ipseeker.java

社区文章采用的是平板、树形自由选择的两种展示方式

			return returnlong;
		}
	}

	/**
	 * 从offset位置读取3个字节为一个long，因为java为big-endian格式，所以没办法
	 * 用了这么一个函数来做转换
	 * @param offset
	 * @return 读取的long值，返回-1表示读取文件失败
	 */
	private long readLong3(long offset) {
		if(logger.isDebugEnabled())
		{
			logger.debug("readLong3(long) - start");
		}

		long ret = 0;
		try {
			ipFile.seek(offset);
			ipFile.readFully(b3);
			ret |= (b3[0] & 0xFF);
			ret |= ((b3[1] << 8) & 0xFF00);
			ret |= ((b3[2] << 16) & 0xFF0000);

			if(logger.isDebugEnabled())
			{
				logger.debug("readLong3(long) - end");
			}
			return ret;
		} catch (IOException e) {
			logger.error("readLong3(long)", e);

			long returnlong = -1;
			if(logger.isDebugEnabled())
			{
				logger.debug("readLong3(long) - end");
			}
			return returnlong;
		}
	}

	/**
	 * 从当前位置读取3个字节转换成long
	 * @return
	 */
	private long readLong3() {
		if(logger.isDebugEnabled())
		{
			logger.debug("readLong3() - start");
		}

		long ret = 0;
		try {
			ipFile.readFully(b3);
			ret |= (b3[0] & 0xFF);
			ret |= ((b3[1] << 8) & 0xFF00);
			ret |= ((b3[2] << 16) & 0xFF0000);

			if(logger.isDebugEnabled())
			{
				logger.debug("readLong3() - end");
			}
			return ret;
		} catch (IOException e) {
			logger.error("readLong3()", e);

			long returnlong = -1;
			if(logger.isDebugEnabled())
			{
				logger.debug("readLong3() - end");
			}
			return returnlong;
		}
	}

	/**
	 * 从offset位置读取四个字节的ip地址放入ip数组中，读取后的ip为big-endian格式，但是
	 * 文件中是little-endian形式，将会进行转换
	 * @param offset
	 * @param ip
	 */
	private void readIP(long offset, byte[] ip) {
		if(logger.isDebugEnabled())
		{
			logger.debug("readIP(long, byte[]) - start");
		}

		try {
			ipFile.seek(offset);
			ipFile.readFully(ip);
			byte temp = ip[0];
			ip[0] = ip[3];
			ip[3] = temp;
			temp = ip[1];
			ip[1] = ip[2];
			ip[2] = temp;
		} catch (IOException e) {
			logger.error("readIP(long, byte[])", e);

			if(logger.isDebugEnabled())
			{
				logger.debug("readIP() - " + e.getMessage());
			}
		}

		if(logger.isDebugEnabled())
		{
			logger.debug("readIP(long, byte[]) - end");
		}
	}

	/**
	 * 从offset位置读取四个字节的ip地址放入ip数组中，读取后的ip为big-endian格式，但是
	 * 文件中是little-endian形式，将会进行转换
	 * @param offset
	 * @param ip
	 */
	private void readIP(int offset, byte[] ip) {
		if(logger.isDebugEnabled())
		{
			logger.debug("readIP(int, byte[]) - start");
		}

	    mbb.position(offset);
	    mbb.get(ip);
		byte temp = ip[0];
		ip[0] = ip[3];
		ip[3] = temp;
		temp = ip[1];
		ip[1] = ip[2];
		ip[2] = temp;

		if(logger.isDebugEnabled())
		{
			logger.debug("readIP(int, byte[]) - end");
		}
	}

	/**
	 * 把类成员ip和beginIp比较，注意这个beginIp是big-endian的
	 * @param ip 要查询的IP
	 * @param beginIp 和被查询IP相比较的IP
	 * @return 相等返回0，ip大于beginIp则返回1，小于返回-1。
	 */
	private int compareIP(byte[] ip, byte[] beginIp) {
		if(logger.isDebugEnabled())
		{
			logger.debug("compareIP(byte[], byte[]) - start");
		}

		for(int i = 0; i < 4; i++) {
			int r = compareByte(ip[i], beginIp[i]);
			if(r != 0)
				return r;
		}

		if(logger.isDebugEnabled())
		{
			logger.debug("compareIP(byte[], byte[]) - end");
		}
		return 0;
	}

	/**
	 * 把两个byte当作无符号数进行比较
	 * @param b1
	 * @param b2
	 * @return 若b1大于b2则返回1，相等返回0，小于返回-1
	 */
	private int compareByte(byte b1, byte b2) {
		if(logger.isDebugEnabled())
		{
			logger.debug("compareByte(byte, byte) - start");
		}

		if((b1 & 0xFF) > (b2 & 0xFF)) // 比较是否大于
			return 1;
		else if((b1 ^ b2) == 0)// 判断是否相等
			return 0;
		else
			return -1;
	}

	/**
	 * 这个方法将根据ip的内容，定位到包含这个ip国家地区的记录处，返回一个绝对偏移
	 * 方法使用二分法查找。
	 * @param ip 要查询的IP
	 * @return 如果找到了，返回结束IP的偏移，如果没有找到，返回-1
	 */
	private long locateIP(byte[] ip) {
		if(logger.isDebugEnabled())
		{
			logger.debug("locateIP(byte[]) - start");
		}

		long m = 0;
		int r;
		// 比较第一个ip项
		readIP(ipBegin, b4);
		r = compareIP(ip, b4);
		if(r == 0) return ipBegin;
		else if(r < 0) return -1;
		// 开始二分搜索
		for(long i = ipBegin, j = ipEnd; i < j; ) {
			m = getMiddleOffset(i, j);
			readIP(m, b4);
			r = compareIP(ip, b4);
			// log.debug(IPUtils.getIpStringFromBytes(b));
			if(r > 0)
				i = m;
			else if(r < 0) {
				if(m == j) {
					j -= IP_RECORD_LENGTH;
					m = j;
				} else
					j = m;
			} else
				return readLong3(m + 4);
		}
		// 如果循环结束了，那么i和j必定是相等的，这个记录为最可能的记录，但是并非
		//     肯定就是，还要检查一下，如果是，就返回结束地址区的绝对偏移
		m = readLong3(m + 4);
		readIP(m, b4);
		r = compareIP(ip, b4);
		if(r <= 0) return m;
		else return -1;
	}

	/**
	 * 得到begin偏移和end偏移中间位置记录的偏移
	 * @param begin
	 * @param end
	 * @return
	 */
	private long getMiddleOffset(long begin, long end) {
		if(logger.isDebugEnabled())
		{
			logger.debug("getMiddleOffset(long, long) - start");
		}

		long records = (end - begin) / IP_RECORD_LENGTH;
		records >>= 1;
		if(records == 0) records = 1;
		long returnlong = begin + records * IP_RECORD_LENGTH;
		if(logger.isDebugEnabled())
		{
			logger.debug("getMiddleOffset(long, long) - end");
		}
		return returnlong;
	}

	/**
	 * 给定一个ip国家地区记录的偏移，返回一个IPLocation结构
	 * @param offset
	 * @return
	 */
	private IPLocation getIPLocation(long offset) {
		if(logger.isDebugEnabled())
		{
			logger.debug("getIPLocation(long) - start");
		}
		try {
			// 跳过4字节ip
			ipFile.seek(offset + 4);
			// 读取第一个字节判断是否标志字节
			byte b = ipFile.readByte();
			if(b == AREA_FOLLOWED) {
				// 读取国家偏移
				long countryOffset = readLong3();
				// 跳转至偏移处
				ipFile.seek(countryOffset);
				// 再检查一次标志字节，因为这个时候这个地方仍然可能是个重定向
				b = ipFile.readByte();
				if(b == NO_AREA) {
					loc.country = readString(readLong3());
					ipFile.seek(countryOffset + 4);
				} else
					loc.country = readString(countryOffset);
				// 读取地区标志
				loc.area = readArea(ipFile.getFilePointer());
			} else if(b == NO_AREA) {
				loc.country = readString(readLong3());
				loc.area = readArea(offset + 8);
			} else {
				loc.country = readString(ipFile.getFilePointer() - 1);
				loc.area = readArea(ipFile.getFilePointer());
			}

			if(logger.isDebugEnabled())
			{
				logger.debug("getIPLocation(long) - end");
			}
			return loc;
		} catch (IOException e) {
			logger.error("getIPLocation(long)", e);

			if(logger.isDebugEnabled())
			{
				logger.debug("getIPLocation(long) - end");
			}
			return null;
		}
		
	}

	/**
	 * @param offset
	 * @return
	 */
	private IPLocation getIPLocation(int offset) {
		if(logger.isDebugEnabled())
		{
			logger.debug("getIPLocation(int) - start");
		}
		// 跳过4字节ip
	    mbb.position(offset + 4);
		// 读取第一个字节判断是否标志字节
		byte b = mbb.get();
		if(b == AREA_FOLLOWED) {
			// 读取国家偏移
			int countryOffset = readInt3();
			// 跳转至偏移处
			mbb.position(countryOffset);
			// 再检查一次标志字节，因为这个时候这个地方仍然可能是个重定向
			b = mbb.get();
			if(b == NO_AREA) {
				loc.country = readString(readInt3());
				mbb.position(countryOffset + 4);
			} else
				loc.country = readString(countryOffset);
			// 读取地区标志
			loc.area = readArea(mbb.position());
		} else if(b == NO_AREA) {
			loc.country = readString(readInt3());
			loc.area = readArea(offset + 8);
		} else {
			loc.country = readString(mbb.position() - 1);
			loc.area = readArea(mbb.position());
		}

		if(logger.isDebugEnabled())
		{
			logger.debug("getIPLocation(int) - end");
		}
		return loc;
	}

	/**
	 * 从offset偏移开始解析后面的字节，读出一个地区名
	 * @param offset
	 * @return 地区名字符串
	 * @throws IOException
	 */
	private String readArea(long offset) throws IOException {
		if(logger.isDebugEnabled())
		{
			logger.debug("readArea(long) - start");
		}

		ipFile.seek(offset);
		byte b = ipFile.readByte();
		if(b == 0x01 || b == 0x02) {
			long areaOffset = readLong3(offset + 1);
			if(areaOffset == 0)
				return "未知地区";
			else
				return readString(areaOffset);
		} else
			return readString(offset);
	}

	/**
	 * @param offset
	 * @return
	 */
	private String readArea(int offset) {
		if(logger.isDebugEnabled())
		{
			logger.debug("readArea(int) - start");
		}

		mbb.position(offset);
		byte b = mbb.get();
		if(b == 0x01 || b == 0x02) {
			int areaOffset = readInt3();
			if(areaOffset == 0)
				return "未知地区";
			else
				return readString(areaOffset);
		} else
			return readString(offset);
	}

	/**
	 * 从offset偏移处读取一个以0结束的字符串
	 * @param offset
	 * @return 读取的字符串，出错返回空字符串
	 */
	private String readString(long offset) {
		if(logger.isDebugEnabled())
		{
			logger.debug("readString(long) - start");
		}

		try {
			ipFile.seek(offset);
			int i;
			for(i = 0, buf[i] = ipFile.readByte(); buf[i] != 0; buf[++i] = ipFile.readByte());
			if(i != 0)
			    return IPUtils.getString(buf, 0, i, "GBK");
		} catch (IOException e) {
			logger.error("readString(long)", e);

			if(logger.isDebugEnabled())
			{
				logger.debug("readString() - " + e.getMessage());
			}
		}

		if(logger.isDebugEnabled())
		{
			logger.debug("readString(long) - end");
		}
		return "";
	}

	/**
	 * 从内存映射文件的offset位置得到一个0结尾字符串
	 * @param offset
	 * @return
	 */
	private String readString(int offset) {
		if(logger.isDebugEnabled())
		{
			logger.debug("readString(int) - start");
		}

	    try {
			mbb.position(offset);
			int i;
			for(i = 0, buf[i] = mbb.get(); buf[i] != 0; buf[++i] = mbb.get());
			if(i != 0)
			    return IPUtils.getString(buf, 0, i, "GBK");
	    } catch (IllegalArgumentException e) {
			logger.error("readString(int)", e);

			if(logger.isDebugEnabled())
			{
				logger.debug("readString() - " + e.getMessage());
			}
	    }

		if(logger.isDebugEnabled())
		{
			logger.debug("readString(int) - end");
		}
	    return "";
	}

	public String getAddress(String ip){
		if(logger.isDebugEnabled())
		{
			logger.debug("getAddress(String) - start");
		}
		
		String country = getCountry(ip);
		String area = getArea(ip).equals("www.YeQiangWei.com")?"":getArea(ip);
        String address = country+" "+area;
		String returnString = address.trim();
		if(logger.isDebugEnabled())
		{
			logger.debug("getAddress(String) - end");
		}
		return returnString;
	}
	
	public IPModel getIPModel(String ip){
		if(logger.isDebugEnabled())
		{
			logger.debug("getAddress(String) - start");
		}
		String country = getCountry(ip);
		String area = getArea(ip).equals("www.YeQiangWei.com")?"":getArea(ip);
        //String address = country+" "+area;
		//String returnString = address.trim();
		IPModel model = new IPModel();
		model.setIp(ip);
		model.setCountry(country);
		model.setArea(area);
		//model.setCity();
		return model;
	}
	
	/**
	 * 主要用于将纯真库IP地址中文按Lucene的分词方法切分便于索引查找
	 * @param ip
	 * @return
	 * @throws IOException 
	 */
	public List<String> IPParser(String ip){
		if(Validator.isEmpty(ip)){
			return null;
		}		
		IPSeeker ipseeker = IPSeeker.getInstance();
		IPModel ipmodel= ipseeker.getIPModel(ip);
		String address = ipmodel.getCountry();
		if(Validator.isEmpty(address)){
			return null;
		}else{
			address = address.replaceAll("省","").replaceAll("市","");
		}
		List<String> list = null;
		Token[] tokens;
		try {
			tokens = AnalyzerUtils.tokensFromAnalysis(AnalyzerFactory.getAnalyzer(), address);
			if(!Validator.isEmpty(tokens)){
				list = new ArrayList<String>();
				for (int i = 0; i < tokens.length; i++) {
					String temp = tokens[i].termText();
					list.add(temp);
					//System.out.println(temp);
				}
			}
		} catch (IOException e) {
			logger.error(e.toString());
		}
		return list;
	}
	
	public static void main(String args[])
	{
	    IPSeeker ip = new IPSeeker();
	    List<String> m = ip.IPParser("218.25.62.58");
	    System.out.println(m.get(0));
	    
	}
}