algorithm - Natural sort in C - "array of strings, containing numbers and letters"

Question

Looking for a proven to work algorithm for production. Did see this example but not finding much else on the web or in books.

i.e. file_10.txt > file_2.txt

Thanks.

Answer 1

Here is a (tested) comparison function that does the job. It understands only unsigned integers, not signed integers or floating point:

#include <stdlib.h>
#include <ctype.h>

/* like strcmp but compare sequences of digits numerically */
int strcmpbynum(const char *s1, const char *s2) {
  for (;;) {
    if (*s2 == '')
      return *s1 != '';
    else if (*s1 == '')
      return 1;
    else if (!(isdigit(*s1) && isdigit(*s2))) {
      if (*s1 != *s2)
        return (int)*s1 - (int)*s2;
      else
        (++s1, ++s2);
    } else {
      char *lim1, *lim2;
      unsigned long n1 = strtoul(s1, &lim1, 10);
      unsigned long n2 = strtoul(s2, &lim2, 10);
      if (n1 > n2)
        return 1;
      else if (n1 < n2)
        return -1;
      s1 = lim1;
      s2 = lim2;
    }
  }
}

If you want to use it with qsort, use this auxiliary function:

static int compare(const void *p1, const void *p2) {
  const char * const *ps1 = p1;
  const char * const *ps2 = p2;
  return strcmpbynum(*ps1, *ps2);
}

And you can do something on the order of

qsort(lines, next, sizeof(lines[0]), compare);