Remove accents from a dataframe column in R

Question

I got a data.table base. I got a term column in this data.table

class(base$term)
[1] character
length(base$term)
[1] 27486

I\'m able to remove

Answer 1

You can apply this function

    rm_accent <- function(str,pattern="all") {
   if(!is.character(str))
    str <- as.character(str)

  pattern <- unique(pattern)

  if(any(pattern=="Ç"))
    pattern[pattern=="Ç"] <- "ç"

  symbols <- c(
    acute = "áéíóúÁÉÍÓÚýÝ",
    grave = "àèìòùÀÈÌÒÙ",
    circunflex = "âêîôûÂÊÎÔÛ",
    tilde = "ãõÃÕñÑ",
    umlaut = "äëïöüÄËÏÖÜÿ",
    cedil = "çÇ"
  )

  nudeSymbols <- c(
    acute = "aeiouAEIOUyY",
    grave = "aeiouAEIOU",
    circunflex = "aeiouAEIOU",
    tilde = "aoAOnN",
    umlaut = "aeiouAEIOUy",
    cedil = "cC"
  )

  accentTypes <- c("´","`","^","~","¨","ç")

  if(any(c("all","al","a","todos","t","to","tod","todo")%in%pattern)) # opcao retirar todos
    return(chartr(paste(symbols, collapse=""), paste(nudeSymbols, collapse=""), str))

  for(i in which(accentTypes%in%pattern))
    str <- chartr(symbols[i],nudeSymbols[i], str) 

  return(str)
}