SQL is pretty horrifying when you start getting tree structures or recursive structures. While Datalog handles those like a champ.
SQL is really nice for columnar data, and it's well supported almost everywhere.
Though Datalog isn't half bad at columnar data either.
I like SQL more when working with tabular data (especially for analytical use cases), but that has (thus far) dominated the kinds of work I've done.
SQL is pretty horrifying when you start getting tree structures or recursive structures. While Datalog handles those like a champ.
SQL is really nice for columnar data, and it's well supported almost everywhere.
Though Datalog isn't half bad at columnar data either.