Re: Converting utf-8 to base64 and back

[LanX]

Here a more concise demonstration.

(please note that PM has problems displaying wide-characters in code blocks, e.g. "ř" stands for "ř")

use strict;
use warnings;
use utf8 ;

use Encode;
use Data::Dump qw/dd pp/;
use Devel::Peek;
use MIME::Base64 ;
use open IO => ':encoding(UTF-8)', ':std';


roundtrip($_) for 'Ä', 'ř';



sub roundtrip {

   my $orig = shift;

   warn "\n\n****** START\n";
   peek( orig => $orig);


   my $encode_utf8 = Encode::encode_utf8($orig);
   peek (encode_utf8 =>$encode_utf8);


   my $encode_b64 = MIME::Base64::encode_base64($encode_utf8);
   peek(encode_b64=>$encode_b64);

   my $decode_b64 = MIME::Base64::decode_base64($encode_b64);
   peek (decode_b64=>$decode_b64);


   my $decode_utf8 = Encode::decode_utf8($decode_b64);
   peek (decode_utf8 => $decode_utf8);
}


sub peek {
   my ($name,$str) = @_;
   my (undef, $file, $line) = caller(0);
   my $pp = pp($str);
   warn "\n*** $name = '$str' = $pp at $file line $line\n";
   Dump $_[1];

}

****** START

*** orig = 'Ä' = "\xC4" at c:/tmp/b64_utf8_2.pl line 21
SV = PV(0x36c9d8) at 0x25c8308
  REFCNT = 1
  FLAGS = (PADMY,POK,pPOK,UTF8)
  PV = 0x367478 "\303\204"\0 [UTF8 "\x{c4}"]
  CUR = 2
  LEN = 16

*** encode_utf8 = 'Ä' = "\xC3\x84" at c:/tmp/b64_utf8_2.pl line 
+25
SV = PV(0x2607c48) at 0x25c8110
  REFCNT = 1
  FLAGS = (PADMY,POK,pPOK)
  PV = 0x28320c8 "\303\204"\0
  CUR = 2
  LEN = 16

*** encode_b64 = 'w4Q=
' = "w4Q=\n" at c:/tmp/b64_utf8_2.pl line 29
SV = PV(0x2607c58) at 0x25c80e0
  REFCNT = 1
  FLAGS = (PADMY,POK,pPOK)
  PV = 0x2832188 "w4Q=\n"\0
  CUR = 5
  LEN = 16

*** decode_b64 = 'Ä' = "\xC3\x84" at c:/tmp/b64_utf8_2.pl line 3
+2
SV = PV(0x2607c38) at 0x25c7f48
  REFCNT = 1
  FLAGS = (PADMY,POK,pPOK)
  PV = 0x2832398 "\303\204"\0
  CUR = 2
  LEN = 16

*** decode_utf8 = 'Ä' = "\xC4" at c:/tmp/b64_utf8_2.pl line 36
SV = PV(0x2607bf8) at 0x25c7f00
  REFCNT = 1
  FLAGS = (PADMY,POK,pPOK,UTF8)
  PV = 0x28323c8 "\303\204"\0 [UTF8 "\x{c4}"]
  CUR = 2
  LEN = 16


****** START

*** orig = 'ř' = "\x{159}" at c:/tmp/b64_utf8_2.pl line 21
SV = PV(0x36c9d8) at 0x25c8308
  REFCNT = 1
  FLAGS = (PADMY,POK,pPOK,UTF8)
  PV = 0x367478 "\305\231"\0 [UTF8 "\x{159}"]
  CUR = 2
  LEN = 16

*** encode_utf8 = 'Å™' = "\xC5\x99" at c:/tmp/b64_utf8_2.pl line 
+25
SV = PV(0x2607c48) at 0x25c8110
  REFCNT = 1
  FLAGS = (PADMY,POK,pPOK)
  PV = 0x28324e8 "\305\231"\0
  CUR = 2
  LEN = 16

*** encode_b64 = 'xZk=
' = "xZk=\n" at c:/tmp/b64_utf8_2.pl line 29
SV = PV(0x2607c58) at 0x25c80e0
  REFCNT = 1
  FLAGS = (PADMY,POK,pPOK)
  PV = 0x2832518 "xZk=\n"\0
  CUR = 5
  LEN = 16

*** decode_b64 = 'Å™' = "\xC5\x99" at c:/tmp/b64_utf8_2.pl line 3
+2
SV = PV(0x2607c38) at 0x25c7f48
  REFCNT = 1
  FLAGS = (PADMY,POK,pPOK)
  PV = 0x2832428 "\305\231"\0
  CUR = 2
  LEN = 16

*** decode_utf8 = 'ř' = "\x{159}" at c:/tmp/b64_utf8_2.pl line 36
SV = PV(0x2607bf8) at 0x25c7f00
  REFCNT = 1
  FLAGS = (PADMY,POK,pPOK,UTF8)
  PV = 0x28322a8 "\305\231"\0 [UTF8 "\x{159}"]
  CUR = 2
  LEN = 16