<?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",
);
echo "++Invalid UTF-8 in pattern\n";
foreach ( $examples as $name => $str ) {
echo "$name\n";
preg_match("/".$str."/u",'Testing');
}
echo "++ preg_match() examples\n";
foreach ( $examples as $name => $str ) {
preg_match("/\xf8\xa1\xa1\xa1\xa1/u", $str, $ar);
echo "$name: ";
if ( count($ar) == 0 ) {
echo "Matched nothing!\n";
} else {
echo "Matched {$ar[0]}\n";
}
}
echo "++ preg_match_all() examples\n";
foreach ( $examples as $name => $str ) {
preg_match_all('/./u', $str, $ar);
echo "$name: ";
$num_utf8_chars = count($ar[0]);
if ( $num_utf8_chars == 0 ) {
echo "Matched nothing!\n";
} else {
echo "Matched $num_utf8_chars character\n";
}
}
preferences:
33.4 ms | 402 KiB | 5 Q