Load XML to Dataframe in R with parent node attributes

Question

I have an XML file (a TEI-encoded play) that I want to process into a data.frame in R, where every row of the data.frame contains one line of the play, the line number, the

Answer 1

Added additional xpathApply for sp elements:

bodyToDF <- function(x){
  scenenum <- xmlGetAttr(x, "n")
  scenetype <- xmlGetAttr(x, "type")
  sp <- xpathApply(x, 'sp', function(sp) {
    who <- xmlGetAttr(sp, "who")
    if(is.null(who))
      who <- NA
    line_num <- xpathSApply(sp, 'l', function(l) { xmlGetAttr(l,"n")})
    linecontent = xpathSApply(sp, 'l', function(l) { xmlValue(l,"n")})
    data.frame( scenenum, scenetype, who, line_num, linecontent)
  })
  do.call(rbind, sp)  
}

res <- xpathApply(doc, '//div1', bodyToDF)
temp.df <- do.call(rbind, res)

First 4 columns:

# > temp.df[,1:4]
#   scenenum scenetype  who line_num
# 1        1     scene  fau       30
# 2        1     scene  fau       31
# 3        1     scene  fau       32
# 4        1     scene eang      105
# 5        2     scene sch1       NA
# 6        2     scene sch2       NA
# 7        2     scene sch1       NA
# 8        2     scene  wag       NA