note 68491 added to function.html-entity-decode

Here is the ultimate functions to convert HTML entities to UTF-8 : The main function is htmlentities2utf8 Others are helper functions function chr_utf8($code) { if ($code < 0) return false; elseif ($code < 128) return chr($code); elseif ($code < 160) // Remove Windows Illegals Cars { if ($code==128) $code=8364; elseif ($code==129) $code=160; // not affected elseif ($code==130) $code=8218; elseif ($code==131) $code=402; elseif ($code==132) $code=8222; elseif ($code==133) $code=8230; elseif ($code==134) $code=8224; elseif ($code==135) $code=8225; elseif ($code==136) $code=710; elseif ($code==137) $code=8240; elseif ($code==138) $code=352; elseif ($code==139) $code=8249; elseif ($code==140) $code=338; elseif ($code==141) $code=160; // not affected elseif ($code==142) $code=381; elseif ($code==143) $code=160; // not affected elseif ($code==144) $code=160; // not affected elseif ($code==145) $code=8216; elseif ($code==146) $code=8217; elseif ($code==147) $code=8220; elseif ($code==148) $code=8221; elseif ($code==149) $code=8226; elseif ($code==150) $code=8211; elseif ($code==151) $code=8212; elseif ($code==152) $code=732; elseif ($code==153) $code=8482; elseif ($code==154) $code=353; elseif ($code==155) $code=8250; elseif ($code==156) $code=339; elseif ($code==157) $code=160; // not affected elseif ($code==158) $code=382; elseif ($code==159) $code=376; } if ($code < 2048) return chr(192 | ($code >> 6)) . chr(128 | ($code & 63)); elseif ($code < 65536) return chr(224 | ($code >> 12)) . chr(128 | (($code >> 6) & 63)) . chr(128 | ($code & 63)); else return chr(240 | ($code >> 18)) . chr(128 | (($code >> 12) & 63)) . chr(128 | (($code >> 6) & 63)) . chr(128 | ($code & 63)); } // Callback for preg_replace_callback('~&(#(x?))?([^;]+);~', 'html_entity_replace', $str); function html_entity_replace($matches) { if ($matches[2]) { return chr_utf8(hexdec($matches[3])); } elseif ($matches[1]) { return chr_utf8($matches[3]); } switch ($matches[3]) { case "nbsp": return chr_utf8(160); case "iexcl": return chr_utf8(161); case "cent": return chr_utf8(162); case "pound": return chr_utf8(163); case "curren": return chr_utf8(164); case "yen": return chr_utf8(165); //... etc with all named HTML entities } return false; } function htmlentities2utf8 ($string) // because of the html_entity_decode() bug with UTF-8 { $string = preg_replace_callback('~&(#(x?))?([^;]+);~', 'html_entity_replace', $string); return $string; } ---- Server IP: 217.174.203.10 Probable Submitter: 82.249.138.219 ---- X-Spam-Status: Yes, hits=7.4 required=5.0 tests=DATE_MISSING,FROM_NO_LOWER, HEAD_ILLEGAL_CHARS autolearn=no version=2.64 ---- Manual Page -- http://www.php.net/manual/en/function.html-entity-decode.php Edit -- http://master.php.net/note/edit/68491 Del: integrated -- http://master.php.net/note/delete/68491/integrated Del: useless -- http://master.php.net/note/delete/68491/useless Del: bad code -- http://master.php.net/note/delete/68491/bad+code Del: spam -- http://master.php.net/note/delete/68491/spam Del: non-english -- http://master.php.net/note/delete/68491/non-english Del: in docs -- http://master.php.net/note/delete/68491/in+docs Del: other reasons-- http://master.php.net/note/delete/68491 Reject -- http://master.php.net/note/reject/68491 Search -- http://master.php.net/manage/user-notes.php