2
Test get_next_char(), used by htmlentities()/htmlspecialchars(): validity of UTF-8 sequences
6
/* conformance to Unicode 5.2, section 3.9, D92 */
9
array(array(0x00, 0x7F)),
10
array(array(0xC2, 0xDF), array(0x80, 0xBF)),
11
array(array(0xE0, 0xE0), array(0xA0, 0xBF), array(0x80, 0xBF)),
12
array(array(0xE1, 0xEC), array(0x80, 0xBF), array(0x80, 0xBF)),
13
array(array(0xED, 0xED), array(0x80, 0x9F), array(0x80, 0xBF)),
14
array(array(0xEE, 0xEF), array(0x80, 0xBF), array(0x80, 0xBF)),
15
array(array(0xF0, 0xF0), array(0x90, 0xBF), array(0x80, 0xBF), array(0x80, 0xBF)),
16
array(array(0xF1, 0xF3), array(0x80, 0xBF), array(0x80, 0xBF), array(0x80, 0xBF)),
17
array(array(0xF4, 0xF4), array(0x80, 0x8F), array(0x80, 0xBF), array(0x80, 0xBF)),
20
function is_valid($seq) {
23
foreach ($val_ranges as $l) {
24
if ($b >= $l[0][0] && $b <= $l[0][1]) {
25
if (count($l) != strlen($seq)) {
28
for ($n = 1; $n < strlen($seq); $n++) {
29
if (ord($seq[$n]) < $l[$n][0] || ord($seq[$n]) > $l[$n][1]) {
39
function concordance($s) {
40
$vhe = strlen(htmlspecialchars($s, ENT_QUOTES, "UTF-8")) > 0;
45
for ($b1 = 0xC0; $b1 < 0xE0; $b1++) {
46
for ($b2 = 0x80; $b2 < 0xBF; $b2++) {
47
$s = chr($b1).chr($b2);
49
echo "Discordance for ".bin2hex($s),"\n";
54
for ($b1 = 0xE0; $b1 < 0xEF; $b1++) {
55
for ($b2 = 0x80; $b2 < 0xBF; $b2++) {
56
$s = chr($b1).chr($b2)."\x80";
58
echo "Discordance for ".bin2hex($s),"\n";
59
$s = chr($b1).chr($b2)."\xBF";
61
echo "Discordance for ".bin2hex($s),"\n";
65
for ($b1 = 0xF0; $b1 < 0xFF; $b1++) {
66
for ($b2 = 0x80; $b2 < 0xBF; $b2++) {
67
$s = chr($b1).chr($b2)."\x80\x80";
69
echo "Discordance for ".bin2hex($s),"\n";
70
$s = chr($b1).chr($b2)."\xBF\x80";
72
echo "Discordance for ".bin2hex($s),"\n";
73
$s = chr($b1).chr($b2)."\x80\xBF";
75
echo "Discordance for ".bin2hex($s),"\n";
76
$s = chr($b1).chr($b2)."\xBF\xBF";
78
echo "Discordance for ".bin2hex($s),"\n";