Tinyhttpd:源码分析【3】

一、问题引入

通过 Tinyhttpd:运行测试【1】 和 抓包分析【2】,基本完成了对程序的功能测试和通信原理。此时可以进一步对源码进行分析,本文不考虑代码一行一行的分析,仅对关键部分代码解析。

二、解决过程

2-1 main()函数

主函数主要创建http的监听套接字,等待客户端的连接。一旦有新客户端连接http,则创建一个新线程与客户端通信,而主线程(即main函数)继续等待客户端的连接。

int main(void)
{
    int server_sock = -1;
    u_short port = 10080;
    int client_sock = -1;
    struct sockaddr_in client_name;
    socklen_t  client_name_len = sizeof(client_name);
    pthread_t newthread;

    server_sock = startup(&port);
    printf("httpd running on port %d\n", port);

    while (1)
    {
        client_sock = accept(server_sock,(struct sockaddr *) &client_name, &client_name_len);
        if (client_sock == -1)
            error_die("accept");
        /* accept_request(&client_sock); */
        if (pthread_create(&newthread , NULL, (void *)accept_request, (void *)(intptr_t)client_sock) != 0)
            perror("pthread_create");
    }
    close(server_sock);

    return(0);
}

2-2 startup()函数

如果熟悉套接字编程,那么肯定对上面的代码肯定很眼熟。该函数的功能就是服务器在指定端口创建监听套接字。但同时对监听的端口做了冗余处理,若指定的端口为0,则动态的申请一个端口号。

int startup(u_short *port)
{
    int httpd = 0;
    int on = 1;
    struct sockaddr_in name;

    httpd = socket(PF_INET, SOCK_STREAM, 0);
    if (httpd == -1)
        error_die("socket");
    memset(&name, 0, sizeof(name));
    name.sin_family = AF_INET;
    name.sin_port = htons(*port);
    name.sin_addr.s_addr = htonl(INADDR_ANY);
    if ((setsockopt(httpd, SOL_SOCKET, SO_REUSEADDR, &on, sizeof(on))) < 0)  /* set port reuse */
    {  
        error_die("setsockopt failed");
    }
    if (bind(httpd, (struct sockaddr *)&name, sizeof(name)) < 0)
        error_die("bind");
    if (*port == 0)  /* if dynamically allocating a port */
    {
        socklen_t namelen = sizeof(name);
        if (getsockname(httpd, (struct sockaddr *)&name, &namelen) == -1)
            error_die("getsockname");
        *port = ntohs(name.sin_port);
    }
    if (listen(httpd, 5) < 0)
        error_die("listen");
    return(httpd);
}

2-3 accept_request()函数

该线程回调函数是整个程序最核心、最关键的部分,它包含了如何解析客户端发送的http request和服务区根据客户端的请求如何发送http respond。

void accept_request(void *arg)
{
    int client = (intptr_t)arg;
    char buf[1024];
    size_t numchars;
    char method[255];
    char url[255];
    char path[512];
    size_t i, j;
    struct stat st;
    int cgi = 0;      /* becomes true if server decides this is a CGI
                       * program */
    char *query_string = NULL;

    numchars = get_line(client, buf, sizeof(buf));
    i = 0; j = 0;
    while (!ISspace(buf[i]) && (i < sizeof(method) - 1))
    {
        method[i] = buf[i];
        i++;
    }
    j=i;
    method[i] = '\0';

    if (strcasecmp(method, "GET") && strcasecmp(method, "POST"))
    {
        unimplemented(client);
        return;
    }

    if (strcasecmp(method, "POST") == 0)
        cgi = 1;

    i = 0;
    while (ISspace(buf[j]) && (j < numchars))
        j++;
    while (!ISspace(buf[j]) && (i < sizeof(url) - 1) && (j < numchars))
    {
        url[i] = buf[j];
        i++; j++;
    }
    url[i] = '\0';

    if (strcasecmp(method, "GET") == 0)
    {
        query_string = url;
        while ((*query_string != '?') && (*query_string != '\0'))
            query_string++;
        if (*query_string == '?')
        {
            cgi = 1;
            *query_string = '\0';
            query_string++;
        }
    }

    sprintf(path, "htdocs%s", url);
    if (path[strlen(path) - 1] == '/')
        strcat(path, "index.html");
    if (stat(path, &st) == -1) {
        while ((numchars > 0) && strcmp("\n", buf))  /* read & discard headers */
            numchars = get_line(client, buf, sizeof(buf));
        not_found(client);
    }
    else
    {
        if ((st.st_mode & S_IFMT) == S_IFDIR)
            strcat(path, "/index.html");
        if ((st.st_mode & S_IXUSR) ||
                (st.st_mode & S_IXGRP) ||
                (st.st_mode & S_IXOTH)    )
            cgi = 1;
        if (!cgi)
            serve_file(client, path);
        else
            execute_cgi(client, path, method, query_string);
    }

    close(client);
}

解析第一行

http 请求行包括三个字段:请求方法、URL、协议版本。

解析请求方法:仅支持GET和POST。若为POST时,cgi标志位置1

numchars = get_line(client, buf, sizeof(buf));
i = 0; j = 0;
while (!ISspace(buf[i]) && (i < sizeof(method) - 1))
{
    method[i] = buf[i];
    i++;
}
j=i;
method[i] = '\0';

if (strcasecmp(method, "GET") && strcasecmp(method, "POST"))
{
    unimplemented(client);
    return;
}

if (strcasecmp(method, "POST") == 0)
    cgi = 1;

解析URL,并在GET方法时,将URL中的第一个?处替换为\0

i = 0;
while (ISspace(buf[j]) && (j < numchars))
    j++;
while (!ISspace(buf[j]) && (i < sizeof(url) - 1) && (j < numchars))
{
    url[i] = buf[j];
    i++; j++;
}
url[i] = '\0';

if (strcasecmp(method, "GET") == 0)
{
    query_string = url;
    while ((*query_string != '?') && (*query_string != '\0'))
        query_string++;
    if (*query_string == '?')
    {
        cgi = 1;
        *query_string = '\0';
        query_string++;
    }
}

判断URL是文件还是文件夹,若为文件夹,则拼接相对路径path htdocs/xxx/.../xxx/index.html
判断path是否存在,若不存在,先清空读缓存,执行函数 not_found();若存在且cgi标志位为1,执行函数 execute_cgi(),若存在且cgi不为1,执行函数 serve_file()

sprintf(path, "htdocs%s", url);
if (path[strlen(path) - 1] == '/')
    strcat(path, "index.html");
if (stat(path, &st) == -1) {
    while ((numchars > 0) && strcmp("\n", buf))  /* read & discard headers */
        numchars = get_line(client, buf, sizeof(buf));
    not_found(client);
}
else
{
    if ((st.st_mode & S_IFMT) == S_IFDIR)
        strcat(path, "/index.html");
    if ((st.st_mode & S_IXUSR) ||
            (st.st_mode & S_IXGRP) ||
            (st.st_mode & S_IXOTH)    )
        cgi = 1;
    if (!cgi)
        serve_file(client, path);
    else
        execute_cgi(client, path, method, query_string);
}

三、反思总结

整体理解下来,httpd.c可以解析来自客户端的GET和POST请求。

  • GET方法

可以处理请求格式:

  1. GET / HTTP/1.1 \r\n
  2. GET /index.html \r\n
  3. GET /color.cgi \r\n
  4. GET /color.cgi?color=pink \r\n
  • POST方法

可以处理请求格式:

  1. POST /color.cgi HTTP/1.1 \r\n + "color" = "green"

四、参考引用

EZLippi/Tinyhttpd

热门相关:洪荒二郎传   修仙界最后的单纯   特工重生:快穿全能女神   朕是红颜祸水   特工重生:快穿全能女神