Use of Data Package resources to describe APIs

[rufuspollock]

Have stated from first version of spec in 2007 that one can use resources to describe data "sources" which would include APIs (not just data files). Perhaps need to make this more explicit and think further through any implications (should we indicate something is an API?)

Also may want to compare against e.g. Swagger spec - https://github.com/wordnik/swagger-spec/blob/master/versions/1.2.md#433-data-type-fields (looks like we have a large amount in common which is good!)

[pwalsh]

@rgrp interesting. wondering if there is a conversation to pickup here?

[cottrell]

I think we are closing #590 and merging the discussion thread into here. Basically, it was summarized as this

As a Data Consumer
I want to request a subset of data from a Data Platform and have the result returned to me in a Data Package
So that I can work with the data using Frictionless Data software and others can easily reproduce the same data

So, what changes to the specification are needed to support this?

How do we describe the requested data in a machine-readable way so that the data package explains it’s a subset and so other Data Consumers can request the same data in the future and get the same result?

I think collections of API queries is kind of what we were getting at. Cemi-concrete examples are things like GET(date=2018-01-01).