Shell Programming and Scripting

awk '
BEGIN {
    rn="MDCLXVI" # Roman numerals desc order
    split("1000 500 100 50 10 5 1",v) # value for each numeral
}
function roman_val(s,val,c,d,p,q) {
    if(s !~ "^[" rn tolower(rn) "]+$") return 0;
    c = split(toupper(s),d,"")
    val = v[index(rn,d[c])]
    while (--c) {
      p = index(rn,d[c])
      q = index(rn,d[c+1])
      val += (p>q)? -v[p] : v[p]
    }
    return val
}
/p_[0-9]+/ {
  x=$0
  while(match(x, "p_[0-9]+")) {
      pg=substr(x,RSTART+2,RLENGTH-2)-16
      n=n substr(x,1,RSTART) "p_" pg
      x=substr(x,RSTART+RLENGTH)
  }
  $0= n x
}

$0 ~ "p_[" rn tolower(rn) "]+" {
  while(match($0, "p_[" rn tolower(rn) "]+")) {
      pg=roman_val(substr($0,RSTART+2,RLENGTH-2))-2
      x=substr($0,1,RSTART) "p_" pg substr($0,RSTART+RLENGTH)
      $0=x
  }
} 1' your_uncompressed.pdf

use warnings;
use strict;

use Roman;

our @array = `find -P . -type f -name \'*.pdf\'`;

foreach my $p (@array){

    chomp($p);
    open(my $source, $p) or die "Cannot open file $p";
    open(my $dest, '>', $p . ".new") or die "Cannot open output file $p.new";
    binmode($source);
    binmode($dest);

    while(my $line = <$source>){
        while (my ($page) = $line =~ /pp_(\d+)/) {
            my $newpage = $page-16;
            $line =~ s/pp_$page/zUNIQz_$newpage/;
        }
        while (my ($rdigit) = $line =~ /pp_([MDCLXVI]+)/i) {
           my $newpage = arabic($rdigit)-2;
           $line =~ s/pp_$rdigit/zUNIQz_$newpage/;
        }
        $line =~ s/zUNIQz_/pp_/g;
        print $dest $line;
    }
    close($source);
    close($dest);
    rename "$p" => "$p.bak" or
          die "can't rename $p to $p.bak";
    rename "$p.new" => "$p" or
          die "can't rename $p.new to $p";
}