Created
March 9, 2015 20:45
-
-
Save svdberg/c5ab76073cd720864519 to your computer and use it in GitHub Desktop.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
{-# LANGUAGE OverloadedStrings #-} | |
module Main where | |
import Data.Digest.Pure.MD5 | |
import Data.List.Split | |
import Data.List | |
import System.Environment | |
import qualified Data.ByteString.Lazy as LBS | |
import qualified Data.ByteString.Char8 as C | |
main = do | |
args <- getArgs | |
let filename = head args | |
tsvData <- C.readFile filename | |
let | |
lns = C.lines $ tsvData | |
mdLines = map splitByTabAndMd5 lns | |
C.writeFile "temp.txt" $ C.unlines mdLines | |
return () | |
splitByTabAndMd5 s = C.concat $ map (flip C.snoc ' ' . md5IfEmail) $ C.words s | |
md5IfEmail :: C.ByteString -> C.ByteString | |
md5IfEmail s = if C.isInfixOf "@" s then emailToMD5 s else s | |
emailToMD5 :: C.ByteString -> C.ByteString | |
emailToMD5 s = C.concat ["\"", C.pack $ show $ md5 $ LBS.fromStrict $ stripQuotes s, "\""] | |
stripQuotes :: C.ByteString -> C.ByteString | |
stripQuotes s = C.take l $ C.drop 1 s | |
where | |
l = C.length s - 2 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
File: MPA_users_all.txt: Little-endian UTF-16 Unicode text, with CRLF line terminators