PHP_PHP チュートリアルで GB エンコーディングを UTF-8 に動的に変換するいくつかの方法の評価

require_once ("func_ip.php");
function u2utf8($c) {
$str = "";
if ($c < 0x80) {
$str .= $c;
} elseif ($c < 0x800) {
$str .= chr(0xC0 | $c >> 6);
   $str .= chr(0x80 | $c & 0x3F);
 } elseif ($c < 0x10000) {
$str .= chr(0xE0 | $c >> 12);
   $str .= chr(0x80 | $c >> 6 & 0x3F);
   $str .= chr(0x80 | $c & 0x3F);
 } elseif ($c < 0x200000) {
$str .= chr(0xF0 | $c >> 18);
   $str .= chr(0x80 | $c >> 12 & 0x3F);
   $str .= chr(0x80 | $c >> 6 & 0x3F);
   $str .= chr(0x80 | $c & 0x3F);
 }
 return $str;
}
function GB2UTF8_SQL($strGB) {
 if (!trim($strGB)) return $strGB;
 $strRet = "";
 $intLen = strlen($strGB);
 for ($i = 0; $i < $intLen; $i++) {
if (ord($strGB{$i}) > 127) {
       $strCurr = substr($strGB, $i, 2);
       $intGB = hexdec(bin2hex($strCurr)) - 0x8080;
       $strSql = "SELECT code_unicode FROM nnstats_gb_unicode
         WHERE code_gb = ".$intGB." LIMIT 1"
       ;
       $resResult = mysql_query($strSql);
       if ($arrCode = mysql_fetch_array($resResult)) $strRet .= u2utf8($arrCode["code_unicode"]);
       else $strRet .= "??";
       $i++;
   } else {
       $strRet .= $strGB{$i};
   }
 }
 return $strRet;
}
function GB2UTF8_FILE($strGB) {
 if (!trim($strGB)) return $strGB;
 $arrLines = file("gb_unicode.txt");
 foreach ($arrLines as $strLine) {
   $arrCodeTable[hexdec(substr($strLine, 0, 6))] = hexdec(substr($strLine, 7, 6));
 }
 $strRet = "";
 $intLen = strlen($strGB);
 for ($i = 0; $i < $intLen; $i++) {
if (ord($strGB{$i}) > 127) {
       $strCurr = substr($strGB, $i, 2);
       $intGB = hexdec(bin2hex($strCurr)) - 0x8080;
       if ($arrCodeTable[$intGB]) $strRet .= u2utf8($arrCodeTable[$intGB]);
       else $strRet .= "??";
       $i++;
   } else {
       $strRet .= $strGB{$i};
   }
 }
 return $strRet;
}
function EncodeIp($strDotquadIp) {
 $arrIpSep = explode(., $strDotquadIp);
 if (count($arrIpSep) != 4) return 0;
 $intIp = 0;  
 foreach ($arrIpSep as $k => $v) $intIp += (int)$v * pow(256, 3 - $k);
 return $intIp;
 //return sprintf(\%02x%02x%02x%02x, $arrIpSep[0], $arrIpSep[1], $arrIpSep[2], $arrIpSep[3]);
}
function GetMicroTime() {
 list($msec, $sec) = explode(" ", microtime());
 return ((double)$msec + (double)$sec);
}
for ($i = 0; $i < 100; $i++) { // 随机产生100个ip地址
$strIp = mt_rand(0, 255).".".mt_rand(0, 255).".".mt_rand(0, 255).".".mt_rand(0, 255);
$arrAddr[$i] = ip2addr(EncodeIp($strIp));
}
$resConn = mysql_connect("localhost", "netnest", "netnest");
mysql_select_db("test");
// 测评MySQL查询的编码转换
$dblTimeStart = GetMicroTime();
for ($i = 0; $i < 100; $i++) {
$strUTF8Region = GB2UTF8_SQL($arrAddr[$i]["region"]);
$strUTF8Address = GB2UTF8_SQL($arrAddr[$i]["address"]);
}
$dblTimeDuration = GetMicroTime() - $dblTimeStart;
// 测评结束并输出结果
echo $dblTimeDuration; echo " ";
// 测评文本文件查询的编码转换
$dblTimeStart = GetMicroTime();
for ($i = 0; $i < 100; $i++) {
$strUTF8Region = GB2UTF8_FILE($arrAddr[$i]["region"]);
$strUTF8Address = GB2UTF8_FILE($arrAddr[$i]["address"]);
}
$dblTimeDuration = GetMicroTime() - $dblTimeStart;
// 测评结束并输出结果
echo $dblTimeDuration; echo " ";
?>

0x2121 0x3000 #IDEOGRAPHIC SPACE
0x2122 0x3001 #IDEOGRAPHIC COMMA
0x2123 0x3002 #IDEOGRAPHIC FULL STOP
0x2124 0x30FB #カタカナ中点
0x2125 0x02C9 #修飾文字 MACRON (中国語の最初の声調)
……
0x552A 0x6458 #
0x552B 0x658B #
0x552C 0x5B85 #
0x552D 0x7A84 #
……
0x777B 0x9F37 #
0x777 C 0x9F3D #
0x777D 0x9F3E # ;
0x777E 0x9F44 #

$arrLines = file("gb_unicode.txt");
foreach ($arrLines as $strLine) {
$arrCodeTable[hexdec(substr($strLine, 0, 6))] = hexdec(substr( $strLine, 7, 6));
}
ksort($arrCodeTable);
$intCount = count($arrCodeTable);
$strCount = chr($intCount % 256) chr(floor($intCount / 256)) ;
$fileGBU = fopen("gbu.dat", "wb");
fwrite($fileGBU, $strCount);
foreach ($arrCodeTable as $k => $v) {
$strData = chr($ k % 256) . chr($v % 256) ;
fwrite($fileGBU, $strData);
}
fclose( $fileGBU);
?>

function GB2UTF8_FILE1($strGB) {
if (!trim($strGB)) return $strGB;
$fileGBU = fopen("gbu.dat", "rb");
$strBuf = fread($fileGBU, 2) ;
$intCount = ord($strBuf{0}) + 256 * ord($strBuf{1});
$strRet = "";
$intLen = strlen($strGB);
for ($i = 0; $i if (ord($strGB{$i}) > 127) {
$strCurr = substr($strGB, $i, 2);
$intGB = hexdec(bin2hex) ($strCurr)) - 0x8080;
$intStart = 1;
$intEnd = $intCount;
while ($intStart < $intEnd - 1) { // ハーフメソッドで検索
$intMid = Floor (($intStart + $ intEnd