Kuba Martin

Hey @dcmoura! I've actualy already done the necessary changes in OctoSQL that I described in the [HN thread](https://news.ycombinator.com/item?id=31038182). Thanks for motivating me :) It was much less work than I...

@dcmoura Hey, looks like a parser issue affecting division (you can totally write i.e. `overall + 5.0`) I'll look into it. In the meantime, you can use the alternative notation...

I think it makes sense to include the use case of taking the first n rows/records/etc. of the file. It's fairly intuitive behavior and a common use case (at least...

Sure! Here's a draft implementation @ashutosh-narkar: https://github.com/open-policy-agent/opa/pull/4997

Hey, it would basically be copy pasting the postgres data source and changing the sql generation parts to fit the dialect. MySQL support was added in like half an hour...

I've written a small datasource contribution guide if that helps: https://github.com/cube2222/octosql/tree/master/storage

Hey @Xirui, glad to hear that! OctoSQL doesn't accept contributions right now, as is detailed in the README: https://github.com/cube2222/octosql#contributing However, since this issue was created, OctoSQL adopted a plugin model...

The plugin architecture is meant to keep datasources decoupled from the main repository, so 99% this will be implemented as a plugin. That said, you won't need additional tooling nor...

> Got it on the tooling bit, but the connectivity thing seems contradictory? Sorry, what I meant is that you only need it once, on setup. > Put in folder...

Prometheus would be fairly easy to add (column per label, with filtering on those and on timestamps). However, prometheus has semantics which may better fit a streaming context. Which is...