项目：TinyHttpd:c语言实现的最简单的服务器

TinyHttpd:c语言实现的最简单的服务器（一）

预备知识：
1.http协议相关：
https://github.com/CyC2018/CS-Notes/blob/master/notes/HTTP.md
2.url相关：
https://blog.csdn.net/vikeyyyy/article/details/80596988
https://blog.csdn.net/zhouym_/article/details/90733536
3.关于POST 中的content_length的内容：
https://www.cnblogs.com/nxlhero/p/11670942.html
4.关于本项目中用到的管道的理解：
个人认为：
这里开两个管道是实现双工通信 因为匿名管道在父子进程间是单向通信的，这样开两个管道，一个专门用来父对子通信 一个专门用来子对父通信

通过这个图可以很好的理解，图片来源：
https://www.cnblogs.com/qiyeboy/p/6296387.html
阅读了源码，接下来想在这个模型的基础上，改为epoll模型。。。。
注释为自己添加的，有些函数还做了注释：

/* 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))  //如果输入为空格回车制表符，则返回真  否则返回假

#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 
 在这个函数中，如果不是出错的话，只读了浏览器客户端的http请求，其他还都没读*/
/**********************************************************************/
void accept_request(void *arg)
{
    int client = (intptr_t)arg;   //int 类型 保证各平台的通用性
    char buf[1024];
    size_t numchars;
    char method[255];  //存储方法  get 、 post
    char url[255];  // 存储 url
    char path[512];
    size_t i, j;
    struct stat st;
    int cgi = 0;      /* becomes true if server decides this is a CGI
                       * program */
    /* 这里简单说一下cgi，它是使服务器端动态的生成万维网文档的程序 而不是原来就静态生成好的*/
    char *query_string = NULL;

    numchars = get_line(client, buf, sizeof(buf));  //读取一行数据 返回的是 读取请求的第一行
    i = 0; j = 0;
    while (!ISspace(buf[i]) && (i < sizeof(method) - 1))  //读取客户端的请求方法到metho数组
    {
        method[i] = buf[i];

        
        i++;
    }
    j=i;  //j这里记录了一直到方法的字段
    method[i] = '\0';

    if (strcasecmp(method, "GET") && strcasecmp(method, "POST"))//strcasecmp()用来比较参数s1 和s2 字符串，比较时会自动忽略大小写的差异。
//返回值：若参数s1 和s2 字符串相同则返回0。s1 长度大于s2 长度则返回大于0 的值，s1 长度若小于s2 长度则返回小于0 的值。
    {
        unimplemented(client);   //这里表示 如果不是 GET 或者   POST请求的处理方法  就做无法处理的处理
        return;
    }

    if (strcasecmp(method, "POST") == 0)
        cgi = 1;  //如果请求是POST cgi 设置为1

//读取url 
    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++;  //i 这里记录了url的长度  j记录了在原字符串中一直读到url完，所在的位置
    }
    url[i] = '\0';

    if (strcasecmp(method, "GET") == 0) //如果请求是get  处理方法
    {
        query_string = url;
        while ((*query_string != '?') && (*query_string != '\0'))
            query_string++;
        if (*query_string == '?')   // 如果碰到了'?'  说明是用于动态网站  那就要设置 cgi 并将请求存在query_string中
        {
            cgi = 1;
            *query_string = '\0';
            query_string++;
        }
    }

    sprintf(path, "htdocs%s", url);  //相当于在url之前添加 htdoc相当于添加路径
    if (path[strlen(path) - 1] == '/')  //代表访问的是一个网站的主页
        strcat(path, "index.html");
    if (stat(path, &st) == -1) {   //如果读不到文件的属性信息 那么就丢弃所有http请求头  并且回应客户端
        while ((numchars > 0) && strcmp("\n", buf))  /* read & discard headers  strcmp函数在字符串相等的时候返回0*/
            numchars = get_line(client, buf, sizeof(buf));
        not_found(client);  //如果url的链接出错  则进行错误处理 
    }
    else
    {
        if ((st.st_mode & S_IFMT) == S_IFDIR)  //判断是不是目录
            strcat(path, "/index.html");  //如果是个目录，则默认使用该目录下 index.html 文件
        if ((st.st_mode & S_IXUSR) ||
                (st.st_mode & S_IXGRP) ||
                (st.st_mode & S_IXOTH)    )  //验证文件权限  如果是可执行文件则执行cgi程序
            cgi = 1;
        if (!cgi)
            serve_file(client, path);   //根据cgi的不同选择不同的服务返回方式 
        else
            execute_cgi(client, path, method, query_string);
    }

    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]; //管道
    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)   //如果是GET方法  则丢弃所有的请求报头
        while ((numchars > 0) && strcmp("\n", buf))  /* read & discard headers */
            numchars = get_line(client, buf, sizeof(buf)); // 读取header并且丢弃
    else if (strcasecmp(method, "POST") == 0) /*POST*/
    {
        numchars = get_line(client, buf, sizeof(buf));
        /*以下程序的目的是 对 POST 的 HTTP 请求中找出 content_length */
        while ((numchars > 0) && strcmp("\n", buf))
        {
            buf[15] = '\0'; /*利用 \0 进行分隔 */
            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);  //错误请求
            return;
        }
    }
    else/*HEAD or other*/
    {
    }
    //这里开两个管道我认为是实现双工通信 因为匿名管道在父子进程间是单向通信的，这样开两个管道，一个专门用来父对子通信 一个专门用来子对父通信

    if (pipe(cgi_output) < 0) {
        cannot_execute(client); //错误处理
        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); //向客户端浏览器发送 正确状态码 200


    if (pid == 0)  /* child: CGI script */   //在子进程中运行 cgi脚本 perl语言
    {
        char meth_env[255];
        char query_env[255];
        char length_env[255];

        dup2(cgi_output[1], STDOUT); //把 STDOUT 重定向到 cgi_output 的写入端
        dup2(cgi_input[0], STDIN); //把 STDIN 重定向到 cgi_input 的读取端
        close(cgi_output[0]);   //关闭 cgi_input 的写入端 和 cgi_output 的读取端
        close(cgi_input[1]);
        //CGI标准需要将请求的方法存储环境变量中，然后和cgi脚本进行交互
        sprintf(meth_env, "REQUEST_METHOD=%s", method);
        putenv(meth_env);   //设置 request_method 的环境变量
        if (strcasecmp(method, "GET") == 0) {
            sprintf(query_env, "QUERY_STRING=%s", query_string);
            putenv(query_env);  //设置 query_string 的环境变量
        }
        else {   /* POST */
            sprintf(length_env, "CONTENT_LENGTH=%d", content_length);
            putenv(length_env); //设置 content_length 的环境变量
        }
        execl(path, NULL);  //运行cgi程序
        exit(0);
    } else {    /* parent */
        close(cgi_output[1]); //关闭了cgi_output中的写通道，注意这是父进程中cgi_output变量和子进程要区分开
        close(cgi_input[0]);关闭了cgi_input中的读通道
        if (strcasecmp(method, "POST") == 0)
            for (i = 0; i < content_length; i++) {
                recv(client, &c, 1, 0);   //从客户端读取http请求 报头
                write(cgi_input[1], &c, 1); // 将数据给cgi  进行一定的处理
            }
        while (read(cgi_output[0], &c, 1) > 0) // 读由cgi程序返回的数据
            send(client, &c, 1, 0);    //向客户端发送数据

        close(cgi_output[0]);
        close(cgi_input[1]);
        waitpid(pid, &status, 0);
    }
}
//  https://www.cnblogs.com/qiyeboy/p/6296387.html
/**********************************************************************/
/* 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)
 从套接字获取一行数据，无论该行以换行符结尾，回车符还是CRLF组合。 用空字符终止读取的字符串。 
 如果在缓冲区末尾之前未找到换行符，则该字符串以null终止。 如果读取以上三个行终止符中的任何一个，
 则字符串的最后一个字符将是换行符，并且该字符串将以空字符终止。 返回的是读取的字符的个数*/
/**********************************************************************/
int get_line(int sock, char *buf, int size)
{
    int i = 0;
    char c = '\0';
    int n;

    while ((i < size - 1) && (c != '\n'))
    {
        n = recv(sock, &c, 1, 0);  //recv函数从套接字中接收信息，一次接受一个信息
        /* DEBUG printf("%02X\n", c); */
        if (n > 0)
        {
            if (c == '\r')
            {
                n = recv(sock, &c, 1, MSG_PEEK);//MSG_PEEK表示查看TCP buf
                //中的数据，而不取走它，下次读的时候还在，并且读出来的就是这个字符或字符串（视缓冲区大小而定）
                /* DEBUG printf("%02X\n", c); */
                if ((n > 0) && (c == '\n'))
                    recv(sock, &c, 1, 0);
                else
                    c = '\n';
            }
            buf[i] = c;
            i++;
        }
        else
            c = '\n';
    }
    buf[i] = '\0';
//这样读每一行的结果就是  无论这一行以 /r /n  /r/n 或者其他的结尾   到最后都以/n /0结尾
    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; //FILE为文件流指针
    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));
    /*打开 sever 的文件*/
    resource = fopen(filename, "r");
    if (resource == NULL)
        not_found(client);
    else
    {
        headers(client, filename); //写返回给client的回应http请求
        cat(client, resource);// 将要在服务器上已经有的静态网页传送回去
    }
    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.   296/5000
此函数开始侦听指定端口上的Web连接的过程。 如果端口为0，则动态分配端口并修改原始端口变量以反映实际端口
 * Parameters: pointer to variable containing the port to connect on
 * Returns: the socket */
/**********************************************************************/
int startup(u_short *port)
{
    int httpd = 0;
    int on = 1;
    struct sockaddr_in name;

    httpd = socket(PF_INET, SOCK_STREAM, 0);  // 等同于  socket(AF_INET,SOCK_STREAM,0)   这里创建套接字
    //AF 表示 addres family  PF 表示 protocol family 
    if (httpd == -1)
        error_die("socket");
    memset(&name, 0, sizeof(name));
    name.sin_family = AF_INET;
    name.sin_port = htons(*port); //将主机字节序转换为网络字节序  这里如果*port为0，内核会随机分配一个端口号，下边有相应的处理
    name.sin_addr.s_addr = htonl(INADDR_ANY);//随机分配一个ip地址
    if ((setsockopt(httpd, SOL_SOCKET, SO_REUSEADDR, &on, sizeof(on))) < 0) //端口复用
    {  
        error_die("setsockopt failed");
    }
    if (bind(httpd, (struct sockaddr *)&name, sizeof(name)) < 0)  //将IP地址和端口号与套接字绑定
        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);
        //这里的 getsockname 函数就是获得和httpd套接字绑定的IP 和端口号，通过name参数返回
    }
    if (listen(httpd, 5) < 0)  //最多监听五个请求
        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) //未实行的
{
    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;
    u_short port = 4000;
    int client_sock = -1;
    struct sockaddr_in client_name;
    socklen_t  client_name_len = sizeof(client_name);
    pthread_t newthread;

    server_sock = startup(&port); //startup: 初始化 httpd 服务，包括建立套接字，绑定端口，进行监听等。

    printf("httpd running on port %d\n", port);

    while (1)
    {
        client_sock = accept(server_sock,
                (struct sockaddr *)&client_name,   //建立三次握手成功后返回返回的是可以用来通讯的套接字文件描述符
                &client_name_len);
        if (client_sock == -1)
            error_die("accept");  //把错误信息写到 perror 并退出。
       
        if (pthread_create(&newthread , NULL, (void *)accept_request, (void *)(intptr_t)client_sock) != 0);
        //accept_request:  处理从套接字上监听到的一个 HTTP 请求，在这里可以很大一部分地体现服务器处理请求流程。
            perror("pthread_create");
    }

    close(server_sock);

    return(0);
}

参考：
https://www.cnblogs.com/qiyeboy/p/6296387.html
https://blog.csdn.net/jcjc918/article/details/42129311