madsbuch

/**
 * This is a small informal performance test to see how it best makes sense to
 * read JSON-lines files. The JSONL format is a file with a JSON object on each
 * line. This is opposed to a JSON file with an array on the top level
 * containing each object.
 * 
 * I test two evaluation strategies:
 * 
 * 1. Split the string on new lines and parse each string individually
 * 2. Massage the string into a stringifies JSON array and parse it

madsbuch

{-# LANGUAGE GADTs #-}
{-
  The following code is based on experimental code by Aslan Askerov
  based on Ramsey and Pfeffers "Stochastic Lambda Calculus and Monads of
  Probability Distributions". Implementation of random n is from
  Audebaud and Paulin-Mohring paper, so is the random walk example.

  This gist is used here http://madsbuch.com/the-probability-monad/

  The class hierarchy is as follows:

madsbuch

{-# LANGUAGE GADTs                #-} -- Soft dependent types
{-# LANGUAGE PolyKinds            #-} -- Allow general specification of Refl
{-# LANGUAGE RankNTypes           #-} -- Explicit quantification and inline type context
{-# LANGUAGE DataKinds            #-} -- Lift data constructors to Kind level
{-# LANGUAGE TypeFamilies         #-} -- Equational reasoning about types
{-# LANGUAGE TypeOperators        #-} -- Allow types such as :~:

-- Starting the interactive shell:
-- 
-- ghci -XDataKinds -XTypeOperators -Wall -Werror Script.hs