Combine values in huge XML-files

We'll use the XML package

library(XML)

and create a closure that contains a function to handle the 'SCHOOL' node, as well as two helper functions to retrieve results when done. The SCHOOL function is invoked on each SCHOOL node. If it finds a hockey team, it uses the /SCHOOL/NAME/text() as a 'key', and the /SCHOOL/TEAMS/HOCKEY/text() and //STUDENT/text() (or /SCHOOL/GRADES/STUDENT/text()) as values. A message is printed for every 100 (by default) schools with hockey teams, so that there's some indication of progress. The 'get' function is used after the fact to retrieve the result.

teams <- function(progress=1000) {
    res <- new.env(parent=emptyenv())   # for results
    it <- 0L                            # iterator -- nodes visited
    list(SCHOOL=function(elt) {
        ## handle 'SCHOOL' nodes 
        if (getNodeSet(elt, "not(/SCHOOL/TEAMS/HOCKEY)"))
            ## early exit -- no hockey team
            return(NULL)
        it <<- it + 1L
        if (it %% progress == 0L)
            message(it)
        school <- getNodeSet(elt, "string(/SCHOOL/NAME/text())") # 'key'
        res[[school]] <-
            list(team=getNodeSet(elt,
                   "normalize-space(/SCHOOL/TEAMS/HOCKEY/text())"),
                 students= xpathSApply(elt, "//STUDENT", xmlValue))
    }, getres = function() {
        ## retrieve the 'res' environment when done
        res
    }, get=function() {
        ## retrieve 'res' environment as data.frame
        school <- ls(res)
        team <- unlist(eapply(res, "[[", "team"), use.names=FALSE)
        student <- eapply(res, "[[", "students")
        len <- sapply(student, length)
        data.frame(school=rep(school, len), team=rep(team, len),
                   student=unlist(student, use.names=FALSE))
    })
}

We use the function as

branches <- teams()
xmlEventParse("event.xml", handlers=NULL, branches=branches)
branches$get()