note 75942 deleted from function.utf8-encode by cmb
| From: | cmb@php.net | Date: | Sun, 22 Dec 2019 09:00:39 +0000 |
| Subject: | note 75942 deleted from function.utf8-encode by cmb | ||
| References: | 1 | Groups: | php.notes |
| Request: | Send a blank email to php-notes+get-213575@lists.php.net to get a copy of this message | ||
Note Submitter: luka8088 at gmail dot com
----
simple HTML to UTF-8 conversion:
function html_to_utf8 ($data)
{
return preg_replace("/\\&\\#([0-9]{3,10})\\;/e",
'_html_to_utf8("\\1")', $data);
}
function _html_to_utf8 ($data)
{
if ($data > 127)
{
$i = 5;
while (($i--) > 0)
{
if ($data != ($a = $data % ($p = pow(64, $i))))
{
$ret = chr(base_convert(str_pad(str_repeat(1, $i + 1), 8, "0"), 2, 10) + (($data - $a)
/ $p));
for ($i; $i > 0; $i--)
$ret .= chr(128 + ((($data % pow(64, $i)) - ($data % ($p = pow(64, $i - 1)))) / $p));
break;
}
}
}
else
$ret = "&#$data;";
return $ret;
}
Example:
echo html_to_utf8("a b č ć ž こ に ち
わ ()[]{}!#$?* < >");
Output:
a b Ä Ä Å¾ ã ã« ã¡ ã ()[]{}!#$?* < >