unicode escapeされた文字をunicodeの文字に変換する。

unicode.hs

{-# LANGUAGE NoMonomorphismRestriction, OverloadedStrings #-}

import qualified Data.ByteString.Char8 as BS
import qualified Data.Attoparsec.ByteString as AB
import qualified Data.Attoparsec.ByteString.Char8 as AC
import Control.Applicative ((<*), (*>), (<$>), (<|>))
import Data.Conduit.Attoparsec
import Data.Conduit
import Data.Char

unicodeChar :: AB.Parser Char
unicodeChar = do
  AC.string "\\u"
  code <- AC.count 4 hexDigit
  return $ toChar code
  where
    hexDigit = AC.satisfy isHexDigit
    toChar x = chr $ read $ "0x" ++ x

escapedChar :: AB.Parser Char
escapedChar = toChar <$> AC.char '\\' *> oneOf "\"\\/nrftb"
  where
    oneOf s = AC.satisfy $ \c -> elem c s
    toChar '\"' = '"'
    toChar '\\' = '\\'
    toChar '/'  = '/'
    toChar 'n'  = '\n'
    toChar 'r'  = '\r'
    toChar 'f'  = '\f'
    toChar 't'  = '\t'
    toChar 'b'  = '\b'

unicodeString :: AB.Parser String
unicodeString = do
  isEnd <- AC.atEnd
  if isEnd then
    return []
    else do
    c <- unicodeChar <|> escapedChar <|> AC.anyChar
    s <- unicodeString
    return (c:s)

sample = "Coq\\u307f\\u305f\\u3044\\u306a\\u611f\\u3058\\u306b\n\\u6570\\u5f0f\\u5909\\u5f62\\u3092\\u88dc\\u4f50\\u3057\\u3066\\u304f\\u308c\\u308b\\u30b7\t\\u30b9\\u30c6\\u30e0\\u304c\\u6b32\\u3057\\u3044\\u3002YO!"

main = do
  let (Right x) = AB.parseOnly unicodeString sample
  putStrLn x