1) || /* multi-byte [unicode] */
($o < 32 || $o > 126) || /* <- control / latin weirdos -> */
($o > 33 && $o < 40) || /* quotes + ampersand */
($o > 59 && $o < 63) /* html */
) {
// convert to numeric entity
$c = mb_encode_numericentity($c, array(0x0, 0xffff, 0, 0xffff), 'UTF-8');
if ($allow_html) {
if ($c == '<') $c = '<';
if ($c == '>') $c = '>';
if ($c == '=') $c = '=';
if ($c == '"') $c = '"';
if ($c == ''') $c = '\'';
if ($c == '&') $c = '&'; // DM 24.08.2016 Re-added because OIDplus 1.0 XML export
}
if (!$encode_linebreaks) {
if ($allow_html) {
if ($c == "
") $c = "
";
if ($c == "
") $c = "
";
} else {
if ($c == "
") $c = "\n";
if ($c == "
") $c = "\r";
}
}
}
$str2 .= $c;
}
return $str2;
}
function ordUTF8($c, $index = 0, &$bytes = null) {
// http://de.php.net/manual/en/function.ord.php#78032
$len = strlen($c);
$bytes = 0;
if ($index >= $len) {
return false;
}
$h = ord($c[$index]);
if ($h <= 0x7F) {
$bytes = 1;
return $h;
} else if ($h < 0xC2) {
return false;
} else if ($h <= 0xDF && $index < $len - 1) {
$bytes = 2;
return ($h & 0x1F) << 6 | (ord($c[$index + 1]) & 0x3F);
} else if ($h <= 0xEF && $index < $len - 2) {
$bytes = 3;
return ($h & 0x0F) << 12 | (ord($c[$index + 1]) & 0x3F) << 6
| (ord($c[$index + 2]) & 0x3F);
} else if ($h <= 0xF4 && $index < $len - 3) {
$bytes = 4;
return ($h & 0x0F) << 18 | (ord($c[$index + 1]) & 0x3F) << 12
| (ord($c[$index + 2]) & 0x3F) << 6
| (ord($c[$index + 3]) & 0x3F);
} else {
return false;
}
}
function utf16_to_utf8($str) {
// http://betamode.de/2008/09/08/php-utf-16-zu-utf-8-konvertieren/
// http://www.moddular.org/log/utf16-to-utf8
$c0 = ord($str[0]);
$c1 = ord($str[1]);
if ($c0 == 0xFE && $c1 == 0xFF) {
$be = true;
} else if ($c0 == 0xFF && $c1 == 0xFE) {
$be = false;
} else {
return $str;
}
$str = substr($str, 2);
$len = strlen($str);
$dec = '';
for ($i = 0; $i < $len; $i += 2) {
$c = ($be) ? ord($str[$i]) << 8 | ord($str[$i + 1]) :
ord($str[$i + 1]) << 8 | ord($str[$i]);
if ($c >= 0x0001 && $c <= 0x007F) {
$dec .= chr($c);
} else if ($c > 0x07FF) {
$dec .= chr(0xE0 | (($c >> 12) & 0x0F));
$dec .= chr(0x80 | (($c >> 6) & 0x3F));
$dec .= chr(0x80 | (($c >> 0) & 0x3F));
} else {
$dec .= chr(0xC0 | (($c >> 6) & 0x1F));
$dec .= chr(0x80 | (($c >> 0) & 0x3F));
}
}
return $dec;
}
function html_named_to_numeric_entities($str) {
$str = mb_convert_encoding($str, 'UTF-8');
return mb_htmlentities(decodeNamedEntities($str));
}
if (!function_exists('decodeNamedEntities')) {
function decodeNamedEntities($string) {
// https://stackoverflow.com/questions/20406599/how-to-encode-for-entity-igrave-not-defined-error-in-xml-feed
static $entities = NULL;
if (NULL === $entities) {
$entities = array_flip(
array_diff(
get_html_translation_table(HTML_ENTITIES, ENT_COMPAT | ENT_HTML401, 'UTF-8'),
get_html_translation_table(HTML_ENTITIES, ENT_COMPAT | ENT_XML1, 'UTF-8')
)
);
}
return str_replace(array_keys($entities), $entities, $string);
}
}
if (!function_exists('mb_convert_encoding')) {
// https://riptutorial.com/php/example/15633/converting-unicode-characters-to-their-numeric-value-and-or-html-entities-using-php
function mb_convert_encoding($str, $to_encoding, $from_encoding = NULL) {
return iconv(($from_encoding === NULL) ? mb_internal_encoding() : $from_encoding, $to_encoding, $str);
}
}
if (!function_exists('mb_ord')) {
// https://riptutorial.com/php/example/15633/converting-unicode-characters-to-their-numeric-value-and-or-html-entities-using-php
function mb_ord($char, $encoding = 'UTF-8') {
if ($encoding === 'UCS-4BE') {
list(, $ord) = (strlen($char) === 4) ? @unpack('N', $char) : @unpack('n', $char);
return $ord;
} else {
return mb_ord(mb_convert_encoding($char, 'UCS-4BE', $encoding), 'UCS-4BE');
}
}
}
if (!function_exists('mb_htmlentities')) {
// https://riptutorial.com/php/example/15633/converting-unicode-characters-to-their-numeric-value-and-or-html-entities-using-php
// modified
function mb_htmlentities($string, $hex = true, $encoding = 'UTF-8') {
return preg_replace_callback('/[\x{80}-\x{10FFFF}]/u', function ($match) use ($hex, $encoding) {
$ord = (strtoupper($encoding) == 'UTF-8') ? ordUTF8($match[0]) : mb_ord($match[0], 'UTF-8');
return sprintf($hex ? '&#x%X;' : '&#%d;', $ord);
}, $string);
}
}