset NONE in
>metadata extraction and I've got a question.

Patrick,

I've just looked at the collation_id and character_set_id
fields in rdb$fields for a simple database. There seems to
be neither rhyme nor reason to the use of null and zero in
those fields. Normally that means there's something major
I haven't understood, so I'm looking for a correction here.


If we use 0:0 to mean an explicit NONE, and null:null to mean
unspecified, then here is the assignment order I would use:

if a charset, including null, is specified for a field,
that field retains that char set.

else if a charset is set for the database
fields from that table retain that charset

else the field adopts the charset of its new database.

Patrick's puzzle:

>Database A has no default character set.
>
>Database A has the table T1 with field F1 with no character set specified.
>
>Database A has the table T2 with field F2 with character set NONE explicitly
>specified.
>
>
>Database B uses the default character set WIN1251.
>
>
>Using ISQL to copy the table structure for T1 into Database B, what
>character set should be used for the field F1?

WIN1251, by default.

>Using ISQL to copy the table structure for T2 into Database B, what
>character set should be used for the field F2?

None, explicitly.

>And, for extra credit, how about:
>
>Database C uses the default character set WIN1251
>
>Database C has the table T3 with field F3 with no character set specified
>(will be defined with WIN1251)
>
>Database C has the table T4 with field F4 with character set NONE explicitly
>specified.
>
>
>Database D uses the default character set CYRL.
>
>
>Using ISQL to copy the table structure for T3 into Database D, what
>character set should be used for the field F3?

Win1251.

>Using ISQL to copy the table structure for T4 into Database D, what
>character set should be used for the field F4?

None, explicitly

>Should fields with no explicit character set in one database assume the
>default character set of the target database?

Not always. If the source database has a default character set, then
those fields should carry that character set.

>Should fields explicitly or implicitly using the default character set of
>one database assume the default character set of the target database?

Fields that explicitly use a character set (including NONE) in
one database should use the same character set in other databases.

Fields that implicitly use a character set in one database should
continue to use that character set if and only if source database
has an explicit character set.

Fields defined with no explicit character set should have a null
collation id and a null



Regards,

Ann
www.ibphoenix.com
We have answers.