httpd.c

/* J. David's webserver */
/* This is a simple webserver.
 * Created November 1999 by J. David Blackstone.
 * CSE 4344 (Network concepts), Prof. Zeigler
 * University of Texas at Arlington
 */
/* This program compiles for Sparc Solaris 2.6.
 * To compile for Linux:
 *  1) Comment out the #include <pthread.h> line.
 *  2) Comment out the line that defines the variable newthread.
 *  3) Comment out the two lines that run pthread_create().
 *  4) Uncomment the line that runs accept_request().
 *  5) Remove -lsocket from the Makefile.
 */
#include <stdio.h>
#include <sys/socket.h>
#include <sys/types.h>
#include <netinet/in.h>
#include <arpa/inet.h>
#include <unistd.h>
#include <ctype.h>
#include <strings.h>
#include <string.h>
#include <sys/stat.h>
#include <pthread.h>
#include <sys/wait.h>
#include <stdlib.h>
#include <stdint.h>

#define ISspace(x) isspace((int)(x))

#define SERVER_STRING "Server: jdbhttpd/0.1.0\r\n"
#define STDIN   0
#define STDOUT  1
#define STDERR  2

void accept_request(void *);
void bad_request(int);
void cat(int, FILE *);
void cannot_execute(int);
void error_die(const char *);
void execute_cgi(int, const char *, const char *, const char *);
int get_line(int, char *, int);
void headers(int, const char *);
void not_found(int);
void serve_file(int, const char *);
int startup(u_short *);
void unimplemented(int);

/**********************************************************************/
/* A request has caused a call to accept() on the server port to
 * return.  Process the request appropriately.
 * Parameters: the socket connected to the client */
/**********************************************************************/
void accept_request(void *arg)
{
    int client = (intptr_t)arg;  //传给线程的参数是已连接套接字描述符
    char buf[1024];
    size_t numchars;             //读取到的字节数据
    char method[255];            //方法
    char url[255];               //地址
    char path[512];              //路径
    size_t i, j;
    struct stat st;
    int cgi = 0;      /* becomes true if server decides this is a CGI
                       * program */
    char *query_string = NULL;

    //从已连接套接字描述符读取一行数据
    numchars = get_line(client, buf, sizeof(buf));
    i = 0; j = 0;   //i用于遍历method、url、path数组，j用于遍历buf
    //从buf中抽取方法数据，保存到method中
    while (!ISspace(buf[i]) && (i < sizeof(method) - 1))
    {
        method[i] = buf[i];
        i++;
    }
    j=i;
    method[i] = '\0';

    //strcasecmp：忽略大小写的字符串比较
    //如果既不是GET方法，也不是POST方法，调用unimplemented函数处理
    if (strcasecmp(method, "GET") && strcasecmp(method, "POST"))
    {
        unimplemented(client);
        return;
    }

    //如果是POST方法、则将cgi设置为1
    if (strcasecmp(method, "POST") == 0)
        cgi = 1;

    i = 0;
    //跳过方法数据后的空格
    while (ISspace(buf[j]) && (j < numchars))
        j++;
    //从buf中抽取url数据
    while (!ISspace(buf[j]) && (i < sizeof(url) - 1) && (j < numchars))
    {
        url[i] = buf[j];
        i++; j++;
    }
    url[i] = '\0';

    //如果method是GET，那么需要在获取url后处理
    if (strcasecmp(method, "GET") == 0)
    {
        query_string = url;
        //下面的处理主要是判断URL中有没有包含'?'，如果包含了'?'，需要将cgi设置为1
        //然后将url从'?'处截断，并使query_string指向'?'之后
        while ((*query_string != '?') && (*query_string != '\0'))
            query_string++;
        if (*query_string == '?')
        {
            cgi = 1;
            *query_string = '\0';
            query_string++;
        }
    }

    //path："htdocs"+url 
    sprintf(path, "htdocs%s", url);
    //如果url末尾为'/'，表示是个目录，那么更新path："htdocs"+url+"index.html"
    if (path[strlen(path) - 1] == '/')
        strcat(path, "index.html");
    //获取文件的状态，保存到st中
    if (stat(path, &st) == -1) {//如果文件状态获取失败（文件不存在）
        //读取客户html请求剩余的数据，然后调用not_found向客户端返回文件不存在错误
        while ((numchars > 0) && strcmp("\n", buf))  /* read & discard headers */
            numchars = get_line(client, buf, sizeof(buf));
        not_found(client);
    }
    else//如果文件存在
    {
        //如果文件是个目录，那么path："htdocs"+url+"/index.html"
        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;
        //如果没设置cgi，那么调用serve_file进行响应
        //如果设置了cgi，那么调用execute_cgi进行响应
        if (!cgi)
            serve_file(client, path);
        else
            execute_cgi(client, path, method, query_string);
    }

    //处理完客户端的html请求后，关闭已连接套接字描述符（关闭TCP连接）
    close(client);
}

/**********************************************************************/
/* Inform the client that a request it has made has a problem.
 * Parameters: client socket */
/**********************************************************************/
void bad_request(int client)
{
    char buf[1024];

    sprintf(buf, "HTTP/1.0 400 BAD REQUEST\r\n");
    send(client, buf, sizeof(buf), 0);
    sprintf(buf, "Content-type: text/html\r\n");
    send(client, buf, sizeof(buf), 0);
    sprintf(buf, "\r\n");
    send(client, buf, sizeof(buf), 0);
    sprintf(buf, "<P>Your browser sent a bad request, ");
    send(client, buf, sizeof(buf), 0);
    sprintf(buf, "such as a POST without a Content-Length.\r\n");
    send(client, buf, sizeof(buf), 0);
}

/**********************************************************************/
/* Put the entire contents of a file out on a socket.  This function
 * is named after the UNIX "cat" command, because it might have been
 * easier just to do something like pipe, fork, and exec("cat").
 * Parameters: the client socket descriptor
 *             FILE pointer for the file to cat */
/**********************************************************************/
void cat(int client, FILE *resource)
{
    char buf[1024];

    fgets(buf, sizeof(buf), resource);
    while (!feof(resource))
    {
        send(client, buf, strlen(buf), 0);
        fgets(buf, sizeof(buf), resource);
    }
}

/**********************************************************************/
/* Inform the client that a CGI script could not be executed.
 * Parameter: the client socket descriptor. */
/**********************************************************************/
void cannot_execute(int client)
{
    char buf[1024];

    sprintf(buf, "HTTP/1.0 500 Internal Server Error\r\n");
    send(client, buf, strlen(buf), 0);
    sprintf(buf, "Content-type: text/html\r\n");
    send(client, buf, strlen(buf), 0);
    sprintf(buf, "\r\n");
    send(client, buf, strlen(buf), 0);
    sprintf(buf, "<P>Error prohibited CGI execution.\r\n");
    send(client, buf, strlen(buf), 0);
}

/**********************************************************************/
/* Print out an error message with perror() (for system errors; based
 * on value of errno, which indicates system call errors) and exit the
 * program indicating an error. */
/**********************************************************************/
void error_die(const char *sc)
{
    perror(sc);
    exit(1);
}

/**********************************************************************/
/* Execute a CGI script.  Will need to set environment variables as
 * appropriate.
 * Parameters: client socket descriptor
 *             path to the CGI script */
/**********************************************************************/
void execute_cgi(int client, const char *path,
        const char *method, const char *query_string)
{
    char buf[1024];
    int cgi_output[2];
    int cgi_input[2];
    pid_t pid;
    int status;
    int i;
    char c;
    int numchars = 1;
    int content_length = -1;

    buf[0] = 'A'; buf[1] = '\0';
    if (strcasecmp(method, "GET") == 0)
        while ((numchars > 0) && strcmp("\n", buf))  /* read & discard headers */
            numchars = get_line(client, buf, sizeof(buf));
    else if (strcasecmp(method, "POST") == 0) /*POST*/
    {
        numchars = get_line(client, buf, sizeof(buf));
        while ((numchars > 0) && strcmp("\n", buf))
        {
            buf[15] = '\0';
            if (strcasecmp(buf, "Content-Length:") == 0)
                content_length = atoi(&(buf[16]));
            numchars = get_line(client, buf, sizeof(buf));
        }
        if (content_length == -1) {
            bad_request(client);
            return;
        }
    }
    else/*HEAD or other*/
    {
    }


    if (pipe(cgi_output) < 0) {
        cannot_execute(client);
        return;
    }
    if (pipe(cgi_input) < 0) {
        cannot_execute(client);
        return;
    }

    if ( (pid = fork()) < 0 ) {
        cannot_execute(client);
        return;
    }
    sprintf(buf, "HTTP/1.0 200 OK\r\n");
    send(client, buf, strlen(buf), 0);
    if (pid == 0)  /* child: CGI script */
    {
        char meth_env[255];
        char query_env[255];
        char length_env[255];

        dup2(cgi_output[1], STDOUT);
        dup2(cgi_input[0], STDIN);
        close(cgi_output[0]);
        close(cgi_input[1]);
        sprintf(meth_env, "REQUEST_METHOD=%s", method);
        putenv(meth_env);
        if (strcasecmp(method, "GET") == 0) {
            sprintf(query_env, "QUERY_STRING=%s", query_string);
            putenv(query_env);
        }
        else {   /* POST */
            sprintf(length_env, "CONTENT_LENGTH=%d", content_length);
            putenv(length_env);
        }
        execl(path, NULL);
        exit(0);
    } else {    /* parent */
        close(cgi_output[1]);
        close(cgi_input[0]);
        if (strcasecmp(method, "POST") == 0)
            for (i = 0; i < content_length; i++) {
                recv(client, &c, 1, 0);
                write(cgi_input[1], &c, 1);
            }
        while (read(cgi_output[0], &c, 1) > 0)
            send(client, &c, 1, 0);

        close(cgi_output[0]);
        close(cgi_input[1]);
        waitpid(pid, &status, 0);
    }
}

/**********************************************************************/
/* Get a line from a socket, whether the line ends in a newline,
 * carriage return, or a CRLF combination.  Terminates the string read
 * with a null character.  If no newline indicator is found before the
 * end of the buffer, the string is terminated with a null.  If any of
 * the above three line terminators is read, the last character of the
 * string will be a linefeed and the string will be terminated with a
 * null character.
 * Parameters: the socket descriptor
 *             the buffer to save the data in
 *             the size of the buffer
 * Returns: the number of bytes stored (excluding null) */
/**********************************************************************/
int get_line(int sock, char *buf, int size)
{
    int i = 0;       //buf中保存读取到的字符的起始下标
    char c = '\0';   //用以保存读取到的每个字符
    int n;

    while ((i < size - 1) && (c != '\n'))
    {
        //每次读入一个字符，保存在c中
        n = recv(sock, &c, 1, 0);
        /* DEBUG printf("%02X\n", c); */
        if (n > 0)
        {
            if (c == '\r')
            {
                //MSG_PEEK允许我们查看已经可读的数据，并且系统不在recv返回后丢弃这些数据
                //如果读到'\r'，有些系统是以"\r\n"为换行，有些是以"\r"为换行
                //这里通过查看下一个字符是不是'\n'来处理"\r\n"的情况
                n = recv(sock, &c, 1, MSG_PEEK);
                /* DEBUG printf("%02X\n", c); */
                if ((n > 0) && (c == '\n'))
                    recv(sock, &c, 1, 0);
                else
                    c = '\n';
            }
            buf[i] = c; //还没读到行尾，则将读到的字符存入buf
            i++;        //更新起始下标
        }
        else //下面语句会导致循环终止
            c = '\n';
    }
    buf[i] = '\0';

    return(i);
}

/**********************************************************************/
/* Return the informational HTTP headers about a file. */
/* Parameters: the socket to print the headers on
 *             the name of the file */
/**********************************************************************/
void headers(int client, const char *filename)
{
    char buf[1024];
    (void)filename;  /* could use filename to determine file type */

    strcpy(buf, "HTTP/1.0 200 OK\r\n");
    send(client, buf, strlen(buf), 0);
    strcpy(buf, SERVER_STRING);
    send(client, buf, strlen(buf), 0);
    sprintf(buf, "Content-Type: text/html\r\n");
    send(client, buf, strlen(buf), 0);
    strcpy(buf, "\r\n");
    send(client, buf, strlen(buf), 0);
}

/**********************************************************************/
/* Give a client a 404 not found status message. */
/**********************************************************************/
void not_found(int client)
{
    char buf[1024];

    sprintf(buf, "HTTP/1.0 404 NOT FOUND\r\n");
    send(client, buf, strlen(buf), 0);
    sprintf(buf, SERVER_STRING);
    send(client, buf, strlen(buf), 0);
    sprintf(buf, "Content-Type: text/html\r\n");
    send(client, buf, strlen(buf), 0);
    sprintf(buf, "\r\n");
    send(client, buf, strlen(buf), 0);
    sprintf(buf, "<HTML><TITLE>Not Found</TITLE>\r\n");
    send(client, buf, strlen(buf), 0);
    sprintf(buf, "<BODY><P>The server could not fulfill\r\n");
    send(client, buf, strlen(buf), 0);
    sprintf(buf, "your request because the resource specified\r\n");
    send(client, buf, strlen(buf), 0);
    sprintf(buf, "is unavailable or nonexistent.\r\n");
    send(client, buf, strlen(buf), 0);
    sprintf(buf, "</BODY></HTML>\r\n");
    send(client, buf, strlen(buf), 0);
}

/**********************************************************************/
/* Send a regular file to the client.  Use headers, and report
 * errors to client if they occur.
 * Parameters: a pointer to a file structure produced from the socket
 *              file descriptor
 *             the name of the file to serve */
/**********************************************************************/
void serve_file(int client, const char *filename)
{
    FILE *resource = NULL;
    int numchars = 1;
    char buf[1024];

    buf[0] = 'A'; buf[1] = '\0';
    while ((numchars > 0) && strcmp("\n", buf))  /* read & discard headers */
        numchars = get_line(client, buf, sizeof(buf));

    resource = fopen(filename, "r");
    if (resource == NULL)
        not_found(client);
    else
    {
        headers(client, filename);
        cat(client, resource);
    }
    fclose(resource);
}

/**********************************************************************/
/* This function starts the process of listening for web connections
 * on a specified port.  If the port is 0, then dynamically allocate a
 * port and modify the original port variable to reflect the actual
 * port.
 * Parameters: pointer to variable containing the port to connect on
 * Returns: the socket */
/**********************************************************************/
int startup(u_short *port)
{
    int httpd = 0;            //服务器监听套接字描述符
    int on = 1;               //设置监听套接字的套接字选项时，作为参数传入，表示开启
    struct sockaddr_in name;  //ipv4套接字地址结构

    //创建服务器监听套接字描述符
    httpd = socket(PF_INET, SOCK_STREAM, 0);
    if (httpd == -1)
        error_die("socket");
    //初始化、设置套接字地址结构
    memset(&name, 0, sizeof(name));
    name.sin_family = AF_INET;                  //IPV4协议
    name.sin_port = htons(*port);               //传入的4000号端口
    name.sin_addr.s_addr = htonl(INADDR_ANY);   //通配地址
    // SO_REUSEADDR 有4个作用：
    //    1）允许启动一个监听服务器并捆绑其众所周知端口，即使以前建立的将该端口用作它们的
    //       本地端口的连接仍然存在
    //    2）允许在同一端口上启动同一服务器的多个实例，只要每个实例捆绑一个不同的本地IP地
    //       址即可
    //    3）允许单个进程捆绑同一端口到多个套接字上，只要每次捆绑指定不同的本地IP地址即可
    //    4）允许完全重复的捆绑：当一个IP地址和端口已捆绑到某个套接字上时，如果传输协议支
    //       持，同样的IP地址和端口还可以捆绑到到另一个套接字上
    // 这里应该是为了起到作用1）的效果
    if ((setsockopt(httpd, SOL_SOCKET, SO_REUSEADDR, &on, sizeof(on))) < 0)  
    {
        error_die("setsockopt failed");
    }
    //调用bind将监听套接字描述符与地址绑定
    if (bind(httpd, (struct sockaddr *)&name, sizeof(name)) < 0)
        error_die("bind");
    //如果传入的端口号为0，说明希望内核分配一个，因此调用getsockname获取内核
    //分配的地址信息，进一步获取分配的端口号
    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);  //获取内核分配的端口号，网络字节序转主机字节序
    }
    //调用listen进行监听，backlog参数为5，即已完成和未完成队列中的连接总数为5
    if (listen(httpd, 5) < 0)
        error_die("listen");
    return(httpd);
}

/**********************************************************************/
/* Inform the client that the requested web method has not been
 * implemented.
 * Parameter: the client socket */
/**********************************************************************/
void unimplemented(int client)
{
    char buf[1024];

    sprintf(buf, "HTTP/1.0 501 Method Not Implemented\r\n");
    send(client, buf, strlen(buf), 0);
    sprintf(buf, SERVER_STRING);
    send(client, buf, strlen(buf), 0);
    sprintf(buf, "Content-Type: text/html\r\n");
    send(client, buf, strlen(buf), 0);
    sprintf(buf, "\r\n");
    send(client, buf, strlen(buf), 0);
    sprintf(buf, "<HTML><HEAD><TITLE>Method Not Implemented\r\n");
    send(client, buf, strlen(buf), 0);
    sprintf(buf, "</TITLE></HEAD>\r\n");
    send(client, buf, strlen(buf), 0);
    sprintf(buf, "<BODY><P>HTTP request method not supported.\r\n");
    send(client, buf, strlen(buf), 0);
    sprintf(buf, "</BODY></HTML>\r\n");
    send(client, buf, strlen(buf), 0);
}

/**********************************************************************/

int main(void)
{
    int server_sock = -1;   //服务器监听套接字描述符
    u_short port = 4000;    //服务器默认监听端口号
    int client_sock = -1;   //已连接套接字描述符
    struct sockaddr_in client_name; //已连接套接字地址结构
    socklen_t  client_name_len = sizeof(client_name);
    pthread_t newthread;    //线程ID

    //根据port创建监听套接字描述符，绑定到相应地址进行监听，得到监听描述符
    server_sock = startup(&port);
    printf("httpd running on port %d\n", port);

    while (1)
    {
        //阻塞于accept，接收来自客户端的连接请求
        client_sock = accept(server_sock,
                (struct sockaddr *)&client_name,
                &client_name_len);
        if (client_sock == -1)
            error_die("accept");
        /* accept_request(&client_sock); */
        //创建线程处理来自客户端的请求
        if (pthread_create(&newthread , NULL, (void *)accept_request, (void *)(intptr_t)client_sock) != 0)
            perror("pthread_create");
    }

    close(server_sock);

    return(0);
}