Tinyhttpd-源码阅读笔记

简介

这是一个用c实现的简单的http服务器
业务流程大约是创建socket
然后把监听链接,有链接就把connfd给accept_request线程
由accept_request处理线程
    然后线程再根据GET和POST方法,有没有参数传递过来,是不是可执行文件来确定需不需要启动进程处理数据
    不需要执行权限的,直接把页面返回,需要执行的,交个子进程执行,结果返回给父进程,返回给浏览器

报文

请求index时的报文
GET / HTTP/1.1
Host: 192.168.36.42:57046
Connection: keep-alive
Accept: text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8
Upgrade-Insecure-Requests: 1
User-Agent: Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/46.0.2490.86 Safari/537.36
Accept-Encoding: gzip, deflate, sdch
Accept-Language: zh-CN,zh;q=0.8

--------------------------------------------------------------------
请求cgi时的报文
POST /color.cgi HTTP/1.1
Host: 192.168.36.42:60566
Connection: keep-alive
Content-Length: 6
Cache-Control: max-age=0
Accept: text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8
Origin: http://192.168.36.42:60566
Upgrade-Insecure-Requests: 1
User-Agent: Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/46.0.2490.86 Safari/537.36
Content-Type: application/x-www-form-urlencoded
Referer: http://192.168.36.42:60566/
Accept-Encoding: gzip, deflate
Accept-Language: zh-CN,zh;q=0.8

color=
------------------------------------------------
回复请求cgi的报文

HTTP/1.0 200 OK

源码

#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 <string.h>
#include <strings.h>
#include <sys/stat.h>
#include <pthread.h>
#include <sys/wait.h>
#include <stdlib.h>

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

#define SERVER_STRING "Server: jdbhttpd/0.1.0\r\n"

void accept_request(int);
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); /* 读一行 */
void headers(int , const char *);
void not_found(int);    /* 404 */
void serve_file(int, const char *);
int startup(u_short *);
void unimplemented(int);    /* 501 */

void accept_request(int client)
{
    char buf[1024];
    int numchars;
    char method[255];
    char url[255];
    char path[512];
    size_t i, j;
    struct stat st;
    int cgi = 0;    /* 请求的是否是可执行文件 */

    char *query_string = NULL;

#if 0   /* Debug 打印接收到的浏览器信息请求 */
    recv(client, buf, 1024, MSG_PEEK);
    printf("%s\n", buf);
#endif

    numchars = get_line(client, buf, sizeof(buf));
    i = 0, j = 0;

    /* 从消息头中分割出是GET还是POST */
    while (!ISspace(buf[j]) && (i < sizeof(method)-1)) {
        method[i] = buf[j];
        i++, j++;
    }
    method[i] = ‘\0‘;

    if (strcasecmp(method, "GET") && strcasecmp(method, "POST")) {
        /* 既不是GET也不是POST,
         * 回应浏览器 501 消息 */
        unimplemented(client);
        return ;
    }

    if (strcasecmp(method, "POST") == 0) {
        cgi = 1;    /* post,就要执行文件 */
    }

    i = 0;
    while (ISspace(buf[j]) && (j < sizeof(buf)))  {
        j++;    /* 越过空格 */
    }

    /* 找出GET后面的url */
    while (!ISspace(buf[j]) && (i < sizeof(url)-1) 
            && (j < sizeof(buf))) {
        url[i++] = buf[j++];
    }
    url[i] = ‘\0‘;

    if (strcasecmp(method, "GET") == 0) {   /* 如果是GET */
        query_string = url;
        /* 找在url中使用GET传送来的参数 */
        while ((*query_string != ‘?‘) && (*query_string != ‘\0‘)) {
            query_string++;
        }
        /* 如果真有参数,那就需要执行CGI来处理 */
        if (*query_string == ‘?‘) {
            cgi = 1;
            *query_string = ‘\0‘;   /* 从?号截断*/
            query_string++; /* 保存参数的首地址 */
        }
    }

    /* 把"/"修改成相对于服务器的路径 "/"--> "htdocs/" */
    sprintf(path, "htdocs%s", url);
    if (path[strlen(path)-1] == ‘/‘) {
        /* 如果以"#/", 自动补成"#/index.html" */
        strcat(path, "index.html");
    }

    if (stat(path, &st) == -1) { /* 如果读取文件信息失败 */
        /* stat失败,首先把client消息头都读完 */
        while ((numchars > 0) && strcmp("\n", buf)) {
            numchars = get_line(client, buf, sizeof(buf));
        }
        not_found(client);  /* 返回404页面 */
    } else {    /* stat成功, 有这个文件 */
        /* 如果这个文件是文件夹,
         * 就默认请求的是这个文件夹的index.html*/
        if ((st.st_mode & S_IFMT) == S_IFDIR)
            strcat(path, "/index.html");

        /* 如果请求的文件是可执行文件 */
        if ((st.st_mode & S_IXUSR) || 
                (st.st_mode & S_IXGRP) ||
                (st.st_mode & S_IXOTH)) {
            cgi = 1;  /* 再次把cgi设置成1 */
        }

        if (!cgi) {
            /* 如果cgi是0, 传入的cgi文件路径和sock文件描述符 */
            serve_file(client, path);
        } else {
            /*client, cgi文件路径, 请求的方法 ?后面跟的参数*/
            execute_cgi(client, path, method, query_string);
        }
        close(client);
    }
}

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, i, numchars = 1;
    int content_length = -1;
    char c;

    buf[0] = ‘A‘; buf[1] = ‘\0‘;

    /*  如果是GET,那参数就在url中传递,已经提取到了query_string
     * 把剩余的消息头丢掉
     * */
    if (strcasecmp(method, "GET") == 0) {
        while ((numchars > 0) && strcmp("\n", buf)) 
            numchars = get_line(client, buf, sizeof(buf));
    } else {
        /* POST  参数在消息实体中传递 */
        numchars = get_line(client, buf, sizeof(buf));

        while ((numchars > 0) && strcmp("\n", buf)) {
            buf[15] = ‘\0‘;
            /* 把内容按行读,筛选出Content-Length这个字段
             * 得到消息实体的长度*/
            if (strcasecmp(buf, "Content-Length:") == 0)
                content_length = atoi(&(buf[16]));
            numchars = get_line(client, buf, sizeof(buf));
        }
        /* content_length=-1, 说明消息头中没有Content-Length这个字段 */
        if (content_length == -1) {
            bad_request(client);    /* 给浏览器返回400,请求出现语法错误 */
            return ;
        }
    }

    sprintf(buf, "HTTP/1.0 200 OK\r\n");
    send(client, buf, strlen(buf), 0);

    /* 创建与子进程通信的管道 */
    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 ;
    }

    if (pid == 0) { /* child: CGI script */
        char meth_env[255];
        char query_env[255];
        char length_env[255];

        /* 把子进程的标准输入和标准输出都重定向到管道上
         * 进行读参数, 写数据的操作*/
        dup2(cgi_output[1], 1);
        dup2(cgi_input[0], 0);
        close(cgi_output[0]);
        close(cgi_input[1]);

        /* 拼接回应的请求方式 */
        sprintf(meth_env, "REQUEST_METHOD=%s", method);
        putenv(meth_env);   /* 添加meth_env到子进程的环境变量中 */

        /* 如果是GET方法
         * 就把从URL中提取的参数放到QUERY_STRING这个环境变量里*/
        if (strcasecmp(method, "GET") == 0) {
            sprintf(query_env, "QUERY_STRING=%s", query_string);
            putenv(query_env);
        } else {    /* POST 把消息实体的长度设置为环境变量*/
            sprintf(length_env, "CONTENT_LENGTH=%d", content_length);
            putenv(length_env);
        }
        /* exec把cgi的这个应用拉起来 */
        execl(path, path, NULL);
    } else {    /* parent */
        /* 关闭不需要的管道读写端 */
        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);
    }
}

/* 发送文件中的内容 */
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);
    }
}

int get_line(int sock, char *buf, int size)
{
    int i = 0, n;
    char c = ‘0‘;

    while ((i < size-1) && (c != ‘\n‘)) {
        n = recv(sock, &c, 1, 0);

        /* 一个字节一个字节的从sock中读内容 */
        if (n > 0) {    /* 读到内容 */
            if (c == ‘\r‘) {
                /* 读到‘\r‘,就代表这一行结束,
                 * 如果后面有\n就读出来,
                 * 如果没有,就自己加上‘\n‘ */
                /* MSG_PEEK 返回的数据并不会在系统内删除,
                 * 如果再次调用recv()会返回相同的数据*/
                n = recv(sock, &c, 1, MSG_PEEK);
                if ((n > 0) && (c == ‘\n‘))
                    recv(sock, &c, 1, 0);
                else
                    c = ‘\n‘;
            }
            buf[i] = c;
            i++;
        } else {
            c = ‘\n‘;
        }
    }
    buf[i] = ‘\0‘;      /* 字符串补0 */
    return (i); /* 返回读到的字符串 */
}

void serve_file(int client, const char *filename)
{
    FILE *resource = NULL;
    int numchars = 1;
    char buf[1024];

    buf[0] = ‘A‘; buf[1] = ‘\0‘;

    /* 读取并且丢弃消息头 */
    while ((numchars > 0) && strcmp("\n", buf)) {
        numchars = get_line(client, buf, sizeof(buf));
    }

    resource = fopen(filename, "r");
    if (resource == NULL)
        not_found(client);  /* 打开失败, 返回404 */
    else {
        headers(client, filename);  /* 发送消息头 */
        cat(client, resource);  /*  发送文件内容 */
    }
    fclose(resource);
}

int startup(u_short *port)
{
    int httpd = 0;
    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 (bind(httpd, (struct sockaddr*)&name, sizeof(name)) < 0)
        error_die("bind");
    /* 如果port=0, htons动态分配一个端口
     * 从httpd中得到端口号*/
    if (*port == 0) {   
        int 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("listed");
    return (httpd);
}

int main(void)
{
    int server_sock = -1;
    u_short port = 0;
    int client_sock = -1;
    struct sockaddr_in client_name;
    int client_name_len = sizeof(client_name);
    pthread_t newthread;

    server_sock = startup(&port);   /* 获得socketfd 和端口号*/
    printf("httpd running on port %d\n", port);

    /* 监听服务器的sock,把接收到client_sock交给线程处理 */
    while (1) {
        client_sock = accept(server_sock,
                (struct sockaddr*)&client_name,
                &client_name_len);
        if (client_sock == -1) {
            error_die("accept");
        }
        if (pthread_create(&newthread, NULL, accept_request, client_sock) != 0) {
           perror("pthread_create");
        }
    }

    close(server_sock);

    return 0;
}


/*-----------------------------------------------------*/
void bad_request(int client)    /* 400 */
{
    char buf[1024];

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

    send(client, buf, strlen(buf), 0);
}


/* 执行CGI出错 返回500 */
void cannot_execute(int client)
{
    char buf[1024];

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

void headers(int client, const char *filename)  /* 200恢复头*/
{
    char buf[1024];

    sprintf(buf, "HTTP/1.0 200 OK\r\n");
    sprintf(buf, "%s%s", buf, SERVER_STRING);
    sprintf(buf, "%sContent-Type: text/html\r\n\r\n", buf);

    send(client, buf, strlen(buf), 0);
}

void not_found(int client)  /* 404 not found */
{
    char buf[1024];

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

void unimplemented(int client)  /* 501 */
{
    char buf[1024];
    sprintf(buf, "HTTP/1.0 501 Method Not Implemented\r\n");
    sprintf(buf, "%s%s", buf, SERVER_STRING);
    sprintf(buf, "%sContent-Type: text/html\r\n\r\n", buf);
    sprintf(buf, "%s<HTML><HEAD><TITLE>Method Not Implemented\r\n", buf);
    sprintf(buf, "%s</TITLE></HEAD>\r\n", buf);
    sprintf(buf, "%s<BODY><P>HTTP request method not supported.\r\n", buf);
    sprintf(buf, "%s</BODY></HTML>\r\n", buf);

    send(client, buf, strlen(buf), 0);
}

void error_die(const char *sc)
{
    perror(sc);
    exit(1);
}