note 99422 deleted from function.utf8-encode by danbrown

Note Submitter: petepostma at gmail ---- squeegee, good idea! I fixed up the code, used output buffering over repeated string concatenation, combined them to a single function, changed the initial preg to match multiple of any valid characters (instead of just ascii), and a few more speed ups. Little quicker through out and and easier on memory on the second part. function fix_encoding($instr){ if(mb_check_encoding($instr,'UTF-8'))return $instr; // no need for the rest if it's all valid UTF-8 already global $NIBBLE_GOOD_CHARS,$ENCODE_BYTE_MAP; if(empty($ENCODE_BYTE_MAP)) { $ENCODE_BYTE_MAP=array(); //byte-map-array, empty $cp1252_map=array( //windows-1252 char re-map information "\x80"=>"\xE2\x82\xAC", // EURO SIGN "\x82" => "\xE2\x80\x9A", // SINGLE LOW-9 QUOTATION MARK "\x83" => "\xC6\x92", // LATIN SMALL LETTER F WITH HOOK "\x84" => "\xE2\x80\x9E", // DOUBLE LOW-9 QUOTATION MARK "\x85" => "\xE2\x80\xA6", // HORIZONTAL ELLIPSIS "\x86" => "\xE2\x80\xA0", // DAGGER "\x87" => "\xE2\x80\xA1", // DOUBLE DAGGER "\x88" => "\xCB\x86", // MODIFIER LETTER CIRCUMFLEX ACCENT "\x89" => "\xE2\x80\xB0", // PER MILLE SIGN "\x8A" => "\xC5\xA0", // LATIN CAPITAL LETTER S WITH CARON "\x8B" => "\xE2\x80\xB9", // SINGLE LEFT-POINTING ANGLE QUOTATION MARK "\x8C" => "\xC5\x92", // LATIN CAPITAL LIGATURE OE "\x8E" => "\xC5\xBD", // LATIN CAPITAL LETTER Z WITH CARON "\x91" => "\xE2\x80\x98", // LEFT SINGLE QUOTATION MARK "\x92" => "\xE2\x80\x99", // RIGHT SINGLE QUOTATION MARK "\x93" => "\xE2\x80\x9C", // LEFT DOUBLE QUOTATION MARK "\x94" => "\xE2\x80\x9D", // RIGHT DOUBLE QUOTATION MARK "\x95" => "\xE2\x80\xA2", // BULLET "\x96" => "\xE2\x80\x93", // EN DASH "\x97" => "\xE2\x80\x94", // EM DASH "\x98" => "\xCB\x9C", // SMALL TILDE "\x99" => "\xE2\x84\xA2", // TRADE MARK SIGN "\x9A" => "\xC5\xA1", // LATIN SMALL LETTER S WITH CARON "\x9B" => "\xE2\x80\xBA", // SINGLE RIGHT-POINTING ANGLE QUOTATION MARK "\x9C" => "\xC5\x93", // LATIN SMALL LIGATURE OE "\x9E" => "\xC5\xBE", // LATIN SMALL LETTER Z WITH CARON "\x9F" => "\xC5\xB8" // LATIN CAPITAL LETTER Y WITH DIAERESIS ); //build the encode_byte_map array keeping the index in incrementing order for($x=128;$x<256;++$x){ $ch = chr($x); //get the character if(isset($cp1252_map[$ch])) //look up if its Windows-1252 $ENCODE_BYTE_MAP[$ch] = $cp1252_map[$ch]; else $ENCODE_BYTE_MAP[$ch]=utf8_encode($ch); //simple conversion } } if(empty($NIBBLE_GOOD_CHARS)) { $ascii_char='[\x00-\x7F]'; $cont_byte='[\x80-\xBF]'; $utf8_2='[\xC0-\xDF]'.$cont_byte; $utf8_3='[\xE0-\xEF]'.$cont_byte.'{2}'; $utf8_4='[\xF0-\xF7]'.$cont_byte.'{3}'; $utf8_5='[\xF8-\xFB]'.$cont_byte.'{4}'; //set it took look for any good character combinations repeatedly $NIBBLE_GOOD_CHARS = "@^(($ascii_char|$utf8_2|$utf8_3|$utf8_4|$utf8_5)+)(.*)$@s"; } ob_start(); $char=''; $rest=''; while((strlen($instr))>0){ //match all good characters if(1==preg_match($NIBBLE_GOOD_CHARS,$instr,$match)){ $char=$match[1]; $instr=$match[3]; echo $char; unset($match); } //we can continue with the operations if the string is not empty if(!empty($instr)) { //'byting' the string is 30% more efficient than preg('/(.)(.*)/s' $char=$instr[0]; if(strlen($instr)>1) $instr=substr($instr,1); //set to remainder of string else $instr=''; //set to empty if its done and let the loop terminate echo $ENCODE_BYTE_MAP[$char]; } } $outstr = ob_get_clean(); return $outstr; }