{-# LANGUAGE Safe #-}
-- |
-- Module       : Data.Text.Lazy.Encoding.Base64
-- Copyright    : (c) 2019-2020 Emily Pillmore
-- License      : BSD-style
--
-- Maintainer   : Emily Pillmore <emilypi@cohomolo.gy>
-- Stability    : stable
-- Portability  : non-portable
--
-- This module contains 'Data.Text.Lazy.Text'-valued combinators
-- implementing the RFC 4648 specification for the Base64
-- encoding format. This includes lenient decoding variants, and
-- external + internal validations for canonicity.
--
module Data.Text.Lazy.Encoding.Base64
( -- * Encoding
  encodeBase64
  -- * Decoding
, decodeBase64
, decodeBase64With
, decodeBase64Lenient
  -- * Validation
, isBase64
, isValidBase64
) where


import Data.Bifunctor (first)
import Data.ByteString.Lazy (ByteString)
import qualified Data.ByteString.Lazy.Base64 as BL64

import qualified Data.Text as T
import Data.Text.Encoding.Base64.Error
import qualified Data.Text.Lazy as TL
import qualified Data.Text.Lazy.Encoding as TL

-- | Encode a 'TL.Text' value in Base64 with padding.
--
-- See: <https://tools.ietf.org/html/rfc4648#section-4 RFC-4648 section 4>
--
-- === __Examples__:
--
-- >>> encodeBase64 "Sun"
-- "U3Vu"
--
encodeBase64 :: TL.Text -> TL.Text
encodeBase64 :: Text -> Text
encodeBase64 = ByteString -> Text
BL64.encodeBase64 (ByteString -> Text) -> (Text -> ByteString) -> Text -> Text
forall b c a. (b -> c) -> (a -> b) -> a -> c
. Text -> ByteString
TL.encodeUtf8
{-# INLINE encodeBase64 #-}

-- | Decode a padded Base64-encoded 'TL.Text' value
--
-- See: <https://tools.ietf.org/html/rfc4648#section-4 RFC-4648 section 4>
--
-- /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.
--
-- === __Examples__:
--
-- >>> decodeBase64 "U3Vu"
-- Right "Sun"
--
-- >>> decodeBase64 "U3V"
-- Left "Base64-encoded bytestring requires padding"
--
-- >>> decodebase64 "U3V="
-- Left "non-canonical encoding detected at offset: 2"
--
decodeBase64 :: TL.Text -> Either T.Text TL.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
TL.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
BL64.decodeBase64 (ByteString -> Either Text ByteString)
-> (Text -> ByteString) -> Text -> Either Text ByteString
forall b c a. (b -> c) -> (a -> b) -> a -> c
. Text -> ByteString
TL.encodeUtf8
{-# INLINE decodeBase64 #-}

-- | Attempt to decode a 'ByteString' value as Base64, converting from
-- 'ByteString' to 'TL.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' 'TL.decodeUtf8''
--   :: 'ByteString' -> 'Either' ('Base64Error' 'UnicodeException') 'TL.Text'
-- @
--
decodeBase64With
    :: (ByteString -> Either err TL.Text)
      -- ^ convert a bytestring to text (e.g. 'TL.decodeUtf8'')
    -> ByteString
      -- ^ Input text to decode
    -> Either (Base64Error err) TL.Text
decodeBase64With :: (ByteString -> Either err Text)
-> ByteString -> Either (Base64Error err) Text
decodeBase64With ByteString -> Either err Text
f ByteString
t = case ByteString -> Either Text ByteString
BL64.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 'TL.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.
--
-- === __Examples__:
--
-- >>> decodeBase64Lenient "U3Vu"
-- "Sun"
--
-- >>> decodeBase64Lenient "U3V"
-- "Su"
--
-- >>> decodebase64Lenient "U3V="
-- "Su"
--
decodeBase64Lenient :: TL.Text -> TL.Text
decodeBase64Lenient :: Text -> Text
decodeBase64Lenient = ByteString -> Text
TL.decodeLatin1
    (ByteString -> Text) -> (Text -> ByteString) -> Text -> Text
forall b c a. (b -> c) -> (a -> b) -> a -> c
. ByteString -> ByteString
BL64.decodeBase64Lenient
    (ByteString -> ByteString)
-> (Text -> ByteString) -> Text -> ByteString
forall b c a. (b -> c) -> (a -> b) -> a -> c
. Text -> ByteString
TL.encodeUtf8
{-# INLINE decodeBase64Lenient #-}

-- | Tell whether a 'TL.Text' value is Base64-encoded.
--
-- === __Examples__:
--
-- >>> isBase64 "U3Vu"
-- True
--
-- >>> isBase64 "U3V"
-- False
--
-- >>> isBase64 "U3V="
-- False
--
isBase64 :: TL.Text -> Bool
isBase64 :: Text -> Bool
isBase64 = ByteString -> Bool
BL64.isBase64 (ByteString -> Bool) -> (Text -> ByteString) -> Text -> Bool
forall b c a. (b -> c) -> (a -> b) -> a -> c
. Text -> ByteString
TL.encodeUtf8
{-# INLINE isBase64 #-}

-- | Tell whether a 'TL.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 'TL.Text' value, use 'isBase64'.
--
-- === __Examples__:
--
-- >>> isValidBase64 "U3Vu"
-- True
--
-- >>> isValidBase64 "U3V"
-- True
--
-- >>> isValidBase64 "U3V="
-- True
--
-- >>> isValidBase64 "%"
-- False
--
isValidBase64 :: TL.Text -> Bool
isValidBase64 :: Text -> Bool
isValidBase64 = ByteString -> Bool
BL64.isValidBase64 (ByteString -> Bool) -> (Text -> ByteString) -> Text -> Bool
forall b c a. (b -> c) -> (a -> b) -> a -> c
. Text -> ByteString
TL.encodeUtf8
{-# INLINE isValidBase64 #-}