{-# LANGUAGE BangPatterns #-}
{-# LANGUAGE MultiWayIf #-}
{-# LANGUAGE TypeApplications #-}
-- |
-- Module       : Data.ByteString.Base64.Internal.W32.Loop
-- Copyright    : (c) 2019-2020 Emily Pillmore
-- License      : BSD-style
--
-- Maintainer   : Emily Pillmore <emilypi@cohomolo.gy>
-- Stability    : Experimental
-- Portability  : portable
--
-- 'Word32'-optimized inner loop
--
module Data.ByteString.Base64.Internal.W32.Loop
( innerLoop
, decodeLoop
, lenientLoop
) where


import Data.Bits
import Data.ByteString.Internal
import Data.ByteString.Base64.Internal.Utils
import qualified Data.ByteString.Base64.Internal.W16.Loop as W16
import Data.Text (Text)

import Foreign.ForeignPtr
import Foreign.Ptr
import Foreign.Storable

import GHC.Word


-- | Encoding inner loop. Packs 3 bytes from src pointer into
-- the first 6 bytes of 4 'Word8''s (using the encoding table,
-- as 2 'Word12''s ), writing these to the dst pointer.
--
innerLoop
    :: Ptr Word16
    -> Ptr Word32
    -> Ptr Word32
    -> Ptr Word32
    -> (Ptr Word8 -> Ptr Word8 -> IO ByteString)
    -> IO ByteString
innerLoop !etable !sptr !dptr !end finish = go sptr dptr
  where
    go !src !dst
      | plusPtr src 3 >= end =
        W16.innerLoop etable (castPtr src) (castPtr dst) (castPtr end) finish
      | otherwise = do
        !w <- peekWord32BE src

        let !a = unsafeShiftR w 20
            !b = unsafeShiftR w 8

        !x <- w32_16 <$> peekElemOff etable (fromIntegral a)
        !y <- w32_16 <$> peekElemOff etable (fromIntegral b)

        let !z = x .|. (unsafeShiftL y 16)
        poke dst (fromIntegral z)

        go (plusPtr src 3) (plusPtr dst 4)
    {-# INLINE go #-}
{-# INLINE innerLoop #-}

decodeLoop
    :: Ptr Word8
    -> Ptr Word8
        -- ^ src pointer
    -> Ptr Word8
        -- ^ dst pointer
    -> Ptr Word8
        -- ^ end of src ptr
    -> (Ptr Word8 -> Ptr Word8 -> IO (Either Text ByteString))
    -> IO (Either Text ByteString)
decodeLoop = W16.decodeLoop
{-# INLINE decodeLoop #-}

lenientLoop
    :: Ptr Word8
        -- ^ decode lookup table
    -> Ptr Word8
        -- ^ src pointer
    -> Ptr Word8
        -- ^ dst pointer
    -> Ptr Word8
        -- ^ end of src ptr
    -> ForeignPtr Word8
        -- ^ dst foreign ptr (for consing bs)
    -> IO ByteString
lenientLoop = W16.lenientLoop