Home >Backend Development >PHP Tutorial >Brief Analysis of Coral IP Library_PHP Tutorial
Brief Analysis of Coral IP Library_PHP Tutorial
- WBOYOriginal
- 2016-07-21 15:57:11999browse
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;
}
/**
* Pack the IP address into binary data in big endian (high endian) format
* The data storage format is little endian (low endian), such as:
* 00 28 C6 DA 218.198.40.0 little endian
* 3F 28 C6 DA 218.198.40.0 little endian
* Such data cannot be compared by binary search, so the obtained IP data must first be converted to big endian
* @param using strrev $ip
* @return binary data in big endian format
*/
private function packip($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：
big endian和little endian是CPU处理多字节数的不同方式。例如“汉”字的Unicode编码是6C49。那么写到文件里时，究竟是将6C写在前面，还是将49写在前面？如果将6C写在前面，就是big endian。还是将49写在前面，就是little endian。
“endian”这个词出自《格列佛游记》。小人国的内战就源于吃鸡蛋时是究竟从大头(Big-Endian)敲开还是从小头(Little-Endian)敲开，由此曾发生过六次叛乱，其中一个皇帝送了命，另一个丢了王位。
我们一般将endian翻译成“字节序”，将big endian和little endian称作“大尾”和“小尾”。
文件头：
红色框框里的就是文件头，前4个字节是索引区的开始地址，后4个字节是索引区的结束地址。
如下图所示：
点击放大
由于数据库是使用了little endian的字节库，所以我们需要把它倒过来。
把文件头的0-3的字节读取出来，再使用 unpack 函数把二进制数据转换为big endian格式的无符号整型。
处理后，索引区的开始地址位置是：00077450 ；索引区的结束地址位置是：000CE17C。
如果你手头上有UltraEdit的软件，可以打开CoralWry.dat文件，查找地址为：00077450 的位置，那就是IP地址索引区的开始。
如下图所示：
点击放大
红色框框住那就是索引区的开始位置。