use HTML::Entities qw( decode_entities ); use locale qw(); my $lc = decode_entities('ä'); my $uc = decode_entities('Ä'); utf8::downgrade($uc); for (0..2) { if ($_ == 0) { utf8::downgrade($lc); locale->unimport(); print("Byte Semantics\n"); print("--------------\n"); } elsif ($_ == 1) { utf8::downgrade($lc); locale->import(); print("Locale Semantics\n"); print("----------------\n"); } elsif ($_ == 2) { utf8::upgrade($lc); locale->unimport(); print("Unicode Semantics\n"); print("-----------------\n"); } if ($lc =~ /^\Q$uc\E\z/) { print("case sensitive match\n"); } elsif ($lc =~ /^\Q$uc\E\z/i) { print("case insensitive match\n"); } else { print("no match\n"); } if ($lc =~ /^[[:alpha:]]\z/) { print("[:alpha:]\n"); } else { print("Not [:alpha:]\n"); } if ($lc =~ /^[\p{IsAlpha}]\z/) { print("\\p{IsAlpha}\n"); } else { print("Not \\p{IsAlpha}\n"); } print("\n"); } #### Byte Semantics -------------- no match Not [:alpha:] \p{IsAlpha} Locale Semantics ---------------- no match Not [:alpha:] \p{IsAlpha} Unicode Semantics ----------------- case insensitive match [:alpha:] \p{IsAlpha}