#!/usr/bin/perl
# Demonstrate some real-world encoding fixes.
# This has been tested on Perls 5.6.1 and 5.8.0.

BEGIN {
        require v5.6.0;
}
use utf8;
no bytes;
binmode STDOUT, ':utf8' if $] >= 5.008;   # suppresses a warning

# Correctly encoded data (string-is-unicode bit set)

print "\n\$good:\n";
$good = chr(0x03B1) . chr(0x00DF) . chr(0x044D);
print $good, "\n",
      length($good), "\n";     # three characters


# Make a copy without the string-is-unicode bit set on it
# This is the kind of thing DBD::mysql returns if you put something like $good
# into the database originally.

binmode STDOUT, ':bytes' if $] >= 5.008;
print "\n\$bad:\n";
$bad = pack("C0C*", unpack("C0C*", $good));
print $bad, "\n",
      length($bad), "\n";      # six bytes

print "\n(\$bad eq \$good): " . (($bad eq $good) ? "yes" : "no") . "\n";
# At Perl 5.6.1, this says "yes".
# At Perl 5.8.0, this says "no".

# Repack the bad string into another correctly-tagged string

binmode STDOUT, ':utf8' if $] >= 5.008;
print "\n\$also_good:\n";
$also_good = pack("U0U*", unpack("U0U*", $bad));
print $also_good, "\n",
      length($also_good), "\n";


print "\n(\$bad eq \$also_good): "
        . (($bad eq $also_good) ? "yes" : "no") . "\n";
print "(\$good eq \$also_good): "
        . (($good eq $also_good) ? "yes" : "no") . "\n\n";