剖析tinyhttpd服务器

tinyhttpd是一个小型的http服务器，虽然小但是功能也多，剖析tinyhttpd有助于理解http服务器的工作流程，加深对web服务器的认识。
一、原理图

二、源码剖析
下面是tinyhttpd的源码，自己对它进行了剖析，并对绝大多数内容加上了注释。

#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))                   //ISspace宏用来判断是否为空格

#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)                    //处理客户端的请求
{
char buf[1024];
int numchars;
char method[255];                                 //保存http请求行中使用的方法
char url[255];                                    //保存请求资源的路径
char path[512];                             
size_t i, j;
struct stat st;                                   //用来记录客户端所请求的资源的信息
int cgi = 0;                                      //用来标记是不是需要运行cgi程序
char *query_string = NULL;                        //记录参数的地址

numchars = get_line(client, buf, sizeof(buf));     //获取请求行(method url http版本号)
i = 0; j = 0;
while (!ISspace(buf[j]) && (i < sizeof(method) - 1))      //获取请求方法
{
  method[i] = buf[j];
  i++; j++;
}
method[i] = '\0';

if (strcasecmp(method, "GET") && strcasecmp(method, "POST"))   //判断是不是GET或POST方法(只实现了GET和POST方法)
{
  unimplemented(client);                              //客户端方法错误
  return;
}

if (strcasecmp(method, "POST") == 0)              //如果是POST方法，使用CGI程序处理
  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)))  //保存URL
{
  url[i] = buf[j];
  i++; j++;
}
url[i] = '\0';

if (strcasecmp(method, "GET") == 0)              //判断是不是GET方法（GET方法可以带参也可以不带参，路径和参数之间以?分隔）
{
  query_string = url;
  while ((*query_string != '?') && (*query_string != '\0'))     //寻找"?"字符
   query_string++;
  if (*query_string == '?')                       //如果有“？”则表示GET是带参的
  {
   cgi = 1;                                       //带参数的GET方法使用CGI进行处理
   *query_string = '\0';                
   query_string++;                                //用来记录参数的起始位置
  }
}

sprintf(path, "htdocs%s", url);                  //将请求资源的路径保存到path中
if (path[strlen(path) - 1] == '/')               //如果请求的路径最后是"/"，则表示请求的是个目录，默认她请求的是该目录下的首页
  strcat(path, "index.html");
if (stat(path, &st) == -1) {                     //获取请求的资源的信息
  while ((numchars > 0) && strcmp("\n", buf))           //如果失败则返回404错误
   numchars = get_line(client, buf, sizeof(buf));
  not_found(client);                              //请求的资源没找到
}
else
{
  if ((st.st_mode & S_IFMT) == S_IFDIR)          //如果请求的资源的路径是一个目录(path的最后不是"/"，文件信息中显示的是目录)
   strcat(path, "/index.html");                  //默认请求的是该目录下的首页
  if ((st.st_mode & S_IXUSR) ||
      (st.st_mode & S_IXGRP) ||
      (st.st_mode & S_IXOTH)    )                //如果该文件具有执行权限，则使用cgi程序处理
   cgi = 1;
  if (!cgi)                                      //判断cgi标志是否被设置
   serve_file(client, path);                     //如果没有设置cgi标记，则直接返回客户端请求的文件
  else
   execute_cgi(client, path, method, query_string);   //设置了CGI标记，则将运行结果返回回去
}

close(client);
}

/**********************************************************************/
/* Inform the client that a request it has made has a problem.
* Parameters: client socket */
/**********************************************************************/
void bad_request(int client)                 //返回资源错误
{
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)    //读取文件内容并发送到客户端浏览器(可以改成sendfile)
{
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)       //服务器错误
{
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)      //执行cgi程序，用子进程取执行cgi程序
{
char buf[1024];
int cgi_output[2];                                            //记录两个文件描述符
int cgi_input[2];                                             //记录两个文件描述符
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)                //首先判断是不是GET方法，如果是GET方法
  while ((numchars > 0) && strcmp("\n", buf))       //清空消息报头
   numchars = get_line(client, buf, sizeof(buf));
else                                                //如果是POST方法
{
  numchars = get_line(client, buf, sizeof(buf));     
  while ((numchars > 0) && strcmp("\n", buf))        //获取Content-Length参数，并清空消息报头
  {
   buf[15] = '\0';
   if (strcasecmp(buf, "Content-Length:") == 0)      //在消息报头中获取消息正文的大小
    content_length = atoi(&(buf[16]));
   numchars = get_line(client, buf, sizeof(buf));
  }
  if (content_length == -1) {                        //如果Content-Length是-1,则表示POST方法没有上传参数
   bad_request(client);                              //返回请求资源的错误
   return;
  }
}

sprintf(buf, "HTTP/1.0 200 OK\r\n");   
send(client, buf, strlen(buf), 0);                   //首先向客户端发送响应行

if (pipe(cgi_output) < 0) {                          //创建一个管道，用于父子进程之间通信
  cannot_execute(client);                             //失败的话返回服务器错误
  return;
}
if (pipe(cgi_input) < 0) {                           //创建一个管道用于父子进程之间通信
  cannot_execute(client);
  return;
}

if ( (pid = fork()) < 0 ) {                          //创建一个子进程，用于执行cgi程序
  cannot_execute(client);                             //失败的话返回服务器错误
  return;
}
if (pid == 0)                                        //子进程执行CGI程序
{
  char meth_env[255];
  char query_env[255];
  char length_env[255];

  dup2(cgi_output[1], 1);                             //重定向标准输入
  dup2(cgi_input[0], 0);                              //重定向标准输出
  close(cgi_output[0]);
  close(cgi_input[1]);
  sprintf(meth_env, "REQUEST_METHOD=%s", method);      //将method设置为环境变量
  putenv(meth_env);
  if (strcasecmp(method, "GET") == 0) {  
   sprintf(query_env, "QUERY_STRING=%s", query_string);        //如果是GET方法，则把参数的地址设置为环境变量
   putenv(query_env);
  }
  else {   /* POST */
   sprintf(length_env, "CONTENT_LENGTH=%d", content_length);     //如果是POST方法，则把Content-length设置为环境变量
   putenv(length_env);
  }
  execl(path, path, NULL);                                       //执行cgi程序
  exit(0);
} else {                                                      //父进程
  close(cgi_output[1]);
  close(cgi_input[0]);
  if (strcasecmp(method, "POST") == 0)                         //如果是POST方法，则父进程需要把参数通过管道传递给子进程
   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)                        //父进程从读取子进程返回的结果，并发送到客户端浏览器上
   send(client, &c, 1, 0);

  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)            //获取http报文中的一行信息
{
int i = 0;
char c = '\0';
int n;

while ((i < size - 1) && (c != '\n'))   //因为在linux下文件结尾是\r\n，windows下是\n,为了保证兼容性，需要对这两种情况进行处理
{
  n = recv(sock, &c, 1, 0);
  /* DEBUG printf("%02X\n", c); */
  if (n > 0)
  {
   if (c == '\r')                           //如果读到\r,需要判断下一个字符是不是\n
   {
    n = recv(sock, &c, 1, MSG_PEEK);        //从sock中预读一个字符
    /* DEBUG printf("%02X\n", c); */
    if ((n > 0) && (c == '\n'))             //判断是不是\n
     recv(sock, &c, 1, 0);
    else
     c = '\n';
   }
   buf[i] = c;
   i++;
  }
  else
   c = '\n';
}
buf[i] = '\0';
return(i);                                //返回这一行读到的字符数量
}

/**********************************************************************/
/* 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);                 //发送响应行
strcpy(buf, SERVER_STRING);
send(client, buf, strlen(buf), 0);                 //发送响应报头
sprintf(buf, "Content-Type: text/html\r\n");
send(client, buf, strlen(buf), 0);
strcpy(buf, "\r\n");                               //发送空行
send(client, buf, strlen(buf), 0);
}

/**********************************************************************/
/* Give a client a 404 not found status message. */
/**********************************************************************/
void not_found(int client)                          //发送404错误
{
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)       //向客户端发送文件
{
FILE *resource = NULL;
int numchars = 1;
char buf[1024];

buf[0] = 'A'; buf[1] = '\0';
while ((numchars > 0) && strcmp("\n", buf))            //清空http的报头信息
  numchars = get_line(client, buf, sizeof(buf));

resource = fopen(filename, "r");                       //打开请求的文件
if (resource == NULL)
  not_found(client);                                    //打开失败就返回错误信息
else
{
  headers(client, filename);                            //先发送响应行
  cat(client, resource);                                //发送文件
}
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;                                             //http变量用来保存套接字
struct sockaddr_in name;

httpd = socket(PF_INET, SOCK_STREAM, 0);                   //创建一个网络套接字，使用TCP/IP协议
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)     //将地址和套接字绑定
  error_die("bind");
if (*port == 0)                                             //如果给定的port为0，则从系统获取端口
{
  int namelen = sizeof(name);
  if (getsockname(httpd, (struct sockaddr *)&name, &namelen) == -1)  //获取该套接字的信息
   error_die("getsockname");
  *port = ntohs(name.sin_port);                                      //得到端口               
}
if (listen(httpd, 5) < 0)                                           //对这个端口进行监听，backlog设置为5
  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)                                        //客户端端请求方法错误
{
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;                               //服务端套接字
u_short port = 0;                                   //服务端端口
int client_sock = -1;                               //客户端套接字
struct sockaddr_in client_name;                     //定义一个ip4类型的地变量，client_name用来接收用户的地址
int client_name_len = sizeof(client_name);          //ip4地址变量的长度
pthread_t newthread;                                //记录线程ID的变量

server_sock = startup(&port);                       //创建一个服务器的套接字
printf("httpd running on port %d\n", port);        

while (1)
{
  client_sock = accept(server_sock,
                       (struct sockaddr *)&client_name,
                       &client_name_len);                //接收客户端的请求
  if (client_sock == -1)
   error_die("accept");
/* accept_request(client_sock); */
if (pthread_create(&newthread , NULL, accept_request, client_sock) != 0)   //创建一个线程取处理这个请求
   perror("pthread_create");
}

close(server_sock);                                   //关闭服务端套接字

return(0);
}