PHP Invalid UTF-8 Samples

Submitted by michael on Thu, 09/02/2021 - 09:42
Excerpt

<?php
$examples
= array(
   
'Valid ASCII' => "a",
   
'Valid 2 Octet Sequence' => "\xc3\xb1",
   
'Invalid 2 Octet Sequence' => "\xc3\x28",
   
'Invalid Sequence Identifier' => "\xa0\xa1",
   
'Valid 3 Octet Sequence' => "\xe2\x82\xa1",
   
'Invalid 3 Octet Sequence (in 2nd Octet)' => "\xe2\x28\xa1",
   
'Invalid 3 Octet Sequence (in 3rd Octet)' => "\xe2\x82\x28",

   
'Valid 4 Octet Sequence' => "\xf0\x90\x8c\xbc",
   
'Invalid 4 Octet Sequence (in 2nd Octet)' => "\xf0\x28\x8c\xbc",
   
'Invalid 4 Octet Sequence (in 3rd Octet)' => "\xf0\x90\x28\xbc",
   
'Invalid 4 Octet Sequence (in 4th Octet)' => "\xf0\x28\x8c\x28",
   
'Valid 5 Octet Sequence (but not Unicode!)' => "\xf8\xa1\xa1\xa1\xa1",
   
'Valid 6 Octet Sequence (but not Unicode!)' => "\xfc\xa1\xa1\xa1\xa1\xa1",
);