| public static convertToASCIIDumbLossless ( string $str ) : string | ||
| $str | string | UTF-8 string to be converted to ASCII |
| return | string | ASCII encoded string with non-ASCII character entity-ized |
public static function convertToASCIIDumbLossless($str)
{
$bytesleft = 0;
$result = '';
$working = 0;
$len = strlen($str);
for ($i = 0; $i < $len; $i++) {
$bytevalue = ord($str[$i]);
if ($bytevalue <= 0x7f) {
//0xxx xxxx
$result .= chr($bytevalue);
$bytesleft = 0;
} elseif ($bytevalue <= 0xbf) {
//10xx xxxx
$working = $working << 6;
$working += $bytevalue & 0x3f;
$bytesleft--;
if ($bytesleft <= 0) {
$result .= "&#" . $working . ";";
}
} elseif ($bytevalue <= 0xdf) {
//110x xxxx
$working = $bytevalue & 0x1f;
$bytesleft = 1;
} elseif ($bytevalue <= 0xef) {
//1110 xxxx
$working = $bytevalue & 0xf;
$bytesleft = 2;
} else {
//1111 0xxx
$working = $bytevalue & 0x7;
$bytesleft = 3;
}
}
return $result;
} /**
* Converts a string from UTF-8 based on configuration.
* @note Currently, this is a lossy conversion, with unexpressable
* characters being omitted.
*/
public static function convertFromUTF8($str, $config, $context)
{
static $iconv = null;
if ($iconv === null) {
$iconv = function_exists('iconv');
}
$encoding = $config->get('Core', 'Encoding');
if ($encoding === 'utf-8') {
return $str;
}
if ($config->get('Core', 'EscapeNonASCIICharacters')) {
$str = HTMLPurifier_Encoder::convertToASCIIDumbLossless($str);
}
if ($iconv && !$config->get('Test', 'ForceNoIconv')) {
return @iconv('utf-8', $encoding . '//IGNORE', $str);
} elseif ($encoding === 'iso-8859-1') {
return @utf8_decode($str);
}
trigger_error('Encoding not supported', E_USER_ERROR);
}
