#!/usr/bin/perl -w
use strict;
my $s = "Ä";
print length($s)."\n";

use utf8;

0000000   #   !   /   b   i   n   /   p   e   r   l  lf  lf   m   y  sp
                23212f62        696e2f70        65726c0a        0a6d7920
0000020   $   s  sp   =  sp   "   D   "  ;  lf   p   r   i   n   t  sp
                2473203d        2022c422        3b0a7072        696e7420
...

use utf8;

use CGI;
use Encode;

my $q = CGI->new;
my $s = decode("utf-8", $q->param("s") || '');

print "Content-Type: text/plain\n\n";
print "length of s: ", length($s), "\n";

#!/usr/local/bin/perl 
use Encode qw(decode _utf8_off);

open(my $fh_8bit, ">", "utf8.txt") or die "open utf8.txt: $^E";
open(my $fh_utf8, ">", "utf8.utf") or die "open utf8.utf: $^E";
# byte order mark für UTF-8 
print $fh_utf8 "\xef\xbb\xbf";

for my $num (128 .. 255) {
   my $chr_8bit = chr($num);
   
   # von 8-Bit Zeichensatz (z.B. Windows CP1252) nach UTF-8 übersetzen
   my $chr_utf8 = decode("cp1252", $chr_8bit);

   # wir wollen die raw octets auslesen
   my $utf_octets = $chr_utf8;
   _utf8_off($utf_octets);

   my $raw_hex = "";
   for my $byte (split(//, $utf_octets)) {
      $raw_hex .= sprintf("%02x", ord($byte));
   }
   printf $fh_8bit ("Zeichen \\x%02x (%s) = UTF-8 \\x%s\n", $num, $chr_8bit, $raw_hex);
   printf $fh_utf8 ("UTF-8 \\x%-6s = Zeichen (%s) Octets %d Chars %d\n",
                               $raw_hex, $utf_octets, length($utf_octets), length($chr_utf8));
}