This module has some utilities for working with Text in Hadoop streaming.

Word count example:

 {-# LANGUAGE OverloadedStrings, TupleSections #-}

 import Data.Conduit (ConduitT)
 import qualified Data.Conduit as C
 import qualified Data.Conduit.Combinators as C
 import Data.Void (Void)
 import HadoopStreaming
 import qualified HadoopStreaming.Text as HT
 import Data.Text (Text)
 import qualified Data.Text as Text

 mapper :: Mapper Text Text Void IO
 mapper = Mapper dec enc trans
   where
     dec :: Text -> Either Void [Text]
     dec = Right . Text.words

     enc :: Text -> Int -> Text
     enc = HT.defaultKeyValueEncoder id (Text.pack . show)

     trans :: ConduitT [Text] (Text, Int) IO ()
     trans = C.concatMap (map (,1))

 reducer :: Reducer Text Text Void IO
 reducer = Reducer dec enc trans
   where
     dec :: Text -> Either Void (Text, Int)
     dec i = Right (i1, read . tail . Text.unpack $ i2)
       where (i1, i2) = Text.break (== '\\t') i

     enc :: (Text, Int) -> Text
     enc (t, c) = t <> "," <> Text.pack (show c)

     trans :: Text -> Int -> ConduitT Int (Text, Int) IO ()
     trans k v0 = C.foldl (+) v0 >>= C.yield . (k,)