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>

#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);
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(int client)
{
	char buf[1024];
	int numchars;
	char method[255];
	char url[255];
	char path[512];
	size_t i, j;

	struct stat st; // 文件状态信息
	/* stat是用来描述一个文件属性的结构体，有两种方法获得一个文件的属性。
	利用文件的路径：
		int stat(const char *path, struct stat *struct_stat);
		int lstat(const char *path, struct stat *struct_stat); 可以处理软链接
	利用fd：
		int fstat(int fd, struct stat *struct_stat);
	*/

	/* 公共网关接口(Common Gateway Interface, CGI)
	CGI是Web服务器和外部扩展程序交互的标准接口。按CGI编写的程序可以扩展服务器功能。
	CGI应用程序能与浏览器进行交互，还可通过数据API与数据库服务器等外部数据源进行通信，
	从数据库服务器中获取数据。格式化为HTML文档后，发送给浏览器，也可以将从浏览器获得的数据放到数据库中。
	*/
	int cgi = 0;      /* becomes true if server decides this is a CGI
					   * program */
	char* query_string = NULL;

	// get_line()函数每次读到'\n'或者'\r\n'结束，并且将'\n'和'\r\n'替换成'\n\0'结束
	numchars = get_line(client, buf, sizeof(buf));
	i = 0; j = 0;
	while (!ISspace(buf[j]) && (i < sizeof(method) - 1))
	{
		method[i] = buf[j];
		i++; j++;
	}
	method[i] = '\0';

	// method是报文中的请求方法，如GET，POST

	// strcasecmp()头文件为string.h，为linux下的函数，windows对应的库函数为_stricmp()
	// 忽略大小写比较字符串，s1s2相同返回0，s1长度小于s2长度返回小于0的值，s1长度大于s2长度返回大于0的值
	if (strcasecmp(method, "GET") && strcasecmp(method, "POST"))
	{
		unimplemented(client);
		return;
	}

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

	i = 0;
	while (ISspace(buf[j]) && (j < sizeof(buf)))
		j++;
	while (!ISspace(buf[j]) && (i < sizeof(url) - 1) && (j < sizeof(buf)))
	{
		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");
	// stat返回值：成功返回0，失败返回-1
	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); // 普通页面请求，不需要cgi
		else
			execute_cgi(client, path, method, query_string); // 调用cgi
	}

	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    /* POST */
	{
		numchars = get_line(client, buf, sizeof(buf));
		while ((numchars > 0) && strcmp("\n", buf))
		{
			buf[15] = '\0'; // "Content-Length:"是15个字符，在后面加一个'\0'，在下一行比较
			if (strcasecmp(buf, "Content-Length:") == 0)
				content_length = atoi(&(buf[16])); // 赋值
			numchars = get_line(client, buf, sizeof(buf));
		}
		if (content_length == -1) {
			bad_request(client);
			return;
		}
	}

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

	if (pipe(cgi_output) < 0) { // 创建管道，cgi_output[1]写
		cannot_execute(client);
		return;
	}
	if (pipe(cgi_input) < 0) { // cgi_input[0]读
		cannot_execute(client);
		return;
	}

	if ((pid = fork()) < 0) { // 创建子进程
		cannot_execute(client);
		return;
	}
	if (pid == 0)  /* child: CGI script */
	{
		char meth_env[255];
		char query_env[255];
		char length_env[255];

		dup2(cgi_output[1], 1); // 把stdout重定向到管道读端
		dup2(cgi_input[0], 0); // 把stdin重定向到管道写端
		close(cgi_output[0]);
		close(cgi_input[1]); // 关闭不需要的读写端
		// 设置request_method的环境变量
		sprintf(meth_env, "REQUEST_METHOD=%s", method); // 通过环境变量传递信息，实现进程间通信
		putenv(meth_env);
		if (strcasecmp(method, "GET") == 0) {
			sprintf(query_env, "QUERY_STRING=%s", query_string);
			putenv(query_env);
		}
		else {   /* POST */
			// 设置content_length的环境变量
			sprintf(length_env, "CONTENT_LENGTH=%d", content_length); // 告诉需要读的长度
			putenv(length_env);
		}
		/* int execl(const char *path, const char *arg, ...);
		执行参数path串代表的文件路径，后面的参数代表执行文件时的参数argv[0], argv[1], ...，最后一个参数是NULL
		*/
		execl(path, path, NULL); // 运行cgi程序
		exit(0);
	}
	else {    /* parent */
		close(cgi_output[1]); // 关闭不需要的读写端：cgi_input的写入端，cgi_output的读取端
		close(cgi_input[0]);
		if (strcasecmp(method, "POST") == 0) // 从客户端读取请求数据，发送给cgi
			for (i = 0; i < content_length; i++) {
				recv(client, &c, 1, 0); 
				write(cgi_input[1], &c, 1); // 把POST传递的参数写入stdin，即cgi_input
			}
		while (read(cgi_output[0], &c, 1) > 0) 
			send(client, &c, 1, 0); // 从cgi子进程读取响应数据，返回给客户端

		close(cgi_output[0]);
		close(cgi_input[1]);
		waitpid(pid, &status, 0); // 等待子进程结束
	}
}

/**********************************************************************/
/* 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 = '\0';
	int n;

	while ((i < size - 1) && (c != '\n'))
	{
		n = recv(sock, &c, 1, 0);
		/* DEBUG printf("%02X\n", c); */
		if (n > 0)
		{
			if (c == '\r') // 收到'\r'则继续接收下个字节，因为换行符可能是'\r\n'
			{
				n = recv(sock, &c, 1, MSG_PEEK);
				/* 通常recv的flags参数被设为0，这时recv会把tcp buffer的数据读到buf，并清除tcp buffer中已读的数据
				将recv的flags参数设置为MSG_PEEK，这时只把tcp buffer中的数据读到buf中，不会清除tcp buffer中已读的数据，再次调用recv仍然可以读到之前读过的数据
				*/
				/* DEBUG printf("%02X\n", c); */
				if ((n > 0) && (c == '\n'))
					recv(sock, &c, 1, 0); // 读掉'\n'
				else
					c = '\n';
			}
			buf[i] = c;
			i++;
		}
		else
			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); // 404
	else
	{
		headers(client, filename); // 状态码、响应头
		cat(client, resource); // 发送访问的文件
	}
	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;
	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); // INADDR_ANY
	if (bind(httpd, (struct sockaddr*)&name, sizeof(name)) < 0)
		error_die("bind");
	// 如果传入参数port是0，就动态分配一个
	if (*port == 0)  /* if dynamically allocating a port */
	{
		int namelen = sizeof(name);
		/* int getsockname(int sockfd, struct scokaddr *addr, socklen_t *addrlen);
		   getsockname将addr的内容按照sockfd绑定的socket设置
		   返回值：正常情况下返回0，否则返回-1
		*/
		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\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 = 0;
	int client_sock = -1;
	struct sockaddr_in client_name;
	int client_name_len = sizeof(client_name);
	/*pthread_t newthread;*/

	// 如果port是0，就动态分配一个端口
	server_sock = startup(&port); // 完成socket的bind，listen
	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); // accept_request()处理连接请求
		/*if (pthread_create(&newthread, NULL, accept_request, client_sock) != 0)
			perror("pthread_create");*/
	}

	close(server_sock);

	return(0);
}