{-# LANGUAGE OverloadedStrings #-}
-- |
-- Module       : Data.ByteString.Base16.Lazy
-- Copyright 	: (c) 2020 Emily Pillmore
-- License	: BSD-style
--
-- Maintainer	: Emily Pillmore <emilypi@cohomolo.gy>
-- Stability	: Experimental
-- Portability	: portable
--
-- This module contains the combinators implementing the
-- RFC 4648 specification for the Base16 encoding including
-- unpadded and lenient variants for lazy bytestrings
--
module Data.ByteString.Lazy.Base16
( encodeBase16
, encodeBase16'
, decodeBase16
, decodeBase16Lenient
, isBase16
, isValidBase16
) where


import Prelude hiding (all, elem)

import qualified Data.ByteString as B
import Data.ByteString.Lazy (all, elem, fromChunks, toChunks)
import Data.ByteString.Lazy.Internal (ByteString(..))
import qualified Data.ByteString.Base16.Internal.Head as B16
import Data.ByteString.Base16.Internal.Utils (reChunk)
import Data.Either
import qualified Data.Text as T
import Data.Text.Lazy (Text)
import qualified Data.Text.Lazy.Encoding as TL


-- | Encode a lazy 'ByteString' value as Base16 'Text' with padding.
--
-- See: <https://tools.ietf.org/html/rfc4648#section-8 RFC-4648 section 8>
--
encodeBase16 :: ByteString -> Text
encodeBase16 :: ByteString -> Text
encodeBase16 = ByteString -> Text
TL.decodeUtf8 (ByteString -> Text)
-> (ByteString -> ByteString) -> ByteString -> Text
forall b c a. (b -> c) -> (a -> b) -> a -> c
. ByteString -> ByteString
encodeBase16'
{-# INLINE encodeBase16 #-}

-- | Encode a lazy 'ByteString' value as a Base16 'ByteString'  value with padding.
--
-- See: <https://tools.ietf.org/html/rfc4648#section-8 RFC-4648 section 8>
--
encodeBase16' :: ByteString -> ByteString
encodeBase16' :: ByteString -> ByteString
encodeBase16' ByteString
Empty = ByteString
Empty
encodeBase16' (Chunk ByteString
b ByteString
bs) = ByteString -> ByteString -> ByteString
Chunk (ByteString -> ByteString
B16.encodeBase16_ ByteString
b) (ByteString -> ByteString
encodeBase16' ByteString
bs)
{-# INLINE encodeBase16' #-}

-- | Decode a padded Base16-encoded lazy 'ByteString' value.
--
-- See: <https://tools.ietf.org/html/rfc4648#section-8 RFC-4648 section 8>
--
decodeBase16 :: ByteString -> Either T.Text ByteString
decodeBase16 :: ByteString -> Either Text ByteString
decodeBase16 ByteString
Empty = ByteString -> Either Text ByteString
forall a b. b -> Either a b
Right ByteString
Empty
decodeBase16 (Chunk ByteString
b ByteString
bs) = ByteString -> ByteString -> ByteString
Chunk (ByteString -> ByteString -> ByteString)
-> Either Text ByteString -> Either Text (ByteString -> ByteString)
forall (f :: * -> *) a b. Functor f => (a -> b) -> f a -> f b
<$> ByteString -> Either Text ByteString
B16.decodeBase16_ ByteString
b Either Text (ByteString -> ByteString)
-> Either Text ByteString -> Either Text ByteString
forall (f :: * -> *) a b. Applicative f => f (a -> b) -> f a -> f b
<*> ByteString -> Either Text ByteString
decodeBase16 ByteString
bs
{-# INLINE decodeBase16 #-}

-- | Decode a Base16-encoded 'ByteString' value leniently, using a
-- strategy that never fails
--
-- N.B.: this is not RFC 4648-compliant. It may give you garbage if you're not careful!
--
decodeBase16Lenient :: ByteString -> ByteString
decodeBase16Lenient :: ByteString -> ByteString
decodeBase16Lenient = [ByteString] -> ByteString
fromChunks
  ([ByteString] -> ByteString)
-> (ByteString -> [ByteString]) -> ByteString -> ByteString
forall b c a. (b -> c) -> (a -> b) -> a -> c
. (ByteString -> ByteString) -> [ByteString] -> [ByteString]
forall (f :: * -> *) a b. Functor f => (a -> b) -> f a -> f b
fmap ByteString -> ByteString
B16.decodeBase16Lenient_
  ([ByteString] -> [ByteString])
-> (ByteString -> [ByteString]) -> ByteString -> [ByteString]
forall b c a. (b -> c) -> (a -> b) -> a -> c
. [ByteString] -> [ByteString]
reChunk
  ([ByteString] -> [ByteString])
-> (ByteString -> [ByteString]) -> ByteString -> [ByteString]
forall b c a. (b -> c) -> (a -> b) -> a -> c
. (ByteString -> ByteString) -> [ByteString] -> [ByteString]
forall (f :: * -> *) a b. Functor f => (a -> b) -> f a -> f b
fmap ((Word8 -> Bool) -> ByteString -> ByteString
B.filter ((Word8 -> ByteString -> Bool) -> ByteString -> Word8 -> Bool
forall a b c. (a -> b -> c) -> b -> a -> c
flip Word8 -> ByteString -> Bool
elem ByteString
"0123456789abcdef"))
  ([ByteString] -> [ByteString])
-> (ByteString -> [ByteString]) -> ByteString -> [ByteString]
forall b c a. (b -> c) -> (a -> b) -> a -> c
. ByteString -> [ByteString]
toChunks
{-# INLINE decodeBase16Lenient #-}

-- | Tell whether a lazy 'ByteString' value is base16 encoded.
--
-- Examples:
--
-- This example will fail. It conforms to the alphabet, but
-- is not valid because it has an incorrect (odd) length.
--
-- >>> isBase16 "666f6"
-- False
--
-- This example will succeed because it satisfies the alphabet
-- and is considered "valid" (i.e. of the correct size and shape).
--
-- >>> isBase16 "666f"
-- True
--
isBase16 :: ByteString -> Bool
isBase16 :: ByteString -> Bool
isBase16 ByteString
bs = ByteString -> Bool
isValidBase16 ByteString
bs Bool -> Bool -> Bool
&& Either Text ByteString -> Bool
forall a b. Either a b -> Bool
isRight (ByteString -> Either Text ByteString
decodeBase16 ByteString
bs)
{-# INLINE isBase16 #-}

-- | Tell whether a lazy 'ByteString' value is a valid Base16 format.
--
-- This will not tell you whether or not this is a correct Base16 representation,
-- only that it conforms to the correct alphabet. To check whether it is a true
-- Base16 encoded 'ByteString' value, use 'isBase16'.
--
-- Examples:
--
-- This example will fail because it does not conform to the Hex
-- alphabet.
--
-- >>> isValidBase16 "666f+/6"
-- False
--
-- This example will succeed because it satisfies the alphabet
-- and is considered "valid" (i.e. of the correct size and shape), but
-- is not correct base16 because it is the wrong shape.
--
-- >>> isValidBase16 "666f6"
-- True
--
isValidBase16 :: ByteString -> Bool
isValidBase16 :: ByteString -> Bool
isValidBase16 = (Word8 -> Bool) -> ByteString -> Bool
all ((Word8 -> ByteString -> Bool) -> ByteString -> Word8 -> Bool
forall a b c. (a -> b -> c) -> b -> a -> c
flip Word8 -> ByteString -> Bool
elem ByteString
"0123456789abcdef")
{-# INLINE isValidBase16 #-}