Websocket server code protocol analysis, learn to do their own protocol ideas.

Let's first introduce HTTP and Websocket The relationship between .

HTTP Yes 1.1 and 1.0 The said , It's called keep-alive , The multiple HTTP Request to merge into one , however Websocket It's actually a The new agreement , Follow HTTP The agreement has little to do with , Just for compatible Handshake specification of existing browsers , That is to say, it is HTTP A supplement to the agreement can be understood through such a diagram

There is intersection , But not all , It should be noted that both of them are based on tcp Support On the basis of .
Let's first introduce http and websoket The relationship between ：
First ,Websocket It's a Persistent protocol , be relative to HTTP such non-durable In terms of the agreement . Let's take a simple example , It is widely used at present PHP Life cycle to explain .

HTTP Through the life cycle of Request To define , That's one Request One Response , So in HTTP1.0 in , This time, HTTP The request is over .

stay HTTP1.1 Improved in , So that there is a keep-alive, in other words , In a HTTP Connecting , Can send multiple Request, Receive multiple Response. But remember Request = Response , stay HTTP China is always like this , That is to say a request There can only be one response. And this response It's also passive , Can't initiate .

Websocket be based on HTTP The agreement is not very accurate , Think of it as Websocket Compatible with HTTP, Or borrow HTTP The protocol to complete part of the handshake .

Look at this picture

Whether it's IPv4 Message or TCP,UDP message , They all have a certain format , The picture above shows websocket Corresponding message format .

In the future, if you are based on tcp do Custom protocol , You need to master these key steps .

• opcode
• Bag length
• mask-key ( It can be understood as the way of data encryption )
• Data section

ad locum , We go through websocket The framework code of the server , Let's explain , In the agreement , how Encapsulate all parts of the message format . At the end of the article , I will give the complete code .

First, let's sort it out ,websocket The client and websocket Server connection process ：

One thing we need to know , Why do we say http Agreement or websocket Agreement is be based on tcp Of , In fact, these agreements are just tcp On the Carry out a series of functional packaging , A specific protocol that is encapsulated by a specific protocol rule standard .
When websoket Client and websocket The server is set up tcp After connection . First websocket The client will send the corresponding handshake data to the server port , Carry out the handshake process , Of course, the handshake here , No Refers to tcp Three handshakes during connection ( Three handshakes are tcp Connection process , Here is after connection ).

The data sent by the client contains a paragraph similar to
Sec-WebSocket-Key: x3JJHMbDL1EzLkh9GBhXDw==
The data of .
The server side decides to name one by one GUID Value , This value is globally unique , It can be understood as websocket A rule of agreement .

The server will match the data sent by the customer service end with the globally unique GUID Value . Get the corresponding hash value through a hash function , Then get the final result from the server through a specific coding method
Sec-WebSocket-Accept ：

Use pseudo code to explain this process ：

str = strcat(linebuf, GUID);   // Connect part of the handshake data sent by the client to the server GUID
sta = SHA1(str); //  It is converted to the corresponding hash value by a specific hash function 
base64_encode(sta); // By specific encoding , Get the final value Sec-WebSocket-Accept :

Specific handshake code
It is recommended to watch the code , Because the complete code defines many structures and encapsulated functions , So it may not be easy to understand the partial code alone , Therefore, it is recommended to just read and understand the local code later , The specific process , Finally, I suggest you take a good look at the complete code .

int handshark(struct sockitem *si, struct reactor *mainloop) {
    

	char linebuf[256];
	char sec_accept[32]; 
	int level = 0;
	unsigned char sha1_data[SHA_DIGEST_LENGTH+1] = {
    0};
	char head[BUFFER_LENGTH] = {
    0};  

	do {
            
		memset(linebuf, 0, sizeof(linebuf));        
		level = readline(si->recvbuffer, level, linebuf); 

		if (strstr(linebuf,"Sec-WebSocket-Key") != NULL)        {
       
			
			strcat(linebuf, GUID);    
			
			SHA1((unsigned char*)&linebuf+19,strlen(linebuf+19),(unsigned char*)&sha1_data);  
			
			base64_encode(sha1_data,strlen(sha1_data),sec_accept);           
			sprintf(head, "HTTP/1.1 101 Switching Protocols\r\n" \
				"Upgrade: websocket\r\n" \
				"Connection: Upgrade\r\n" \
				"Sec-WebSocket-Accept: %s\r\n" \
				"\r\n", sec_accept);            

			printf("response\n");            
			printf("%s\n\n\n", head);            
#if 0
			if (write(cli_fd, head, strlen(head)) < 0)     //write ---> send 
				perror("write");            
#else
			memset(si->recvbuffer, 0, BUFFER_LENGTH);

			memcpy(si->sendbuffer, head, strlen(head)); // to send 
			si->slength = strlen(head);

			// to set epollout events
			struct epoll_event ev;
			ev.events = EPOLLOUT | EPOLLET;
			//ev.data.fd = clientfd;
			si->sockfd = si->sockfd;
			si->callback = send_cb;
			si->status = WS_DATATRANSFORM;
			ev.data.ptr = si;

			epoll_ctl(mainloop->epfd, EPOLL_CTL_MOD, si->sockfd, &ev);

#endif
			break;        
		}    

	} while((si->recvbuffer[level] != '\r' || si->recvbuffer[level+1] != '\n') && level != -1);    

	return 0;
}

After handshake , It involves the data exchange process between the server and the client , Next code , It will show you ,websocket How is the message format encapsulated by code .
Notice these two functions
decode_packet // unpacking
encode_packet // Package

int transform(struct sockitem *si, struct reactor *mainloop) {
    

	int ret = 0;
	char mask[4] = {
    0};
	char *data = decode_packet(si->recvbuffer, mask, si->rlength, &ret);
	// there decode_packet It is to unpack data packets , Pick out the data section , Discard message header .

	printf("data : %s , length : %d\n", data, ret);

	ret = encode_packet(si->sendbuffer, mask, data, ret);
	// there encode_packet Is to add the header to the data part , To form a complete websocket package .
	si->slength = ret;

	memset(si->recvbuffer, 0, BUFFER_LENGTH);

	struct epoll_event ev;
	ev.events = EPOLLOUT | EPOLLET;
	//ev.data.fd = clientfd;
	si->sockfd = si->sockfd;
	si->callback = send_cb;
	si->status = WS_DATATRANSFORM;
	ev.data.ptr = si;

	epoll_ctl(mainloop->epfd, EPOLL_CTL_MOD, si->sockfd, &ev);

	return 0;
}

summary ：

• such as http,websocket agreement , These seemingly tall and incomprehensible agreements , Their essence is based on tcp Connected code , complete Deeper encapsulation , Of course, in the process of packaging , We can use some methods to enhance the efficiency of network programming , For example, it is used here I/O In multiplexing epoll, Finish right Reactor Encapsulation ,Reactor It is an efficient event processing mode .
• Encapsulation of message format , Used several Structure For each part of message format encapsulate , So as to realize the Add head and remove head The function of .
• Key points of custom protocol ：
  1. opcode 2. Bag length 3. Non essential election ：mask-key( Encrypt data ) 4. Data section

Complete server-side code ：

#include <stdio.h>
#include <stdlib.h>
#include <string.h>

#include <unistd.h>
#include <netinet/tcp.h>
#include <arpa/inet.h>
#include <pthread.h>

#include <fcntl.h>
#include <errno.h>
#include <sys/epoll.h>

#include <openssl/sha.h>
#include <openssl/pem.h>
#include <openssl/bio.h>
#include <openssl/evp.h>

#define BUFFER_LENGTH 1024
#define GUID "258EAFA5-E914-47DA-95CA-C5AB0DC85B11"


enum  WEBSOCKET_STATUS {
    
	WS_HANDSHARK,
	WS_DATATRANSFORM,
	WS_DATAEND,
};


struct sockitem {
     //
	int sockfd;
	int (*callback)(int fd, int events, void *arg);

	char recvbuffer[BUFFER_LENGTH]; //
	char sendbuffer[BUFFER_LENGTH];

	int rlength;
	int slength;

	int status;

};

// mainloop / eventloop --> epoll --> 
struct reactor {
    

	int epfd;
	struct epoll_event events[512];
	
	

};


struct reactor *eventloop = NULL;

int recv_cb(int fd, int events, void *arg);
int send_cb(int fd, int events, void *arg);

#if 1 // websocket

char* decode_packet(char *stream, char *mask, int length, int *ret);
int encode_packet(char *buffer,char *mask, char *stream, int length);

struct _nty_ophdr {
    

	unsigned char opcode:4,
		 rsv3:1,
		 rsv2:1,
		 rsv1:1,
		 fin:1;
	unsigned char payload_length:7,
		mask:1;

} __attribute__ ((packed));

struct _nty_websocket_head_126 {
    
	unsigned short payload_length;
	char mask_key[4];
	unsigned char data[8];
} __attribute__ ((packed));

struct _nty_websocket_head_127 {
    

	unsigned long long payload_length;
	char mask_key[4];

	unsigned char data[8];
	
} __attribute__ ((packed));

typedef struct _nty_websocket_head_127 nty_websocket_head_127;
typedef struct _nty_websocket_head_126 nty_websocket_head_126;
typedef struct _nty_ophdr nty_ophdr;


int base64_encode(char *in_str, int in_len, char *out_str) {
        
	BIO *b64, *bio;    
	BUF_MEM *bptr = NULL;    
	size_t size = 0;    

	if (in_str == NULL || out_str == NULL)        
		return -1;    

	b64 = BIO_new(BIO_f_base64());    
	bio = BIO_new(BIO_s_mem());    
	bio = BIO_push(b64, bio);
	
	BIO_write(bio, in_str, in_len);    
	BIO_flush(bio);    

	BIO_get_mem_ptr(bio, &bptr);    
	memcpy(out_str, bptr->data, bptr->length);    
	out_str[bptr->length-1] = '\0';    
	size = bptr->length;    

	BIO_free_all(bio);    
	return size;
}


int readline(char* allbuf,int level,char* linebuf) {
        
	int len = strlen(allbuf);    

	for (;level < len; ++level)    {
            
		if(allbuf[level]=='\r' && allbuf[level+1]=='\n')            
			return level+2;        
		else            
			*(linebuf++) = allbuf[level];    
	}    

	return -1;
}

int handshark(struct sockitem *si, struct reactor *mainloop) {
    

	char linebuf[256];
	char sec_accept[32]; 
	int level = 0;
	unsigned char sha1_data[SHA_DIGEST_LENGTH+1] = {
    0};
	char head[BUFFER_LENGTH] = {
    0};  

	do {
            
		memset(linebuf, 0, sizeof(linebuf));        
		level = readline(si->recvbuffer, level, linebuf); 

		if (strstr(linebuf,"Sec-WebSocket-Key") != NULL)        {
       
			
			strcat(linebuf, GUID);    
			
			SHA1((unsigned char*)&linebuf+19,strlen(linebuf+19),(unsigned char*)&sha1_data);  
			
			base64_encode(sha1_data,strlen(sha1_data),sec_accept);           
			sprintf(head, "HTTP/1.1 101 Switching Protocols\r\n" \
				"Upgrade: websocket\r\n" \
				"Connection: Upgrade\r\n" \
				"Sec-WebSocket-Accept: %s\r\n" \
				"\r\n", sec_accept);            

			printf("response\n");            
			printf("%s\n\n\n", head);            
#if 0
			if (write(cli_fd, head, strlen(head)) < 0)     //write ---> send 
				perror("write");            
#else
			memset(si->recvbuffer, 0, BUFFER_LENGTH);

			memcpy(si->sendbuffer, head, strlen(head)); // to send 
			si->slength = strlen(head);

			// to set epollout events
			struct epoll_event ev;
			ev.events = EPOLLOUT | EPOLLET;
			//ev.data.fd = clientfd;
			si->sockfd = si->sockfd;
			si->callback = send_cb;
			si->status = WS_DATATRANSFORM;
			ev.data.ptr = si;

			epoll_ctl(mainloop->epfd, EPOLL_CTL_MOD, si->sockfd, &ev);

#endif
			break;        
		}    

	} while((si->recvbuffer[level] != '\r' || si->recvbuffer[level+1] != '\n') && level != -1);    

	return 0;
}

int transform(struct sockitem *si, struct reactor *mainloop) {
    

	int ret = 0;
	char mask[4] = {
    0};
	char *data = decode_packet(si->recvbuffer, mask, si->rlength, &ret);


	printf("data : %s , length : %d\n", data, ret);

	ret = encode_packet(si->sendbuffer, mask, data, ret);
	si->slength = ret;

	memset(si->recvbuffer, 0, BUFFER_LENGTH);

	struct epoll_event ev;
	ev.events = EPOLLOUT | EPOLLET;
	//ev.data.fd = clientfd;
	si->sockfd = si->sockfd;
	si->callback = send_cb;
	si->status = WS_DATATRANSFORM;
	ev.data.ptr = si;

	epoll_ctl(mainloop->epfd, EPOLL_CTL_MOD, si->sockfd, &ev);

	return 0;
}

void umask(char *data,int len,char *mask) {
        
	int i;    
	for (i = 0;i < len;i ++)        
		*(data+i) ^= *(mask+(i%4));
}

char* decode_packet(char *stream, char *mask, int length, int *ret) {
    

	nty_ophdr *hdr =  (nty_ophdr*)stream;
	unsigned char *data = stream + sizeof(nty_ophdr);
	int size = 0;
	int start = 0;
	//char mask[4] = {0};
	int i = 0;

	//if (hdr->fin == 1) return NULL;

	if ((hdr->mask & 0x7F) == 126) {
    
		// Someone here may be confused ,mask Isn't it mask flag bit ？ How to judge like this .
		// Because mask Although it only occupies one place , But point to this one , That is, it points to the whole byte ,
		//0x7F == 0111 1111 , I didn't use it when comparing mask position 

		nty_websocket_head_126 *hdr126 = (nty_websocket_head_126*)data;
		size = hdr126->payload_length;
		
		for (i = 0;i < 4;i ++) {
    
			mask[i] = hdr126->mask_key[i];
		}
		
		start = 8;
		
	} else if ((hdr->mask & 0x7F) == 127) {
    

		nty_websocket_head_127 *hdr127 = (nty_websocket_head_127*)data;
		size = hdr127->payload_length;
		
		for (i = 0;i < 4;i ++) {
    
			mask[i] = hdr127->mask_key[i];
		}
		
		start = 14;

	} else {
    
		size = hdr->payload_length;

		memcpy(mask, data, 4);
		start = 6;
	}

	*ret = size;
	umask(stream+start, size, mask);

	return stream + start;
	
}


int encode_packet(char *buffer,char *mask, char *stream, int length) {
    
	nty_ophdr head = {
    0};
	head.fin = 1;
	head.opcode = 1;
	int size = 0;

	if (length < 126) {
    
		head.payload_length = length;
		memcpy(buffer, &head, sizeof(nty_ophdr));
		size = 2;
	} else if (length < 0xffff) {
    
		nty_websocket_head_126 hdr = {
    0};
		hdr.payload_length = length;
		memcpy(hdr.mask_key, mask, 4);

		memcpy(buffer, &head, sizeof(nty_ophdr));
		memcpy(buffer+sizeof(nty_ophdr), &hdr, sizeof(nty_websocket_head_126));
		size = sizeof(nty_websocket_head_126);//8
		//size = sizeof(nty_ophdr) + sizeof(nty_websocket_head_126);
		//size = 8;
	} else {
    
		
		nty_websocket_head_127 hdr = {
    0};
		hdr.payload_length = length;
		memcpy(hdr.mask_key, mask, 4);
		
		memcpy(buffer, &head, sizeof(nty_ophdr));
		memcpy(buffer+sizeof(nty_ophdr), &hdr, sizeof(nty_websocket_head_127));

		size = sizeof(nty_websocket_head_127);
		//size = sizeof(nty_ophdr) + sizeof(nty_websocket_head_127);
		//size = 14;
	}

	memcpy(buffer+2, stream, length);
	//memcpy(buffer+size, stream, length);

	return length + 2;
	//return length + size ;
}


#endif 



static int set_nonblock(int fd) {
      // Set to non blocking 
	int flags;

	flags = fcntl(fd, F_GETFL, 0);
	if (flags < 0) return flags;
	flags |= O_NONBLOCK;
	if (fcntl(fd, F_SETFL, flags) < 0) return -1;
	return 0;
}


int send_cb(int fd, int events, void *arg) {
    

	struct sockitem *si = (struct sockitem*)arg;

	send(fd, si->sendbuffer, si->slength, 0); //

	struct epoll_event ev;
	ev.events = EPOLLIN | EPOLLET;
	//ev.data.fd = clientfd;
	si->sockfd = fd;
	si->callback = recv_cb;
	ev.data.ptr = si;
	
	memset(si->sendbuffer, 0, BUFFER_LENGTH);

	epoll_ctl(eventloop->epfd, EPOLL_CTL_MOD, fd, &ev);

}

// ./epoll 8080

int recv_cb(int fd, int events, void *arg) {
    

	//int clientfd = events[i].data.fd;
	struct sockitem *si = (struct sockitem*)arg;
	struct epoll_event ev;

	int ret = recv(fd, si->recvbuffer, BUFFER_LENGTH, 0);
	if (ret < 0) {
    

		if (errno == EAGAIN || errno == EWOULDBLOCK) {
     //
			return -1;
		} else {
    
			
		}

		ev.events = EPOLLIN;
		//ev.data.fd = fd;
		epoll_ctl(eventloop->epfd, EPOLL_CTL_DEL, fd, &ev);
		close(fd);
		free(si);
		

	} else if (ret == 0) {
     //

		// 
		printf("disconnect %d\n", fd);
		ev.events = EPOLLIN;
		//ev.data.fd = fd;
		epoll_ctl(eventloop->epfd, EPOLL_CTL_DEL, fd, &ev);
		close(fd);
		free(si);
		
	} else {
    

		//printf("Recv: %s, %d Bytes\n", si->recvbuffer, ret);
		si->rlength = 0;

		if (si->status == WS_HANDSHARK) {
    
			printf("request\n");    
			printf("%s\n", si->recvbuffer);   

			handshark(si, eventloop);
		} else if (si->status == WS_DATATRANSFORM) {
    
			transform(si, eventloop);
		} else if (si->status == WS_DATAEND) {
    

		}

	}

}


int accept_cb(int fd, int events, void *arg) {
    

	struct sockaddr_in client_addr;
	memset(&client_addr, 0, sizeof(struct sockaddr_in));
	socklen_t client_len = sizeof(client_addr);
	
	int clientfd = accept(fd, (struct sockaddr*)&client_addr, &client_len);
	if (clientfd <= 0) return -1;

	set_nonblock(clientfd);

	char str[INET_ADDRSTRLEN] = {
    0};
	printf("recv from %s at port %d\n", inet_ntop(AF_INET, &client_addr.sin_addr, str, sizeof(str)),
		ntohs(client_addr.sin_port));

	struct epoll_event ev;
	ev.events = EPOLLIN | EPOLLET;
	//ev.data.fd = clientfd;

	struct sockitem *si = (struct sockitem*)malloc(sizeof(struct sockitem));
	si->sockfd = clientfd;
	si->callback = recv_cb;
	si->status = WS_HANDSHARK;
	ev.data.ptr = si;
	
	epoll_ctl(eventloop->epfd, EPOLL_CTL_ADD, clientfd, &ev);
	
	return clientfd;
}

int main(int argc, char *argv[]) {
    

	if (argc < 2) {
    
		return -1;
	}

	int port = atoi(argv[1]);

	

	int sockfd = socket(AF_INET, SOCK_STREAM, 0);
	if (sockfd < 0) {
    
		return -1;
	}

	set_nonblock(sockfd);

	struct sockaddr_in addr;
	memset(&addr, 0, sizeof(struct sockaddr_in));

	addr.sin_family = AF_INET;
	addr.sin_port = htons(port);
	addr.sin_addr.s_addr = INADDR_ANY;

	if (bind(sockfd, (struct sockaddr*)&addr, sizeof(struct sockaddr_in)) < 0) {
    
		return -2;
	}

	if (listen(sockfd, 5) < 0) {
    
		return -3;
	}

	eventloop = (struct reactor*)malloc(sizeof(struct reactor));
	// epoll opera

	eventloop->epfd = epoll_create(1);
	
	struct epoll_event ev;
	ev.events = EPOLLIN;
	
	struct sockitem *si = (struct sockitem*)malloc(sizeof(struct sockitem));
	si->sockfd = sockfd;
	si->callback = accept_cb;
	ev.data.ptr = si;
	
	epoll_ctl(eventloop->epfd, EPOLL_CTL_ADD, sockfd, &ev);

	while (1) {
    

		int nready = epoll_wait(eventloop->epfd, eventloop->events, 512, -1);
		if (nready < -1) {
    
			break;
		}

		int i = 0;
		for (i = 0;i < nready;i ++) {
    



			if (eventloop->events[i].events & EPOLLIN) {
    
				//printf("sockitem\n");
				struct sockitem *si = (struct sockitem*)eventloop->events[i].data.ptr;
				si->callback(si->sockfd, eventloop->events[i].events, si);
			}

			if (eventloop->events[i].events & EPOLLOUT) {
    
				struct sockitem *si = (struct sockitem*)eventloop->events[i].data.ptr;
				si->callback(si->sockfd, eventloop->events[i].events, si);
			}
		}

	}

}