动态转换GB-UTF-8编码至少有四种方法:
用PHP的iconv扩展转换
用PHP的mb_string扩展转换
用对换表转换,对换表存储在MySQL数据库中
用对换表转换,对换表存储在文本文件中
前两种方法要服务器作了相应设置(编译安装了相应扩展)才能使用。我的虚拟主机没有这两个扩展,只好考虑后两种方法。前两个方法本文也不进行测评。
测评程序如下(func_ip.php参见《IP地址-地理位置转换的测评》一文):
<?php
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;
//r