tinyhttpd.c

#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"
#define MAXDATASIZE 1
#define MAXBUFFSIZE 1024
#define CONTENT_LENGTH_POS 15
#define STDIN   0
#define STDOUT  1
#define STDERR  2

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 setup_server(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_sock) {
  char buf[MAXBUFFSIZE];
  int numchars;
  char method[255];
  char url[255];
  char path[512];
  size_t i, buff_ptr;
  struct stat st;
  int is_cgi = 0;
  char *query_string = NULL;

  // Step 1: 读 http 请求的第一行（request line），并把请求方法存进 method 中
  numchars = get_line(client_sock, buf, sizeof(buf));
  i = 0;
  buff_ptr = 0;
  while (!ISspace(buf[buff_ptr]) && (i < sizeof(method) - 1)) {
    method[i] = buf[buff_ptr];
    i++;
    buff_ptr++;
  }
  method[i] = '\0';

  i = 0;
  while (ISspace(buf[buff_ptr]) && (buff_ptr < sizeof(buf))) // 跳过所有的空白字符(空格)
    buff_ptr++;

  // Step 2: 把 URL 存到 url 数组中
  while (!ISspace(buf[buff_ptr]) && (i < sizeof(url) - 1) && (buff_ptr < sizeof(buf))) {
    url[i] = buf[buff_ptr];
    i++;
    buff_ptr++;
  }
  url[i] = '\0';
  
  // Step 3: 分析当前请求是否为 CGI 请求
  if (strcasecmp(method, "POST") == 0) { // POST 请求一定是 CGI
    is_cgi = 1;
  } else if (strcasecmp(method, "GET") == 0) { // GET 请求不一定是 CGI，如果带参数则是，不带则默认为请求 index.html
    query_string = url;

    while ((*query_string != '?') && (*query_string != '\0')) // 检查 url 中有无参数, 如 /color.cgi?color=red
      query_string++;

    if (*query_string == '?') { // 如果是 CGI 请求，则将 query_string 指向 ? 后的参数，如 color=red
      is_cgi = 1;
      *query_string = '\0';
      query_string++;
    }
  } else { // Neither POST nor GET
    unimplemented(client_sock);
    return;
  }

  sprintf(path, "htdocs%s", url);

  // "/" => "/index.html"
  if (path[strlen(path) - 1] == '/')
    strcat(path, "index.html");

  // Step 4: 查找 path 指向的文件
  if (stat(path, &st) == -1) { // 如果不存在，那把这次 http 的请求后续的内容(head 和 body)全部读完并忽略
    while ((numchars > 0) && strcmp("\n", buf)) /* read & discard headers */
      numchars = get_line(client_sock, buf, sizeof(buf));
    not_found(client_sock);
  }
  else {
    // 如果 path 是目录，则默认使用该目录下 index.html 文件
    if ((st.st_mode & S_IFMT) == S_IFDIR)
      strcat(path, "/index.html");

    // 如果 path 是可执行文件，设置 cgi 标识
    if ((st.st_mode & S_IXUSR) ||
        (st.st_mode & S_IXGRP) ||
        (st.st_mode & S_IXOTH))
      is_cgi = 1;

    if (!is_cgi) // 静态页面请求
      serve_file(client_sock, path);
    else // 动态页面请求
      execute_cgi(client_sock, path, method, query_string);
  }

  close(client_sock);
}

/**********************************************************************/
/* 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];
  do {
    fgets(buf, sizeof(buf), resource);
    send(client, buf, strlen(buf), 0);
  } while(!feof(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)
{
  //包含于<stdio.h>,基于当前的 errno 值，在标准错误上产生一条错误消息。参考《TLPI》P49
  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) /* GET */
    while ((numchars > 0) && strcmp("\n", buf)) // 读取并忽略 header，因为信息都在 url (query_string) 里
      numchars = get_line(client, buf, sizeof(buf));
  else { /* POST */
    // 找出 header 中的 Content-Length (size of the entity-body) 的值，其余都忽略。因为只有该值对确定客户端传来的请求参数有用
    numchars = get_line(client, buf, sizeof(buf));
    while ((numchars > 0) && strcmp("\n", buf)) {
      buf[CONTENT_LENGTH_POS] = '\0';
      if (strcasecmp(buf, "Content-Length:") == 0){
        content_length = atoi(&(buf[16]));
      }
      numchars = get_line(client, buf, sizeof(buf));
    }

    // 如果 http 请求的 header 没有 Content-Length，则报错返回
    if (content_length == -1) {
      bad_request(client);
      return;
    }
  }

  sprintf(buf, "HTTP/1.0 200 OK\r\n");
  send(client, buf, strlen(buf), 0);

  // 创建两个管道，用于父子进程间通信
  if (pipe(cgi_output) < 0) {
    cannot_execute(client);
    return;
  }
  if (pipe(cgi_input) < 0) {
    cannot_execute(client);
    return;
  }

  // 创建子进程
  if ((pid = fork()) < 0) {
    cannot_execute(client);
    return;
  }

  if (pid == 0) /* 子进程: CGI script */ {
    char meth_env[255];
    char query_env[255];
    char length_env[255];

    // 复制文件句柄，重定向进程的标准输入输出
    dup2(cgi_output[1], STDOUT); // 将子进程输入管道的读端口和 STDOUT 绑定（重定向）
    dup2(cgi_input[0], STDIN); // 将子进程输出管道的写端口和 STDIN 绑定
    close(cgi_output[0]); // 关闭 cgi_ouput 管道的读端
    close(cgi_input[1]); // 关闭 cgi_input 管道的写端

    sprintf(meth_env, "REQUEST_METHOD=%s", method);
    putenv(meth_env);

    // 根据 http 请求的不同方法，构造并存储不同的环境变量
    if (strcasecmp(method, "GET") == 0) {
      /* 设置 query_string 的环境变量 */
      // 如果服务器与CGI程序信息的传递方式是GET，这个环境变量的值即使所传递的信息。这个信息经跟在CGI程序名的后面，两者中间用一个问号'?'分隔。
      sprintf(query_env, "QUERY_STRING=%s", query_string);
      putenv(query_env);
    } else { /* POST */
      /* 设置 content_length 的环境变量 */
      // 如果服务器与 CGI 程序信息的传递方式是POST，这个环境变量即使从标准输入 STDIN 中可以读到的有效数据的字节数。这个环境变量在读取所输入的数据时必须使用。
      sprintf(length_env, "CONTENT_LENGTH=%d", content_length);
      putenv(length_env);
    }

    // exec 函数簇，执行 CGI 脚本，获取 cgi 的标准输出作为相应内容发送给客户端
    // 将子进程替换成另一个进程并执行 cgi 脚本
    execl(path, path, NULL);

    // 子进程退出
    exit(0);
  } else { /* parent */
    // 父进程则关闭了 cgi_output 管道的写端和 cgi_input 管道的读端
    close(cgi_output[1]);
    close(cgi_input[0]);

    // 如果是 POST 方法的话就继续读 body 的内容，并写到 cgi_input 管道里让子进程去读
    if (strcasecmp(method, "POST") == 0) {
      for (i = 0; i < content_length; i++) {
        recv(client, &c, MAXDATASIZE, 0);
        write(cgi_input[1], &c, 1);
      }
    }

    // 从 cgi_output 管道中读子进程的输出，并发送到客户端去
    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]);
    // 等待子进程的退出
    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) */
/**********************************************************************/
// 该函数不管行原来是以 \r 还是 \r\n 结束，均转化为以 \n 再加 \0 字符结束。
int get_line(int sock, char *buf, int size) {
  int num_bytes = 0;
  char c = '\0';
  int n;

  while ((num_bytes < size - 1) && (c != '\n'))
  {
    n = recv(sock, &c, MAXDATASIZE, 0); // int recv(int sockfd, void *buf, int len, unsigned int flags); 读一个字节的数据存放在 c 中, 包含于<sys/socket.h>
    if (n > 0) {
      if (c == '\r') {
        n = recv(sock, &c, MAXDATASIZE, MSG_PEEK); // Peek
        if ((n > 0) && (c == '\n')) {
          recv(sock, &c, MAXDATASIZE, 0); // "\r\n"
        }
        else
          c = '\n'; // "\r"
      }
      buf[num_bytes] = c; // "\n" or other common c
      num_bytes++;
    }
    else
      c = '\n';
    // printf("%c", c);
  }
  buf[num_bytes] = '\0';
  return (num_bytes);
}

/**********************************************************************/
/* 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[MAXBUFFSIZE];

  buf[0] = 'A'; // 确保 buf 里面有东西，能进入下面的 while 循环
  buf[1] = '\0';
  while ((numchars > 0) && strcmp("\n", buf)) // 读取并忽略掉这个 http 请求后面的所有内容
    numchars = get_line(client, buf, sizeof(buf));
  
  resource = fopen(filename, "r");
  if (resource == NULL)
    not_found(client);
  else {
    headers(client, filename); // 将请求文件的基本信息封装成 response 的头部 (header) 并返回
    cat(client, resource); // 把请求文件的内容读出来作为 response 的 body 发送到客户端
  }

  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 setup_server(u_short *port) {
  // 创建 socket
  int server_sock = 0;
  server_sock = socket(PF_INET, SOCK_STREAM, 0); // PF_INET 其实是与 AF_INET 同义
  if (server_sock == -1)
    error_die("socket");

  // 创建 sockaddr，指定了 IP 和 port
  struct sockaddr_in server_addr;
  memset(&server_addr, 0, sizeof(server_addr));
  server_addr.sin_family = AF_INET;
  server_addr.sin_port = htons(*port);             // htons()，ntohs() 和 htonl()包含于<arpa/inet.h>, 将 *port 转换成以网络字节序表示的16位整数
  server_addr.sin_addr.s_addr = htonl(INADDR_ANY); // INADDR_ANY是一个 IPV4 通配地址的常量，包含于<netinet/in.h>，大多实现都将其定义成了0.0.0.0

  // 将 socket 和 sockaddr 绑定
  if (bind(server_sock, (struct sockaddr *)&server_addr, sizeof(server_addr)) < 0) // 由于传进去的 sockaddr 结构中的 sin_port 指定为 0，系统会选择一个临时的端口号
    error_die("bind");

  // 如果调用 bind 后端口号仍然是0，则手动调用 getsockname() 获取端口号
  if (*port == 0) /* if dynamically allocating a port */ {
    int namelen = sizeof(server_addr);
    if (getsockname(server_sock, (struct sockaddr *)&server_addr, &namelen) == -1) //调用 getsockname() 获取系统给 httpd 这个 socket 随机分配的端口号
      error_die("getsockname");
    *port = ntohs(server_addr.sin_port);
  }

  // 进入监听状态，等待用户发起请求
  if (listen(server_sock, 5) < 0) // 最初的 BSD socket 实现中，backlog 的上限是5
    error_die("listen");
  printf("httpd running on http://localhost:%d\n", *port);

  return (server_sock);
}

/**********************************************************************/
/* 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;
  server_sock = setup_server(&port);

  int client_sock = -1;
  struct sockaddr_in client_name;
  int client_name_len = sizeof(client_name);
  pthread_t newthread;

  while (1) {
    client_sock = accept(server_sock,
                         (struct sockaddr *)&client_name,
                         &client_name_len);
    if (client_sock == -1)
      error_die("accept");
    if (pthread_create(&newthread, NULL, accept_request, client_sock) != 0)
      perror("pthread_create");
  }

  close(server_sock);

  return (0);
}