php utf-8

<?php
//mb_internal_encoding("UTF-8");


$conn = mssql_connect( "MyServer2k", "user", "password" );
mssql_select_db('testing', $conn);



$query = "select top 10 * from member2";
$result = mssql_query( $query );

while( $row = mssql_fetch_array( $result ) ) {
 //echo strtoupper(ucs2toutf8($row['title']))."<br>";
 //echo iconv('UCS-2LE', 'UTF-8', $row['title'])."<br>";
 $title = $row['note2'];
 //$whichcode = mb_detect_encoding( $row['title'], "auto" );
 //$whichcode = is_utf8( $row['title'] );

 //$title = mb_convert_encoding( $row['title'], "UTF-8", "UCS-2LE" );

 //$title = preg_replace("/([\xE0-\xFA])/e","chr(215).chr(ord(\${1})-80)",$title);
 
 //$title = iconv( "", "UTF-8", $title );
 
 //$title = ucs2html( $title );

 echo $title."<br>";
}

echo "code: ".$whichcode;

 

function is_utf8($string) {
   
   // From http://w3.org/International/questions/qa-forms-utf-8.html
   return preg_match('%^(?:
         [\x09\x0A\x0D\x20-\x7E]            # ASCII
       | [\xC2-\xDF][\x80-\xBF]             # non-overlong 2-byte
       |  \xE0[\xA0-\xBF][\x80-\xBF]        # excluding overlongs
       | [\xE1-\xEC\xEE\xEF][\x80-\xBF]{2}  # straight 3-byte
       |  \xED[\x80-\x9F][\x80-\xBF]        # excluding surrogates
       |  \xF0[\x90-\xBF][\x80-\xBF]{2}     # planes 1-3
       | [\xF1-\xF3][\x80-\xBF]{3}          # planes 4-15
       |  \xF4[\x80-\x8F][\x80-\xBF]{2}     # plane 16
   )*$%xs', $string);
   
} // function is_utf8

function ucs2toutf8($str)
{
       for ($i=0;$i < strlen($str);$i+=4)
       {
               $substring1 = $str[$i].$str[$i+1];
               $substring2 = $str[$i+2].$str[$i+3];

               if ($substring1 == "00")
               {
                       $byte1 = "";
                       $byte2 = $substring2;
               }
               else
               {
                       $substring = $substring1.$substring2;
                       $byte1 = dechex(192+(hexdec($substring)/64));
                       $byte2 = dechex(128+(hexdec($substring)%64));
               }
               $utf8 .= $byte1.$byte2;
       }
       return $utf8;
}
function CP1251toUTF8($string){
 $out = '';
 for ($i = 0; $i < strlen($string); ++$i){
   $ch = ord($string{$i});
   if ($ch < 0x80) $out .= chr($ch);
   else
     if ($ch >= 0xC0)
       if ($ch < 0xF0)
            $out .= "\xD0".chr(0x90 + $ch - 0xC0); // А-Я, а-п (A-YA, a-p)
       else $out .= "\xD1".chr(0x80 + $ch - 0xF0); // р-я (r-ya)
     else
       switch($ch){
         case 0xA8: $out .= "\xD0\x81"; break; // YO
         case 0xB8: $out .= "\xD1\x91"; break; // yo
         // ukrainian
         case 0xA1: $out .= "\xD0\x8E"; break; // Ў (U)
         case 0xA2: $out .= "\xD1\x9E"; break; // ў (u)
         case 0xAA: $out .= "\xD0\x84"; break; // Є (e)
         case 0xAF: $out .= "\xD0\x87"; break; // Ї (I..)
         case 0xB2: $out .= "\xD0\x86"; break; // I (I)
         case 0xB3: $out .= "\xD1\x96"; break; // i (i)
         case 0xBA: $out .= "\xD1\x94"; break; // є (e)
         case 0xBF: $out .= "\xD1\x97"; break; // ї (i..)
         // chuvashian
         case 0x8C: $out .= "\xD3\x90"; break; // Ӑ (A)
         case 0x8D: $out .= "\xD3\x96"; break; // Ӗ (E)
         case 0x8E: $out .= "\xD2\xAA"; break; // Ҫ (SCH)
         case 0x8F: $out .= "\xD3\xB2"; break; // Ӳ (U)
         case 0x9C: $out .= "\xD3\x91"; break; // ӑ (a)
         case 0x9D: $out .= "\xD3\x97"; break; // ӗ (e)
         case 0x9E: $out .= "\xD2\xAB"; break; // ҫ (sch)
         case 0x9F: $out .= "\xD3\xB3"; break; // ӳ (u)
       }
 }
 return $out;
}

function ucs2html($str) {
$str=trim($str); // if you are reading from file
$len=strlen($str);
$html='';
for($i=0;$i < $len;$i+=2)
$html.='&#'.hexdec(dechex(ord($str[$i+1])).
          sprintf("%02s",dechex(ord($str[$i])))).';';
return($html);
}
?>