Tinyhttpd——搭建轻量型webserver

这是我在学习搭建webserver时的笔记。此开源项目由C语言实现。

github开源项目链接：https://github.com/EZLippi/Tinyhttpd

建议参考：TinyHTTPd开源项目总结 - Caso_卡索 - 博客园 (cnblogs.com)

Tinyhttpd精读解析 - nengm - 博客园 (cnblogs.com)

HTTP服务器的本质:tinyhttpd源码分析及拓展 - 七夜的故事 - 博客园 (cnblogs.com)

这几个博客原理和代码讲得比较详细，有些遇到的问题可以参考着解决。

本人计算机小白，在搭建webserver之前建议小白先了解：HTTP协议、TCP协议、基本TCP套接字编程以及linux基本操作指令、vim的使用、如何makefile等等。

有几个需要注意的地方：

1、关于脚本实现的部分。

（1）测试CGI时需要本机安装PERL，同时安装perl-cgi。我的ubuntu系统自带perl，测试时报错：Can‘t locate CGI.pm in @INC (you may need to install the CGI module)

因此需要装perl-cgi模块，参考解决 Can‘t locate CGI.pm in @INC (you may need to install the CGI module)_胡鹄的博客-CSDN博客；

（2）需要修改htdocs文件夹下的.cgi代码首行路径为本机perl所在路径。在ubuntu终端可用指令which perl查看本机perl的路径。

2、关于makefile部分。

不需要按照原开源项目的makefile实现，可以只实现httpd，改成：

all: httpd
  
httpd: httpd.c
        gcc -g -W -Wall -pthread -o httpd httpd.c

clean:
        rm httpd

3、如何运行webserver

在ubuntu终端运行httpd程序，然后可在ubuntu系统的firefox浏览器中打开127.0.0.1:对应端口号。

下面是httpd.c的代码：

#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 <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
"
#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;
    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] = '';

    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] = '';

    if (strcasecmp(method, "GET") == 0)　　//完善查询语句URL+资源位置
    {
        query_string = url;
        while ((*query_string != '?') && (*query_string != ''))
            query_string++;
        if (*query_string == '?')
        {
            cgi = 1;
            *query_string = '';
            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("
", 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);
}

/**********************************************************************/
/* 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
");
    send(client, buf, sizeof(buf), 0);
    sprintf(buf, "Content-type: text/html
");
    send(client, buf, sizeof(buf), 0);
    sprintf(buf, "
");
    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.
");
    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
");
    send(client, buf, strlen(buf), 0);
    sprintf(buf, "Content-type: text/html
");
    send(client, buf, strlen(buf), 0);
    sprintf(buf, "
");
    send(client, buf, strlen(buf), 0);
    sprintf(buf, "<P>Error prohibited CGI execution.
");
    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] = '';
    if (strcasecmp(method, "GET") == 0)
        while ((numchars > 0) && strcmp("
", 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("
", buf))
        {
            buf[15] = '';
            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
");
    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);
　　　　 execl(path, 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);　　//waitpid()会暂停目前进程的执行，直到有信号来或子进程结束
    }
}

/**********************************************************************/
/* 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;
    char c = '';
    int n;

    while ((i < size - 1) && (c != '
'))
    {
        n = recv(sock, &c, 1, 0);
        /* DEBUG printf("%02X
", c); */
        if (n > 0)
        {
            if (c == '
')
            {
                n = recv(sock, &c, 1, MSG_PEEK);
                /* DEBUG printf("%02X
", c); */
                if ((n > 0) && (c == '
'))
                    recv(sock, &c, 1, 0);
                else
                    c = '
';
            }
            buf[i] = c;
            i++;
        }
        else
            c = '
';
    }
    buf[i] = '';

    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
");
    send(client, buf, strlen(buf), 0);
    strcpy(buf, SERVER_STRING);
    send(client, buf, strlen(buf), 0);
    sprintf(buf, "Content-Type: text/html
");
    send(client, buf, strlen(buf), 0);
    strcpy(buf, "
");
    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
");
    send(client, buf, strlen(buf), 0);
    sprintf(buf, SERVER_STRING);
    send(client, buf, strlen(buf), 0);
    sprintf(buf, "Content-Type: text/html
");
    send(client, buf, strlen(buf), 0);
    sprintf(buf, "
");
    send(client, buf, strlen(buf), 0);
    sprintf(buf, "<HTML><TITLE>Not Found</TITLE>
");
    send(client, buf, strlen(buf), 0);
    sprintf(buf, "<BODY><P>The server could not fulfill
");
    send(client, buf, strlen(buf), 0);
    sprintf(buf, "your request because the resource specified
");
    send(client, buf, strlen(buf), 0);
    sprintf(buf, "is unavailable or nonexistent.
");
    send(client, buf, strlen(buf), 0);
    sprintf(buf, "</BODY></HTML>
");
    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] = '';
    while ((numchars > 0) && strcmp("
", 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;
    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)  
    {  
        error_die("setsockopt failed");
    }
    if (bind(httpd, (struct sockaddr *)&name, sizeof(name)) < 0)
        error_die("bind");
    if (*port == 0)  /*动态分配端口*/
    {
        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);
}

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

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

int main(void)
{
    int server_sock = -1;　　　　//服务器sock
    u_short port = 4000;　　　　 //端口号
    int client_sock = -1;　　　　//客户端sock
    struct sockaddr_in client_name;
    socklen_t  client_name_len = sizeof(client_name);
    pthread_t newthread;

    server_sock = startup(&port);　　//开启服务端
    printf("httpd running on port %d
", port);

    while (1)
    {
        client_sock = accept(server_sock,
                (struct sockaddr *)&client_name,
                &client_name_len);　　//accept返回已连接的对端进程（客户）的协议地址
        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);
}

一些函数的定义：

1、accept

accept由TCP服务器调用，从已完成TCP连接队列的队头返回下一个已完成的连接。

int accept(int sockfd, struct sockaddr *cliaddr, socklen_t *addrlen);

若成功返回非负描述符，否则返回-1。

此时sockfd为监听套接字描述符，返回已连接套接字描述符。

2、socket

#include<sys/socket.h>

int socket(int family, int type, int protocol);

family：地址族，协议族所使用的地址集合。

type：协议族，不同协议的集合。

指定期望的通信协议类型，若成功返回一个小的非负整数值，即套接字描述符sockfd，失败时返回-1。

3、bind

int bind(int sockfd, const struct sockaddr *myaddr, socklen_t addrlen);

若成功返回0，否则返回-1。

4、listen

int listen(int sockfd, int backlog);

5、pipe

pipe创建管道，单向数据流。

#include<unistd.h>

int pipe(int fd[2]);

若成功返回0， 否则返回-1。

并返回两个文件描述符fd[0]打开读，fd[1]打开写。

6、fork

#include<unistd.h>

pid_t fork(void);

fork调用一次，返回两次。在父进程返回一次，返回子进程的进程ID号；在子进程返回一次，值为0；出错返回-1。

注意：fork之后管道都复制了一份，因此需要关闭无用端口，避免浪费。

参考书籍：《UNIX网络编程 卷1：套接字联网API》《计算机网络自顶向下方法》 

如有错误，请在评论中指出，谢谢！