parse_logs.hs

-- zcat 2015/07/0723*trace* |
-- grep -o "__id.*duration_..__" |
-- sed 's/__*\|id\|duration/ /g' |
-- sed 's/^  *\|  *$//g' |
-- sed 's/  */ /' |
-- nawk '{
--      max[$1] = !($1 in max) ? $2 : ($2 > max[$1]) ? $2 : max[$1]
-- } END {
--      for (i in max)
--          print i, max[i]
-- }' |
-- sed 's/..* //' |
-- sort -n | uniq -c

module Main where

import Control.Arrow
import Data.Function (on)
import Data.List (sortBy, groupBy)
import Data.Ord (comparing)
import Text.Regex.PCRE

groupLog :: [(Int, Int)] -> [(Int, [Int])]
groupLog logs = map (\l -> (fst . head $ l, map snd l)) $ groupBy ((==) `on` fst) $ sortBy (comparing fst) logs

removeDuplicate :: [(Int, [Int])] -> [(Int, Int)]
removeDuplicate = map (second maximum)

getInfo :: String -> (Int, Int)
getInfo line = (user, duration)
    where
        (user:duration:_) = concatMap (map read . (drop 1)) userAndDuration
        userAndDuration = line =~ "__id_(.*?)__duration_(..)__" :: [[String]]

main :: IO ()
main = do
    logs <- readFile "./072300_trace-adv.log"
    print (removeDuplicate . groupLog $ map getInfo $ (take 100) (lines logs))