textmessage.R

library(data.table)
dict.orig = tolower(readLines("/usr/share/dict/american-english"))

#words shorter than the longest padded with "" for simpler retrieval
dictDT = setDT(tstrsplit(dict.orig, split = "", fill = ""))

#lookup table for conversion
lookup = data.table(num = c(rep(2L, 3), rep(3L, 3), rep(4L, 3),
                            rep(5L, 3), rep(6L, 3), rep(7L, 4),
                            rep(8L, 3), rep(9L, 4)),
                    let = letters)
#the following are found in the dictionary and would need
#  to be handled separately (accents should just be
#  appended to matches for unaccented version):
#      c("", "'", "á", "â", "å", "ä",
#        "ç", "é", "è", "ê", "í", "ñ",
#        "ó", "ô", "ö", "û", "ü")
lookup[ , num := paste0(num)]

for (col in names(dictDT)) {
  dictDT[lookup, (col) := i.num, on = setNames("let", col)]
}

#back to character vector
dict.num = do.call(paste0, dictDT)

#sorting for faster vector search
idx = order(dict.num)
dict.num = dict.num[idx]
dict.orig = dict.orig[idx]

possibilities = function(input) dict.orig[dict.num == input]

#lapply for multiple inputs
lapply(c("43556", "469", "47", "48", "46464", "3637", "8447", "22882559", "9675", "67", "9428"), possibilities)