Guten Tag Lester Caine lester@... [firebird-support],

Strings with charset none need only 1 byte per char in the receive buffer of your software
UFT-8 will reserve 4 Bytes per char , regardless if it is needed or not ,
this can cause some problems on larger records

> For 20 odd years I've only ever created databases with a charset of NONE
> and because of the way PHP works the odd UTF8 string just works as raw
> data. Strange names and address strings just work and there is normally
> only a problem when the string was corrupt anyway.

> Now I think it's time I started to look at tidying things up, and move
> to UTF8 as the default character set. I've various notes across several
> versions of FB, but is there a good current crib sheet on how to handle
> this? I think I'm simply looking at creating a new empty UTF8 copy of
> the database and pumping over from the NONE version?

> I'm just trying to decide if it's worth upgrading ibWebAdmin to handle
> the transfer so I can play with csv dumps and pick up some other raw
> data sources, but are there other tools working with FB3. I'm find a
> number of the tools like XMLWizard are being blocked by my ISP but I
> think they are the same versions as I downloaded some time ago but which
> will not run on my current version of SUSE :(

--
Mit freundlichen Grüssen
Hannes Streicher mailto:HStreicher@...