{-# LANGUAGE OverloadedStrings #-}
-- |
-- Module       : Data.Text.Encoding.Base64
-- Copyright 	: (c) 2019-2020 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 Base64 encoding including
-- unpadded and lenient variants
--
module Data.Text.Encoding.Base64
( encodeBase64
, decodeBase64
, decodeBase64With
, decodeBase64Lenient
, isBase64
, isValidBase64
) where


import Data.Bifunctor (first)
import Data.ByteString (ByteString)
import qualified Data.ByteString.Base64 as B64

import Data.Text (Text)
import qualified Data.Text.Encoding as T
import Data.Text.Encoding.Base64.Error

-- | Encode a 'Text' value in Base64 with padding.
--
-- See: <https://tools.ietf.org/html/rfc4648#section-4 RFC-4648 section 4>
--
encodeBase64 :: Text -> Text
encodeBase64 :: Text -> Text
encodeBase64 = ByteString -> Text
B64.encodeBase64 (ByteString -> Text) -> (Text -> ByteString) -> Text -> Text
forall b c a. (b -> c) -> (a -> b) -> a -> c
. Text -> ByteString
T.encodeUtf8
{-# INLINE encodeBase64 #-}

-- | Decode a padded Base64-encoded 'Text' value.
--
-- /Note:/ This function makes sure that decoding is total by deferring to
-- 'T.decodeLatin1'. This will always round trip for any valid Base64-encoded
-- text value, but it may not round trip for bad inputs. The onus is on the
-- caller to make sure inputs are valid. If unsure, defer to `decodeBase64With`
-- and pass in a custom decode function.
--
-- See: <https://tools.ietf.org/html/rfc4648#section-4 RFC-4648 section 4>
--
decodeBase64 :: Text -> Either Text Text
decodeBase64 :: Text -> Either Text Text
decodeBase64 = (ByteString -> Text) -> Either Text ByteString -> Either Text Text
forall (f :: * -> *) a b. Functor f => (a -> b) -> f a -> f b
fmap ByteString -> Text
T.decodeLatin1 (Either Text ByteString -> Either Text Text)
-> (Text -> Either Text ByteString) -> Text -> Either Text Text
forall b c a. (b -> c) -> (a -> b) -> a -> c
. ByteString -> Either Text ByteString
B64.decodeBase64 (ByteString -> Either Text ByteString)
-> (Text -> ByteString) -> Text -> Either Text ByteString
forall b c a. (b -> c) -> (a -> b) -> a -> c
. Text -> ByteString
T.encodeUtf8
{-# INLINE decodeBase64 #-}

-- | Attempt to decode a 'Text' value as Base64, converting from
-- 'ByteString' to 'Text' according to some encoding function. In practice,
-- This is something like 'decodeUtf8'', which may produce an error.
--
-- See: <https://tools.ietf.org/html/rfc4648#section-4 RFC-4648 section 4>
--
-- Example:
--
-- @
-- 'decodeBase64With' 'T.decodeUtf8''
--   :: 'ByteString' -> 'Either' ('Base64Error' 'UnicodeException') 'Text'
-- @
--
decodeBase64With
    :: (ByteString -> Either err Text)
      -- ^ convert a bytestring to text (e.g. 'T.decodeUtf8'')
    -> ByteString
      -- ^ Input text to decode
    -> Either (Base64Error err) Text
decodeBase64With :: (ByteString -> Either err Text)
-> ByteString -> Either (Base64Error err) Text
decodeBase64With ByteString -> Either err Text
f ByteString
t = case ByteString -> Either Text ByteString
B64.decodeBase64 ByteString
t of
  Left Text
de -> Base64Error err -> Either (Base64Error err) Text
forall a b. a -> Either a b
Left (Base64Error err -> Either (Base64Error err) Text)
-> Base64Error err -> Either (Base64Error err) Text
forall a b. (a -> b) -> a -> b
$ Text -> Base64Error err
forall e. Text -> Base64Error e
DecodeError Text
de
  Right ByteString
a -> (err -> Base64Error err)
-> Either err Text -> Either (Base64Error err) Text
forall (p :: * -> * -> *) a b c.
Bifunctor p =>
(a -> b) -> p a c -> p b c
first err -> Base64Error err
forall e. e -> Base64Error e
ConversionError (ByteString -> Either err Text
f ByteString
a)
{-# INLINE decodeBase64With #-}

-- | Leniently decode a Base64-encoded 'Text' value. This function
-- will not generate parse errors. If input data contains padding chars,
-- then the input will be parsed up until the first pad character.
--
-- __Note:__ This is not RFC 4648-compliant.
--
decodeBase64Lenient :: Text -> Text
decodeBase64Lenient :: Text -> Text
decodeBase64Lenient = ByteString -> Text
T.decodeLatin1
    (ByteString -> Text) -> (Text -> ByteString) -> Text -> Text
forall b c a. (b -> c) -> (a -> b) -> a -> c
. ByteString -> ByteString
B64.decodeBase64Lenient
    (ByteString -> ByteString)
-> (Text -> ByteString) -> Text -> ByteString
forall b c a. (b -> c) -> (a -> b) -> a -> c
. Text -> ByteString
T.encodeUtf8
{-# INLINE decodeBase64Lenient #-}

-- | Tell whether a 'Text' value is Base64-encoded.
--
isBase64 :: Text -> Bool
isBase64 :: Text -> Bool
isBase64 = ByteString -> Bool
B64.isBase64 (ByteString -> Bool) -> (Text -> ByteString) -> Text -> Bool
forall b c a. (b -> c) -> (a -> b) -> a -> c
. Text -> ByteString
T.encodeUtf8
{-# INLINE isBase64 #-}

-- | Tell whether a 'Text' value is a valid Base64 format.
--
-- This will not tell you whether or not this is a correct Base64 representation,
-- only that it conforms to the correct shape. To check whether it is a true
-- Base64 encoded 'Text' value, use 'isBase64'.
--
isValidBase64 :: Text -> Bool
isValidBase64 :: Text -> Bool
isValidBase64 = ByteString -> Bool
B64.isValidBase64 (ByteString -> Bool) -> (Text -> ByteString) -> Text -> Bool
forall b c a. (b -> c) -> (a -> b) -> a -> c
. Text -> ByteString
T.encodeUtf8
{-# INLINE isValidBase64 #-}