Difference between revisions of "Output/Input"
Jump to navigation
Jump to search
(Minor changes) |
m |
||
| (96 intermediate revisions by the same user not shown) | |||
| Line 1: | Line 1: | ||
| + | Regarding <code>IO a</code>, Haskell's monadic I/O type: |
||
| − | Let me guess...you've read every other guide, tutorial, lesson and introduction and none of them have helped - you still don't understand I/O in Haskell. |
||
| + | <blockquote> |
||
| − | Alright then - have a look at this: |
||
| + | Some operations are primitive actions, |
||
| + | corresponding to conventional I/O operations. Special operations (methods in the class <code>Monad</code>, see Section 6.3.6) |
||
| + | sequentially compose actions, corresponding to sequencing operators (such as the semicolon) in imperative |
||
| + | languages. |
||
| + | :<small>[https://www.haskell.org/definition/haskell2010.pdf The Haskell 2010 Report], (page 107 of 329).</small> |
||
| − | <haskell> |
||
| + | </blockquote> |
||
| − | data OI -- abstract, primitive |
||
| + | So for I/O, the monadic interface merely provides [[Monad tutorials timeline|an abstract way]] to sequence its actions. However there is another, more direct approach to sequencing: |
||
| − | partOI :: OI -> (OI, OI) -- |
||
| − | getchar :: OI -> Char -- primitives |
||
| − | putchar :: Char -> OI -> () -- |
||
| − | |||
| − | seq :: a -> b -> b -- also primitive |
||
| − | |||
| − | instance Partible OI where ... |
||
| − | |||
| − | class Partible a where |
||
| − | part :: a -> (a, a) |
||
| − | parts :: a -> [a] |
||
| − | . |
||
| − | . |
||
| − | . |
||
| − | </haskell> |
||
| − | |||
| − | No up-front explanation; I'm guessing you've seen more than enough of those, so I'm trying something different. I will explain it later... |
||
| − | |||
| − | Yes, of course there's more to Haskell I/O than <code>getchar</code> and <code>putchar</code>; I've downsized it for convenience. If you want, you can add the rest afterwards... |
||
| − | |||
| − | Yes, they're somewhat arcane, but they can be used to emulate all the classic approaches to I/O in Haskell, albeit in miniature: |
||
<haskell> |
<haskell> |
||
| + | Control.Parallel.pseq :: a -> b -> b |
||
| − | -- for GHC 8.6.5 |
||
| − | {-# LANGUAGE BangPatterns #-} |
||
| − | module ClassicIO where |
||
| − | import Prelude(Char, String) |
||
| − | import Prelude(($), (.)) |
||
| − | import Data.List(map, foldr, zipWith) |
||
| − | import OutputInput |
||
| − | import Partible |
||
| − | |||
| − | -- simple text -- |
||
| − | |||
| − | {- main :: (String -> String) -} |
||
| − | |||
| − | runMain_text :: (String -> String) -> OI -> () |
||
| − | runMain_text main = \u -> let !(u1, u2) = part u in |
||
| − | putchars (main (getchars u1)) u2 |
||
| − | |||
| − | getchars :: OI -> String |
||
| − | getchars = map getchar . parts |
||
| − | |||
| − | putchars :: String -> OI -> () |
||
| − | putchars s = foldr seq () . zipWith putchar s . parts |
||
| − | |||
| − | |||
| − | -- dialogues -- |
||
| − | |||
| − | {- main :: Dialogue -} |
||
| − | |||
| − | runMain_dial :: Dialogue -> OI -> () |
||
| − | runMain_dial main = \u -> foldr seq () $ yet $ |
||
| − | \l -> zipWith respond (main l) (parts u) |
||
| − | |||
| − | type Dialogue = [Response] -> [Request] |
||
| − | |||
| − | data Request = Getq | Putq Char |
||
| − | data Response = Getp Char | Putp |
||
| − | |||
| − | yet :: (a -> a) -> a |
||
| − | yet f = f (yet f) |
||
| − | |||
| − | respond :: Request -> OI -> Response |
||
| − | respond Getq = \u -> case getchar u of c -> Getp c |
||
| − | respond (Putq c) = \u -> seq (putchar c u) Putp |
||
| − | |||
| − | |||
| − | -- continuations -- |
||
| − | |||
| − | {- main :: (() -> IOResult) -> IOResult -} |
||
| − | |||
| − | runMain_cont :: ((() -> IOResult) -> IOResult) -> OI -> () |
||
| − | runMain_cont main = call (main done) |
||
| − | |||
| − | newtype IOResult = R (OI -> ()) |
||
| − | |||
| − | call :: IOResult -> OI -> () |
||
| − | call (R a) = a |
||
| − | |||
| − | done :: () -> IOResult |
||
| − | done () = R $ \ u -> part u `seq` () |
||
| − | |||
| − | getchar_cont :: (Char -> IOResult) -> IOResult |
||
| − | getchar_cont k = R $ \u -> let !(u1, u2) = part u in |
||
| − | let !c = getchar u1 in |
||
| − | call (k c) u2 |
||
| − | |||
| − | putchar_cont :: Char -> (() -> IOResult) -> IOResult |
||
| − | putchar_cont c k = R $ \u -> let !(u1, u2) = part u in |
||
| − | seq (putchar c u) (call (k ()) u2) |
||
| − | |||
| − | |||
| − | -- state-passing -- |
||
| − | |||
| − | {- main :: IOState -> ((), IOState) -} |
||
| − | |||
| − | runMain_stat :: (IOState -> ((), IOState)) -> OI -> () |
||
| − | runMain_stat main = \u -> seq (main (ini_st u)) () |
||
| − | |||
| − | newtype IOState = S OI |
||
| − | |||
| − | ini_st :: OI -> IOState |
||
| − | ini_st = S |
||
| − | |||
| − | getchar_stat :: IOState -> (Char, IOState) |
||
| − | getchar_stat (S u) = let !(u1, u2) = part u in |
||
| − | let !c = getchar u1 in |
||
| − | (c, S u2) |
||
| − | |||
| − | putchar_stat :: Char -> IOState -> ((), IOState) |
||
| − | putchar_stat c (S u) = let !(u1, u2) = part u in |
||
| − | seq (putchar c u1) ((), S u2) |
||
| − | |||
| − | |||
| − | -- and those weird, fickle things ;-) |
||
| − | |||
| − | {- main :: IO () -} |
||
| − | |||
| − | runMain_wfth :: IO () -> OI -> () |
||
| − | runMain_wfth main = main |
||
| − | |||
| − | type IO a = OI -> a |
||
| − | |||
| − | getchar_wfth :: IO Char |
||
| − | getchar_wfth = getchar |
||
| − | |||
| − | putchar_wfth :: Char -> IO () |
||
| − | putchar_wfth = putchar |
||
| − | |||
| − | unit :: a -> IO a |
||
| − | unit x = \u -> part u `seq` x |
||
| − | |||
| − | bind :: IO a -> (a -> IO b) -> IO b |
||
| − | bind m k = \u -> case part u of |
||
| − | (u1, u2) -> (\x -> x `seq` k x u2) (m u1) |
||
</haskell> |
</haskell> |
||
| + | (as opposed to the [[seq|<b>non</b>]]-sequential <code>Prelude.seq</code>.) That means a more direct way of preserving [[Referential transparency|referential transparency]] is also needed. For simple teletype I/O: |
||
| − | Here are examples for each of those approaches: |
||
<haskell> |
<haskell> |
||
| + | data OI |
||
| − | module Echoes where |
||
| + | partOI :: OI -> (OI, OI) |
||
| − | import Prelude(String, Char(..), Eq(..)) |
||
| + | getChar :: OI -> Char |
||
| − | import Prelude(($)) |
||
| + | putChar :: Char -> OI -> () |
||
| − | import ClassicIO |
||
| − | import OutputInput(runOI) |
||
| − | |||
| − | echo_text :: String -> String |
||
| − | echo_text (c:cs) = if c == '\n' then [] else c : echo_text cs |
||
| − | |||
| − | echo_dial :: Dialogue |
||
| − | echo_dial p = Getq : |
||
| − | case p of |
||
| − | Getp c : p' -> |
||
| − | if c == '\n' then |
||
| − | [] |
||
| − | else |
||
| − | Putq c : |
||
| − | case p' of |
||
| − | Putp : p'' -> echo_dial p'' |
||
| − | |||
| − | echo_cont :: (() -> IOResult) -> IOResult |
||
| − | echo_cont k = getchar_cont $ \c -> |
||
| − | if c == '\n' then |
||
| − | k () |
||
| − | else |
||
| − | putchar_cont c (\_ -> echo_cont k) |
||
| − | |||
| − | echo_wfth :: IO () |
||
| − | echo_wfth = getchar_wfth `bind` \c -> |
||
| − | if c == '\n' then |
||
| − | unit () |
||
| − | else |
||
| − | putchar_wfth c `bind` \_ -> echo_wfth |
||
</haskell> |
</haskell> |
||
| + | where: |
||
| − | What was that - using <code>Prelude.seq</code> that way won't work in Haskell 2010? ''You are correct!'' |
||
| + | * <code>OI</code> isn't an ordinary Haskell type - ordinary Haskell types represent values without (externally-visible) side-effects, hence <code>OI</code> being abstract. |
||
| − | This should work as expected[1][2]: |
||
| + | * The action <code>partOI</code> is needed because each <code>OI</code> value can only be used once. |
||
| − | <haskell> |
||
| − | -- for GHC 8.6.5 |
||
| − | {-# LANGUAGE MagicHash, UnboxedTuples #-} |
||
| − | module Sequential(seq) where |
||
| − | import GHC.Base(seq#, realWorld#) |
||
| + | * The action <code>getChar</code> obtains the the next character of input. |
||
| − | infixr 0 `seq` |
||
| − | seq :: a -> b -> b |
||
| − | x `seq` y = case seq# x realWorld# of |
||
| − | (# s, _ #) -> case seq# y s of |
||
| − | (# _, t #) -> t |
||
| − | </haskell> |
||
| + | * The function <code>putChar</code> expects a character, and returns an action which will output the given character. |
||
| − | It didn't work? Try this instead: |
||
| − | < |
+ | <br> |
| − | -- for GHC 8.6.5 |
||
| − | {-# LANGUAGE CPP #-} |
||
| − | #define during seq |
||
| − | module Sequential(seq) where |
||
| − | import qualified Prelude(during) |
||
| − | import GHC.Base(lazy) |
||
| + | Now for a few other I/O interfaces - if <code>seq</code> was actually sequential: |
||
| − | infixr 0 `seq` |
||
| − | seq :: a -> b -> b |
||
| − | seq x y = Prelude.during x (lazy y) |
||
| − | </haskell> |
||
| − | |||
| − | As for those extensions - they stay with each definition. |
||
| − | |||
| − | That still didn't work? Well, give this a try: |
||
| − | |||
| − | <haskell> |
||
| − | yet :: (a -> a) -> a |
||
| − | yet f = y where y = f y |
||
| − | </haskell> |
||
| − | |||
| − | Now that we're firmly on the topic of implementation details, did you notice how easy it was to define that allegedly ''warm, fuzzy''[3] <code>IO</code> type using this curious new <code>OI</code> type, and those primitives? |
||
| − | |||
| − | Sometimes that can be a hint that doing the opposite will be difficult or even impossible to do while staying within standard Haskell 2010. As it happens, this is one of those cases... |
||
| − | |||
| − | To define <code>OI</code>, <code>partOI</code>, <code>getchar</code> and <code>putchar</code> will require: |
||
| − | |||
| − | * modifying your preferred Haskell implementation - lots of work; |
||
| − | |||
| − | * using some other language for the definitions, with Haskell then calling the foreign code - extra work to deal with two different languages; |
||
| − | |||
| − | * using unsafe or implementation-specific primitives - work needed to avoid conflicts with Haskell semantics; |
||
| − | |||
| − | * using implementation-specific extensions - work needed to track relevant extensions, and possible conflicts with Haskell semantics. |
||
| − | |||
| − | For now, I'll just use the extensions - they're ugly, but at least they're contained, just like those alternate definitions of <code>seq</code>. But who knows - if this approach to I/O proves useful enough, it might make its way into a future Haskell standard...that's how <code>IO</code> happened[4]. |
||
| − | |||
| − | In the meantime, take a deep breath: |
||
| − | |||
| − | <haskell> |
||
| − | -- for GHC 8.6.5 |
||
| − | {-# LANGUAGE BangPatterns, MagicHash, UnboxedTuples #-} |
||
| − | module OutputInput(OI, runOI, seq, getchar, putchar) where |
||
| − | import Prelude(Char, String) |
||
| − | import Prelude(($), (++), putChar, getChar, error) |
||
| − | import Partible |
||
| − | import Sequential |
||
| − | import GHC.Base(IO(..), State#, MutVar#, RealWorld) |
||
| − | import GHC.Base(seq#, realWorld#, newMutVar#, atomicModifyMutVar#) |
||
| − | |||
| − | data OI = OI OI# |
||
| − | |||
| − | instance Partible OI where |
||
| − | part = partOI |
||
| − | |||
| − | partOI :: OI -> (OI, OI) |
||
| − | partOI (OI r) = case expire# "partOI" r realWorld# of |
||
| − | s -> case newMutVar# () s of |
||
| − | (# s', r1 #) -> |
||
| − | case newMutVar# () s' of |
||
| − | (# _, r2 #) -> (OI r1, OI r2) |
||
| − | |||
| − | runOI :: (OI -> a) -> IO a |
||
| − | runOI g = IO $ \s -> case newMutVar# () s of |
||
| − | (# s', r #) -> seq# (g (OI r)) s' |
||
| − | |||
| − | getchar :: OI -> Char |
||
| − | getchar (OI r) = case expire# "getchar" r realWorld# of |
||
| − | s -> case undo# getChar s of |
||
| − | (# _, c #) -> c |
||
| + | * [[Monad|monad]] |
||
| − | putchar :: Char -> OI -> () |
||
| − | putchar c (OI r) = case expire# "putchar" r realWorld# of |
||
| − | s -> case undo# (putChar c) s of |
||
| − | (# _, x #) -> x |
||
| + | :<haskell> |
||
| + | type M a = OI -> a |
||
| + | unit :: a -> M a |
||
| − | -- Local definitions |
||
| + | unit x = \ u -> let !_ = partOI u in x |
||
| − | -- |
||
| − | type OI# = MutVar# RealWorld () |
||
| − | + | bind :: M a -> (a -> M b) -> M b |
|
| + | bind m k = \ u -> let !(u1, u2) = partOI u in |
||
| − | expire# name r s = case atomicModifyMutVar# r flick s of |
||
| − | + | let !x = m u1 in |
|
| − | + | let !y = k x u2 in |
|
| − | + | y |
|
| − | flick x@() = (error nowUsed, x) |
||
| + | getcharM :: M Char |
||
| − | nowUsed = name ++ ": argument already used" |
||
| + | getcharM = getChar |
||
| + | putcharM :: Char -> M () |
||
| − | undo# :: IO a -> State# RealWorld -> (# State# RealWorld, a #) |
||
| + | putcharM = putChar |
||
| − | undo# (IO a) = a |
||
</haskell> |
</haskell> |
||
| + | * [[Comonad|comonad]]: |
||
| − | Now you can start breathing again :-) |
||
| − | <haskell> |
+ | :<haskell> |
| + | type C a = (OI, a) |
||
| − | module Partible where |
||
| + | extract :: C a -> a |
||
| − | class Partible a where |
||
| + | extract (u, x) = let !_ = partOI u in x |
||
| − | part :: a -> (a, a) |
||
| − | parts :: a -> [a] |
||
| + | duplicate :: C a -> C (C a) |
||
| − | -- Minimal complete definition: part or parts |
||
| + | duplicate (u, x) = let !(u1, u2) = partOI u in |
||
| − | part u = case parts u of u1:u2:_ -> (u1, u2) |
||
| − | + | (u2, (u1, x)) |
|
| − | </haskell> |
||
| + | extend :: (C a -> b) -> C a -> C b |
||
| − | If you remember, I dispensed with an up-front explanation to try something different. Now that you've |
||
| + | extend h (u, x) = let !(u1, u2) = partOI u in |
||
| − | seen just how different this all is, here's the explanation... |
||
| + | let !y = h (u1, x) in |
||
| + | (u2, y) |
||
| + | getcharC :: C () -> Char |
||
| − | That abstract <code>partOI</code> and its overloaded associates <code>part</code> and <code>parts</code>? They help an optimising Haskell implementation to determine when it's safe to use those optimisations. Consider this definition: |
||
| + | getcharC (u, ()) = getChar u |
||
| + | putcharC :: C Char -> () |
||
| − | <haskell> |
||
| + | putcharC (u, c) = putChar c u |
||
| − | testme n = n^2 + n^2 |
||
</haskell> |
</haskell> |
||
| + | * [[Arrow|arrow]]: |
||
| − | One simple optimisation would be to replace the duplicates of <code>n^2</code> with a single, shared local definition: |
||
| − | <haskell> |
+ | :<haskell> |
| − | + | type A b c = (OI -> b) -> (OI -> c) |
|
| − | </haskell> |
||
| + | arr :: (b -> c) -> A b c |
||
| − | This definition: |
||
| + | arr f = \ c' u -> let !x = c' u in f x |
||
| + | both :: A b c -> A b' c' -> A (b, b') (c, c') |
||
| − | <haskell> |
||
| + | f' `both` g' = \ c' u -> let !(u1:u2:u3:_) = partsOI u in |
||
| − | main' u = putchars "ha" u `seq` putchars "ha" u |
||
| + | let !(x, x') = c' u1 in |
||
| + | let !y = f' (unit x) u2 in |
||
| + | let !y' = g' (unit x') u3 in |
||
| + | (y, y') |
||
| + | where |
||
| + | unit x u = let !_ = partOI u in x |
||
| + | getcharA :: A () Char |
||
| − | </haskell> |
||
| + | getcharA = \ c' u -> let !(u1, u2) = partOI u in |
||
| + | let !_ = c' u1 in |
||
| + | let !ch = getChar u2 in |
||
| + | ch |
||
| + | putcharA :: A Char () |
||
| − | would likewise be rewritten, with the result being: |
||
| + | putcharA = \ c' u -> let !(u1, u2) = partOI u in |
||
| − | |||
| + | let !ch = c' u1 in |
||
| − | <haskell> |
||
| + | let !z = putChar ch u2 in |
||
| − | main' u = let x = putchars "ha" u in x `seq` x |
||
| + | z |
||
</haskell> |
</haskell> |
||
| + | The <code>OI</code> interface can also be used to implement [https://web.archive.org/web/20210414160729/https://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.91.3579&rep=rep1&type=pdf I/O models used in earlier versions] of Haskell: |
||
| − | but, as noted by Philip Wadler[5]: |
||
| + | * dialogues[https://www.haskell.org/definition/haskell-report-1.2.ps.gz <span></span>][https://dl.acm.org/doi/pdf/10.1145/130697.130699 <span></span>]: |
||
| − | <blockquote>''[...] the laugh is on us: the program prints only a single <code>"ha"</code>, at the time variable <br><code>x</code> is bound. In the presence of side effects, equational reasoning in its simplest form <br>becomes invalid.''</blockquote> |
||
| + | :<haskell> |
||
| − | ''Equational reasoning'' is the basis for that simple optimisation and many others in implementations like GHC - so far they've been serving us quite well. |
||
| + | runD :: ([Response] -> [Request]) -> OI -> () |
||
| + | runD d u = foldr (\ (!_) -> id) () $ yet $ \ l -> zipWith respond (d l) (partsOI u) |
||
| + | yet :: (a -> a) -> a |
||
| − | What - just treat I/O-centric definitions as some special case by modifying GHC? Haskell implementations like GHC are complicated enough as is! |
||
| + | yet f = f (yet f) |
||
| + | respond :: Request -> OI -> Response |
||
| − | The problem is being caused by the code being treated as though it's pure, so let's modify the code instead. In this case, the easiest solution is to make all calls to I/O-centric definitions unique: |
||
| + | respond Getq u = let !c = getChar u in Getp c |
||
| + | respond (Putq c) u = let !_ = putChar c u in Putp |
||
| + | data Request = Getq | Putq Char |
||
| − | <haskell> |
||
| + | data Response = Getp Char | Putp |
||
| − | main u = let !(u1, u2) = part u in |
||
| − | putchars "ha" u1 `seq` putchars "ha" u2 |
||
</haskell> |
</haskell> |
||
| + | * [[Continuation|continuations]]: |
||
| − | But what about: |
||
| − | <haskell> |
+ | :<haskell> |
| − | + | type Answer = OI -> () |
|
| + | runK :: Answer -> OI -> () |
||
| − | main' = oops (putchars "ha") (putchars "ha") |
||
| + | runK a u = a u |
||
| − | </haskell> |
||
| + | doneK :: Answer |
||
| − | Will the laugh be on us, again? |
||
| + | doneK = \ u -> let !_ = partOI u in () |
||
| + | getcharK :: (Char -> Answer) -> Answer |
||
| − | This is Haskell, not Clean[6] - there are no uniqueness types to help fend off such potentially-troublesome expressions. For now, the simplest way to make sure <code>OI</code> values are only used once is to have the implementation treat their reuse as being invalid e.g. by throwing an exception or raising an error to stop the offending program. |
||
| + | getcharK k = \ u -> let !(u1, u2) = partOI u in |
||
| + | let !c = getChar u1 in |
||
| + | let !a = k c in |
||
| + | a u2 |
||
| + | putcharK :: Char -> Answer -> Answer |
||
| − | In the prototype implementation, the maintenance of this all-important ''single-use'' property is performed by <code>expire#</code>. |
||
| + | putcharK c a = \ u -> let !(u1, u2) = partOI u in |
||
| − | |||
| + | let !_ = putChar c u1 in |
||
| − | Now for the much-maligned[7] <code>seq</code>...you could be tempted into avoiding its use by using a new data type: |
||
| + | a u2 |
||
| − | |||
| − | <haskell> |
||
| − | newtype Result a = Is a |
||
| − | |||
| − | getchar' :: OI -> Result Char |
||
| − | putchar' :: Char -> OI -> Result () |
||
</haskell> |
</haskell> |
||
| + | ...and even <i>that</i> <s><i>world</i></s> state-passing style used in GHC, and by [https://web.archive.org/web/20130607204300/https://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.17.935&rep=rep1&type=pdf Clean], [https://staff.science.uva.nl/c.u.grelck/publications/HerhSchoGrelDAMP09.pdf Single-Assignment C] and as part of the I/O model used for the verification of interactive programs in [https://cakeml.org/vstte18.pdf CakeML], remembering that <code>OI</code> values can only be used once: |
||
| − | and case-expressions: |
||
<haskell> |
<haskell> |
||
| + | newtype World = W OI |
||
| − | respond' :: Request -> OI -> Response |
||
| − | respond' Getq = \u -> case getchar' u of Is c -> Getp c |
||
| − | respond' (Putq c) = \u -> case putchar' c u of Is _ -> Putp |
||
| − | </haskell> |
||
| + | getcharL :: World -> (Char, World) |
||
| − | But before you succumb: |
||
| + | getcharL (W u) = let !(u1, u2) = partOI u in |
||
| + | let !c = getChar u1 in |
||
| + | (c, W u2) |
||
| + | putcharL :: Char -> World -> World |
||
| − | <haskell> |
||
| + | putcharL c (W u) = let !(u1, u2) = partOI u in |
||
| − | unit_Result :: a -> Result a |
||
| − | + | let !_ = putChar c u1 in |
|
| + | W u2 |
||
| − | |||
| − | bind_Result :: Result a -> (a -> Result b) -> Result b |
||
| − | bind_Result (Is x) k = k x |
||
</haskell> |
</haskell> |
||
| − | + | (Rewriting those examples to use <code>pseq</code> is left as an exercise.) |
|
| − | |||
| − | The bang-pattern extension? So you can instead write: |
||
| − | |||
| − | <haskell> |
||
| − | respond'' :: Request -> OI -> Response |
||
| − | respond'' Getq = \u -> let !c = getchar u in Getp c |
||
| − | respond'' (Putq c) = \u -> let !z = putchar c u in Putp |
||
| − | </haskell> |
||
| − | |||
| − | As you can see, <code>z</code> isn't used anywhere - there is no need for it. This being Haskell, if it isn't needed, it isn't evaluated - that allows implementations like GHC to rewrite a definition like <code>respond''</code> as: |
||
| − | |||
| − | <haskell> |
||
| − | respond'' :: Request -> OI -> Response |
||
| − | respond'' Getq = \u -> let !c = getchar u in Getp c |
||
| − | respond'' (Putq c) = \u -> Putp |
||
| − | </haskell> |
||
| − | |||
| − | You could try all manner of ways to avoid using <code>seq</code> - you might even find one that you like; all well and good...but others might not. For me, the simplest way I've found to make this approach to I/O work is with <code>seq</code> - one that's actually sequential. |
||
| − | |||
| − | But maybe - after all that - you still want <code>seq</code> banished from Haskell. Perhaps you still don't understand I/O in Haskell. It could be that you're dismayed by what you've read here. Alternately, you may have seen or tried this all before, and know it doesn't work - darn... |
||
| − | |||
| − | If that's you, the corresponding language proposal[8] has a list of other articles and research papers I've found which describe or refer to other approaches - perhaps one (or more) of them will be more acceptable. |
||
| − | |||
| − | As noted by Owen Stephens[9]: |
||
| − | |||
| − | <blockquote>''I/O is not a particularly active area of research, but new approaches are still being discovered, <br>iteratees being a case in point.''</blockquote> |
||
| − | |||
| − | Who knows - the Haskell language could return to having a pure, fully-defined approach to I/O...and it could be you that finds it :-D |
||
| − | |||
| − | |||
| − | P.S: Why the name <code>OI</code>? Many years ago I was tinkering with arrows for performing I/O, labelling them <code>OI a b</code> out of expediency. More recently, I discovered a set of slides[10] describing another approach to I/O which used values of type <code>OI a</code> in a similar fashion to what I've been describing here. I've reused the name because of that similarity. |
||
| − | |||
| − | |||
| − | References: |
||
| − | |||
| − | [1] [[Sequential ordering of evaluation]]; Haskell Wiki.<br> |
||
| − | |||
| − | [2] [https://gitlab.haskell.org/ghc/ghc/-/issues/5129 Ticket# 5129: "evaluate" optimized away]; GHC bug tracker.<br> |
||
| − | |||
| − | [3] [https://www.cs.nott.ac.uk/~pszgmh/appsem-slides/peytonjones.ppt Wearing the hair shirt: a retrospective on Haskell]; Simon Peyton Jones.<br> |
||
| − | |||
| − | [4] [https://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.168.4008&rep=rep1&type=pdf A History of Haskell: being lazy with class]; Paul Hudak, John Hughes, Simon Peyton Jones and Philip Wadler.<br> |
||
| − | |||
| − | [5] [https://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.91.3579&rep=rep1&type=pdf How to Declare an Imperative]; Philip Wadler.<br> |
||
| − | |||
| − | [6] [https://clean.cs.ru.nl/Clean The Clean homepage]; Radboud University, Nijmegen, The Netherlands.<br> |
||
| − | |||
| − | [7] [https://mail.haskell.org/pipermail/haskell/2002-May/009622.html Thread: State monads don't respect the monad laws in Haskell]; Haskell mail archive.<br> |
||
| − | |||
| − | [8] [[Partibles for composing monads]]; Haskell Wiki.<br> |
||
| − | |||
| − | [9] [https://www.owenstephens.co.uk/assets/static/research/masters_report.pdf Approaches to Functional I/O]; Owen Stephens.<br> |
||
| + | See also: |
||
| − | [10] <span style="color:#ba0000">Non-Imperative Functional Programming</span>; Nobuo Yamashita.<br> |
||
| + | * [[Plainly partible]] |
||
| + | * [[Disposing of dismissives]] |
||
| + | * [[IO then abstraction]] |
||
| + | [[Category:Theoretical foundations]] |
||
| − | [[User:Atravers|Atravers]] 03:05, 20 August 2020 (UTC) |
||
Latest revision as of 22:02, 16 September 2024
Regarding IO a, Haskell's monadic I/O type:
Some operations are primitive actions, corresponding to conventional I/O operations. Special operations (methods in the class
Monad, see Section 6.3.6) sequentially compose actions, corresponding to sequencing operators (such as the semicolon) in imperative languages.
- The Haskell 2010 Report, (page 107 of 329).
So for I/O, the monadic interface merely provides an abstract way to sequence its actions. However there is another, more direct approach to sequencing:
Control.Parallel.pseq :: a -> b -> b
(as opposed to the non-sequential Prelude.seq.) That means a more direct way of preserving referential transparency is also needed. For simple teletype I/O:
data OI
partOI :: OI -> (OI, OI)
getChar :: OI -> Char
putChar :: Char -> OI -> ()
where:
OIisn't an ordinary Haskell type - ordinary Haskell types represent values without (externally-visible) side-effects, henceOIbeing abstract.
- The action
partOIis needed because eachOIvalue can only be used once.
- The action
getCharobtains the the next character of input.
- The function
putCharexpects a character, and returns an action which will output the given character.
Now for a few other I/O interfaces - if seq was actually sequential:
type M a = OI -> a unit :: a -> M a unit x = \ u -> let !_ = partOI u in x bind :: M a -> (a -> M b) -> M b bind m k = \ u -> let !(u1, u2) = partOI u in let !x = m u1 in let !y = k x u2 in y getcharM :: M Char getcharM = getChar putcharM :: Char -> M () putcharM = putChar
type C a = (OI, a) extract :: C a -> a extract (u, x) = let !_ = partOI u in x duplicate :: C a -> C (C a) duplicate (u, x) = let !(u1, u2) = partOI u in (u2, (u1, x)) extend :: (C a -> b) -> C a -> C b extend h (u, x) = let !(u1, u2) = partOI u in let !y = h (u1, x) in (u2, y) getcharC :: C () -> Char getcharC (u, ()) = getChar u putcharC :: C Char -> () putcharC (u, c) = putChar c u
type A b c = (OI -> b) -> (OI -> c) arr :: (b -> c) -> A b c arr f = \ c' u -> let !x = c' u in f x both :: A b c -> A b' c' -> A (b, b') (c, c') f' `both` g' = \ c' u -> let !(u1:u2:u3:_) = partsOI u in let !(x, x') = c' u1 in let !y = f' (unit x) u2 in let !y' = g' (unit x') u3 in (y, y') where unit x u = let !_ = partOI u in x getcharA :: A () Char getcharA = \ c' u -> let !(u1, u2) = partOI u in let !_ = c' u1 in let !ch = getChar u2 in ch putcharA :: A Char () putcharA = \ c' u -> let !(u1, u2) = partOI u in let !ch = c' u1 in let !z = putChar ch u2 in z
The OI interface can also be used to implement I/O models used in earlier versions of Haskell:
runD :: ([Response] -> [Request]) -> OI -> () runD d u = foldr (\ (!_) -> id) () $ yet $ \ l -> zipWith respond (d l) (partsOI u) yet :: (a -> a) -> a yet f = f (yet f) respond :: Request -> OI -> Response respond Getq u = let !c = getChar u in Getp c respond (Putq c) u = let !_ = putChar c u in Putp data Request = Getq | Putq Char data Response = Getp Char | Putp
type Answer = OI -> () runK :: Answer -> OI -> () runK a u = a u doneK :: Answer doneK = \ u -> let !_ = partOI u in () getcharK :: (Char -> Answer) -> Answer getcharK k = \ u -> let !(u1, u2) = partOI u in let !c = getChar u1 in let !a = k c in a u2 putcharK :: Char -> Answer -> Answer putcharK c a = \ u -> let !(u1, u2) = partOI u in let !_ = putChar c u1 in a u2
...and even that world state-passing style used in GHC, and by Clean, Single-Assignment C and as part of the I/O model used for the verification of interactive programs in CakeML, remembering that OI values can only be used once:
newtype World = W OI
getcharL :: World -> (Char, World)
getcharL (W u) = let !(u1, u2) = partOI u in
let !c = getChar u1 in
(c, W u2)
putcharL :: Char -> World -> World
putcharL c (W u) = let !(u1, u2) = partOI u in
let !_ = putChar c u1 in
W u2
(Rewriting those examples to use pseq is left as an exercise.)
See also: