tinyhttpd-0.1.0源码分析

httpd-0.1.0源码分析

httpd-0.1.0介绍

TinyHTTPd是一个轻量级的http server。可以作为初级学习Linux网络编程或者C/C++入门小程序学习。此程序为开源项目。

前期准备

我个人理解的B/S架构是：
1.server先在相应的机器上运行起来，之后server程序检测端口是否有请求。
2.浏览器这时就可以通过网络访问已经运行起来的server。我们通过浏览器访问一个网站（URL可以经过一系列的解析过程变成IP地址），会发送http请求给http 服务器，如果请求的是一个静态的页面或图片，服务器会直接返回结果给浏览器。但如果要完成一个动态的请求，比如需要查询数据库这样的操作，服务器会运行一个单独的程序来执行，这个程序处理完成后会把结果转化为服务器(或者浏览器)可以识别的格式输出。

客户端

不管是C/S还是B/S要想实现功能，server必须先运行起来。

#include <stdio.h>
#include <sys/types.h>
#include <sys/socket.h>
#include <netinet/in.h>
#include <arpa/inet.h>
#include <unistd.h>

int main(int argc, char *argv[])
{
 int sockfd;
 int len;
 struct sockaddr_in address;
 int result;
 char ch = 'A';

 sockfd = socket(AF_INET, SOCK_STREAM, 0);
 /*AF_INET（又称 PF_INET）是 IPv4 网络协议的套接字类型，
 AF_INET6 则是 IPv6 的；而 AF_UNIX 则是 Unix 系统本地通信。        
 SOCK_STREAM提供面向连接的稳定数据传输，即TCP协议。
 SOCK_STREAM应用在C语言socket编程中，
 在进行网络连接前，需要用socket函数向系统申请一个通信端口。
 SOCK_STREAM 是数据流,一般是tcp/ip协议的编程,
 SOCK_DGRAM分是数据包,是udp协议网络编程。
 */
 address.sin_family = AF_INET;
 address.sin_addr.s_addr = inet_addr("127.0.0.1");
 address.sin_port = htons(9734);

 /*
 struct sockaddr_in

{
short sin_family;   //Address family一般来说AF_INET（地址族）PF_INET（协议族） 
unsigned short sin_port;  //Port number(必须要采用网络数据格式,普通数字可以用htons()函数转换成网络数据格式的数字)

struct in_addr sin_addr; // IP address in network byte order（Internet address）

unsigned char sin_zero[8]; //  Same size as struct sockaddr没有实际意义,只是为了　跟SOCKADDR结构在内存中对齐
};

 */
 len = sizeof(address);
 result = connect(sockfd, (struct sockaddr *)&address, len); //client

 if (result == -1)
 {
  perror("oops: client1");
  exit(1);
 }
 write(sockfd, &ch, 1);
 read(sockfd, &ch, 1);
 printf("char from server = %c\n", ch);
 close(sockfd);
 exit(0);
}

客户端程序非常简单，就是基本的流程，先创建socket，之后调用connect函数与server建立TCP连接。write和read是Linux提供的I/O函数。用来向socket输入输出数据。

服务器端

#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 */
/**********************************************************************/

/*
TCP连接建立成功后，服务器启动一个新的线程来处理
客户端的其他请求。
服务器启动一个新的线程来处理客户端的请求(accept_request)，
处理完成后，重新等待新的客户端请求。
*/

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));  //从线程中获取数据
 i = 0; j = 0;
 while (!ISspace(buf[j]) && (i < sizeof(method) - 1))
 {
  method[i] = buf[j];
  i++; j++;
 }
 method[i] = '\0';

 /*
 一个HTTP请求报文由
 请求行（requestline）、请求头部（header）、
 空行和请求数据4个部分组成，
 请求行由请求方法字段(get或post)、URL字段
 和HTTP协议版本字段3个字段组成，它们用空格分隔。
 例如，GET /index.html HTTP/1.1。
 上面这段代码就是解析请求行，
 把方法字段保存在method变量中。
 */

 if (strcasecmp(method, "GET") && strcasecmp(method, "POST")) //忽略大小写比较字符串
 {
  unimplemented(client); //将一个网页发给客户端
  return;
 }

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

 i = 0;
 while (ISspace(buf[j]) && (j < sizeof(buf))) //判断字符是否为空格字符
  j++;
 while (!ISspace(buf[j]) && (i < sizeof(url) - 1) && (j < sizeof(buf)))
 { //不是空格 i没有到url末尾时
  url[i] = buf[j];
  i++; j++;
 }
 url[i] = '\0';

 /*
 如果是get方法，请求参数和对应的值附加在URL后面,
 利用一个问号（"?"）代表URL的结尾与请求参数的开始，
 传递参数长度受限制。例如，/index.jsp?10023
 其中10023就是要传递的参数。
 这段代码把参数保存在query_string中。
 */

 if (strcasecmp(method, "GET") == 0)
 {
  query_string = url;
  while ((*query_string != '?') && (*query_string != '\0'))
   query_string++;
  if (*query_string == '?')
  {
   cgi = 1;
   *query_string = '\0';
   query_string++;
  }
 }

 /*
 这段代码保存有效的url地址并加上请求地址的主页索引。
 默认的根目录是在htdocs下。
 */
 sprintf(path, "htdocs%s", url);
 if (path[strlen(path) - 1] == '/')
  strcat(path, "index.html");
 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");
  if ((st.st_mode & S_IXUSR) ||
      (st.st_mode & S_IXGRP) ||
      (st.st_mode & S_IXOTH)    )
   cgi = 1;
  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)
  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];

  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);
  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]);
  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]);
  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)  // 1024
{
 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
 {
  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 */
/**********************************************************************/
/*程序创建一个服务器socket对象，然后绑写(bind)，
并监听指定的端口(listen)，这些动作都是在startup函数实现的。
这些也是Linux建立TCP连接的基本准备。
有一个细节稍微注意一下，如果传来的端口是0,
程序会随机分配一个监听的端口。
并通过指向port变量的地址返回该值。
*/

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)); //内存清空
 name.sin_family = AF_INET;  //IPv4
 name.sin_port = htons(*port);   //端口号
 name.sin_addr.s_addr = htonl(INADDR_ANY); //INADDR_ANY就是指定地址为0.0.0.0的地址，这个地址事实上表示不确定地址，或“所有地址”、“任意地址”。 一般来说，在各个系统中均定义成为0值。
 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) // 获得套接字名称
   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); //初始化
 printf("httpd running on port %d\n", port);

 while (1)
 {
  /*套接字收到客户端连接请求*/  
  client_sock = accept(server_sock,
                       (struct sockaddr *)&client_name,
                       &client_name_len);//新的socket来完成数据传输的任务，
  if (client_sock == -1)
   error_die("accept");

  /*派生新线程用accept_request 函数处理新请求*/  
  /* accept_request(client_sock); */
  if (pthread_create(&newthread , NULL, accept_request, client_sock) != 0) // 线程开启
   perror("pthread_create");
 }

 close(server_sock);

 return(0);
}

服务器程序也是先创建socket，之后调用startup函数初始化端口，然后服务器会在accpet函数阻塞。
当客户端的TCP连接请求到达时，accpet函数返回一个新的专用于数据传输的socket。此后服务器读写数据都是通过新的socket。
之后服务器程序开启一个线程负责这个TCP连接的数据传输。
accept_request函数会回应客户端的http请求，cat函数将读到的内容作为http响应报文的数据部分发送回客户端。