reut21578 <- system.file("texts", "reut21578", package = "tm")
reut21578TDC <- Corpus(DirSource(reut21578), readerControl = list(reader = readReut21578XML, language = "en_US", load = TRUE))
reut21578TDC[[1]]
asPlain(reut21578TDC[[1]])
Run the code above in your browser using DataLab