parsingxml.R

parsingxml.R

#!/usr/bin/Rscript
library(XML)

args = commandArgs(trailingOnly=TRUE)
if (!length(args)==2) {
  stop("Two arguments must be supplied (input file name ,output file name - csv ext).n", call.=FALSE)
} 


#read XML line by line
con <- file(args[1], "r")
lines <- readLines(con, -1)
test <- lapply(lines,function(x){return(xmlTreeParse(x,useInternalNodes = TRUE))})

#parsing XML to get variables
ID <- as.numeric(sapply(test,function(x){return(xpathSApply(x, "//row",xmlGetAttr, "Id"))}))
Tags <- sapply(test,function(x){return(xpathSApply(x, "//row",xmlGetAttr, "Tags"))})
Title <- as.character(sapply(test,function(x){return(xpathSApply(x, "//row",xmlGetAttr, "Title"))}))
Body <- as.character(sapply(test,function(x){return(xpathSApply(x, "//row",xmlGetAttr, "Body"))}))
text = paste(Title,Body)

label = as.numeric(sapply(Tags,function(x){return(grep("python",x))}))
label[is.na(label)]=0

#final data frame for export
df <- as.data.frame(cbind(ID,label,text),stringsAsFactors = FALSE)
df$ID=as.numeric(df$ID)
df$label=as.numeric(df$label)
#write to csv
write.csv(df, file=args[2],row.names=FALSE)
print("output file created....")