unicode characters conversion in R

Question

I have this MTST column, which when printed yields

 [1] \"G          


        

Answer 1

Here's another alternative for recovering the true uncode character encoded in a string (borrowed from this question). Here we carefully match the form and unroll that hex value into a properly sized unicode character with some bit manipulation.

trueunicode <- function(x) {
    packuni<-Vectorize(function(cp) {
        bv <- intToBits(cp)
        maxbit <- tail(which(bv!=as.raw(0)),1)
        if(maxbit < 8) {
            rawToChar(as.raw(codepoint))
        } else if (maxbit < 12) {
            rawToChar(rev(packBits(c(bv[1:6], as.raw(c(0,1)), bv[7:11], as.raw(c(0,1,1))), "raw")))
        } else if (maxbit < 17){
            rawToChar(rev(packBits(c(bv[1:6], as.raw(c(0,1)), bv[7:12], as.raw(c(0,1)), bv[13:16], as.raw(c(0,1,1,1))), "raw")))    
        } else {
           stop("too many bits")
        }
    })
    m <- gregexpr("", x)
    codes <- regmatches(x,m)
    chars <- lapply(codes, function(x) {
        codepoints <- strtoi(paste0("0x", substring(x,4,7)))
        packuni(codepoints)

    })
    regmatches(x,m) <- chars
    Encoding(x)<-"UTF-8"
    x
}

using the sample

input <- c("G", "GS","G", "G", "S","()")

you get

trueunicode(input)
# [1] "ΑGΡΙΝΙΟ"        "ΑGΧΙΑΛΟS"       "ΑΙGΙΝΑ"         "ΑΙGΙΟ"         
# [5] "ΑΙΔΗΨΟS"        "ΑΚΤΙΟ(ΠΡΕΒΕΖΑ)"