I know that to get the number of bytes used by a variable type, you use sizeof(int) for instance. How do you get the value of the individual bytes used when you store a number with that variable type? (i.e. int x = 125.)
You have to know the number of bits (often 8) in each "byte". Then you can extract each byte in turn by ANDing the int with the appropriate mask. Imagine that an int is 32 bits, then to get 4 bytes out of the_int:
int a = (the_int >> 24) & 0xff; // high-order (leftmost) byte: bits 24-31
int b = (the_int >> 16) & 0xff; // next byte, counting from left: bits 16-23
int c = (the_int >> 8) & 0xff; // next byte, bits 8-15
int d = the_int & 0xff; // low-order byte: bits 0-7
And there you have it: each byte is in the low-order 8 bits of a, b, c, and d.
You can get the bytes by using some pointer arithmetic:
int x = 12578329; // 0xBFEE19
for (size_t i = 0; i < sizeof(x); ++i) {
// Convert to unsigned char* because a char is 1 byte in size.
// That is guaranteed by the standard.
// Note that is it NOT required to be 8 bits in size.
unsigned char byte = *((unsigned char *)&x + i);
printf("Byte %d = %u\n", i, (unsigned)byte);
}
On my machine (Intel x86-64), the output is:
Byte 0 = 25 // 0x19
Byte 1 = 238 // 0xEE
Byte 2 = 191 // 0xBF
Byte 3 = 0 // 0x00
You could make use of a union but keep in mind that the byte ordering is processor dependent and is called Endianness http://en.wikipedia.org/wiki/Endianness
#include <stdio.h>
#include <stdint.h>
union my_int {
int val;
uint8_t bytes[sizeof(int)];
};
int main(int argc, char** argv) {
union my_int mi;
int idx;
mi.val = 128;
for (idx = 0; idx < sizeof(int); idx++)
printf("byte %d = %hhu\n", idx, mi.bytes[idx]);
return 0;
}
If you want to get that information, say for:
int value = -278;
(I selected that value because it isn't very interesting for 125 - the least significant byte is 125 and the other bytes are all 0!)
You first need a pointer to that value:
int* pointer = &value;
You can now typecast that to a 'char' pointer which is only one byte, and get the individual bytes by indexing.
for (int i = 0; i < sizeof(value); i++) {
char thisbyte = *( ((char*) pointer) + i );
// do whatever processing you want.
}
Note that the order of bytes for ints and other data types depends on your system - look up 'big-endian' vs 'little-endian'.
This should work:
int x = 125;
unsigned char *bytes = (unsigned char *) (&x);
unsigned char byte0 = bytes[0];
unsigned char byte1 = bytes[1];
...
unsigned char byteN = bytes[sizeof(int) - 1];
But be aware that the byte order of integers is platform dependent.
Related
I know that to get the number of bytes used by a variable type, you use sizeof(int) for instance. How do you get the value of the individual bytes used when you store a number with that variable type? (i.e. int x = 125.)
You have to know the number of bits (often 8) in each "byte". Then you can extract each byte in turn by ANDing the int with the appropriate mask. Imagine that an int is 32 bits, then to get 4 bytes out of the_int:
int a = (the_int >> 24) & 0xff; // high-order (leftmost) byte: bits 24-31
int b = (the_int >> 16) & 0xff; // next byte, counting from left: bits 16-23
int c = (the_int >> 8) & 0xff; // next byte, bits 8-15
int d = the_int & 0xff; // low-order byte: bits 0-7
And there you have it: each byte is in the low-order 8 bits of a, b, c, and d.
You can get the bytes by using some pointer arithmetic:
int x = 12578329; // 0xBFEE19
for (size_t i = 0; i < sizeof(x); ++i) {
// Convert to unsigned char* because a char is 1 byte in size.
// That is guaranteed by the standard.
// Note that is it NOT required to be 8 bits in size.
unsigned char byte = *((unsigned char *)&x + i);
printf("Byte %d = %u\n", i, (unsigned)byte);
}
On my machine (Intel x86-64), the output is:
Byte 0 = 25 // 0x19
Byte 1 = 238 // 0xEE
Byte 2 = 191 // 0xBF
Byte 3 = 0 // 0x00
You could make use of a union but keep in mind that the byte ordering is processor dependent and is called Endianness http://en.wikipedia.org/wiki/Endianness
#include <stdio.h>
#include <stdint.h>
union my_int {
int val;
uint8_t bytes[sizeof(int)];
};
int main(int argc, char** argv) {
union my_int mi;
int idx;
mi.val = 128;
for (idx = 0; idx < sizeof(int); idx++)
printf("byte %d = %hhu\n", idx, mi.bytes[idx]);
return 0;
}
If you want to get that information, say for:
int value = -278;
(I selected that value because it isn't very interesting for 125 - the least significant byte is 125 and the other bytes are all 0!)
You first need a pointer to that value:
int* pointer = &value;
You can now typecast that to a 'char' pointer which is only one byte, and get the individual bytes by indexing.
for (int i = 0; i < sizeof(value); i++) {
char thisbyte = *( ((char*) pointer) + i );
// do whatever processing you want.
}
Note that the order of bytes for ints and other data types depends on your system - look up 'big-endian' vs 'little-endian'.
This should work:
int x = 125;
unsigned char *bytes = (unsigned char *) (&x);
unsigned char byte0 = bytes[0];
unsigned char byte1 = bytes[1];
...
unsigned char byteN = bytes[sizeof(int) - 1];
But be aware that the byte order of integers is platform dependent.
I have a 32-bit int and I want to set the first 10 bit to a specific number.
IE
The 32-bit int is:
11101010101010110101100100010010
I want the first 10 bit to be the number 123, which is
0001111011
So the result would be
00011110111010110101100100010010
Does anyone know the easiest way I would be able to do this? I know that we have to do bit-shifting but I'm not good at it so I'm not sure
Thank you!
uint32_t result = (input & 0x3fffff) | (newval << 22);
0x3fffff masks out the highest 10 bits (it has the lowest 22 bits set). You have to shift your new value for the highest 10 bits by 22 places.
Convert inputs to unsigned 32-bit integers
uint32_t num = strtoul("11101010101010110101100100010010", 0, 2);
uint32_t firstbits = 123;
Mask off the lower 32-10 bits. Create mask by shifting a unsigned long 1 22 places left making 100_0000_0000_0000_0000_0000 then decrementing to 11_1111_1111_1111_1111_1111
uint32_t mask = (1UL << (32-10)) - 1;
num &= mask;
Or in firstbits shifted left by 32-10
num |= firstbits << (32-10);
Or in 1 line:
(num & (1UL << (32-10)) - 1) | (firstbits*1UL << (32-10))
Detail about firstbits*1UL. The type of firstbits is not defined by OP and may only be a 16-bit int. To insure code can shift and form an answer that exceeds 16 bits (the minimum width of int), multiple by 1UL to insure the value is unsigned and has at least 32 bit width.
You can "erase" bits (set them to 0) by using a bit wise and ('&'); bits that are 0 in either value will be 0 in the result.
You can set bits to 1 by using a bit wise or ('|'); bits that are 1 in either value will be 1 in the result.
So: and your number with a value where the first 10 bits are 0 and the rest are 1; then 'or' it with the first 10 bits you want put in, and 0 for the other bits. If you need to calculate that value, then a left-shift would be the way to go.
You can also take a mask and replace approach where you zero the lower bits required to hold 123 and then simply | (OR) the value with 123 to gain the final result. You can accomplish the exact same thing with shifts as shown by several other answers, or you can accomplish it with masks:
#include <stdio.h>
#ifndef BITS_PER_LONG
#define BITS_PER_LONG 64
#endif
#ifndef CHAR_BIT
#define CHAR_BIT 8
#endif
char *binpad2 (unsigned long n, size_t sz);
int main (void) {
unsigned x = 0b11101010101010110101100100010010;
unsigned mask = 0xffffff00; /* mask to zero lower 8 bits */
unsigned y = 123; /* value to replace zero bits */
unsigned masked = x & mask; /* zero the lower bits */
/* show intermediate results */
printf ("\n x : %s\n", binpad2 (x, sizeof x * CHAR_BIT));
printf ("\n & mask : %s\n", binpad2 (mask, sizeof mask * CHAR_BIT));
printf ("\n masked : %s\n", binpad2 (masked, sizeof masked * CHAR_BIT));
printf ("\n | 123 : %s\n", binpad2 (y, sizeof y * CHAR_BIT));
masked |= y; /* apply the final or with 123 */
printf ("\n final : %s\n", binpad2 (masked, sizeof masked * CHAR_BIT));
return 0;
}
/** returns pointer to binary representation of 'n' zero padded to 'sz'.
* returns pointer to string contianing binary representation of
* unsigned 64-bit (or less ) value zero padded to 'sz' digits.
*/
char *binpad2 (unsigned long n, size_t sz)
{
static char s[BITS_PER_LONG + 1] = {0};
char *p = s + BITS_PER_LONG;
register size_t i;
for (i = 0; i < sz; i++)
*--p = (n>>i & 1) ? '1' : '0';
return p;
}
Output
$ ./bin/bitsset
x : 11101010101010110101100100010010
& mask : 11111111111111111111111100000000
masked : 11101010101010110101100100000000
| 123 : 00000000000000000000000001111011
final : 11101010101010110101100101111011
How about using bit fields in C combined with a union? The following structure lets you set the whole 32-bit value, the top 10 bits or the bottom 22 bits. It isn't as versatile as a generic function but you can't easily make a mistake when using it. Be aware this and most solutions may not work on all integer sizes and look out for endianness as well.
union uu {
struct {
uint32_t bottom22 : 22;
uint32_t top10 : 10;
} bits;
uint32_t value;
};
Here is an example usage:
int main(void) {
union uu myuu;
myuu.value = 999999999;
printf("value = 0x%08x\n", myuu.value);
myuu.bits.top10 = 0;
printf("value = 0x%08x\n", myuu.value);
myuu.bits.top10 = 0xfff;
printf("value = 0x%08x\n", myuu.value);
return 0;
}
The output is:
value = 0x3b9ac9ff
value = 0x001ac9ff
value = 0xffdac9ff
How do we convert 8 byte char array into long since << does not work for type long?
#define word_size 8
long num = 0;
char a[word_size] = "\x88\x99\xaa\x0bb\xcc\xdd\xee\xff";
for (i=0; i < word_size;i++) {
a[(word_size-1) - i] |= (num << (8*(word_size - i - 1))) & 0xFF;
}
printf("%lx\n", num);
The following code is more efficient:
unsigned char[word_size] = ...;
int64_t num = 0;
for ( int i = 0 ; i < sizeof(a) ; i++ )
num = (num << 8) | a[i];
This assumes big endian (highest order byte first) ordering of the bytes in the array. For little endian (as you appear to use) just process it top-down:
for ( int i = sizeof(a) ; --i >= 0 ; )
Note: whether char is signed or unsigned is implementation-dependent, so nail it down to be unsigned, otherwise the logical-or will not work. Better use uint8_t; that is defined to be 8 bits, while char is not.
Note: You should use all-uppercase for constants: WORD_SIZE instead of word_size. That is a commonly accepted standard (quite the only about case for identifiers in C).
Can you explain about how to convert the last 3 bytes of data from unsigned integer to a character array?
Example:
unsigned int unint = some value;
unsigned char array[3];
It's more difficult if you have to convert it to an array, but if you just want to access the individual bytes, then you can do
char* bytes = (char*)&unint;
If you really do want to make an array (and therefore make a copy of the last 3 bytes, not leave them in place) you do
unsigned char bytes[3]; // or char, but unsigned char is better
bytes[0] = unint >> 16 & 0xFF;
bytes[1] = unint >> 8 & 0xFF;
bytes[2] = unint & 0xFF;
You can do using it the bitwise right shift operator:
array[0] = unint;
array[1] = unint >> 8;
array[2] = unint >> 16;
The least signifcant byte of uint is stored in the first element of the array.
Depending on your needs, you may prefer an union:
typedef union {
unsigned int unint;
unsigned char array[3];
} byteAndInt;
or bit-shift operations:
for(int i=0; i<3; i++)
array[i] = (unint>>8*i) & 0xFF;
The former is not endian-safe.
If by last three, you mean lsb+1, lsb+2 and msb (in other words every byte other than the lsb), then you can use this.
unsigned int unint = some value;
unsigned char * array = ( (unsigned char*)&some_value ) + 1;
I need to be able to be able to send a numeric value to a remote socket server and so I need to encode possible numbers as bytes.
The numbers are up to 64 bit, ie requiring up to 8 bytes. The very first byte is the type, and it is always a number under 255 so fits in 1 byte.
For example, if the number was 8 and the type was a 32 bit unsigned integer then the type would be 7 which would be copied to the first (leftmost) byte and then the next 4 bytes would be encoded with the actual number (8 in this case).
So in terms of bytes:
byte1: 7
byte2: 0
byte3: 0
byte4: 0
byte5: 8
I hope this is making sense.
Does this code to perform this encoding look like a reasonable approach?
int type = 7;
uint32_t number = 8;
unsigned char* msg7 = (unsigned char*)malloc(5);
unsigned char* p = msg7;
*p++ = type;
for (int i = sizeof(uint32_t) - 1; i >= 0; --i)
*p++ = number & 0xFF << (i * 8);
You'll want to explicitly cast type to avoid a warning:
*p++ = (unsigned char) type;
You want to encode the number with most significant byte first, but you're shifting in the wrong direction. The loop should be:
for (int i = sizeof(uint32_t) - 1; i >= 0; --i)
*p++ = (unsigned char) ((number >> (i * 8)) & 0xFF);
It looks good otherwise.
Your code is reasonable (although I'd use uint8_t, since you are not using the bytes as “characters”, and Peter is of course right wrt the typo), and unlike the commonly found alternatives like
uint32_t number = 8;
uint8_t* p = (uint8_t *) &number;
or
union {
uint32_t number;
uint8_t bytes[4];
} val;
val.number = 8;
// access val.bytes[0] .. val.bytes[3]
is even guaranteed to work. The first alternative will probably work in a debug build, but more and more compilers might break it when optimizing, while the second one tends to work in practice just about everywhere, but is explicitly marked as a bad thing™ by the language standard.
I would drop the loop and use a "caller allocates" interface, like
int convert_32 (unsigned char *target, size_t size, uint32_t val)
{
if (size < 5) return -1;
target[0] = 7;
target[1] = (val >> 24) & 0xff;
target[2] = (val >> 16) & 0xff;
target[3] = (val >> 8) & 0xff;
target[4] = (val) & 0xff;
return 5;
}
This makes it easier for the caller to concatenate multiple fragments into one big binary packet and keep track of the used/needed buffer size.
Do you mean?
for (int i = sizeof(uint32_t) - 1; i >= 0; --i)
*p++ = (number >> (i * 8)) & 0xFF;
Another option to might be to do
// this would work on Big endian systems, e.g. sparc
struct unsignedMsg {
unsigned char type;
uint32_t value;
}
unsignedMsg msg;
msg.type = 7;
msg.value = number;
unsigned char *p = (unsigned char *) &msg;
or
unsigned char* p =
p[0] = 7;
*((uint32_t *) &(p[1])) = number;