How do I determine the number of digits of an integer in C?
for instance,
n = 3432, result 4
n = 45, result 2
n = 33215, result 5
n = -357, result 3
I guess I could just turn it into a string then get the length of the string but that seems convoluted and hack-y.
Solution 1:
The recursive approach :-)
int numPlaces (int n) {
if (n < 0) return numPlaces ((n == INT_MIN) ? INT_MAX: -n);
if (n < 10) return 1;
return 1 + numPlaces (n / 10);
}
Or iterative:
int numPlaces (int n) {
int r = 1;
if (n < 0) n = (n == INT_MIN) ? INT_MAX: -n;
while (n > 9) {
n /= 10;
r++;
}
return r;
}
Or raw speed:
int numPlaces (int n) {
if (n < 0) n = (n == INT_MIN) ? INT_MAX : -n;
if (n < 10) return 1;
if (n < 100) return 2;
if (n < 1000) return 3;
if (n < 10000) return 4;
if (n < 100000) return 5;
if (n < 1000000) return 6;
if (n < 10000000) return 7;
if (n < 100000000) return 8;
if (n < 1000000000) return 9;
/* 2147483647 is 2^31-1 - add more ifs as needed
and adjust this final return as well. */
return 10;
}
Those above have been modified to better process MININT. On any weird systems that don't follow sensible 2n two's complement rules for integers, they may need further adjustment.
The raw speed version actually outperforms the floating point version, modified below:
int numPlaces (int n) {
if (n == 0) return 1;
return floor (log10 (abs (n))) + 1;
}
With a hundred million iterations, I get the following results:
Raw speed with 0: 0 seconds
Raw speed with 2^31-1: 1 second
Iterative with 2^31-1: 5 seconds
Recursive with 2^31-1: 6 seconds
Floating point with 1: 6 seconds
Floating point with 2^31-1: 7 seconds
That actually surprised me a little - I thought the Intel chips had a decent FPU but I guess general FP operations still can't compete with hand-optimized integer code.
Update following stormsoul's suggestions:
Testing the multiply-iterative solution by stormsoul gives a result of 4 seconds so, while it's much faster than the divide-iterative solution, it still doesn't match the optimized if-statement solution.
Choosing the arguments from a pool of 1000 randomly generated numbers pushed the raw speed time out to 2 seconds so, while it appears there may have been some advantage to having the same argument each time, it's still the fastest approach listed.
Compiling with -O2 improved the speeds but not the relative positions (I increased the iteration count by a factor of ten to check this).
Any further analysis is going to have to get seriously into the inner workings of CPU efficiency (different types of optimization, use of caches, branch prediction, which CPU you actually have, the ambient temperature in the room and so on) which is going to get in the way of my paid work :-). It's been an interesting diversion but, at some point, the return on investment for optimization becomes too small to matter. I think we've got enough solutions to have answered the question (which was, after all, not about speed).
Further update:
This will be my final update to this answer barring glaring errors that aren't dependent on architecture. Inspired by stormsoul's valiant efforts to measure, I'm posting my test program (modified as per stormsoul's own test program) along with some sample figures for all methods shown in the answers here. Keep in mind this is on a particular machine, your mileage may vary depending on where you run it (which is why I'm posting the test code).
Do with it as you wish:
#include <stdio.h>
#include <stdlib.h>
#include <math.h>
#include <limits.h>
#include <time.h>
#define numof(a) (sizeof(a) / sizeof(a[0]))
/* Random numbers and accuracy checks. */
static int rndnum[10000];
static int rt[numof(rndnum)];
/* All digit counting functions here. */
static int count_recur (int n) {
if (n < 0) return count_recur ((n == INT_MIN) ? INT_MAX : -n);
if (n < 10) return 1;
return 1 + count_recur (n / 10);
}
static int count_diviter (int n) {
int r = 1;
if (n < 0) n = (n == INT_MIN) ? INT_MAX : -n;
while (n > 9) {
n /= 10;
r++;
}
return r;
}
static int count_multiter (int n) {
unsigned int num = abs(n);
unsigned int x, i;
for (x=10, i=1; ; x*=10, i++) {
if (num < x)
return i;
if (x > INT_MAX/10)
return i+1;
}
}
static int count_ifs (int n) {
if (n < 0) n = (n == INT_MIN) ? INT_MAX : -n;
if (n < 10) return 1;
if (n < 100) return 2;
if (n < 1000) return 3;
if (n < 10000) return 4;
if (n < 100000) return 5;
if (n < 1000000) return 6;
if (n < 10000000) return 7;
if (n < 100000000) return 8;
if (n < 1000000000) return 9;
/* 2147483647 is 2^31-1 - add more ifs as needed
and adjust this final return as well. */
return 10;
}
static int count_revifs (int n) {
if (n < 0) n = (n == INT_MIN) ? INT_MAX : -n;
if (n > 999999999) return 10;
if (n > 99999999) return 9;
if (n > 9999999) return 8;
if (n > 999999) return 7;
if (n > 99999) return 6;
if (n > 9999) return 5;
if (n > 999) return 4;
if (n > 99) return 3;
if (n > 9) return 2;
return 1;
}
static int count_log10 (int n) {
if (n < 0) n = (n == INT_MIN) ? INT_MAX : -n;
if (n == 0) return 1;
return floor (log10 (n)) + 1;
}
static int count_bchop (int n) {
int r = 1;
if (n < 0) n = (n == INT_MIN) ? INT_MAX : -n;
if (n >= 100000000) {
r += 8;
n /= 100000000;
}
if (n >= 10000) {
r += 4;
n /= 10000;
}
if (n >= 100) {
r += 2;
n /= 100;
}
if (n >= 10)
r++;
return r;
}
/* Structure to control calling of functions. */
typedef struct {
int (*fnptr)(int);
char *desc;
} tFn;
static tFn fn[] = {
NULL, NULL,
count_recur, " recursive",
count_diviter, " divide-iterative",
count_multiter, " multiply-iterative",
count_ifs, " if-statements",
count_revifs, "reverse-if-statements",
count_log10, " log-10",
count_bchop, " binary chop",
};
static clock_t clk[numof (fn)];
int main (int c, char *v[]) {
int i, j, k, r;
int s = 1;
/* Test code:
printf ("%11d %d\n", INT_MIN, count_recur(INT_MIN));
for (i = -1000000000; i != 0; i /= 10)
printf ("%11d %d\n", i, count_recur(i));
printf ("%11d %d\n", 0, count_recur(0));
for (i = 1; i != 1000000000; i *= 10)
printf ("%11d %d\n", i, count_recur(i));
printf ("%11d %d\n", 1000000000, count_recur(1000000000));
printf ("%11d %d\n", INT_MAX, count_recur(INT_MAX));
/* */
/* Randomize and create random pool of numbers. */
srand (time (NULL));
for (j = 0; j < numof (rndnum); j++) {
rndnum[j] = s * rand();
s = -s;
}
rndnum[0] = INT_MAX;
rndnum[1] = INT_MIN;
/* For testing. */
for (k = 0; k < numof (rndnum); k++) {
rt[k] = (fn[1].fnptr)(rndnum[k]);
}
/* Test each of the functions in turn. */
clk[0] = clock();
for (i = 1; i < numof (fn); i++) {
for (j = 0; j < 10000; j++) {
for (k = 0; k < numof (rndnum); k++) {
r = (fn[i].fnptr)(rndnum[k]);
/* Test code:
if (r != rt[k]) {
printf ("Mismatch error [%s] %d %d %d %d\n",
fn[i].desc, k, rndnum[k], rt[k], r);
return 1;
}
/* */
}
}
clk[i] = clock();
}
/* Print out results. */
for (i = 1; i < numof (fn); i++) {
printf ("Time for %s: %10d\n", fn[i].desc, (int)(clk[i] - clk[i-1]));
}
return 0;
}
Remember that you need to ensure you use the correct command line to compile it. In particular, you may need to explicitly list the math library to get
log10()working. The command line I used under Debian wasgcc -o testprog testprog.c -lm.
And, in terms of results, here's the leader-board for my environment:
Optimization level 0:
Time for reverse-if-statements: 1704
Time for if-statements: 2296
Time for binary chop: 2515
Time for multiply-iterative: 5141
Time for divide-iterative: 7375
Time for recursive: 10469
Time for log-10: 26953
Optimization level 3:
Time for if-statements: 1047
Time for binary chop: 1156
Time for reverse-if-statements: 1500
Time for multiply-iterative: 2937
Time for divide-iterative: 5391
Time for recursive: 8875
Time for log-10: 25438
Solution 2:
floor (log10 (abs (x))) + 1
http://en.wikipedia.org/wiki/Logarithm
Solution 3:
The shortest answer: snprintf(0,0,"%+d",n)-1
Solution 4:
Binary search pseudo algorithm to get no of digits of r in v..
if (v < 0 ) v=-v;
r=1;
if (v >= 100000000)
{
r+=8;
v/=100000000;
}
if (v >= 10000) {
r+=4;
v/=10000;
}
if (v >= 100) {
r+=2;
v/=100;
}
if( v>=10)
{
r+=1;
}
return r;
Solution 5:
Here is a very fast method to compute the number of decimal digits by Kendall Willets:
int count_digits(uint32_t n) {
#ifndef __has_builtin
# define __has_builtin(x) 0
#endif
#if __has_builtin(__builtin_clz)
// This increments the upper 32 bits (log10(T) - 1) when >= T is added.
# define K(T) (((sizeof(#T) - 1ull) << 32) - T)
static const uint64_t table[] = {
K(0), K(0), K(0), // 8
K(10), K(10), K(10), // 64
K(100), K(100), K(100), // 512
K(1000), K(1000), K(1000), // 4096
K(10000), K(10000), K(10000), // 32k
K(100000), K(100000), K(100000), // 256k
K(1000000), K(1000000), K(1000000), // 2048k
K(10000000), K(10000000), K(10000000), // 16M
K(100000000), K(100000000), K(100000000), // 128M
K(1000000000), K(1000000000), K(1000000000), // 1024M
K(1000000000), K(1000000000) // 4B
};
return (n + table[__builtin_clz(n | 1) ^ 31]) >> 32u;
#else
int count = 1;
for (;;) {
if (n < 10) return count;
if (n < 100) return count + 1;
if (n < 1000) return count + 2;
if (n < 10000) return count + 3;
n /= 10000u;
count += 4;
}
return count;
#endif
}
The fast path relies on __builtin_clz which is available in GCC and clang but thanks to the fallback that works reasonably well count_digits is fully portable.
This generates very efficient code (godbolt):
count_digits(unsigned int):
mov edx, edi
mov eax, edi
or edx, 1
bsr edx, edx
movsx rdx, edx
add rax, QWORD PTR count_digits(unsigned int)::table[0+rdx*8]
shr rax, 32
ret