Jonathan,

J> should not any corruption be considered a bug, and get reported?

it should, provided the usual checklist (forced writes, known bug,
etc.) is checked.

J> As for logicial corruption, shouldn't we make that as impossible as can
J> as well?

Yes; the archives abound of discussion on this.

J> And therefore, if I get such corruption one day, shouldn't I
J> report it?

I guess you're welcome.
Ciao
--
Nando Dessena
mailto:nandod@...