我正在尝试编写一个 Haskell 程序来解析巨大的文本文件(大约 14Gb),但我不明白如何让它从内存中释放未使用的数据或在 foldr 期间不使堆栈溢出。下面是程序源:
import qualified Data.ByteString.Lazy.Char8 as LBS
import qualified Data.ByteString.Lex.Lazy.Double as BD
import System.Environment
data Vertex =
Vertex{
vertexX :: Double,
vertexY :: Double,
vertexZ :: Double}
deriving (Eq, Show, Read)
data Extent =
Extent{
extentMax :: Vertex,
extentMin :: Vertex}
deriving (Eq, Show, Read)
addToExtent :: Extent -> Vertex -> Extent
addToExtent ext vert = Extent vertMax vertMin where
(vertMin, vertMax) = (makeCmpVert max (extentMax ext) vert, makeCmpVert min (extentMin ext) vert) where
makeCmpVert f v1 v2 = Vertex(f (vertexX v1) (vertexX v2))
(f (vertexY v1) (vertexY v2))
(f (vertexZ v1) (vertexZ v2))
readCoord :: LBS.ByteString -> Double
readCoord l = case BD.readDouble l of
Nothing -> 0
Just (value, _) -> value
readCoords :: LBS.ByteString -> [Double]
readCoords l | LBS.length l == 0 = []
| otherwise = let coordWords = LBS.split ' ' l
in map readCoord coordWords
parseLine :: LBS.ByteString -> Vertex
parseLine line = Vertex (head coords) (coords!!1) (coords!!2) where
coords = readCoords line
processLines :: [LBS.ByteString] -> Extent -> Extent
processLines strs ext = foldr (\x y -> addToExtent y (parseLine x)) ext strs
processFile :: String -> IO()
processFile name = do
putStrLn name
content <- LBS.readFile name
let (countLine:recordsLines) = LBS.lines content
case LBS.readInt countLine of
Nothing -> putStrLn "Can't read records count"
Just (recordsCount, _) -> do
print recordsCount
let vert = parseLine (head recordsLines)
let ext = Extent vert vert
print $ processLines recordsLines ext
main :: IO()
main = do
args <- getArgs
case args of
[] -> do
putStrLn "Missing file path"
xs -> do
processFile (head xs)
return()
文本文件包含用空格字符分隔的三个浮点数的行。该程序总是试图占用计算机上的所有可用内存并因内存不足错误而崩溃。