Description
NOTE: This function checks for 5-Byte sequences, UTF8 has Bytes Sequences with a maximum length of 4.
Parameters
- $str
-
(string) (Required) The string to be checked
Return
(bool) True if $str fits a UTF-8 model, false otherwise.
Source
File: wp-includes/formatting.php
function seems_utf8( $str ) {
mbstring_binary_safe_encoding();
$length = strlen( $str );
reset_mbstring_encoding();
for ( $i = 0; $i < $length; $i++ ) {
$c = ord( $str[ $i ] );
if ( $c < 0x80 ) {
$n = 0; // 0bbbbbbb
} elseif ( ( $c & 0xE0 ) == 0xC0 ) {
$n = 1; // 110bbbbb
} elseif ( ( $c & 0xF0 ) == 0xE0 ) {
$n = 2; // 1110bbbb
} elseif ( ( $c & 0xF8 ) == 0xF0 ) {
$n = 3; // 11110bbb
} elseif ( ( $c & 0xFC ) == 0xF8 ) {
$n = 4; // 111110bb
} elseif ( ( $c & 0xFE ) == 0xFC ) {
$n = 5; // 1111110b
} else {
return false; // Does not match any model.
}
for ( $j = 0; $j < $n; $j++ ) { // n bytes matching 10bbbbbb follow ?
if ( ( ++$i == $length ) || ( ( ord( $str[ $i ] ) & 0xC0 ) != 0x80 ) ) {
return false;
}
}
}
return true;
}
Changelog
Version | Description |
1.2.1 | Introduced. |