我一直在探索
Stack Overflow data dumps，从而利用友好的XML和“解析”正则表达式。我尝试使用各种Haskell XML库来查找特定用户的文档顺序中的第一个帖子，都是讨厌的。
@H_502_16@import Control.Monad
import Text.HTML.TagSoup
userid = "83805"
main = do
posts <- liftM parseTags (readFile "posts.xml")
print $ head $ map (fromAttrib "Id") $
filter (~== ("<row OwnerUserId=" ++ userid ++ ">"))
posts
import Text.XML.HXT.Arrow
import Text.XML.HXT.XPath
userid = "83805"
main = do
runX $ readDoc "posts.xml" >>> posts >>> arr head
where
readDoc = readDocument [ (a_tagsoup,v_1),(a_parse_xml,(a_remove_whitespace,(a_issue_warnings,v_0),(a_trace,v_1)
]
posts :: ArrowXml a => a XmlTree String
posts = getXPathTrees byUserId >>>
getAttrValue "Id"
where byUserId = "/posts/row/@OwnerUserId='" ++ userid ++ "'"
import Control.Monad
import Control.Monad.Error
import Control.Monad.Trans.Maybe
import Data.Either
import Data.Maybe
import Text.XML.Light
userid = "83805"
main = do
[posts,votes] <- forM ["posts","votes"] $
liftM parseXML . readFile . (++ ".xml")
let ps = elemNamed "posts" posts
putStrLn $ maybe "<not present>" show
$ filterElement (byUser userid) ps
elemNamed :: String -> [Content] -> Element
elemNamed name = head . filter ((==name).qName.elName) . onlyElems
byUser :: String -> Element -> Bool
byUser id e = maybe False (==id) (findAttr creator e)
where creator = QName "OwnerUserId" Nothing Nothing
我哪里做错了？使用Haskell处理大量XML文档的正确方法是什么？
