Created
October 30, 2019 21:18
-
-
Save dmjio/8477be4a5acb2106676aae03f2fffc02 to your computer and use it in GitHub Desktop.
This file contains 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 #-} | |
{-# LANGUAGE ScopedTypeVariables #-} | |
module Main where | |
import Control.Monad | |
import qualified Data.ByteString.Lazy.Char8 as BL8 | |
import qualified Data.Csv as CSV | |
import Data.List | |
import qualified Data.Vector as V | |
-- main :: IO () | |
-- main = do | |
-- bytes <- BL8.readFile "file.csv" | |
-- let xs = chuns 34 (BL8.split ',' bytes) | |
-- mapM_ (print . length) xs | |
-- print (last xs) | |
chunks :: Int -> [a] -> [[a]] | |
chunks _ [] = [] | |
chunks n xs = do | |
case splitAt n xs of | |
(ls,rs) -> ls : chunks n rs | |
-- cols :: Int | |
-- cols = do | |
-- length ["Superfamily/Family","Account Number","Trading Currency Code","Account (Account Number)","Superfamily/Family Name","Issue Currency Description(Currency Code)","Trading Currency Description","Entry Date","Trade Date","Settle Date","Transaction ID","Transaction Type","Executing Broker Code","Transaction Comments","Security ID","Security Description","Quantity","Trade Price","Transaction Exchange Rate","Accrued Interest Purchased/Sold","Net Money","CUSIP","Floor Commissions","CMTA Commissions","PB Commissions","Total Commissions","Option Regulatory Fees","SEC Fees","Fees Postage","Fees Service","Fees Other","Total Fees","Dividend Rate","Bloomberg Ticker"] | |
main :: IO () | |
main = do | |
bytes <- BL8.lines <$> BL8.readFile "lol.csv" | |
let chunked = fmap (BL8.split ',') bytes | |
result = groupBy comparator chunked | |
header = BL8.intercalate "," $ BL8.split ',' $ head $ fmap (BL8.intercalate ",") (result !! 0) | |
forM_ result $ \chunkedGroup -> do | |
let fileName = BL8.unpack $ BL8.filter (/='-') ((chunkedGroup !! 0) !! 7) | |
result = (BL8.filter (/='"') header) <> "\n" <> do | |
BL8.intercalate "\n" $ (fmap (BL8.intercalate ",") chunkedGroup) | |
BL8.writeFile (fileName <> ".csv") (result <> "\n") | |
putStrLn "done" | |
comparator :: [BL8.ByteString] -> [BL8.ByteString] -> Bool | |
comparator l r = l !! 8 == r !! 8 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment