An R script to validate Malaysian National Registration Identity Card numbers

NRIC.R

#####################################################################
# A series of functions to manage Malaysian National Registration   #
# Identity Card Number (NRIC) data.  The NRIC was a form            #
# YYMMDD-PB-XXXG[*], where YYMMDD are six digits representing the   #
# date of birth/registration, PB is a two digit code representing   #
# the place of birth XXX is a random digit and G is also a random   #
# digit, the if G is even the NRIC is for a female and if it is odd #
# it is for a male.                                                 #
#-------------------------------------------------------------------#
# The functions:                                                    #
# is.nric() returns a boolean; T if the string is formatted as an   #
# NRIC, otherwise F.                                                #
# sexFromNRIC() returns the sex associated with the NRIC            #
# dobFromNRIC() returns the date of birth.                          #
#                                                                   #
# Author: Daniel D Reidpath                                         #
# Date: 31 October, 2015                                            #
#####################################################################
#

dobFromNRIC <- function(nric, as.date=T){
# nric as an appropriately formatted NRIC YYMMDD-PB-XXXG
# as.date ensure that the returned values are eighter as.Date or as
# strings.
#
  dob <- substr(nric, 1, 6)
  yr <- as.integer(substr(dob, 1,2))
  dob <- sapply(yr, function(century, dobstr){
    if(century>=16){
      dobstr <- paste("19", substr(dobstr, 1,2), "-", substr(dobstr, 3,4), "-", substr(dobstr, 5,6), sep='')
    } else {
      dobstr <- paste("20", substr(dobstr, 1,2), "-", substr(dobstr, 3,4), "-", substr(dobstr, 5,6), sep='')
    }
    return(dobstr)
  }, dob)
  if(as.date==T){
    return( as.Date(as.vector(dob)[1:length(nric)]) )
  }
  if(as.date==F){
    return(as.vector(dob)[1:length(nric)])
  }
  else{
    stop( "as.date must be a logical")
  }
}


is.nric <- function(nric){
# Boolean function checks that nric is formatted correctly
  nric_format <- "[0-9]{2}[0-9]{1}[012]{1}[0123]{1}[0-9]{1}-[1-9]{2}-[0-9]{4}"
  grepl(nric_format, nric)
}


sexFromNRIC <- function(nric){
# nric as an appropriately formatted NRIC YYMMDD-PB-XXXG
# returns the gender associated with the NRIC: 1=Female, 2=Male
  sex <- sapply(nric, function(x){
    if(!is.nric(x)){
      sex <- NA
    } else {
      last_digit <- substr(x, nchar(x), nchar(x))
      last_digit <- as.integer( last_digit )
      sex <- last_digit %% 2 + 1 # 1=Female, 2=Male
      return(sex)
    }
    return(sex)
  })
  return(sex)
}