GenValidity exists to make tests involving Validity types easier and speed up the generation of data for them.

Let's use the example from Data.Validity again: A datatype that represents primes. To implement tests for this datatype, we would have to be able to generate both primes and non-primes. We could do this with (Prime $ arbitrary) suchThat isValid but this is tedious and inefficient.

The GenValid type class allows you to specify how to (efficiently) generate valid data of the given type to allow for easier and quicker testing. Just instantiating GenUnchecked already gives you access to a default instance of GenValid and GenInvalid but writing custom implementations of these functions may speed up the generation of data.

For example, to generate primes, we don't have to consider even numbers other than 2. A more efficient implementation could then look as follows:

instance GenUnchecked Prime where
    genUnchecked = Prime <$> arbitrary

instance GenValid Prime where
    genValid = Prime <$>
       (oneof
         [ pure 2
         , ((\y -> 2 * abs y + 1) <$> arbitrary) `suchThat` isPrime)
         ])

Typical examples of tests involving validity could look as follows:

it "succeeds when given valid input" $ do
    forAll genValid $ \input ->
        myFunction input `shouldSatisfy` isRight

it "produces valid output when it succeeds" $ do
    forAll genUnchecked $ \input ->
        case myFunction input of
            Nothing -> return () -- Can happen
            Just output -> output `shouldSatisfy` isValid