utf8

source of perl for linux application,

  utf8.c AOK

     [utf8_to_uv]
     Malformed UTF-8 character
	my $a = ord "\x80" ;

     Malformed UTF-8 character
	my $a = ord "\xf080" ;
     <<<<<< this warning can't be easily triggered from perl anymore

     [utf16_to_utf8]
     Malformed UTF-16 surrogate		
     <<<<<< Add a test when somethig actually calls utf16_to_utf8

__END__
# utf8.c [utf8_to_uv] -W
BEGIN {
    if (ord('A') == 193) {
        print "SKIPPED\n# ebcdic platforms do not generate Malformed UTF-8 warnings.";
        exit 0;
    }
}
use utf8 ;
my $a = "sn鴖torm" ;
{
    no warnings 'utf8' ;
    my $a = "sn鴖torm";
    use warnings 'utf8' ;
    my $a = "sn鴖torm";
}
EXPECT
Malformed UTF-8 character (unexpected non-continuation byte 0x73, immediately after start byte 0xf8) at - line 9.
Malformed UTF-8 character (unexpected non-continuation byte 0x73, immediately after start byte 0xf8) at - line 14.
########
use warnings 'utf8';
my $d7ff  = chr(0xD7FF);
my $d800  = chr(0xD800);
my $dfff  = chr(0xDFFF);
my $e000  = chr(0xE000);
my $feff  = chr(0xFEFF);
my $fffd  = chr(0xFFFD);
my $fffe  = chr(0xFFFE);
my $ffff  = chr(0xFFFF);
my $hex4  = chr(0x10000);
my $hex5  = chr(0x100000);
my $maxm1 = chr(0x10FFFE);
my $max   = chr(0x10FFFF);
no warnings 'utf8';
my $d7ff  = chr(0xD7FF);
my $d800  = chr(0xD800);
my $dfff  = chr(0xDFFF);
my $e000  = chr(0xE000);
my $feff  = chr(0xFEFF);
my $fffd  = chr(0xFFFD);
my $fffe  = chr(0xFFFE);
my $ffff  = chr(0xFFFF);
my $hex4  = chr(0x10000);
my $hex5  = chr(0x100000);
my $maxm1 = chr(0x10FFFE);
my $max   = chr(0x10FFFF);
EXPECT
UTF-16 surrogate 0xd800 at - line 3.
UTF-16 surrogate 0xdfff at - line 4.
Unicode character 0xfffe is illegal at - line 8.
Unicode character 0xffff is illegal at - line 9.
Unicode character 0x10fffe is illegal at - line 12.
Unicode character 0x10ffff is illegal at - line 13.
########
use warnings 'utf8';
my $d7ff  = pack("U", 0xD7FF);
my $d800  = pack("U", 0xD800);
my $dfff  = pack("U", 0xDFFF);
my $e000  = pack("U", 0xE000);
my $feff  = pack("U", 0xFEFF);
my $fffd  = pack("U", 0xFFFD);
my $fffe  = pack("U", 0xFFFE);
my $ffff  = pack("U", 0xFFFF);
my $hex4  = pack("U", 0x10000);
my $hex5  = pack("U", 0x100000);
my $maxm1 = pack("U", 0x10FFFE);
my $max   = pack("U", 0x10FFFF);
no warnings 'utf8';
my $d7ff  = pack("U", 0xD7FF);
my $d800  = pack("U", 0xD800);
my $dfff  = pack("U", 0xDFFF);
my $e000  = pack("U", 0xE000);
my $feff  = pack("U", 0xFEFF);
my $fffd  = pack("U", 0xFFFD);
my $fffe  = pack("U", 0xFFFE);
my $ffff  = pack("U", 0xFFFF);
my $hex4  = pack("U", 0x10000);
my $hex5  = pack("U", 0x100000);
my $maxm1 = pack("U", 0x10FFFE);
my $max   = pack("U", 0x10FFFF);
EXPECT
UTF-16 surrogate 0xd800 at - line 3.
UTF-16 surrogate 0xdfff at - line 4.
Unicode character 0xfffe is illegal at - line 8.
Unicode character 0xffff is illegal at - line 9.
Unicode character 0x10fffe is illegal at - line 12.
Unicode character 0x10ffff is illegal at - line 13.
########
use warnings 'utf8';
my $d7ff  = "\x{D7FF}";
my $d800  = "\x{D800}";
my $dfff  = "\x{DFFF}";
my $e000  = "\x{E000}";
my $feff  = "\x{FEFF}";
my $fffd  = "\x{FFFD}";
my $fffe  = "\x{FFFE}";
my $ffff  = "\x{FFFF}";
my $hex4  = "\x{10000}";
my $hex5  = "\x{100000}";
my $maxm1 = "\x{10FFFE}";
my $max   = "\x{10FFFF}";
no warnings 'utf8';
my $d7ff  = "\x{D7FF}";
my $d800  = "\x{D800}";
my $dfff  = "\x{DFFF}";
my $e000  = "\x{E000}";
my $feff  = "\x{FEFF}";
my $fffd  = "\x{FFFD}";
my $fffe  = "\x{FFFE}";
my $ffff  = "\x{FFFF}";
my $hex4  = "\x{10000}";
my $hex5  = "\x{100000}";
my $maxm1 = "\x{10FFFE}";
my $max   = "\x{10FFFF}";
EXPECT
UTF-16 surrogate 0xd800 at - line 3.
UTF-16 surrogate 0xdfff at - line 4.
Unicode character 0xfffe is illegal at - line 8.
Unicode character 0xffff is illegal at - line 9.
Unicode character 0x10fffe is illegal at - line 12.
Unicode character 0x10ffff is illegal at - line 13.