如何用有限的资源解析Haskell中的大型XML文件？

实际上,hexpat确实有’streaming’接口(就像xml-conduit).它使用了不太知名的List库和the rather ugly List class it defines.原则上,List包中的ListT type应该运行良好.由于缺少组合器,我很快就放弃了,并为Pipes.ListT的包装版本编写了一个丑陋的List类的适当实例,然后我用它来导出普通的Pipes.Producer函数,如parseProduce.为此需要的微不足道的操作作为PipesSax.hs附加在下面

一旦我们有了parseProducer,我们就可以将ByteString或Text Producer转换为带有Text或ByteString组件的SaxEvents生产者.这是一些简单的操作.我使用的是238M“input.xml”;程序永远不需要超过6 MB的内存,从顶部来判断.

– Sax.hs大多数IO动作都使用在底部定义的registerIds管道,该管道是针对xml的巨大位而定制的,这是一个有效的1000片段http://sprunge.us/WaQK

{-#LANGUAGE OverloadedStrings #-}
import PipesSax ( parseProducer )
import Data.ByteString ( ByteString )
import Text.XML.Expat.SAX 
import Pipes  -- cabal install pipes pipes-bytestring 
import Pipes.ByteString (toHandle,fromHandle,stdin,stdout )
import qualified Pipes.Prelude as P
import qualified System.IO as IO
import qualified Data.ByteString.Char8 as Char8

sax :: MonadIO m => Producer ByteString m () 
                 -> Producer (SAXEvent ByteString ByteString) m ()
sax =  parseProducer defaultParSEOptions

-- stream xml from stdin,yielding hexpat tagstream to stdout;
main0 :: IO ()
main0 =  runEffect $sax stdin >-> P.print

-- stream the extracted 'IDs' from stdin to stdout
main1 :: IO ()
main1 = runEffect $sax stdin >-> registryIds >-> stdout

-- write all IDs to a file
main2 =  
 IO.withFile "input.xml" IO.ReadMode $inp -> 
 IO.withFile "output.txt" IO.WriteMode $out -> 
   runEffect $sax (fromHandle inp) >-> registryIds >-> toHandle out 

-- folds:
-- print number of IDs
main3 =  IO.withFile "input.xml" IO.ReadMode $inp -> 
           do n <- P.length $sax (fromHandle inp) >-> registryIds
              print n

-- sum the meaningful part of the IDs - a dumb fold for illustration
main4 =  IO.withFile "input.xml" IO.ReadMode $inp ->
         do let pipeline =  sax (fromHandle inp) >-> registryIds >-> P.map readIntId
            n <- P.fold (+) 0 id pipeline
            print n
  where
   readIntId :: ByteString -> Integer
   readIntId = maybe 0 (fromIntegral.fst) . Char8.readInt . Char8.drop 2

-- my xml has tags with attributes that appear via hexpat thus:
-- StartElement "FacilitySite" [("registryId","110007915364")] 
-- and the like. This is just an arbitrary demo stream manipulation.
registryIds :: Monad m => Pipe (SAXEvent ByteString ByteString) ByteString m ()
registryIds = do 
  e <- await  -- we look for a 'SAXEvent'
  case e of -- if it matches,we yield,else we go to the next event
    StartElement "FacilitySite" [("registryId",a)] -> do yield a
                                                         yield "n"
                                                         registryIds
    _ -> registryIds

– ‘library’：PipesSax.hs

这只是newtypes Pipes.ListT来获取适当的实例.我们不导出任何与List或ListT有关的东西,只是使用标准的Pipes.Producer概念.

{-#LANGUAGE TypeFamilies,GeneralizedNewtypeDeriving #-}
module PipesSax (parseProducerLocations,parseProducer) where 
import Data.ByteString (ByteString)
import Text.XML.Expat.SAX
import Data.List.Class
import Control.Monad
import Control.Applicative
import Pipes  
import qualified Pipes.Internal as I

parseProducer
  :: (Monad m,GenericXMLString tag,GenericXMLString text) 
  => ParSEOptions tag text
  -> Producer ByteString m () 
  -> Producer (SAXEvent tag text) m ()
parseProducer opt  = enumerate . enumerate_ 
                     . parseG opt 
                     . Select_ . Select

parseProducerLocations
  :: (Monad m,GenericXMLString text) 
  => ParSEOptions tag text
  -> Producer ByteString m () 
  -> Producer (SAXEvent tag text,XMLParseLocation) m ()
parseProducerLocations opt = 
  enumerate . enumerate_ . parseLocationsG opt . Select_ . Select  

newtype ListT_ m a = Select_ { enumerate_ :: ListT m a }
    deriving (Functor,Monad,MonadPlus,MonadIO,Applicative,Alternative,Monoid,MonadTrans)

instance Monad m => List (ListT_ m) where
 type ItemM (ListT_ m) = m
 joinL = Select_ . Select . I.M . liftM (enumerate . enumerate_) 
 runList   = liftM emend  . next  . enumerate . enumerate_
   where 
     emend (Right (a,q)) = Cons a (Select_ (Select q))
     emend _ = Nil