Removed the validation in the schema - it was adding complexity, let the unique constraint on the db throw the exception. This should only ever happen on a race condition which seems unlikely (two people changing a service to the same name at the same time)
Do no set debug=true to the test config. If debug=true it changes the behaviour of the error handlers, throwing the exception rather than returning a 500.
This PR removes the need for the email_safe function. The api does not create the email_from field for the service.
Tests were updated to reflect this change.
Refactored service/rest.py so that all methods are returning a properly formatted error message so that the error message can deal with the response.
Refactoed errors.py to properly format the error message.
Added a test for when there are no users for the service.
Added a test_url_for - do we want to add this test and use url_for in our tests?
Or explictly write the url in the test?
Ideally all the primary keys in the db would be UUID in order to guarantee unique ids across distributed dbs.
This updates the services.id to a UUID. All the tables with a foreign key to the services.id are also updated.
The endpoints no longer state a data type of the <service_id> path param.
All the tests are updated to reflect this update.
The thing to pay attention to is the 0011_uuid_service_id.py migration script.
This commit must go with a commit on the notifications_admin app to keep things working.
There will be a small outage until both deploys have happened.
/service/<service_id>/api-key/renew has been renamed to /service/<service_id>/api-key
/service/<service_id>/api-key now creates a token and no longer expires the existing api key.
Moved test for this endpoint to it's own file.
