myWordList <- function() { token.all <- "" files <- list.files() for (i in files) { token <- "" lines.tmp <- scan(i, what="char") body.lower <- tolower(lines.tmp) body.token <- unlist(strsplit(body.lower, "\\W")) body.token <- body.token[body.token != ""] token.all <- c(token.all, body.token) } word.list <- sort(token.all) word.list <- word.list[word.list != ""] as.data.frame(word.list) }