N-gram tokenizer function without any Java dependencies (like in RWeka)

tokenizer.R

ngrams.tokenizer <- function(x, n = 2) {
  trim <- function(x) gsub("(^\\s+|\\s+$)", "", x)
  terms <- strsplit(trim(x), split = "\\s+")[[1]]
  ngrams <- vector()
  if (length(terms) >= n) {
    for (i in n:length(terms)) {
      ngram <- paste(terms[(i-n+1):i], collapse = " ")
      ngrams <- c(ngrams,ngram)
    }
  }
  ngrams  
}

ngrams.tokenizer(" this  is a sentense to be ngrammized", 3)