珊瑚虫IP库浅析

这不是什么新鲜事情了，很早之前就已经有人做出来了。
就是使用PHP操作纯真IP库或珊瑚虫IP库，根据来访者的IP得到所在的物理位置。

我先帖出代码。然后再慢慢一步步浅析出来。希望对想了解这一块的朋友们有帮助。

Only For PHP5的代码。会继续优化代码的。

class IpLocation{
    private $fp;
    private $wrydat;
    private $wrydat_version;
    private $ipnumber;
    private $firstip;
    private $lastip;
    private $ip_range_begin;
    private $ip_range_end;
    private $country;
    private $area;
    const REDIRECT_MODE_0 = 0;
    const REDIRECT_MODE_1 = 1;
    const REDIRECT_MODE_2 = 2;
    function __construct(){
        $args = func_get_args();
        $this->wrydat = func_num_args()>0?$args[0]:'CoralWry.dat';
        $this->initialize();
    }
    function __destruct(){
        fclose($this->fp);
    }
    private function initialize(){
        if(file_exists($this->wrydat))
            $this->fp = fopen($this->wrydat,'rb');
        $this->getipnumber();
        $this->getwryversion();
    }
    public function get($str){
        return $this->$str;
    }
    public function set($str,$val){
        $this->$str = $val;
    }
    private function getbyte($length,$offset=null){
        if(!is_null($offset)){
            fseek($this->fp,$offset,SEEK_SET);
        }
        $b = fread($this->fp,$length);
        return $b;
    }
/**
* 把IP地址打包成二进制数据，以big endian（高位在前）格式打包
* 数据存储格式为 little endian（低位在前） 如：
* 00 28 C6 DA    218.198.40.0    little endian
* 3F 28 C6 DA    218.198.40.0    little endian
* 这样的数据无法作二分搜索查找的比较，所以必须先把获得的IP数据使用strrev转换为big endian
* @param $ip
* @return big endian格式的二进制数据
*/
    private function packip($ip){
        return pack( "N", intval( ip2long( $ip)));
    }

    private function getlong($length=4, $offset=null){
        $chr=null;
        for($c=0;$length%4!=0&&$c<(4-$length%4);$c++){
            $chr .= chr(0);
        }
        $var = unpack( "Vlong", $this->getbyte($length, $offset).$chr);
        return $var['long'];
    }

    private function getwryversion(){
        $length = preg_match("/coral/i",$this->wrydat)?26:30;
        $this->wrydat_version = $this->getbyte($length, $this->firstip-$length);
    }

    private function getipnumber(){
        $this->firstip = $this->getlong();
        $this->lastip = $this->getlong();
        $this->ipnumber = ($this->lastip-$this->firstip)/7+1;
    }

    private function getstring($data="",$offset=null){
        $char = $this->getbyte(1,$offset);
        while(ord($char) > 0){
            $data .= $char;
            $char = $this->getbyte(1);
        }
        return $data;
    }

    private function iplocaltion($ip){
        $ip = $this->packip($ip);
        $low = 0;
        $high = $this->ipnumber-1;
        $ipposition = $this->lastip;
        while($low <= $high){
            $t = floor(($low+$high)/2);
            if($ip < strrev($this->getbyte(4,$this->firstip+$t*7))){
                $high = $t - 1;
            } else {
                if($ip > strrev($this->getbyte(4,$this->getlong(3)))){
                    $low = $t + 1;
                }else{
                    $ipposition = $this->firstip+$t*7;
                    break;
                }
            }
        }
        return $ipposition;
    }
    private function getarea(){
        $b = $this->getbyte(1);
        switch(ord($b)){
            case self::REDIRECT_MODE_0 :
                return "未知";
                break;
            case self::REDIRECT_MODE_1:
            case self::REDIRECT_MODE_2:
                return $this->getstring("",$this->getlong(3));
                break;
            default:
                return $this->getstring($b);
                break;
        }
    }
    public function getiplocation($ip){
        $ippos = $this->iplocaltion($ip);
        $this->ip_range_begin = long2ip($this->getlong(4,$ippos));
        $this->ip_range_end = long2ip($this->getlong(4,$this->getlong(3)));
        $b = $this->getbyte(1);
        switch (ord($b)){
            case self::REDIRECT_MODE_1:
                $b = $this->getbyte(1,$this->getlong(3));
                if(ord($b) == REDIRECT_MODE_2){
                    $countryoffset = $this->getlong(3);
                    $this->area = $this->getarea();
                    $this->country = $this->getstring("",$countryoffset);
                }else{
                    $this->country = $this->getstring($b);
                    $this->area    = $this->getarea();
                }
                break;

            case self::REDIRECT_MODE_2:
                    $countryoffset = $this->getlong(3);
                    $this->area = $this->getarea();
                    $this->country = $this->getstring("",$countryoffset);
                break;

            default:
                $this->country = $this->getstring($b);
                $this->area    = $this->getarea();
                break;
        }
    }
}
/* */
echo microtime();
echo "\n";
$iploca = new IpLocation;
//$iploca = new IpLocation('QQWry.dat');
echo $iploca->get('wrydat_version');
echo "\n";
echo $iploca->get('ipnumber');
echo "\n";
$iploca->getiplocation('211.44.32.34');
/**/
echo $iploca->get('ip_range_begin');
echo "\n";
echo $iploca->get('ip_range_end');
echo "\n";
echo $iploca->get('country');
echo "\n";
echo $iploca->get('area');

echo "\n";
echo $iploca->get('lastip');
echo "\n";
echo microtime();
echo "\n";
unset($iploca);

参考资料：LumaQQ的 纯真IP数据库格式详解

CoralWry.dat文件结构上分为3个区域：

文件头［固定8个字节］ 数据区［不固定长度，记录IP的地址信息］ 索引区［大小由文件头决定］

该文件数据的存储方式是：little endian。
在这里引用了谈谈Unicode编码里的关于little endian 与 big endian的区别

引用：