- mb_ord: documentation ( source)
- substr: documentation ( source)
- var_dump: documentation ( source)
- function_exists: documentation ( source)
- ord: documentation ( source)
- unpack: documentation ( source)
- sprintf: documentation ( source)
<?php
// PHP < 7.2
// https://github.com/symfony/polyfill-mbstring/blob/master/Mbstring.php#L708-L730
if( ! function_exists("mb_ord") ) {
function mb_ord($s) {
if (1 === \strlen($s)) {
return \ord($s);
}
$code = ($s = unpack('C*', substr($s, 0, 4))) ? $s[1] : 0;
if (0xF0 <= $code) {
return (($code - 0xF0) << 18) + (($s[2] - 0x80) << 12) + (($s[3] - 0x80) << 6) + $s[4] - 0x80;
}
if (0xE0 <= $code) {
return (($code - 0xE0) << 12) + (($s[2] - 0x80) << 6) + $s[3] - 0x80;
}
if (0xC0 <= $code) {
return (($code - 0xC0) << 6) + $s[2] - 0x80;
}
return $code;
}
}
function ord2seqlen($ord) {
if($ord < 128){
return 1;
} else if($ord < 224) {
return 2;
} else if($ord < 240) {
return 3;
} else if($ord < 248) {
return 4;
} else {
throw new \Exception("No support for 5 or 6 byte sequences.");
}
}
function utf8_seq_iter($input) {
for($i=0,$c=strlen($input); $i<$c; ) {
$bytes = ord2seqlen(ord($input[$i]));
yield substr($input, $i, $bytes);
$i += $bytes;
}
}
function escape_codepoint($codepoint, $skip_low=true) {
$ord = mb_ord($codepoint);
if( $skip_low && $ord < 128 ) {
return $codepoint;
} else {
return sprintf("\\u%04x", $ord);
}
}
$input = "आए थे पर्यटक, खुद ही बह गए";
$output = '';
foreach( utf8_seq_iter($input) as $codepoint ) {
$output .= escape_codepoint($codepoint);
}
var_dump($output);