遇到的问题
-
在本地搭建服务器时,如果响应头里的content_type出错,请求服务器时只会下载文件,而不在浏览器中显示
-
unix上标准输入输出都是带有缓存的,一般是行缓存。
对于标准输出,需要输出的数据并不是直接输出到终端上,而是首先缓存到某个地方,当遇到行刷新标志或者该缓存已满的情况下,才会把缓存的数据显示到终端设备上。
ANSI C中定义换行符’\n’可以认为是行刷新标志。所以,printf函数没有带’\n’是不会自动刷新输出流,直至缓存被填满。
程序流程
-
main函数里首先调用startup函数,在该函数中进行服务端套接字的生成(socket),绑定(bind)和监听(listen)。服务端的端口是由内核自动生成的,通过将sockaddr_in(存放套接字)数据结构里的sin_port设为0来实现。然后在main函数中accept客户端的链接,如果收到链接,则新建一个进程执行accept_request函数来处理客户端发送来的信息。
-
accept_request函数处理来自客户端的信息,即浏览器的请求。通过判断请求头里的请求方法(GET or POST)还有URL来决定是否执行CGI脚本还是返回一个index.html。因为该程序逻辑是第一次请求index.html文件,在该文件中提交一个表单,然后会再次以POST方式请求color.cgi脚本,收到该脚本生成的一个html网页。
难点
- 该程序的一个难点是execute_cgi函数中父进程与子进程之间通过两个管道交互。且子进程将标准输入输出绑定在管道上,因此可以通过子进程的标准输入输出和父进程交互。
- 另一个难点是对于header头信息的处理和获取。
- 理解客户端与服务端之间交互的流程
源码笔记
/* 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" //放在响应头里表示服务器类型
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 *tclient)
{
int client=*(int *)tclient;
char buf[1024];
int 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)); //获取请求头里第一行内容
i = 0; j = 0;
while (!ISspace(buf[j]) && (i < sizeof(method) - 1)) //获取请求类型
{
method[i] = buf[j];
i++; j++;
}
method[i] = '\0';
if (strcasecmp(method, "GET") && strcasecmp(method, "POST"))
{
unimplemented(client);
return NULL;
}
if (strcasecmp(method, "POST") == 0)
cgi = 1;
i = 0;
while (ISspace(buf[j]) && (j < sizeof(buf))) //过滤空格
j++;
while (!ISspace(buf[j]) && (i < sizeof(url) - 1) && (j < sizeof(buf))) //获取url
{
url[i] = buf[j];
i++; j++;
}
url[i] = '\0';
if (strcasecmp(method, "GET") == 0) //GET模式下属性包含在url的?后面,以下代码查找不包含属性的url,属性可以通过query_string查询
{
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); //将htdoc+‘url’写入path
if (path[strlen(path) - 1] == '/') //如果url最后是/,则代表该url是个文件夹,自动找到该文件夹下的index.html
strcat(path, "index.html");
if (stat(path, &st) == -1) { //url错误
while ((numchars > 0) && strcmp("\n", buf)) /* read & discard headers */ //舍弃客户端发来的请求头里的其余信息
numchars = get_line(client, buf, sizeof(buf));
not_found(client);
}
else
{
if ((st.st_mode & S_IFMT) == S_IFDIR) //如果path路径是文件夹
strcat(path, "/index.html");
if ((st.st_mode & S_IXUSR) || //判断用户,组,其他是否有该文件的执行权限
(st.st_mode & S_IXGRP) ||
(st.st_mode & S_IXOTH) )
cgi = 1;
if (!cgi) //当请求类型为GET且有参数或者为POST时cgi为1,表示执行cgi脚本
serve_file(client, path); //返回请求文件
else
execute_cgi(client, path, method, query_string);
}
close(client);
return NULL;
}
/**********************************************************************/
/* 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)); //获得post方法所传递的数据长度
while ((numchars > 0) && strcmp("\n", buf)) //获得header其余的每行信息,如果有一行是Content-Length开头的,则获取其数值。当header读完后,再读一行即为Post的参数
{
buf[15] = '\0'; //具体长度和前面的冒号之间会有一个空格
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;
}
}
sprintf(buf, "HTTP/1.0 200 OK\r\n");
send(client, buf, strlen(buf), 0);
//建立两个管道来实现父进程和子进程之间的通信,因为管道是单向的,因此需要两个管道才能实现互相之间的交互。cgi_input是父进程向子进程传输,cgi_output是子进程向父进程传输
if (pipe(cgi_output) < 0) { //管道函数产生一对文件描述符,后面的为写文件描述符,前面的为读文件描述符
cannot_execute(client);
return;
}
if (pipe(cgi_input) < 0) {
cannot_execute(client);
return;
}
//fork进程,子进程用于执行CGI
//父进程用于收数据以及发送子进程处理的回复数据
//将标准输入输出绑定在子进程管道的接受口和传输口来,实现在子进程内通过调用标准输入输出与父进程进行交互,解决了在脚本内与父进程交流,进一步与客户端交流的问题
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];
/*
(stdin)In[0] <-----------x In[1] 接受来自父进程的信息
Out[0] x<----------- Out[1](stdout) 向父进程传输信息
使用标准读(stdin)时会将父进程传过来的信息读出
使用标准写(stdout)时会向父进程发送信息
*/
//printf("adasdad\n");
dup2(cgi_output[1], 1); //将第二个参数的文件描述符复制为第一个参数的,而0,1,2分别代表stdin,stdout,stder三者的文件描述符
//因此该段代码即表示cgi_output[0]读入的内容来自stdout和cgi_output【1】写入的内容,stdout重定向到cgi_output[1]上
dup2(cgi_input[0], 0); //stdin和cgi_input[0]读入的内容来自cgi_input[1]写入的内容,stdin重定向到cgi_input[0]上
close(cgi_output[0]); //关闭不使用的端口,因为子进程只负责接受父进程的信息(cgi_input[0])和向父进程传输信息(cgi_output[1])
close(cgi_input[1]);
for (i = 0; i < content_length; i++) {
//recv(client, &c, 1, 0);
//read(cgi_input[0], &c, 1); //将Post方法里的内容发送给子进程
scanf("%c",&c);
printf("%c",c);
}
printf("\n");
sprintf(meth_env, "REQUEST_METHOD=%s", method); //CGI脚本会根据REQUEST_METHOD环境变量决定从QUERY_STRING中还是stdin中获取客户端传送数据
putenv(meth_env); //增加环境变量
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); //该环境变量决定从stdin中读取多少字节
putenv(length_env);
}
//execl(path, path, NULL);
exit(0);
} else { /* parent */
/*
In[0] x<----------- In[1] 向子进程传输信息
Out[0] <-----------x Out[1] 接受来自子进程的信息
*/
close(cgi_output[1]); //关闭无用端口
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); //将Post方法里的内容发送给子进程
}
while (read(cgi_output[0], &c, 1) > 0){ //从子进程接受信息并发送给客户端
send(client, &c, 1, 0);
//printf("%c",c);
}
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) //当遇到/r/n时接着读,但单独遇到/r或/n时都停止
{
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')
{
//MAG_PEEK表示偷窥缓冲区里的内容但不读走,下次读的时候还在
//因此下面代码意思为如果\r后面是\n会将其读走后再结束
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;
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 */ //舍弃客户端发来的请求头里的其余信息
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;
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");
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);
}
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;
socklen_t client_name_len = sizeof(client_name);
pthread_t newthread;
server_sock = startup(&port);
printf("httpd running on port %d\n", port);
while (1)
{
client_sock = accept(server_sock,
(struct sockaddr *)&client_name,
&client_name_len);
printf("accept\n");
if (client_sock == -1)
error_die("accept");
/*accept_request(client_sock); */
if (pthread_create(&newthread , NULL, accept_request, (void*)&client_sock) != 0)
perror("pthread_create");
}
close(server_sock);
return(0);
}