文字コード自動判別付き変換(any -> Unicode)

enc_detect.hs

import qualified Data.ByteString as BS
import qualified Data.Text as T
import qualified Data.Text.IO as TIO
import Data.Text.ICU.Convert

toUnicodeWithDetect :: FilePath -> IO T.Text
toUnicodeWithDetect fp = do
    a <- BS.readFile fp
    cons <- mapM (flip open Nothing) ns
    let xs = take 1 $ filter (T.all (`notElem` errs)) $ map (flip toUnicode a) cons
    case xs of
        []  -> return T.empty
        [x] -> return x
    where
    ns = ["ucs4", "iso-2022-jp", "euc-jp", "sjis", "cp932", "utf-8"]
    errs = ['\SUB', '\65533']