{-# LANGUAGE UndecidableInstances #-}
{-# LANGUAGE AllowAmbiguousTypes #-}

{- | Magic numbers (also just magic): short constant bytestrings usually
     found at the top of a file, often used as an early sanity check.

TODO unassociated type fams bad (maybe). turn into class -- and turn the reifier
into a default method! (TODO think about this)

There are two main flavors of magics:

  * "random" bytes e.g. Zstandard: @28 B5 2F FD@
  * printable ASCII bytes e.g. Ogg: @4F 67 67 53@ -> OggS

For bytewise magics, use type-level 'Natural' lists.
For ASCII magics, use 'Symbol's (type-level strings).

Previously, I squashed these into a representationally-safe type. Now the check
only occurs during reification. So you are able to define invalid magics now
(bytes over 255, non-ASCII characters), and potentially use them, but you'll get
a clear type error like "no instance for ByteVal 256" when attempting to reify.

String magics are restricted to ASCII, and will type error during reification
otherwise. If you really want UTF-8, please read 'Binrep.Type.Magic.UTF8'.
-}

module Binrep.Type.Magic where

import Binrep
import Binrep.Type.Byte

import GHC.TypeLits
import Data.ByteString qualified as B
import FlatParse.Basic qualified as FP

import GHC.Generics ( Generic )
import Data.Data ( Data )

import Mason.Builder qualified as Mason

import Strongweak

-- | An empty data type representing a magic number (a constant bytestring) via
--   a phantom type.
--
-- The phantom type variable unambiguously defines a short, constant bytestring.
-- A handful of types are supported for using magics conveniently, e.g. for pure
-- ASCII magics, you may use a 'Symbol' type-level string.
data Magic (a :: k) = Magic
    deriving stock (forall a.
(forall x. a -> Rep a x) -> (forall x. Rep a x -> a) -> Generic a
forall k (a :: k) x. Rep (Magic a) x -> Magic a
forall k (a :: k) x. Magic a -> Rep (Magic a) x
$cto :: forall k (a :: k) x. Rep (Magic a) x -> Magic a
$cfrom :: forall k (a :: k) x. Magic a -> Rep (Magic a) x
Generic, Magic a -> DataType
Magic a -> Constr
forall a.
Typeable a
-> (forall (c :: * -> *).
    (forall d b. Data d => c (d -> b) -> d -> c b)
    -> (forall g. g -> c g) -> a -> c a)
-> (forall (c :: * -> *).
    (forall b r. Data b => c (b -> r) -> c r)
    -> (forall r. r -> c r) -> Constr -> c a)
-> (a -> Constr)
-> (a -> DataType)
-> (forall (t :: * -> *) (c :: * -> *).
    Typeable t =>
    (forall d. Data d => c (t d)) -> Maybe (c a))
-> (forall (t :: * -> * -> *) (c :: * -> *).
    Typeable t =>
    (forall d e. (Data d, Data e) => c (t d e)) -> Maybe (c a))
-> ((forall b. Data b => b -> b) -> a -> a)
-> (forall r r'.
    (r -> r' -> r) -> r -> (forall d. Data d => d -> r') -> a -> r)
-> (forall r r'.
    (r' -> r -> r) -> r -> (forall d. Data d => d -> r') -> a -> r)
-> (forall u. (forall d. Data d => d -> u) -> a -> [u])
-> (forall u. Int -> (forall d. Data d => d -> u) -> a -> u)
-> (forall (m :: * -> *).
    Monad m =>
    (forall d. Data d => d -> m d) -> a -> m a)
-> (forall (m :: * -> *).
    MonadPlus m =>
    (forall d. Data d => d -> m d) -> a -> m a)
-> (forall (m :: * -> *).
    MonadPlus m =>
    (forall d. Data d => d -> m d) -> a -> m a)
-> Data a
forall {k} {a :: k}. (Typeable a, Typeable k) => Typeable (Magic a)
forall k (a :: k). (Typeable a, Typeable k) => Magic a -> DataType
forall k (a :: k). (Typeable a, Typeable k) => Magic a -> Constr
forall k (a :: k).
(Typeable a, Typeable k) =>
(forall b. Data b => b -> b) -> Magic a -> Magic a
forall k (a :: k) u.
(Typeable a, Typeable k) =>
Int -> (forall d. Data d => d -> u) -> Magic a -> u
forall k (a :: k) u.
(Typeable a, Typeable k) =>
(forall d. Data d => d -> u) -> Magic a -> [u]
forall k (a :: k) r r'.
(Typeable a, Typeable k) =>
(r -> r' -> r)
-> r -> (forall d. Data d => d -> r') -> Magic a -> r
forall k (a :: k) r r'.
(Typeable a, Typeable k) =>
(r' -> r -> r)
-> r -> (forall d. Data d => d -> r') -> Magic a -> r
forall k (a :: k) (m :: * -> *).
(Typeable a, Typeable k, Monad m) =>
(forall d. Data d => d -> m d) -> Magic a -> m (Magic a)
forall k (a :: k) (m :: * -> *).
(Typeable a, Typeable k, MonadPlus m) =>
(forall d. Data d => d -> m d) -> Magic a -> m (Magic a)
forall k (a :: k) (c :: * -> *).
(Typeable a, Typeable k) =>
(forall b r. Data b => c (b -> r) -> c r)
-> (forall r. r -> c r) -> Constr -> c (Magic a)
forall k (a :: k) (c :: * -> *).
(Typeable a, Typeable k) =>
(forall d b. Data d => c (d -> b) -> d -> c b)
-> (forall g. g -> c g) -> Magic a -> c (Magic a)
forall k (a :: k) (t :: * -> *) (c :: * -> *).
(Typeable a, Typeable k, Typeable t) =>
(forall d. Data d => c (t d)) -> Maybe (c (Magic a))
forall k (a :: k) (t :: * -> * -> *) (c :: * -> *).
(Typeable a, Typeable k, Typeable t) =>
(forall d e. (Data d, Data e) => c (t d e)) -> Maybe (c (Magic a))
forall (c :: * -> *).
(forall b r. Data b => c (b -> r) -> c r)
-> (forall r. r -> c r) -> Constr -> c (Magic a)
forall (c :: * -> *).
(forall d b. Data d => c (d -> b) -> d -> c b)
-> (forall g. g -> c g) -> Magic a -> c (Magic a)
gmapMo :: forall (m :: * -> *).
MonadPlus m =>
(forall d. Data d => d -> m d) -> Magic a -> m (Magic a)
$cgmapMo :: forall k (a :: k) (m :: * -> *).
(Typeable a, Typeable k, MonadPlus m) =>
(forall d. Data d => d -> m d) -> Magic a -> m (Magic a)
gmapMp :: forall (m :: * -> *).
MonadPlus m =>
(forall d. Data d => d -> m d) -> Magic a -> m (Magic a)
$cgmapMp :: forall k (a :: k) (m :: * -> *).
(Typeable a, Typeable k, MonadPlus m) =>
(forall d. Data d => d -> m d) -> Magic a -> m (Magic a)
gmapM :: forall (m :: * -> *).
Monad m =>
(forall d. Data d => d -> m d) -> Magic a -> m (Magic a)
$cgmapM :: forall k (a :: k) (m :: * -> *).
(Typeable a, Typeable k, Monad m) =>
(forall d. Data d => d -> m d) -> Magic a -> m (Magic a)
gmapQi :: forall u. Int -> (forall d. Data d => d -> u) -> Magic a -> u
$cgmapQi :: forall k (a :: k) u.
(Typeable a, Typeable k) =>
Int -> (forall d. Data d => d -> u) -> Magic a -> u
gmapQ :: forall u. (forall d. Data d => d -> u) -> Magic a -> [u]
$cgmapQ :: forall k (a :: k) u.
(Typeable a, Typeable k) =>
(forall d. Data d => d -> u) -> Magic a -> [u]
gmapQr :: forall r r'.
(r' -> r -> r)
-> r -> (forall d. Data d => d -> r') -> Magic a -> r
$cgmapQr :: forall k (a :: k) r r'.
(Typeable a, Typeable k) =>
(r' -> r -> r)
-> r -> (forall d. Data d => d -> r') -> Magic a -> r
gmapQl :: forall r r'.
(r -> r' -> r)
-> r -> (forall d. Data d => d -> r') -> Magic a -> r
$cgmapQl :: forall k (a :: k) r r'.
(Typeable a, Typeable k) =>
(r -> r' -> r)
-> r -> (forall d. Data d => d -> r') -> Magic a -> r
gmapT :: (forall b. Data b => b -> b) -> Magic a -> Magic a
$cgmapT :: forall k (a :: k).
(Typeable a, Typeable k) =>
(forall b. Data b => b -> b) -> Magic a -> Magic a
dataCast2 :: forall (t :: * -> * -> *) (c :: * -> *).
Typeable t =>
(forall d e. (Data d, Data e) => c (t d e)) -> Maybe (c (Magic a))
$cdataCast2 :: forall k (a :: k) (t :: * -> * -> *) (c :: * -> *).
(Typeable a, Typeable k, Typeable t) =>
(forall d e. (Data d, Data e) => c (t d e)) -> Maybe (c (Magic a))
dataCast1 :: forall (t :: * -> *) (c :: * -> *).
Typeable t =>
(forall d. Data d => c (t d)) -> Maybe (c (Magic a))
$cdataCast1 :: forall k (a :: k) (t :: * -> *) (c :: * -> *).
(Typeable a, Typeable k, Typeable t) =>
(forall d. Data d => c (t d)) -> Maybe (c (Magic a))
dataTypeOf :: Magic a -> DataType
$cdataTypeOf :: forall k (a :: k). (Typeable a, Typeable k) => Magic a -> DataType
toConstr :: Magic a -> Constr
$ctoConstr :: forall k (a :: k). (Typeable a, Typeable k) => Magic a -> Constr
gunfold :: forall (c :: * -> *).
(forall b r. Data b => c (b -> r) -> c r)
-> (forall r. r -> c r) -> Constr -> c (Magic a)
$cgunfold :: forall k (a :: k) (c :: * -> *).
(Typeable a, Typeable k) =>
(forall b r. Data b => c (b -> r) -> c r)
-> (forall r. r -> c r) -> Constr -> c (Magic a)
gfoldl :: forall (c :: * -> *).
(forall d b. Data d => c (d -> b) -> d -> c b)
-> (forall g. g -> c g) -> Magic a -> c (Magic a)
$cgfoldl :: forall k (a :: k) (c :: * -> *).
(Typeable a, Typeable k) =>
(forall d b. Data d => c (d -> b) -> d -> c b)
-> (forall g. g -> c g) -> Magic a -> c (Magic a)
Data, Int -> Magic a -> ShowS
forall a.
(Int -> a -> ShowS) -> (a -> String) -> ([a] -> ShowS) -> Show a
forall k (a :: k). Int -> Magic a -> ShowS
forall k (a :: k). [Magic a] -> ShowS
forall k (a :: k). Magic a -> String
showList :: [Magic a] -> ShowS
$cshowList :: forall k (a :: k). [Magic a] -> ShowS
show :: Magic a -> String
$cshow :: forall k (a :: k). Magic a -> String
showsPrec :: Int -> Magic a -> ShowS
$cshowsPrec :: forall k (a :: k). Int -> Magic a -> ShowS
Show, Magic a -> Magic a -> Bool
forall a. (a -> a -> Bool) -> (a -> a -> Bool) -> Eq a
forall k (a :: k). Magic a -> Magic a -> Bool
/= :: Magic a -> Magic a -> Bool
$c/= :: forall k (a :: k). Magic a -> Magic a -> Bool
== :: Magic a -> Magic a -> Bool
$c== :: forall k (a :: k). Magic a -> Magic a -> Bool
Eq)

-- | Weaken a 'Magic a' to the unit. Perhaps you prefer pattern matching on @()@
--   over @Magic@, or wish a weak type to be fully divorced from its binrep
--   origins.
instance Weaken (Magic a) where
    type Weak (Magic a) = ()
    weaken :: Magic a -> Weak (Magic a)
weaken Magic a
_ = ()

-- | Strengthen the unit to some 'Magic a'.
instance Strengthen (Magic a) where
    strengthen :: Weak (Magic a) -> Validation (NonEmpty StrengthenFail) (Magic a)
strengthen Weak (Magic a)
_ = forall (f :: * -> *) a. Applicative f => a -> f a
pure forall k (a :: k). Magic a
Magic

instance (KnownNat (Length (MagicBytes a))) => BLen (Magic a) where
    type CBLen (Magic a) = Length (MagicBytes a)

instance (bs ~ MagicBytes a, ReifyBytes bs) => Put (Magic a) where
    put :: Magic a -> Builder
put Magic a
Magic = forall (ns :: [Natural]). ReifyBytes ns => Builder
reifyBytes @bs

instance (bs ~ MagicBytes a, ReifyBytes bs) => Get (Magic a) where
    get :: Getter (Magic a)
get = do
        let expected :: ByteString
expected = Builder -> ByteString
Mason.toStrictByteString forall a b. (a -> b) -> a -> b
$ forall (ns :: [Natural]). ReifyBytes ns => Builder
reifyBytes @bs
        ByteString
actual <- forall e. Int -> Parser e ByteString
FP.takeBs forall a b. (a -> b) -> a -> b
$ ByteString -> Int
B.length ByteString
expected
        if   ByteString
actual forall a. Eq a => a -> a -> Bool
== ByteString
expected
        then forall (m :: * -> *) a. Monad m => a -> m a
return forall k (a :: k). Magic a
Magic
        else forall a. EBase -> Getter a
eBase forall a b. (a -> b) -> a -> b
$ ByteString -> ByteString -> EBase
EExpected ByteString
expected ByteString
actual

{-
I do lots of functions on lists, because they're structurally simple. But you
can't pass type-level functions as arguments between type families. singletons
solves a related (?) problem using defunctionalization, where you manually write
out the function applications or something. Essentially, you can't do this:

    type family Map (f :: x -> y) (a :: [x]) :: [y] where
        Map _ '[]       = '[]
        Map f (a ': as) = f a ': Map f as

So you have to write that out for every concrete function over lists.
-}

type family SymbolUnicodeCodepoints (a :: Symbol) :: [Natural] where
    SymbolUnicodeCodepoints a = CharListUnicodeCodepoints (SymbolAsCharList a)

type family CharListUnicodeCodepoints (a :: [Char]) :: [Natural] where
    CharListUnicodeCodepoints '[]       = '[]
    CharListUnicodeCodepoints (c ': cs) = CharToNat c ': CharListUnicodeCodepoints cs

type family SymbolAsCharList (a :: Symbol) :: [Char] where
    SymbolAsCharList a = SymbolAsCharList' (UnconsSymbol a)

type family SymbolAsCharList' (a :: Maybe (Char, Symbol)) :: [Char] where
    SymbolAsCharList' 'Nothing = '[]
    SymbolAsCharList' ('Just '(c, s)) = c ': SymbolAsCharList' (UnconsSymbol s)

--------------------------------------------------------------------------------

-- | Types which define a magic value.
class Magical (a :: k) where
    -- | How to turn the type into a list of bytes.
    type MagicBytes a :: [Natural]

-- | Type-level naturals go as-is. (Make sure you don't go over 255, though!)
instance Magical (ns :: [Natural]) where
    type MagicBytes ns = ns

-- | Type-level symbols are turned into their Unicode codepoints - but
--   multibyte characters aren't handled, so they'll simply be overlarge bytes,
--   which will fail further down.
instance Magical (sym :: Symbol) where
    type MagicBytes sym = SymbolUnicodeCodepoints sym