Reading large amount of data from socket in c - c

I have a python tcp server that accepts connections and generates a random string of length between (0,1M) characters, on the other side I have a c client that needs to listen on that socket and read the string and convert it into a single char of the same length as the string returned by the server
int receiver(int soc_desc, char * buffer)
{
char *arr = (char *)malloc(sizeof(char));
unsigned int received , total_received;
while (1)
{
memset(arr, 0, MAX); // clear the buffer
if ( received = recv(soc_desc, arr , MAX, 0) < 0)
{
break;
}
else
{
total_received += received;
}
}
printf("%s\n",arr);
return received;
}
// soc_desc is the socket descriptor
// buffer is the buffer that will hold the final output
The only way that I can think of is using malloc to read chunks of the data returned from the server but I am having bad time trying to figure it out and I need to convert the array of char pointers into a single char when the client is done receiving data from the server

Reassembling network data, particularly from TCP, can get tricky. The following code is untested and surely doesn't account for all contingencies, but hopefully is down the right path of what you need to do.
ssize_t receiver(int soc_desc, char * buffer)
{
// Whats the buffer argument used for?
// what you had before only allocated space for 1 char. That's not what you want
// This allocates for MAX+1 chars (I'm doing +1 for a NUL terminator)
char *arr = malloc(MAX+1);
// if MAX is small enough, you could do
// char arr[MAX+1];
// 0 buffer. You could use calloc instead of malloc + memset
memset(arr, 0, MAX+1);
// initialize total_received to 0
ssize_t received , total_received = 0;
size_t spaceLeftInBuf = MAX;
while (1)
{
// don't memset here, you'll erase the data you received last iteration
// write data to arr+total_receieved. This way you won't overwrite what
// you received the last iteration
received = recv(soc_desc, arr+total_received, spaceLeftInBuf, 0);
if (received < 0)
{
// there was an error
perror("recv failed: ");
// do something with the data already received? Ok, break and
// print what we've got
break;
}
else if (received == 0)
{
// socket closed gracefully, suppose we can break again and print
// what we've got
break;
else
{
// update counters
total_received += received;
spaceLeftInBuf -= received;
// is our buffer full? This may not be the right check, you need to
// decide when to process the data
// total_received better not ever be > MAX...
if (total_received >= MAX)
{
// "process" the data by printing it
printf("%s\n", arr);
// reset
total_received = 0;
spaceLeftInBuf = MAX;
// not particularly necessary to reset this to all 0s, but should
// make sure printing goes smoothly if we break out of this loop
memset(arr, 0, MAX); // arr[MAX] should already be '\0' from above
}
}
}
printf("%s\n",arr);
return received;
}
See Do I cast the result of malloc?

I found a way to do it but this is not tested enough and for sure will cause memory issues
char *arr = malloc(sizeof(char));
char tmp_buff[MAX];
memset(arr,0,MAX);
while (recv(soc_desc, tmp_buff , MAX, 0) > 0 )
{
strcat(arr , tmp_buff);
printf("Size : %ld arr : %s\n",strlen(tmp_buff),tmp_buff);
}

Related

recv all socket (until the message end symbol), C

I want to write a recvall function for socket in C. I assume, that every message in my protocol ends with \r\n. I wrote something like this below:
int recvall (int socket, char *buffer, int numBytes)
{
int bytesRcvd = 0;
numBytes = numBytes - 1;
while(bytesRcvd < numBytes)
{
int chunk = recv(socket, buffer + bytesRcvd, numBytes - bytesRcvd, 0);
if (chunk == 0 || chunk == -1)
break;
if(strstr(buffer, "\r\n"))
break;
bytesRcvd += (chunk);
}
buffer[bytesRcvd] = '\0';
return bytesRcvd;
}
But it shows me that it returns and reads 0 bytes. On the other hand, when I remove:
if(strstr(buffer, "\r\n"))
break;
it hangs. How to improve it?
One mistake here is that strstr expects a zero-terminated string. A fix:
buffer[chunk] = 0;
if(strstr(buffer, "\r\n"))
break;
However, there may be more data following "\r\n", and that data gets lost here.
A common design pattern for receiving data is:
Have a class that maintains a connection with send/receive buffers.
When it has received data into the receive buffer, it calls a message parsing callback passing buffer and buffer_size.
The message parsing callback consumes all available complete messages in the buffer and returns the number of bytes consumed (as you do).
The message parsing callback calls another callback, passing a complete message to it.
Something like this:
typedef struct
{
int socket;
// Message-parsing callback.
size_t(*on_recv_cb)(void*, void*, size_t);
void* on_recv_cb_data;
unsigned char recv_buffer[256 * 1024];
size_t recv_buffer_size; // Initialized with 0;
} Connection;
void Connection_on_socket_ready_for_read(Connection* self) {
// Assumes a non-blocking socket. Read once to avoid starvation of other sockets.
ssize_t received = read(self->socket, self->recv_buffer + self->recv_buffer_size, sizeof self->recv_buffer - self->recv_buffer_size);
if(received > 0) {
self->recv_buffer_size += received;
size_t consumed = self->on_recv_cb(self->on_recv_cb_data, self->recv_buffer, self->recv_buffer_size);
self->recv_buffer_size -= consumed;
memmove(self->on_recv_cb_data, self->recv_buffer + consumed, self->recv_buffer_size);
}
else if(received < 0) {
if(EAGAIN == errno)
return;
perror("error");
// Handle error.
}
else {
// Handle EOF.
}
}
typedef struct {
// Message callback.
void(*on_message_cb)(void*, char*, size_t);
void* on_message_cb_data;
} MessageParserCrLf;
size_t MessageParserCrLf_on_recv(void* cb_data, void* data, size_t data_size) {
MessageParserCrLf* self = cb_data;
char* message_begin = data;
char* message_end = data;
while(data_size - (message_end - (char*)data) >= 2) {
if(message_end[0] == '\r' && message_end[1] == '\n') {
message_end += 2;
self->on_message_cb(self->on_message_cb_data, message_begin, message_end - message_begin);
message_begin = message_end;
}
else {
++message_end;
}
}
return message_begin - (char*)data;
}
void on_message(void* cb_data, char* message, size_t message_size) {
(void)cb_data; // Unused here.
printf("on_message: %.*s\n", (int)message_size, message);
}
int main() {
MessageParserCrLf message_parser = {on_message, NULL};
Connection connection = {0, MessageParserCrLf_on_recv, &message_parser, {}, 0};
Connection_on_socket_ready_for_read(&connection);
}
Outputs:
[~/src/test]$ cat lines.txt
abc
def
end
[~/src/test]$ ./test < lines.txt
on_message: abc
on_message: def
on_message: end
If there is "\r\n" in the received buffer, the following line will break and end the while loop,
if(strstr(buffer, "\r\n")) break;
but bytesRcvd hasn't increased, so the function will return with bytesRcvd=0.
Try to put bytesRcvd increase before judging like this,
bytesRcvd += (chunk);
if(strstr(buffer, "\r\n"))
break;

getting data from server in cycle

my task is get from server data of an file with HTTP protocol
but problem is that i dont know the size of the content so i iterate through read func to get data from socked but it iterates every time only once i dont know really why
int res, len, total, boolk = 0, p=0;
while ((res = read(client_socket,bufferOut,4095)) > 0)
{
bufferOut[res]= '\0';
if(p==0)
{
buffer = calloc(strlen(bufferOut)+1,sizeof(char));
}
else
{
buffer = realloc(buffer,strlen(buffer)*sizeof(char)+strlen(bufferOut)+1*sizeof(char));
}
strcat(buffer,bufferOut);
if(isEnough(bufferOut)!=0 && boolk == 0)
{
index = getIndex(buffer);
kk = getCode(buffer);
len = getLen(buffer);
boolk = 1;
}
if(strlen(bufferOut)>=len+index && boolk == 1)
{
break;
}
p++;
}
function isEnough only looks if full http header arrived getIndex get lenght of header and getLen get length of that file so i wanted to iterate until buffer is same lenght as header file which should be
You're working much too hard.
int
read_until_enough(int client_socket, char **buf_out, size_t *buflen_out)
{
char *rdbuf = xmalloc(INITIAL_BUFFER_SIZE);
size_t buflen = 0, bufalloc = INITIAL_BUFFER_SIZE;
for (;;) {
ssize_t n = recv(client_socket, rdbuf + buflen, bufalloc - buflen);
if (n <= 0) goto recv_failure;
if (is_enough(rdbuf, buflen)) break;
buflen += n;
if (buflen == bufalloc) {
bufalloc *= 2;
rdbuf = xrealloc(rdbuf, bufalloc);
}
}
*rdbuf_out = rdbuf;
*buflen_out = buflen;
return 0;
recv_failure:;
int save_errno = errno;
free(rdbuf);
errno = save_errno;
*rdbuf_out = 0;
*buflen_out = 0;
return -1;
}
Please note that is_enough now takes the size of the received data as an argument, caller gets both the received data and its size, and the buffer is NOT nul-terminated. HTTP is a binary-transparent protocol; you MUST NOTrfc2119 assume that you never receive nul bytes.
Please also note that is_enough is stateless and is expected to do all of the parsing. This is better separation of concerns. Worry about the performance cost of re-parsing the HTTP headers each time around the loop only after you have everything working.
Finally, the functions xmalloc and xrealloc are wrappers around malloc and realloc that either succeed or crash the program. I am using them here to avoid cluttering up the example with error-recovery logic for memory allocation. You will have to decide whether they are appropriate for whatever you're doing.

C - Problems extracting data from buffer. Possibly endianess-related

I'm having some difficulties extracting data from a buffer using memcpy.
First, I memcpy some variables into a buffer:
int l1_connect(const char* hostname, int port) {
// Variables to be stored in the buffer
char *msg = "Hi, I'm a message"; // strlen(msg) == 17
uint16_t sender_id = htons(1); // sizeof(sender_id) == 2
uint16_t packet_size = htons(sizeof(packet_size)+sizeof(sender_id)+strlen(msg)); // sizeof(packet_size) == 2
// Checking values
printf("l1_connect():\nsender_id: %d, packet_size: %d\n\n", ntohs(sender_id), ntohs(packet_size));
// sender_id == 1, packet_size == 21
// The buffer
char buf[100];
// Copying everything
memcpy(&buf, &sender_id, sizeof(sender_id));
memcpy(&buf+sizeof(sender_id), &packet_size, sizeof(packet_size));
memcpy(&buf+sizeof(sender_id)+sizeof(packet_size), &msg, strlen(msg));
// Passing buf to another function
int bytes_sent = l1_send(1, buf, sizeof(buf));
}
I then try to extract that data (checking, before sending over UDP socket):
int l1_send( int device, const char* buf, int length ) {
// Variables in which to store extracted data
uint16_t id = 0;
uint16_t size = 0;
char msg[50];
memcpy(&id, &buf, sizeof(id));
memcpy(&size, &buf+sizeof(id), sizeof(size));
int remaining = ntohs(size) - (sizeof(id) + sizeof(size));
printf("l1_send():\nremaining: %d\n", remaining); // -37041
// memcpy-ing with correct(?) offset
memcpy(&msg, &buf+sizeof(id)+sizeof(size), 50);
msg[49] = '\0';
printf("id: %d\n", ntohs(id)); // 8372
printf("size: %d\n", ntohs(size)); // 37045
printf("msg: %s\n", msg); // ��$_�
return 0; // For now
}
As you can see, the values aren't quite what I'm expecting. Can anyone tell me what I'm doing wrong?
Your pointer math is incorrect. You're using &buf where you should just be using buf. If this doesn't explain what is wrong, nothing else I can say will:
#include <stdio.h>
int main(int argc, char **argv)
{
char buff[100];
printf("buff : %p\nbuff+10 : %p\n&buff+10 : %p\n", buff, buff+10, &buff+10);
return 0;
}
Output (varies by platform, obviously)
buff : 0xbf87a8bc
buff+10 : 0xbf87a8c6
&buff+10 : 0xbf87aca4
See it live. The math you're doing is incrementing by type, which for &buf is a pointer to array of 100 chars; not a simple char address. Therefore, &buff + 10 (in my sample) says "give me the 10th array of 100 chars from where I am now.". The subsequent write is invoking undefined behavior as a consequence.
Valgrind is your buddy here, btw. It would have caught this in a heartbeat.
Update
May as well fill in the entire gambit while I'm here. This is also wrong in l1_send:
memcpy(&id, &buf, sizeof(id));
// this------^
and the subsequent other areas you're using it in that function. You're taking the address of a parameter pointer, not the value within it. I'm confident you need buf there as well.
Try this:
memcpy(buf, &sender_id, sizeof(sender_id));
memcpy(buf + sizeof(sender_id), &packet_size, sizeof(packet_size));
memcpy(buf + sizeof(sender_id) + sizeof(packet_size), msg, strlen(msg));
To help you understand what is wrong with your code, you can read this.
Related: Pointer math vs. Array index

Determining amount of bytes read with recv

I am having an issue with recv. I wrote a function that fills a structure with data, and the length (in bytes) of that data which is read from a socket.
For testing I am just printing the data to stdout byte by byte based on the total amount of bytes read by recv. For some reason the number of bytes being read seems to be correct sometimes and incorrect other times depending on what site I am querying. For example the following code works as intended on some sites:
data->data_sz = 0;
while((i = recv(sock, data->data + data->data_sz, CHUNKSIZE, 0)) > 0)
{
data->data_sz += i;
if(databff - data->data_sz < CHUNKSIZE)
{
databff *= 2;
if(!(tmp = realloc(data->data, databff)))
{
free(data->data);
(void) WSACleanup();
return 0;
}
data->data = tmp;
}
}
i = strsbstr(data->data, "\r\n\r\n") + 4; //i = the position of the first char after header info
if(i >= 0)
{
data->data_sz = data->data_sz - i; //data->data_sz = number of bytes without header info
memmove(data->data, data->data + i, data->data_sz);
if(!(tmp = realloc(data->data, data->data_sz)))
{
free(data->data);
(void)WSACleanup();
return 0;
}
data->data = tmp;
}
else
{
free(data->data);
(void) WSACleanup();
return 0;
}
return 1;
}
To print the data to stdout I just use a for loop:
//t_html->data_sz points to my data->data_sz structure
//t_html->data points to my data->data structure
for(i = 0; i <= t_html->data_sz; i++) (void)fputc((int)t_html->data[i], stdout);
The above code works for some sites but fails on others (for example when querying http://www.google.com I expect the final characters to be </html> but I get </html>l).
Basically my problem is that data->data_sz (the amount of bytes received) is not being calculated correctly, which makes it impossible to correctly use gathered data. I am really at a loss of what to do right now.
EDIT:
here is the strsbstr function which is called in the above code:
int strsbstr(const char *str, const char *sbstr)
{
char *sbstrlc;
if(!(strcmp(str, sbstr))) return 0;
if(!(sbstrlc = strstr(str, sbstr))) return -1;
return (int) (sbstrlc - str);
}
recv(sock, data->data + data->data_sz, CHUNKSIZE, 0) is potentially a problem. Why? Because you may not have CHUNKSIZE room left in your buffer. You have databff - data->data_sz left, actually (assuming data is allocated to a size of databff). It all depends on the initial values of databff and CHUNKSIZE, which I can't see and figure I'd point this out just in case.
Data is not guaranteed to be NULL-character terminated. Your printing loop says i <= t_html->data_sz; which is wrong. It should be i < t_html->data_sz;. If you use <=, you're accessing one past your buffer, which is likely why you get a weird character sometimes, and sometimes not.

Pointer Arithmetic with Arrays

I am new to C programming and I am getting confused with the pointer math. I have an array of characters of size 32. It is my understanding that this means that the array is also 32 bytes since a character variable is 1 byte big therefore 32 characters * 1 byte = 32 bytes. The problem is when having a function that has a void pointer that is pointing to an array of characters as described before. I believe that the code segment
for (count = 0; count < size; count++)
*((int*) raw_sk + count) = 0
should set all of the slots in the raw_sk buffer should be set to 0. However, when I run the program, I get a segmentation fault. I thought that it could be possibly be the fact that I am adding count to the address. I thought that if I were to add one to an address I would be moving to the next slot in the array. Can someone please point out where I am going wrong? The function I am using is below.
Thanks!
void
write_skfile (const char *skfname, void *raw_sk, size_t raw_sklen)
{
int fdsk = 0;
char *s = NULL;
int status = 0;
int count = 0;
int size = (raw_sklen);
/* armor the raw symmetric key in raw_sk using armor64 */
s = armor64(raw_sk, raw_sklen);
/* now let's write the armored symmetric key to skfname */
if ((fdsk = open (skfname, O_WRONLY|O_TRUNC|O_CREAT, 0600)) == -1) {
perror (getprogname ());
/*scrubs the armored buffer*/
for(count = 0; count < armor64len(s); count++)
s[count] = '0';
free (s);
/* scrub the buffer that's holding the key before exiting */
for (count = 0; count < size; count++)
*((int*)raw_sk + count) = 0;
exit (-1);
}
else {
status = write (fdsk, s, strlen (s));
if (status != -1) {
status = write (fdsk, "\n", 1);
}
for (count = 0; (size_t)count < 22; count++)
*((int*)raw_sk + count) = 0;
free (s);
close (fdsk);
/* do not scrub the key buffer under normal circumstances
(it's up to the caller) */
if (status == -1) {
printf ("%s: trouble writing symmetric key to file %s\n",
getprogname (), skfname);
perror (getprogname ());
/* scrub the buffer that's holding the key before exiting */
/* scrub the buffer that's holding the key before exiting MY CODE
for (count = 0; count < size; count++)
*((int*)raw_sk + count) = 0;*/
exit (-1);
}
}
}
You are incrementing the pointer by the size of an int. That is wrong. If you want to zero out the array you increment by the size of a char. Better yet, just use memset.
Your loop iterates over size*sizeof(int) bytes in total (where most probably sizeof(int)==4), but the array is only size bytes large. Hence, segmentation fault.
I think you meant to do
*((char*) raw_sk + count) = 0
since I assume raw_sk is pointing to char array
pointer arithmatic works by moving the memory address by size of type so in this case you want char

Resources