add binding maker and editor for C++

ReadMe.md

@@ -42,6 +42,7 @@ API 介绍，使用文档和测试程序请参考对应 `searcher` 查询客户
 | :white_check_mark: | 已完成  | [erlang](binding/erlang) | erlang xdb 查询客户端实现   | [leihua996](https://github.com/leihua996) |
 |     | 待开始  | [php_ext](binding/php7_ext) | php c 扩展 xdb 查询客户端实现 | 待确定 |
 | :white_check_mark: | 已完成  | [nginx](binding/nginx) | nginx 扩展 xdb 查询客户端实现  | [Wu Jian Ping](https://github.com/wujjpp) |
+| :white_check_mark: | 已完成  | [C++](binding/cpp) | C++ xdb 查询客户端实现    | [Yunbin Liu](https://github.com/liuyunbin) |
 
 
 以下工具链实现由社区开发者通过第三方仓库贡献：
@@ -63,6 +64,7 @@ API 介绍，使用文档和测试程序请参考如下 `maker` 生成程序下
 | :white_check_mark: | 已完成  | [python](maker/python) | python xdb 生成程序实现 | [leolin49](https://github.com/leolin49) |
 | :white_check_mark: | 已完成  | [csharp](maker/csharp) | csharp xdb 生成程序实现 | [Alan Lee](https://github.com/malus2077) |
 | :white_check_mark: | 已完成  | [rust](maker/rust) | rust xdb 生成程序实现 | [KevinWang](https://github.com/KevinWL) |
+| :white_check_mark: | 已完成  | [C++](maker/cpp) | C++ xdb 生成程序实现 | [Yunbin Liu](https://github.com/liuyunbin) |
 
 
 # `xdb` 数据更新
@@ -82,6 +84,7 @@ ip2region 旨在于 <b>研究 IP 数据的存储和快速查询的设计和实
 |:-------------------|:----| :--- |:-------------------| :--- |
 | :white_check_mark: | 已完成 | [golang](maker/golang#xdb-数据编辑) | golang 原始 IP 数据编辑器 | [Lion](https://github.com/lionsoul2014) |
 | &nbsp;&nbsp;&nbsp; | 待开始 | [java](maker/java#xdb-数据编辑) | java 原始 IP 数据编辑器   | [Lion](https://github.com/lionsoul2014) |
+| :white_check_mark: | 已完成 | [C++](maker/cpp#xdb-数据编辑) | C++ 原始 IP 数据编辑器 | [Yunbin Liu](https://github.com/liuyunbin) |
 
 
 ### 检测自动更新

binding/cpp/Makefile

@@ -0,0 +1,11 @@
+
+all: xdb_search xdb_bench
+
+xdb_search: xdb_search.cc xdb_search_test.cc
+	g++ -std=c++11 -O2 $^ -o $@
+
+xdb_bench: xdb_search.cc xdb_bench.cc xdb_bench_test.cc
+	g++ -std=c++11 -O2 $^ -o $@
+
+clean:
+	rm -f xdb_search xdb_bench

binding/cpp/readme.md

@@ -0,0 +1,108 @@
+# ip2region xdb C++ 查询客户端实现
+
+## 使用方式
+### 完全基于文件的查询
+```
+#include <iostream>
+
+#include "xdb_search.h"
+
+int main(int argc, char* argv[]) {
+    char file_name[] = "../../data/ip2region.xdb";
+    char ip[]        = "1.2.3.4";
+
+    xdb_search_t xdb(file_name);
+    xdb.init_file();
+
+    std::cout << xdb.search(ip) << std::endl;
+    return 0;
+}
+```
+
+### 缓存 `vector_index` 索引
+```
+#include <iostream>
+
+#include "xdb_search.h"
+
+int main(int argc, char* argv[]) {
+    char file_name[] = "../../data/ip2region.xdb";
+    char ip[]        = "1.2.3.4";
+
+    xdb_search_t xdb(file_name);
+    xdb.init_vector_index();
+
+    std::cout << xdb.search(ip) << std::endl;
+    return 0;
+}
+```
+
+### 缓存整个 `xdb` 数据
+```
+#include <iostream>
+
+#include "xdb_search.h"
+
+int main(int argc, char* argv[]) {
+    char file_name[] = "../../data/ip2region.xdb";
+    char ip[]        = "1.2.3.4";
+
+    xdb_search_t xdb(file_name);
+    xdb.init_content();
+
+    std::cout << xdb.search(ip) << std::endl;
+    return 0;
+}
+```
+
+## 测试程序编译
+1. 切换到当前目录
+2. 编译
+
+```
+$ make
+g++ -std=c++11 -O2 xdb_search.cc xdb_search_test.cc -o xdb_search
+g++ -std=c++11 -O2 xdb_search.cc xdb_bench.cc xdb_bench_test.cc -o xdb_bench
+```
+
+## 测试查询
+### 说明
+```
+$ ./xdb_search --help
+./xdb_search  [command options]
+options:
+ --db string              ip2region binary xdb file path
+ --cache-policy string    cache policy: file/vector_index/content
+ --help                   print help
+```
+
+### 测试
+```
+$ ./xdb_search --db ../../data/ip2region.xdb --cache-policy vector_index
+cache policy : vector_index
+ip2region>> 1.2.3.4
+美国|0|华盛顿|0|谷歌
+```
+
+## bench 测试
+### 说明
+```
+$ ./xdb_bench --help
+./xdb_bench [command options]
+options:
+ --db string              ip2region binary xdb file path
+ --src string             source ip text file path
+ --cache-policy string    cache policy: file/vector_index/content
+ --help                   print help
+```
+
+### 测试
+```
+$ ./xdb_bench --db ../../data/ip2region.xdb --src ../../data/ip.merge.txt --cache-policy content
+total: 3419220, took: 3.44 s, cost: 0.27 μs/op, io count: 0
+$ ./xdb_bench --db ../../data/ip2region.xdb --src ../../data/ip.merge.txt --cache-policy vector_index
+total: 3419220, took: 45.99 s, cost: 12.24 μs/op, io count: 21739300
+$ ./xdb_bench --db ../../data/ip2region.xdb --src ../../data/ip.merge.txt --cache-policy file
+total: 3419220, took: 60.39 s, cost: 16.32 μs/op, io count: 25158520
+```
+

binding/cpp/xdb_bench.cc

@@ -0,0 +1,135 @@
+
+#include "xdb_bench.h"
+
+#include <arpa/inet.h>
+#include <stdio.h>
+#include <string.h>
+#include <sys/time.h>
+
+#include <iostream>
+#include <vector>
+
+static void log_exit(const std::string &msg) {
+    std::cout << msg << std::endl;
+    exit(-1);
+}
+
+static unsigned long long get_time() {
+    struct timeval tv1;
+    gettimeofday(&tv1, NULL);
+    return (unsigned long long)tv1.tv_sec * 1000 * 1000 + tv1.tv_usec;
+}
+
+static bool ip2uint(const char *buf, unsigned int &ip) {
+    struct in_addr addr;
+    if (inet_pton(AF_INET, buf, &addr) == 0)
+        return false;
+    // 网络字节序为大端存储, 在此转换为小端存储
+    ip = (((addr.s_addr >> 0) & 0xFF) << 24) |
+         (((addr.s_addr >> 8) & 0xFF) << 16) |
+         (((addr.s_addr >> 16) & 0xFF) << 8) |
+         (((addr.s_addr >> 24) & 0xFF) << 0);
+    return true;
+}
+
+static std::string uint2ip(unsigned int ip) {
+    char buf[16];
+    snprintf(buf,
+             sizeof(buf),
+             "%d.%d.%d.%d",
+             (ip >> 24) & 0xFF,
+             (ip >> 16) & 0xFF,
+             (ip >> 8) & 0xFF,
+             ip & 0xFF);
+    return std::string(buf);
+}
+
+xdb_bench_t::xdb_bench_t(const std::string &file_name) : xdb_search(file_name) {
+}
+
+void xdb_bench_t::init_file() {
+    xdb_search.init_file();
+}
+
+void xdb_bench_t::init_vector_index() {
+    xdb_search.init_vector_index();
+}
+
+void xdb_bench_t::init_content() {
+    xdb_search.init_content();
+}
+
+void xdb_bench_t::bench_test_one(unsigned int ip_uint, const char *region) {
+    if (xdb_search.search(uint2ip(ip_uint)) != region)
+        log_exit("failed: " + uint2ip(ip_uint));
+    sum_io_count += xdb_search.get_io_count();
+    sum_cost_time += xdb_search.get_cost_time();
+    sum_count++;
+}
+
+void xdb_bench_t::bench_test_line(char *buf) {
+    size_t buf_len = strlen(buf);
+    if (buf_len == 0)
+        return;
+    buf[buf_len - 1] = '\0';  // 去掉换行符
+
+    char *pos1 = strchr(buf, '|');
+
+    if (pos1 == NULL)
+        log_exit("invalid data: " + std::string(buf));
+    char *pos2 = strchr(pos1 + 1, '|');
+    if (pos2 == NULL)
+        log_exit("invalid data: " + std::string(buf));
+    *pos1 = '\0';
+    *pos2 = '\0';
+
+    unsigned int ip1, ip2;
+    if (!ip2uint(buf, ip1) || !ip2uint(pos1 + 1, ip2) || ip1 > ip2) {
+        *pos1 = *pos2 = '|';
+        log_exit(std::string("invalid data: ") + buf);
+    }
+
+    const char *region = pos2 + 1;
+
+    unsigned int              ip_mid = ip1 + (ip2 - ip1) / 2;
+    std::vector<unsigned int> ip_vec;
+    ip_vec.push_back(ip1);
+    ip_vec.push_back(ip1 + (ip_mid - ip1) / 2);
+    ip_vec.push_back(ip_mid);
+    ip_vec.push_back(ip_mid + (ip2 - ip_mid) / 2);
+    ip_vec.push_back(ip2);
+
+    for (auto &d : ip_vec)
+        bench_test_one(d, region);
+}
+
+void xdb_bench_t::bench_test_file(const std::string &file_name) {
+    FILE *f = fopen(file_name.data(), "r");
+    if (f == NULL)
+        log_exit("can't open " + file_name);
+    char buf[1024];
+    while (fgets(buf, sizeof(buf), f) != NULL)
+        bench_test_line(buf);
+}
+
+void xdb_bench_t::bench(const std::string &file_name) {
+    sum_io_count  = 0;
+    sum_cost_time = 0;
+    sum_count     = 0;
+
+    unsigned long long tv1 = get_time();
+    bench_test_file(file_name);
+    unsigned long long tv2 = get_time();
+
+    double took = (tv2 - tv1) * 1.0 / 1000 / 1000;
+    double cost = sum_cost_time * 1.0 / sum_count;
+
+    printf(
+        "total: %llu, took: %.2f s, cost: %.2f μs/op, io "
+        "count: "
+        "%llu\n",
+        sum_count,
+        took,
+        cost,
+        sum_io_count);
+}

binding/cpp/xdb_bench.h

@@ -0,0 +1,28 @@
+#ifndef XDB_BENCH_H
+#define XDB_BENCH_H
+
+#include "xdb_search.h"
+
+class xdb_bench_t {
+  public:
+    xdb_bench_t(const std::string &file_name);
+
+    void init_file();
+    void init_vector_index();
+    void init_content();
+
+    void bench(const std::string &file_name);
+
+  private:
+    void bench_test_one(unsigned int ip_uint, const char *region);
+    void bench_test_line(char *buf);
+    void bench_test_file(const std::string &file_name);
+
+    xdb_search_t xdb_search;
+
+    unsigned long long sum_io_count;
+    unsigned long long sum_cost_time;
+    unsigned long long sum_count;
+};
+
+#endif

binding/cpp/xdb_bench_test.cc

@@ -0,0 +1,70 @@
+
+#include "xdb_bench.h"
+
+#include <getopt.h>
+
+#include <iostream>
+
+void print_help(int argc, char* argv[]) {
+    printf("./xdb_bench [command options]\n");
+    printf("options:\n");
+    printf(" --db string              ip2region binary xdb file path\n");
+    printf(" --src string             source ip text file path\n");
+    printf(
+        " --cache-policy string    cache policy: "
+        "file/vector_index/content\n");
+    printf(" --help                   print help\n");
+    exit(-1);
+}
+
+int main(int argc, char* argv[]) {
+    struct option long_options[] = {
+        {"db",           required_argument, 0, 'd'},
+        {"cache-policy", required_argument, 0, 't'},
+        {"src",          required_argument, 0, 's'},
+        {"help",         no_argument,       0, 'h'},
+        {0,              0,                 0, 0  }
+    };
+
+    std::string db_file_name  = "../../data/ip2region.xdb";
+    std::string src_file_name = "../../data/ip.merge.txt";
+    std::string cache_policy  = "vector_index";
+
+    while (1) {
+        int c = getopt_long(argc, argv, "", long_options, NULL);
+        if (c == -1)
+            break;
+        switch (c) {
+        case 'd':
+            db_file_name = optarg;
+            break;
+        case 'h':
+            print_help(argc, argv);
+            break;
+        case 't':
+            cache_policy = optarg;
+            break;
+        case 's':
+            src_file_name = optarg;
+            break;
+        case '?':
+            exit(-1);
+        }
+    }
+
+    xdb_bench_t xdb(db_file_name);
+
+    if (cache_policy == "content")
+        xdb.init_content();
+    else if (cache_policy == "vector_index")
+        xdb.init_vector_index();
+    else if (cache_policy == "file")
+        xdb.init_file();
+    else {
+        std::cout << "invalid cache policy: " << cache_policy << std::endl;
+        exit(-1);
+    }
+
+    xdb.bench(src_file_name);
+    return 0;
+}