Something like the following may help (
encode_monk and
decode_monk are only there to save you potential character set problems with your text editor -- don't let them distract you). Cheers.
use strict;
use warnings;
use Encode 'decode_utf8';
my $suspect = decode_utf8( decode_monk('v~C3~A4hicule') );
warn '$suspect='.$suspect;
if ($suspect =~ /^([\p{IsAlnum}]+)$/) {
warn "MATCHES $1\n";
}
exit( 0 );
##------------------------------------------------------------------+
## WARNING: Using sprintf here is too expensive. A
## lookup table may be the best solution.
sub encode_monk {
my ($txt) = @_;
join q(),
map {
( $_ >= 0x20 && $_ <= 0x7D )
? ( sprintf "%c", $_ )
: ( sprintf "~%02X", $_ )
}
unpack "C*", $txt;
}
##------------------------------------------------------------------+
## WARNING: Consider err policy here.
sub decode_monk {
my ($code) = @_;
if (! defined $code or length( $code ) == 0) {
return;
}
$code =~ s/\~([\da-fA-F]{2})/chr( hex( $1 ) )/eg;
return $code;
}
