tinyhttpd-0.1.0源码解析

/* 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;

 numchars = get_line(client, buf, sizeof(buf));
 i = 0; j = 0;
 // 第一个空格前面的字符是http method
 while (!ISspace(buf[j]) && (i < sizeof(method) - 1))
 {
  method[i] = buf[j];
  i++; j++;
 }
 method[i] = '\0';
// 只支持get和post
 if (strcasecmp(method, "GET") && strcasecmp(method, "POST"))
 {
  unimplemented(client);
  return;
 }
 // post方法则执行cgi程序处理
 if (strcasecmp(method, "POST") == 0)
  cgi = 1;

 i = 0;
 // 跳过method后面的空格
 while (ISspace(buf[j]) && (j < sizeof(buf)))
  j++;
// 接着是url
 while (!ISspace(buf[j]) && (i < sizeof(url) - 1) && (j < sizeof(buf)))
 {
  url[i] = buf[j];
  i++; j++;
 }
 url[i] = '\0';
// 是get方法，则解析查询参数
 if (strcasecmp(method, "GET") == 0)
 {
  query_string = url;
  // 遍历url直接找到?字符或找到字符串末尾
  while ((*query_string != '?') && (*query_string != '\0'))
   query_string++;
  // 如果有查询参数则解析
  if (*query_string == '?')
  {
    // 有查询参数说明需要cgi处理，即不是简单的文件读取请求
   cgi = 1;
   // 把?替换为字符串结束符，即url变量里存的的字符串不包括查询参数
   *query_string = '\0';
   // 指向查询参数的第一个字符
   query_string++;
  }
 }
 // 文件路径htdocs下
 sprintf(path, "htdocs%s", url);
 // 最后一个字符是/说明是个目录，则取该目录下的index.html文件
 if (path[strlen(path) - 1] == '/')
  strcat(path, "index.html");
  // 找不到该文件返回404
 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
 {
   // 是个目录
  if ((st.st_mode & S_IFMT) == S_IFDIR)
   strcat(path, "/index.html");
  // 是可执行文件则说明是cgi程序
  if ((st.st_mode & S_IXUSR) ||
      (st.st_mode & S_IXGRP) ||
      (st.st_mode & S_IXOTH)    )
   cgi = 1;
  // 返回静态文件给客户端
  if (!cgi)
   serve_file(client, path);
  else
  // 执行cgi程序
   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)
  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);
 // 获取两个匿名管道
 if (pipe(cgi_output) < 0) {
  cannot_execute(client);
  return;
 }
 if (pipe(cgi_input) < 0) {
  cannot_execute(client);
  return;
 }
 // fork进程
 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];
  // 先断开文件描述符1和标准输出file结构的关联，然后使1指向cgi_ouput[1]指向的file结构
  dup2(cgi_output[1], 1);
  dup2(cgi_input[0], 0);
  // 关闭读端
  close(cgi_output[0]);
  // 关闭写端
  close(cgi_input[1]);
  // 输入参数给处理请求的cgi进程使用
  sprintf(meth_env, "REQUEST_METHOD=%s", method);
  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);
  }
  // 执行cgi进程
  execl(path, path, NULL);
  exit(0);
 } else {    /* parent */
  close(cgi_output[1]);
  close(cgi_input[0]);
  if (strcasecmp(method, "POST") == 0)
   for (i = 0; i < content_length; i++) {
    /*
      读数据然后写入写端cgi_input[1]，对端是子进程的cgi_input[0]，作为子进程的标准读入，
      即子进程可以读到这里写入的数据
    */
    recv(client, &c, 1, 0);
    write(cgi_input[1], &c, 1);
   }
   /*
     等待子进程写入，然后返回给客户端，cgi_output[1]是子进程的标准输出端，
     从cgi_output[1]写入的数据可以从cgi_output[0]读取
   */
  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]);
  // 等到子进程退出
  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) */
/**********************************************************************/
// 读取最多size字节到buf变量里
int get_line(int sock, char *buf, int size)
{
 int i = 0;
 char c = '\0';
 int n;
// 还没读够并且还没有读到换行符
 while ((i < size - 1) && (c != '\n'))
 {
  // 读一个字节
  n = recv(sock, &c, 1, 0);
  /* DEBUG printf("%02X\n", c); */
  // 读取成功
  if (n > 0)
  {
    // 处理\r\n \r的情况
   if (c == '\r')
   {
     // \r的时候预读一个字节，该字节不从tcp缓存中删除
    n = recv(sock, &c, 1, MSG_PEEK);
    /* DEBUG printf("%02X\n", c); */
    // 读取成功并且是\n则进行真正的读取操作，为了消耗掉\n这个字节
    if ((n > 0) && (c == '\n'))
     recv(sock, &c, 1, 0);
    else
    // 后面不是\n则也当做遇到了换行处理，即\r也是换行
     c = '\n';
   }
   buf[i] = c;
   i++;
  }
  else
    // 读取失败就直接当换行处理
   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 */
/**********************************************************************/
// 发送http头
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
 {
  headers(client, filename);
  // 读取一个文件输出到客户端
  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 */
/**********************************************************************/
// 传统的服务器启动流程
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);
  // 绑定一个地址到socket，没有的话ip是本机地址，端口随机
 if (bind(httpd, (struct sockaddr *)&name, sizeof(name)) < 0)
  error_die("bind");
 if (*port == 0)  /* if dynamically allocating a port */
 {
  int namelen = sizeof(name);
  // 获取socket绑定的地址信息
  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;
// 拿到一个监听的文件描述符
 server_sock = startup(&port);
 printf("httpd running on port %d\n", port);

 while (1)
 {
   // 等待连接到来
  client_sock = accept(server_sock,
                       (struct sockaddr *)&client_name,
                       &client_name_len);
  if (client_sock == -1)
   error_die("accept");
 /* accept_request(client_sock); */
 // 每一个连接用一个线程处理，主函数是accept_request
 if (pthread_create(&newthread , NULL, accept_request, client_sock) != 0)
   perror("pthread_create");
 }
// 服务器退出
 close(server_sock);

 return(0);
}