Tinyhttpd源码分析!
Github地址:HERE
最近两天看了小项目,在博客中记录下学习笔记!!!
tinyhttpd是一个简易的HTTP服务器,可以处理POST/GET请求,使用CGI技术实现简单的网页表单提交。代码可以在Linux上运行,涉及POSIX 线程\进程\管道\字符串处理等知识点。是学习Linux网络编程的基础项目。
代码经过简单修改可以直接在Linux系统上make,需要注意的点:
1、使用Linux系统需安装perl和perl-CGI,CGI程序也可以使用Python脚本、SHELL脚本、C和C++;
2、htdocs文件夹中的*.html文件权限设置成644/444等,总之不可执行,*.cgi文件设置成755,可执行;
每个函数的作用:
accept_request: 处理从套接字上监听到的一个 HTTP 请求,进行HTTP请求头处理,对method与url等进行解析。
bad_request: 返回给客户端这是个错误请求,HTTP 状态吗 400 BAD REQUEST。
cat: 读取服务器上某个文件写到 socket 套接字。
cannot_execute: 主要处理发生在执行 cgi 程序时出现的错误。
error_die: 把错误信息写到 perror 并退出。
execute_cgi: 运行 cgi 程序的处理,也是个主要函数。
get_line: 读取套接字的一行,把回车换行等情况都统一为换行符结束。
headers: 把 HTTP 响应的头部写到套接字。
not_found: 主要处理找不到请求的文件时的情况。
sever_file: 调用 cat 把服务器文件返回给浏览器,内部调用headers()函数和cat()函数。
startup: 初始化 httpd 服务,包括建立套接字,绑定端口,进行监听等。
unimplemented: 返回给浏览器表明收到的 HTTP 请求所用的 method 不被支持。
建议源码阅读顺序: main(); startup(); accept_request(); execute_cgi()。
(1)服务器启动,在指定端口或随机选取端口绑定 httpd 服务。
(2)收到一个 HTTP 请求时(其实就是 listen 的端口 accpet 的时候),派生一个线程运行 accept_request 函数。
(3)取出 HTTP 请求中的 method (GET 或 POST) 和 url,。对于 GET 方法,如果有携带参数,则 query_string 指针指向 url 中 ? 后面的 GET 参数。
(4)cpoy url 到 path 数组,表示浏览器请求的服务器文件路径,在 tinyhttpd 中服务器文件是在 htdocs 文件夹下。当 url 以 / 结尾,或 url 是个目录,则默认在 path 中加上 index.html,表示访问主页。
(5)如果文件路径合法,对于无参数的 GET 请求,直接输出服务器文件到浏览器,即用 HTTP 响应头格式写到套接字上,跳到serve_file()函数。其他情况(带参数 GET,POST 方式,url 为可执行文件),则调用 excute_cgi 函数执行 cgi 脚本。
(6)读取整个 HTTP 请求并丢弃,如果是 POST 则找出 Content-Length. 把 HTTP 200 ;状态码写到套接字。
(7)建立两个管道,cgi_input 和 cgi_output, 并 fork 一个进程。
(8)在子进程中,把 STDOUT 重定向到 cgi_output 的写入端,把 STDIN 重定向到 cgi_input 的读取端,关闭 cgi_input 的写入端 和 cgi_output 的读取端,设置 request_method 的环境变量,GET 的话设置 query_string 的环境变量,POST 的话设置 content_length 的环境变量,这些环境变量都是为了给 cgi 脚本调用,接着用 execl 运行 cgi 程序。
(9)在父进程中,关闭 cgi_input 的读取端 和 cgi_output 的写入端,如果 POST 的话,把 POST 数据写入 cgi_input,已被重定向到 STDIN,读取 cgi_output 的管道输出到客户端,该管道输入是 STDOUT。
管道图解:(画的是真的丑
Linux下make 运行:
注释版代码如下:
/* 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>
#include <stdint.h>
#define ISspace(x) isspace((int)(x))
#define SERVER_STRING "Server: jdbhttpd/0.1.0\r\n"
// 标准输入流 标准输出流 标准错误流
#define STDIN 0
#define STDOUT 1
#define STDERR 2
// Http请求,后续主要是处理这个头
//
// GET / HTTP/1.1
// Host: 192.168.1.103:4000
// Connection: keep-alive
// Upgrade-Insecure-Requests: 1
// User-Agent:Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/49.0.2623.22 Safari/537.36 SE 2.X MetaSr 1.0
// Accept: text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*; q = 0.8
// Accept - Encoding: gzip, deflate, sdch
// Accept - Language : zh - CN, zh; q = 0.8
// Cookie: __guid = 179317988.1576506943281708800.1510107225903.8862; monitor_count = 5
//
// POST / color1.cgi HTTP / 1.1
// Host: 192.168.1.103:4000
// Connection : keep - alive
// Content - Length : 10
// Cache - Control : max - age = 0
// Origin : http://192.168.1.103:4000
// Upgrade - Insecure - Requests : 1
// User - Agent : User-Agent:Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/49.0.2623.22 Safari/537.36 SE 2.X MetaSr 1.0
// Content - Type : application / x - www - form - urlencoded
// Accept : text / html, application / xhtml + xml, application / xml; q = 0.9, image / webp, */*;q=0.8
// Referer: http://192.168.1.103:4000/index1.html
// Accept-Encoding: gzip, deflate
// Accept-Language: zh-CN,zh;q=0.8
// Cookie: __guid=179317988.1576506943281708800.1510107225903.8862; monitor_count=281
// Form Data
// color=gray
void accept_request(void *);
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(void *arg)
{
int client = (intptr_t)arg;
char buf[1024];
size_t numchars;
// 请求方法 POST/GET
char method[255];
// 请求的URL
char url[255];
// 服务器端文件路径
char path[512];
size_t i, j;
// Linux下存放文件各种属性的struct
struct stat st;
int cgi = 0; /* becomes true if server decides this is a CGI
* program */
//GET请求的请求参数
char *query_string = NULL;
//从客户端套接字获取一行数据
//GET / HTTP/1.1\n
numchars = get_line(client, buf, sizeof(buf));
i = 0; j = 0;
//遇到空格 获取method结束
while (!ISspace(buf[i]) && (i < sizeof(method) - 1))
{
method[i] = buf[i];
i++;
}
j=i;
method[i] = '\0';
// 服务器只能处理GET/POST请求
if (strcasecmp(method, "GET") && strcasecmp(method, "POST"))
{
unimplemented(client);
return;
}
// POST请求 通过CGI(通用网关接口)实现 动态处理
if (strcasecmp(method, "POST") == 0)
cgi = 1;
// 跳过空格
i = 0;
while (ISspace(buf[j]) && (j < numchars))
j++;
//得到 "/" 如果你的http的网址为http://192.168.0.23:47310/index.html
// 那么你得到的第一条http信息为GET /index.html HTTP/1.1,那么
// 解析得到的就是/index.html
while (!ISspace(buf[j]) && (i < sizeof(url) - 1) && (j < numchars))
{
url[i] = buf[j];
i++; j++;
}
url[i] = '\0';
//含有'?'的GET请求
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++;
}
}
//路径
sprintf(path, "htdocs%s", url);
//默认路径
if (path[strlen(path) - 1] == '/')
strcat(path, "index.html");
//获得文件的信息,若失败则清空套接字缓冲区,并调用not_found()函数
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");
//如果服务器端的文件有执行权限的,自动解析成cgi程序,如果有执行权限但是不能执行,会接受到报错信号
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
//执行CGI
execute_cgi(client, path, method, query_string);
}
// 关闭套接字
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;
//读取的字节数
int numchars = 1;
//Content-Length首部告诉浏览器报文中实体主体的大小。
//这个大小是包含了内容编码的,比如对文件进行了gzip压缩,Content-Length就是压缩后的大小
//设置CGI环境变量时使用
int content_length = -1;
buf[0] = 'A'; buf[1] = '\0';
if (strcasecmp(method, "GET") == 0)
//strcmp()函数 传入的两字符串相等时返回 0 ,
while ((numchars > 0) && strcmp("\n", buf)) /* read & discard headers */
numchars = get_line(client, buf, sizeof(buf));
else if (strcasecmp(method, "POST") == 0) /*POST*/
{
numchars = get_line(client, buf, sizeof(buf));
while ((numchars > 0) && strcmp("\n", buf))
{
buf[15] = '\0';
if (strcasecmp(buf, "Content-Length:") == 0)
////内存从第17位开始就是长度,将17位开始的所有字符串转成整数就是content_length
content_length = atoi(&(buf[16]));
numchars = get_line(client, buf, sizeof(buf));
}
if (content_length == -1) {
bad_request(client);
return;
}
}
else/*HEAD or other*/
{
}
//建立output管道
if (pipe(cgi_output) < 0) {
cannot_execute(client);
return;
}
//建立input管道
if (pipe(cgi_input) < 0) {
cannot_execute(client);
return;
}
if ( (pid = fork()) < 0 ) {
cannot_execute(client);
return;
}
sprintf(buf, "HTTP/1.0 200 OK\r\n");
send(client, buf, strlen(buf), 0);
// fork后管道都复制了一份,都是一样的
// 子进程关闭2个无用的端口,避免浪费
// ×<------------------------->1 output
// 0<-------------------------->× input
// 父进程关闭2个无用的端口,避免浪费
// 0<-------------------------->× output
// ×<------------------------->1 input
// 此时父子进程已经可以通信
//fork进程,子进程用于执行CGI
//父进程用于收数据以及发送子进程处理的回复数据
if (pid == 0) /* child: CGI script */
{
char meth_env[255];
char query_env[255];
char length_env[255];
//子进程输出重定向到output管道的1端
//子进程输入重定向到input管道的0端
dup2(cgi_output[1], STDOUT);
dup2(cgi_input[0], STDIN);
//关闭无用管道口
close(cgi_output[0]);
close(cgi_input[1]);
// 设置CGI环境变量
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);
}
//子进程替换执行path
execl(path, path, NULL);
exit(0);
} else { /* parent */
//关闭无用管道口
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);
}
//父进程从客户端套接字读取字符,通过cgi_input[1]写入cgi_input管道
//cgi_input[0]被子进程重定向到标准输入流中,子进程替换为CGI脚本
//CGI获取标准输入流中的数据,处理后将数据输入到标准输出流中,而标准输出流被重定向到cgi_output[1]中,
//父进程重cgi_output[0]读取端读取要放回给客户端的数据,send到客户端
}
/**********************************************************************/
/* 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) */
/**********************************************************************/
//若客户端为Unix系统,不需要读取到\r即可换行;
//若是Windows系统,读取到\r后在去读下一个字符,下一字符为\n即为换行;
//若是Mac系统,读取到\r后,无论下一字符是什么都认定为换行。
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')
{
//recv()函数,前三个参数与系统调用read()相同,上例中MSG_PEEK为窥看外来消息
//(可以读取得到消息但缓冲区的读取偏移量并没有被改变,故当窥看到下一字符为'\n'时,
//需要再次调用recv()函数以移动缓冲区偏移量)。
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 */
/**********************************************************************/
// 状态码 200 请求头
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);
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;
int on = 1;
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;
// 有主机字节序 转换为 网络字节序 解决不同计算机 大小端问题
name.sin_port = htons(*port);
name.sin_addr.s_addr = htonl(INADDR_ANY);
if ((setsockopt(httpd, SOL_SOCKET, SO_REUSEADDR, &on, sizeof(on))) < 0)
{
error_die("setsockopt failed");
}
if (bind(httpd, (struct sockaddr *)&name, sizeof(name)) < 0)
error_die("bind");
// 若 没有指定端口号 将动态分配一个端口号
if (*port == 0) /* if dynamically allocating a port */
{
socklen_t namelen = sizeof(name);
if (getsockname(httpd, (struct sockaddr *)&name, &namelen) == -1)
error_die("getsockname");
//网络字节序 转换为 主机字节序
*port = ntohs(name.sin_port);
}
// 服务器 套接字 监听队列
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 */
/**********************************************************************/
// 为实现的请求method,向客户端返回 501 状态码
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 = 5000;
int client_sock = -1;
struct sockaddr_in client_name;
socklen_t client_name_len = sizeof(client_name);
pthread_t newthread;
//传入端口号,建立HTTP服务
server_sock = startup(&port);
printf("httpd running on port %d\n", port);
//多线程处理HTTP请求
while (1)
{
//获取客户端请求
client_sock = accept(server_sock,
(struct sockaddr *)&client_name,
&client_name_len);
if (client_sock == -1)
error_die("accept");
/* accept_request(&client_sock); */
//accept_request 线程处理函数
if (pthread_create(&newthread , NULL, (void *)accept_request, (void *)(intptr_t)client_sock) != 0)
perror("pthread_create");
}
close(server_sock);
return(0);
}
over!原创 欢迎指正!!!(有点小小的参考 . . . . . . ...... . . . . . .