tinyhttpd源码阅读

文章目录

1. 1. 运行项目
2. 2. 函数功能分析
3. 3. 函数关系图
4. 4. 注释版代码
5. 5. 参考

tinythhpd是一个超精简的web服务器，作者是1999年写的，到现在仍然能正常运行。
这个web服务器涉及到进程、线程、管道、socket等内容，源码只有五六百行，非常适合初学者阅读。

运行项目

我直接运行make httpd的时候报错说找不到-lsocket，从网上搜到说，这个库会自动链接上，并且也不叫这个名字了。
于是删掉-lsocket，但是又提示未定义的引用pthread_create，原来-lpthread的参数要放到最后边才行。
然后最终运行以下命令，就生成httpd了。

gcc -o httpd httpd.c -lpthread

因为我本机的per在/usr/bin目录下，所以改一下perl脚本中的第一行。
然后执行：

./httpd &

然后在浏览器地址栏输入下面地址测试web服务器。

127.0.0.1:<端口号>

函数功能分析

void accept_request(int);//每次创建一个线程，执行这个函数，用来处理一次http请求。
void bad_request(int);//当客户端发来的请求格式错误时(比如http协议的某些字段印错了),会向客户端发送400信息。
void cat(int, FILE *);//把某个文件的内容全部写入到与客户端的那个连接中。
void cannot_execute(int)//;当服务器身程序执行错误时(比如服务器自己在建立管道，或者fork进程时发生错误)，会调用此函数，会向客户端发送500的信息。
void error_die(const char *);//打印错误信息的函数
void execute_cgi(int, const char *, const char *, const char *);//如果是post请求，这个函数用来执行cgi脚本。
int get_line(int, char *, int);//从连接中读出一行数据。
void headers(int, const char *);//将http的开头的字段写入连接。
void not_found(int);//如果客户端请求的地址不存在，调用此函数，并给客户端返回404.
void serve_file(int, const char *);//负责给返回客户端所请求的文件，通过调用headers(),cat(),not_found,gen_line()几个函数来实现。
int startup(u_short *);//负责程序刚开始建立socket、绑定ip地址、监听连接等工作。
void unimplemented(int);//如果客户端发过来的不死get或post请求，会调用此函数。

程序阅读顺序：可以先大概看看这些函数的功能，再从主函数顺着看一下主体，主函数中先调用startup创建socket连接。
然后监听到连接请求之后再创建新线程执行accept_request来处理请求。

函数关系图

注释版代码

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

 //从连接中读出一行数据，numchars存放所读到的数据长度。
 numchars = get_line(client, buf, sizeof(buf));
 i = 0; j = 0;

 //将buf中的http“请求方式”字段复制到method中，遇到空格停止。
 while (!ISspace(buf[j]) && (i < sizeof(method) - 1))
 {
  method[i] = buf[j];
  i++; j++;
 }
 method[i] = '\0';

 //如果不是get或post这两种，就会调用unimplement函数通知客户端。
 if (strcasecmp(method, "GET") && strcasecmp(method, "POST"))
 {
  unimplemented(client);
  return;
 }

 //如果请求方式是post，就把cgi设置为1，一会再调用cgi脚本
 if (strcasecmp(method, "POST") == 0)
  cgi = 1;

 i = 0;
 //循环吸收空格。
 while (ISspace(buf[j]) && (j < sizeof(buf)))
  j++;
 //再用类似上面获取method的方式从buf中获取url。
 while (!ISspace(buf[j]) && (i < sizeof(url) - 1) && (j < sizeof(buf)))
 {
  url[i] = buf[j];
  i++; j++;
 }
 url[i] = '\0';

 //这个if语句用来把url中存储的地址的格式处理一下，如果中间有问号，
 //就设置cgi为1，随后会调用cgi脚本来处理这个请求(所以get请求也会调用cgi)
 //如果请求方式是get
 if (strcasecmp(method, "GET") == 0)
 {
  query_string = url;
  while ((*query_string != '?') && (*query_string != '\0'))
   query_string++;
  //如果请求的网址中有问号，那就从这里截断(因为本web服务器除了返回页面只有用cgi脚本来处理请求)
  if (*query_string == '?')
  {
   cgi = 1;
   *query_string = '\0';
   query_string++;
  }
 }

 sprintf(path, "htdocs%s", url);
 //如果网址最后一位是"/",那就在后面加上index.html
 if (path[strlen(path) - 1] == '/')
  strcat(path, "index.html");
 //获取那个文件的信息，存放在st中
 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
 {
  //判断这个文件是不是一个目录，如果是目录在后面加上"/index.html"。
  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;
  //如果是一般的get请求，那就调用server_file函数给返回那个文件的内容，
  //否则就执行调用execute_cgi执行cgi脚本
  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\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)
  //如果是get请求，那就把请求头中剩余的内容都读出来(相当于丢弃)
  while ((numchars > 0) && strcmp("\n", buf))  /* read & discard headers */
   numchars = get_line(client, buf, sizeof(buf));
 else//如果是post请求，那么读出数据长度来
 {
  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);

 //给执行cgi脚本的进程创建输入输出的管道。
 if (pipe(cgi_output) < 0) {
  cannot_execute(client);
  return;
 }
 if (pipe(cgi_input) < 0) {
  cannot_execute(client);
  return;
 }

 //fork出子进程来执行cgi脚本
 if ( (pid = fork()) < 0 ) {
  cannot_execute(client);
  return;
 }
 //如果是子进程
 if (pid == 0)  /* child: CGI script */
 {
  char meth_env[255];
  char query_env[255];
  char length_env[255];

  //重定向子进程的标准输入输出
  dup2(cgi_output[1], 1);
  dup2(cgi_input[0], 0);
  close(cgi_output[0]);
  close(cgi_input[1]);
  sprintf(meth_env, "REQUEST_METHOD=%s", method);
  //设置环境变量
  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, path, NULL);
  exit(0);
 } else {    /* parent */
  close(cgi_output[1]);
  close(cgi_input[0]);
  //读出post请求所传过来的消息,然后写入到cgi脚本的"输入管道"中
  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]);
  //等待子进程结束
  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'))
 {
  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 */
/**********************************************************************/
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);
 else//向client所标识的连接写入http头,然后是用cat写入文件内容
 {
  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;

 //创建socket
 httpd = socket(PF_INET, SOCK_STREAM, 0);
 if (httpd == -1)
  error_die("socket");
 memset(&name, 0, sizeof(name));
 name.sin_family = AF_INET;
 //主机字节序转变为网络字节序(即大顶端和小顶端之间的相互转换)
 name.sin_port = htons(*port);
 name.sin_addr.s_addr = htonl(INADDR_ANY);
 //给socket绑定上地址和端口
 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);
 }
 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;

 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);
  if (client_sock == -1)
   error_die("accept");
 /* accept_request(client_sock); */
 //创建新的线程来处理请求
 if (pthread_create(&newthread , NULL, accept_request, client_sock) != 0)
   perror("pthread_create");
 }

 close(server_sock);

 return(0);
}

参考

• https://blog.csdn.net/plus1993/article/details/47748099
• https://www.cnblogs.com/leechanx/p/3322611.html
• htons 主机字节序 网络字节序
• sockaddr_in与sockaddr的区别