tinyhttpd ------ C 语言实现最简单的 HTTP 服务器

工作流程：

1>服务器启动，在指定端口或随机选取端口绑定httpd服务。

2>收到一个http请求时(其实就是listen端口accept的时候)，派生一个线程运行accept_request函数。

3>取出http请求中method(get或post)和url,对于get方法，如果有携带参数，则query_string指针指向url中?后面的get参数。

4>格式化url到path数组，表示浏览器请求的文件路径，在tinyhttpd中服务器文件是在htdocs文件夹下。当url以/结尾，或者url是个目录，则默认在path中加上index.thml，表示访问主页。

5>如果文件路径合法，对于无参数的get请求，直接输出服务器文件到浏览器，即用http格式写到套接字上，跳到(10)。其他情况(带参数get，post方法，url为科执行文件)，则调用execute_cgi函数执行cgi脚本。

6>读取整个http请求并丢弃，如果是post则找出content-length，把http状态码200写到套接字里面。

7>建立两个管道，cgi_input和cgi_output,并fork一个子进程。

8>在子进程中，把stdout重定向到cgi_output的写入端，把stdin重定向到cgi_input的读取端，关闭cgi_input的写入端和cgi_output的读取端，是指request_method的环境变量，get的话设置query_string的环境变量，post的话设置content-length的环境变量，这些环境变量都是为了给cgi脚本调用，接着用execl运行cgi程序。

9>在父进程中，关闭cgi_input的读取端和cgi_output的写入端，如果post的话，把post数据写入到cgo_input，已被重定向到stdin读取cgi_output的管道输出到客户端，等待子进程结束。

10>关闭与浏览器的链接，完成一次http请求与回应，因为http是无连接的。

/* 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);
//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的体现服务器处理请求的流程
void bad_request(int);
//返回给客户端这是个错误请求，HTTP状态码是400 BAD REQUEST
void cat(int, FILE *);
//读取服务器上某个文件写到socket套接字
void cannot_execute(int);
//主要执行在处理cgi程序的处理，也是个主要函数
void error_die(const char *);
//把错误信息写到perror并退出
void execute_cgi(int, const char *, const char *, const char *);
//运行cgi程序的处理，也是哥主函数
int get_line(int, char *, int);
//读取套接字的一行，把回车换行等情况都统一为换行符结束
void headers(int, const char *);
//把HTTP相应头写到套接字
void not_found(int);
//主要处理找不到请求的文件时的情况
void serve_file(int, const char *);
//调用cat把服务器文件返回给浏览器
int startup(u_short *);
//初始化httpd服务，包括建立套接字，绑定端口，进行监听等
void unimplemented(int);
//返回给浏览器表示接收到的http请求所用的method不被支持

/**********************************************************************/
/* 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;
int cgi = 0;      /* becomes true if server decides this is a CGI
* program */
char *query_string = NULL;

numchars = get_line(client, buf, sizeof(buf));
//读取 client端发送的数据并且 返回的参数是 numchars
i = 0;
j = 0;
while (!ISspace(buf[j]) && (i < sizeof(method) - 1))
{
method[i] = buf[j];
i++;
j++;
}
//得到传递的参数是post 还是get方法 还是其他
method[i] = '\0';

if (strcasecmp(method, "GET") && strcasecmp(method, "POST"))
{
//回给浏览器表明收到的 HTTP 请求所用的 method 不被支持
unimplemented(client);
return;
}

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

i = 0;
//http请求行格式是 method urI http-version
while (ISspace(buf[j]) && (j < sizeof(buf)))
j++;
while (!ISspace(buf[j]) && (i < sizeof(url) - 1) && (j < sizeof(buf)))
{
url[i] = buf[j]; //包含请求行中的URI
i++;
j++;
}
url[i] = '\0';
///获取发送数据中的URI
if (strcasecmp(method, "GET") == 0)
{
//get方法 是将参数传递在URI中的？后面如果元素多用&进行链接
query_string = url;
while ((*query_string != '?') && (*query_string != '\0'))
query_string++;
// get 请求？ 后面为参数
if (*query_string == '?')
{
cgi = 1;
*query_string = '\0';
query_string++;
}
}
//格式url存储在path数组 并且html存储在 htdocs文件中
sprintf(path, "htdocs%s", url);
if (path[strlen(path) - 1] == '/')
strcat(path, "index.html");  //字符串进行衔接 + index.html
//stat函数 根据path路径 获取文件内容 存储在 st 结构体中  成功返回0 错误返回-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");
//文件的权限 属主 属组 其它 三种任一个拥有执行权
if ((st.st_mode & S_IXUSR) ||
(st.st_mode & S_IXGRP) ||
(st.st_mode & S_IXOTH)    )
cgi = 1;
//调用cat 把服务器文件返回给浏览器  post方法或者拥有执行权限
if (!cgi)
serve_file(client, path);
else
execute_cgi(client, path, method, query_string)
//运行cgi程序的处理，也是个主要函数
}

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 */
/**********************************************************************/
//读取服务器上的某个文件 写到socket套接字上
void cat(int client, FILE *resource)
{
char buf[1024];

fgets(buf, sizeof(buf), resource);
//检测流上的文件结束符  如果文件结束，则返回非0值，否则返回0，文件结束符只能被clearerr()清除。
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 */
/**********************************************************************/

//运行cgi程序  也是个主函数
void execute_cgi(int client, const char *path,
const char *method, const char *query_string)
{
//在父进程中，关闭cgi_input的读入端和cgi_output的写入端，如果post的话
//把post数据写入到cgi_input，已被重定向到stdin，读取cgi_output的管道
//输出到客户端，该管道输入是stdout，接着关闭所有管道，等待子进程结束。

char buf[1024];
int cgi_output[2];
int cgi_input[2];
//cgi_output[1] cgi_input[1] 为输入端
//cgi_input[0] cgi_output[0] 为输出端
pid_t pid;
int status;
int i;
char c;
int numchars = 1;
int content_length = -1;

buf[0] = 'A';
buf[1] = '\0';
//读入请求头
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';
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);

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stdout重定向到cgi_output的写入端
dup2(cgi_output[1], 1);
//把stdin重定向到cgi_input的读入端
dup2(cgi_input[0], 0);
//关闭cgi_output的读入端 和 cgi_input的 写入端
close(cgi_output[0]);
close(cgi_input[1]);
//设置request_method的环境变量
sprintf(meth_env, "REQUEST_METHOD=%s", method);
putenv(meth_env);
if (strcasecmp(method, "GET") == 0)
{
//设置query_string的环境变量
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);
putenv(length_env);
}
//用execl运行cgi程序
execl(path, path, NULL);
exit(0);
}
else        /* parent */
{
close(cgi_output[1]);
close(cgi_input[0]);
//关闭cgi_output的 写入端 和 cgi_input的读取端
if (strcasecmp(method, "POST") == 0)
//接受post的数据
for (i = 0; i < content_length; i++)
{
recv(client, &c, 1, 0);
write(cgi_input[1], &c, 1);
//讲post数据写入cgi_input，并且重定向到stdin中
}
//读取cgi_output的管道输出到客户端，该管道输入时stdout
while (read(cgi_output[0], &c, 1) > 0)
send(client, &c, 1, 0);
//关闭管道
close(cgi_output[0]);
close(cgi_input[1]);
//等待子进程
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)
{
int i = 0;
char c = '\0';
int n;

while ((i < size - 1) && (c != '\n'))
{
//每次接受一个字符
n = recv(sock, &c, 1, 0);
/* DEBUG printf("%02X\n", c); */
if (n > 0)
{
if (c == '\r')
{
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 */
/**********************************************************************/
//http 响应体
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");//响应的状态行
send(client, buf, strlen(buf), 0);
strcpy(buf, SERVER_STRING);
send(client, buf, strlen(buf), 0);
sprintf(buf, "Content-Type: text/html\r\n"); //响应头
send(client, buf, strlen(buf), 0);
strcpy(buf, "\r\n");        //响应正文段
send(client, buf, strlen(buf), 0);
}

/**********************************************************************/
/* Give a client a 404 not found status message. */
/**********************************************************************/
void not_found(int client)
{
//客户端发送的请求无法实现
char buf[1024];
//响应行
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);
//响应头
sprintf(buf, "Content-Type: text/html\r\n");
send(client, buf, strlen(buf), 0);
sprintf(buf, "\r\n");
//响应头和响应正文段之间有一个空行 表示响应行结束
send(client, buf, strlen(buf), 0);
//响应正文段 text/html
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);
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 allo        //响应正文段cate 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;
//建立套接字
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);
//绑定端口和ip
if (bind(httpd, (struct sockaddr *)&name, sizeof(name)) < 0)
error_die("bind");
if (*port == 0)  /* if dynamically allocating a port */
{
int namelen = sizeof(name);
if (getsockname(httpd, (struct sockaddr *)&name, &namelen) == -1)
error_die("getsockname");
*port = ntohs(name.sin_port);
}
//监听
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)
{
//发回响应信息  http的请求方法不被接受
char buf[1024];
//返回501 错误 未实现 (Not implemented)是指Web 服务器不理解或不支持发送给它的 HTTP 数据流中找到的 HTTP 方法
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");//响应头
send(client, buf, strlen(buf), 0);
sprintf(buf, "\r\n");
send(client, buf, strlen(buf), 0); //响应正文段
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;

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);
//建立链接
if (client_sock == -1)
error_die("accept");
/* accept_request(client_sock); */
//多线程进行控制
if (pthread_create(&newthread , NULL, accept_request, client_sock) != 0)
perror("pthread_create");
}

close(server_sock);

return(0);
}