Hello Michael,

thank you very much. Your examples made everything very clear to me :o)
Best regards,

Jan

Am 06.03.2012 20:13, schrieb Michael Ludwig:

>
> Marsupilami79 schrieb am 06.03.2012 um 09:40 (+0100):
>
> > The statement about the usage of introducers is on Page 172 in the
> > middle of the page in a section with the heading "String Literal":
> > "An introducer will be required if the database column being searched
> > has a character set which is different from that of the client
> > connection."
>
> Okay, and then Helen gives the following example:
>
> ... WHERE name = _ISO8859_1 'joe';
>
> Which is somewhat pointless as "joe" is the same in all ASCII supersets,
> and hence doesn't require conversion. (And Firebird doesn't do EBCDIC.)
> Guess Helen doesn't have the ö on her keyboard. I'd still suggest that
> for the second edition, it should be Jörg instead of Joe.
>
> Here's an example, because I was curious:
>
> D:\ :: isql eins -u milu -p moin -ch utf8
> Database: eins, User: milu
> SQL> create table z(a varchar(20) character set utf8);
> SQL> commit;
> SQL> insert into z (a) values ('Jörg');
> Statement failed, SQLSTATE = 22000
> Dynamic SQL Error
> -SQL error code = -104
> -Malformed string
> SQL> -- I've been lying to FB about the connection charset.
> SQL> -- My connection is really in win1252, not in utf8.
> SQL> -- Still, I can save the party by using an introducer.
> SQL> insert into z (a) values (_win1252 'Jörg');
> SQL> commit;
> SQL> select * from z;
>
> A
> ===============================================================================
> Jörg
>
> SQL> quit;
>
> Note two things in the output above:
>
> (1) FB thinks my connection is utf8 (because I've been lying), so it
> cranks out data in UTF-8, which displays like above on a win1252
> terminal.
>
> (2) The bar is 79 characters long when the column has only 20 chars.
> This is because FB reserves 4 bytes per Unicode character. (Don't ask
> me why it's 79 instead of 80.)
>
> D:\ :: isql eins -u milu -p moin -ch win1252
> Database: eins, User: milu
> SQL> select * from z;
>
> A
> ====================
> Jörg
>
> Everything's fine, text automatically converted for display in win1252.
>
> --
> Michael
>
> > Am 02.03.2012 19:26, schrieb Michael Ludwig:
> > >
> > > Marsupilami79 schrieb am 23.02.2012 um 15:17 (+0100):
> > > >
> > > > I have a problem in understanding when to use the introducer syntax
> > > > for character sets.
> > >
> > > For literals. See here:
> > >
> > > http://dev.mysql.com/doc/refman/5.0/en/charset-literal.html
> > >
> > > > Helen Borrie states in the firebird books
> > >
> > > What page number?
> > >
> > > > that the introducer syntax should be used whenever a column is
> > > > searched and the connection character set is different from the
> > > > character set of that column:
> > > >
> > > > So in case I have a WIN1252 client connection and the database uses
> > > > UTF8, should I really always use something like
> > > > where name = _WIN1252 'Jörg'
> > >
> > > Not needed when you type in the characters in the proper connection
> > > encoding.
> > >
> > > But suppose in your connection you're going to execute a SQL script
> > > which happens to be encoded in UTF-8. In order not to depend on the
> > > connection encoding du jour, you'd play safe and use introducers in
> > > your script.
> > >
> > > > Why should I do that? Normally I would expect firebird to know that
> > > > everything is WIN1252, as this is the connection character set, and
> > > > do the necessary conversions without any further hints?
> > > >
> > > > Or should I use the introducer syntax only when I want to send some
> > > > bytes that are explicitly to be treated in a different way than the
> > > > connection character set?
> > > >
> > > > for example something like
> > > > where name = _UTF8 'Jörg'
> > > > when I have the 'Jörg' in an UTF8 encoded way?
> > >
> > > Exactly.
>
>

[Non-text portions of this message have been removed]