You've got another problem. Your browser incorrectly passed the ę character as %C4%88 that is, as a string which happens to be UTF-8 but should have passed it as %u0119. You've got to *guess* during your URL parsing if someone has started passing you a byte-string which happens to look like a UTF-8 string and if so, reinterpret it as UTF-8 instead. If you're being fully careful, you should also be using the Content-Type of the HTTP header your server sends, the client sends, and the HTML content encoding you sent when generating your page.

Here's what I use.

sub uri_unescape {
    my $to_decode = shift;

    return if ! defined $to_decode;
    $to_decode =~ s/\+/ /g;

    # A "good enough" check to see if the browser encoded high bit
    # characters as UTF-8 by looking for something that resembles a
    # URL-encoded utf8 octet series
    #
    # utf8 encoding starts with 11xxxxxx in the first byte and
    # 10xxxxxx in the subsequent bytes
    # http://en.wikipedia.org/wiki/UTF-8#Description
    my $is_byte_encoded_utf8 = $to_decode =~ /%[c-fC-F][[:xdigit:]]%[8
+9abAB][[:xdigit:]]/;

    $to_decode =~ s/%([[:xdigit:]]{2})/chr hex "0x$1"/eg;

    # Decode the "UTF-8" if it looked like it was such. If I enter
    # this block, the string may now be UTF-8 encoded as a perl
    # string.
    if ($is_byte_encoded_utf8) {
        $to_decode = Encode::decode( 'utf8', $to_decode );
    }

    # Promote %uXXXX escapes up to characters. This is after the
    # Encode call so I don't inadvertently cause a promotion to utf8
    # and then ask Encode to do another promotion.
    $to_decode =~ s/%u([[:xdigit:]]{4})/chr hex "0x$1"/eg;

    return $to_decode;
}
[download]