benchmark fastmatch for string comparison in R

fastmatch-demo.r

library(fastmatch)
library(microbenchmark)

WORDS <- read.table("https://dotnetperls-controls.googlecode.com/files/enable1.txt",
                    stringsAsFactors = FALSE)[[1]]

words_factor <- as.factor(WORDS)

# generate 100 sentences of between 5 and 15 words:
SENTENCES <- lapply(c(1:100), sample, x = WORDS, size = sample(c(5:15), size = 1))

bench_fun <- function(fun)
  lapply(SENTENCES, fun)

# poster's slow solution:
hg_convert <- function(sentence){
  return(which(WORDS %in% sentence))
}

jw_convert_match <- function(sentence) {
  match(sentence, WORDS)
}

jw_convert_match_factor <- function(sentence) {
  match(sentence, words_factor)
}

jw_convert_fastmatch <- function(sentence) {
  fmatch(sentence, WORDS)
}

jw_convert_fastmatch_factor <- function(sentence) {
  fmatch(sentence, words_factor)
}

message("starting benchmark one")
print(microbenchmark(bench_fun(hg_convert),
                     bench_fun(jw_convert_match),
                     bench_fun(jw_convert_match_factor),
                     bench_fun(jw_convert_fastmatch),
                     bench_fun(jw_convert_fastmatch_factor),
                     times = 10))

# now again with big samples
# generating the SENTENCES is quite slow...
SENTENCES <- lapply(c(1:1e6), sample, x = WORDS, size = sample(c(5:15), size = 1))
message("starting benchmark two, compare with factor vs vector of words")
print(microbenchmark(bench_fun(jw_convert_fastmatch),
                     bench_fun(jw_convert_fastmatch_factor),
                     times = 10))

the google code link is broken.

I believe it's been moved to here:
https://storage.googleapis.com/google-code-archive-downloads/v2/code.google.com/dotnetperls-controls/enable1.txt