{-# LANGUAGE DataKinds #-}
-- |
-- Module       : Data.Text.Lazy.Encoding.Base64
-- Copyright    : (c) 2019-2026 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
, decodeBase64Untyped
, decodeBase64UntypedWith
, decodeBase64Lenient
  -- * Parsing
, parseBase64
) where


import Data.Base64.Types

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



-- $setup
--
-- >>> import Data.Base64.Types
-- >>> :set -XOverloadedStrings
-- >>> :set -XTypeApplications
-- >>> :set -XDataKinds
--

-- | 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 -> Base64 'StdPadded TL.Text
encodeBase64 :: Text -> Base64 'StdPadded Text
encodeBase64 = ByteString -> Base64 'StdPadded Text
BL64.encodeBase64 (ByteString -> Base64 'StdPadded Text)
-> (Text -> ByteString) -> Text -> Base64 'StdPadded 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>
--
-- === __Examples__:
--
-- >>> decodeBase64 $ assertBase64 @'StdPadded "U3Vu"
-- "Sun"
--
decodeBase64 :: StdAlphabet k => Base64 k TL.Text -> TL.Text
decodeBase64 :: forall (k :: Alphabet). StdAlphabet k => Base64 k Text -> Text
decodeBase64 = ByteString -> Text
TL.decodeUtf8 (ByteString -> Text)
-> (Base64 k Text -> ByteString) -> Base64 k Text -> Text
forall b c a. (b -> c) -> (a -> b) -> a -> c
. Base64 k ByteString -> ByteString
forall (k :: Alphabet).
StdAlphabet k =>
Base64 k ByteString -> ByteString
BL64.decodeBase64 (Base64 k ByteString -> ByteString)
-> (Base64 k Text -> Base64 k ByteString)
-> Base64 k Text
-> ByteString
forall b c a. (b -> c) -> (a -> b) -> a -> c
. (Text -> ByteString) -> Base64 k Text -> Base64 k ByteString
forall a b. (a -> b) -> Base64 k a -> Base64 k b
forall (f :: * -> *) a b. Functor f => (a -> b) -> f a -> f b
fmap Text -> ByteString
TL.encodeUtf8
{-# INLINE decodeBase64 #-}

-- | Decode a padded, untyped Base64-encoded 'TL.Text' value
--
-- See: <https://tools.ietf.org/html/rfc4648#section-4 RFC-4648 section 4>
--
-- === __Examples__:
--
-- >>> decodeBase64Untyped "U3Vu"
-- Right "Sun"
--
-- >>> decodeBase64Untyped "U3V"
-- Left "Base64-encoded bytestring requires padding"
--
-- >>> decodeBase64Untyped "U3V="
-- Left "non-canonical encoding detected at offset: 2"
--
decodeBase64Untyped :: TL.Text -> Either T.Text TL.Text
decodeBase64Untyped :: Text -> Either Text Text
decodeBase64Untyped = (ByteString -> Text) -> Either Text ByteString -> Either Text Text
forall a b. (a -> b) -> Either Text a -> Either Text b
forall (f :: * -> *) a b. Functor f => (a -> b) -> f a -> f b
fmap ByteString -> Text
TL.decodeUtf8 (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.decodeBase64Untyped (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 decodeBase64Untyped #-}

-- | 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__:
--
-- @
-- 'decodeBase64UntypedWith' 'TL.decodeUtf8''
--   :: 'ByteString' -> 'Either' ('Base64Error' 'UnicodeException') 'TL.Text'
-- @
--
decodeBase64UntypedWith
    :: (ByteString -> Either err TL.Text)
      -- ^ convert a bytestring to text (e.g. 'TL.decodeUtf8'')
    -> ByteString
      -- ^ Input text to decode
    -> Either (Base64Error err) TL.Text
decodeBase64UntypedWith :: forall err.
(ByteString -> Either err Text)
-> ByteString -> Either (Base64Error err) Text
decodeBase64UntypedWith ByteString -> Either err Text
f ByteString
t = case ByteString -> Either Text ByteString
BL64.decodeBase64Untyped 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 a b c. (a -> b) -> Either a c -> Either b c
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 decodeBase64UntypedWith #-}

-- | Leniently decode an untyped 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.decodeUtf8
  (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 #-}

-- | Parse a canonical, padded Base64-encoded 'TL.Text' value.
--
-- Checks the alphabet, length, padding, and unused padding bits. On success,
-- returns the original encoded value wrapped in 'Base64', ready for
-- 'decodeBase64'. On failure, returns the same error as 'decodeBase64Untyped'.
-- The input is neither decoded nor normalized in the returned value.
--
-- This validates the Base64 encoding, not the UTF-8 validity of the decoded
-- bytes. Use 'decodeBase64UntypedWith' to check the decoded text encoding.
--
-- The entire input is validated before returning 'Right'; the original
-- chunk boundaries are preserved in the result.
--
-- === __Examples__:
--
-- >>> parseBase64 "U3Vu"
-- Right "U3Vu"
--
-- >>> fmap decodeBase64 (parseBase64 "U3Vu")
-- Right "Sun"
--
-- >>> parseBase64 "U3V"
-- Left "Base64-encoded bytestring requires padding"
--
-- >>> parseBase64 "U3V="
-- Left "non-canonical encoding detected at offset: 2"
--
-- @since 2.0
--
parseBase64 :: TL.Text -> Either T.Text (Base64 'StdPadded TL.Text)
parseBase64 :: Text -> Either Text (Base64 'StdPadded Text)
parseBase64 Text
bs = Text -> Base64 'StdPadded Text
forall (k :: Alphabet) a. a -> Base64 k a
assertBase64 Text
bs Base64 'StdPadded Text
-> Either Text (Base64 'StdPadded ByteString)
-> Either Text (Base64 'StdPadded Text)
forall a b. a -> Either Text b -> Either Text a
forall (f :: * -> *) a b. Functor f => a -> f b -> f a
<$ ByteString -> Either Text (Base64 'StdPadded ByteString)
BL64.parseBase64 (Text -> ByteString
TL.encodeUtf8 Text
bs)
{-# INLINE parseBase64 #-}