How do I trim leading/trailing whitespace in a sta

Question

Is there a clean, preferably standard method of trimming leading and trailing whitespace from a string in C? I'd roll my own, but I would think this is a common problem with an equally common solution.

Answer 1

Here is how I do it. It trims the string in place, so no worry about deallocating a returned string or losing the pointer to an allocated string. It may not be the shortest answer possible, but it should be clear to most readers.

#include <ctype.h>
#include <string.h>
void trim_str(char *s)
{
    const size_t s_len = strlen(s);

    int i;
    for (i = 0; i < s_len; i++)
    {
        if (!isspace( (unsigned char) s[i] )) break;
    }

    if (i == s_len)
    {
        // s is an empty string or contains only space characters

        s[0] = '\0';
    }
    else
    {
        // s contains non-space characters

        const char *non_space_beginning = s + i;

        char *non_space_ending = s + s_len - 1;
        while ( isspace( (unsigned char) *non_space_ending ) ) non_space_ending--;

        size_t trimmed_s_len = non_space_ending - non_space_beginning + 1;

        if (s != non_space_beginning)
        {
            // Non-space characters exist in the beginning of s

            memmove(s, non_space_beginning, trimmed_s_len);
        }

        s[trimmed_s_len] = '\0';
    }
}

Answer 2

The easiest way to skip leading spaces in a string is, imho,

#include <stdio.h>

int main()
{
char *foo="     teststring      ";
char *bar;
sscanf(foo,"%s",bar);
printf("String is >%s<\n",bar);
    return 0;
}

Answer 3

Here's my C mini library for trimming left, right, both, all, in place and separate, and trimming a set of specified characters (or white space by default).

contents of strlib.h:

#ifndef STRLIB_H_
#define STRLIB_H_ 1
enum strtrim_mode_t {
    STRLIB_MODE_ALL       = 0, 
    STRLIB_MODE_RIGHT     = 0x01, 
    STRLIB_MODE_LEFT      = 0x02, 
    STRLIB_MODE_BOTH      = 0x03
};

char *strcpytrim(char *d, // destination
                 char *s, // source
                 int mode,
                 char *delim
                 );

char *strtriml(char *d, char *s);
char *strtrimr(char *d, char *s);
char *strtrim(char *d, char *s); 
char *strkill(char *d, char *s);

char *triml(char *s);
char *trimr(char *s);
char *trim(char *s);
char *kill(char *s);
#endif

contents of strlib.c:

#include <strlib.h>

char *strcpytrim(char *d, // destination
                 char *s, // source
                 int mode,
                 char *delim
                 ) {
    char *o = d; // save orig
    char *e = 0; // end space ptr.
    char dtab[256] = {0};
    if (!s || !d) return 0;

    if (!delim) delim = " \t\n\f";
    while (*delim) 
        dtab[*delim++] = 1;

    while ( (*d = *s++) != 0 ) { 
        if (!dtab[0xFF & (unsigned int)*d]) { // Not a match char
            e = 0;       // Reset end pointer
        } else {
            if (!e) e = d;  // Found first match.

            if ( mode == STRLIB_MODE_ALL || ((mode != STRLIB_MODE_RIGHT) && (d == o)) ) 
                continue;
        }
        d++;
    }
    if (mode != STRLIB_MODE_LEFT && e) { // for everything but trim_left, delete trailing matches.
        *e = 0;
    }
    return o;
}

// perhaps these could be inlined in strlib.h
char *strtriml(char *d, char *s) { return strcpytrim(d, s, STRLIB_MODE_LEFT, 0); }
char *strtrimr(char *d, char *s) { return strcpytrim(d, s, STRLIB_MODE_RIGHT, 0); }
char *strtrim(char *d, char *s) { return strcpytrim(d, s, STRLIB_MODE_BOTH, 0); }
char *strkill(char *d, char *s) { return strcpytrim(d, s, STRLIB_MODE_ALL, 0); }

char *triml(char *s) { return strcpytrim(s, s, STRLIB_MODE_LEFT, 0); }
char *trimr(char *s) { return strcpytrim(s, s, STRLIB_MODE_RIGHT, 0); }
char *trim(char *s) { return strcpytrim(s, s, STRLIB_MODE_BOTH, 0); }
char *kill(char *s) { return strcpytrim(s, s, STRLIB_MODE_ALL, 0); }

The one main routine does it all. It trims in place if src == dst, otherwise, it works like the strcpy routines. It trims a set of characters specified in the string delim, or white space if null. It trims left, right, both, and all (like tr). There is not much to it, and it iterates over the string only once. Some folks might complain that trim right starts on the left, however, no strlen is needed which starts on the left anyway. (One way or another you have to get to the end of the string for right trims, so you might as well do the work as you go.) There may be arguments to be made about pipelining and cache sizes and such -- who knows. Since the solution works from left to right and iterates only once, it can be expanded to work on streams as well. Limitations: it does not work on unicode strings.

Answer 4

If you can modify the string:

// Note: This function returns a pointer to a substring of the original string.
// If the given string was allocated dynamically, the caller must not overwrite
// that pointer with the returned value, since the original pointer must be
// deallocated using the same allocator with which it was allocated.  The return
// value must NOT be deallocated using free() etc.
char *trimwhitespace(char *str)
{
  char *end;

  // Trim leading space
  while(isspace((unsigned char)*str)) str++;

  if(*str == 0)  // All spaces?
    return str;

  // Trim trailing space
  end = str + strlen(str) - 1;
  while(end > str && isspace((unsigned char)*end)) end--;

  // Write new null terminator character
  end[1] = '\0';

  return str;
}

If you can't modify the string, then you can use basically the same method:

// Stores the trimmed input string into the given output buffer, which must be
// large enough to store the result.  If it is too small, the output is
// truncated.
size_t trimwhitespace(char *out, size_t len, const char *str)
{
  if(len == 0)
    return 0;

  const char *end;
  size_t out_size;

  // Trim leading space
  while(isspace((unsigned char)*str)) str++;

  if(*str == 0)  // All spaces?
  {
    *out = 0;
    return 1;
  }

  // Trim trailing space
  end = str + strlen(str) - 1;
  while(end > str && isspace((unsigned char)*end)) end--;
  end++;

  // Set output size to minimum of trimmed string length and buffer size minus 1
  out_size = (end - str) < len-1 ? (end - str) : len-1;

  // Copy trimmed string and add null terminator
  memcpy(out, str, out_size);
  out[out_size] = 0;

  return out_size;
}

Answer 5

Ok this is my take on the question. I believe it's the most concise solution that modifies the string in place (free will work) and avoids any UB. For small strings, it's probably faster than a solution involving memmove.

void stripWS_LT(char *str)
{
    char *a = str, *b = str;
    while (isspace((unsigned char)*a)) a++;
    while (*b = *a++)  b++;
    while (b > str && isspace((unsigned char)*--b)) *b = 0;
}

Answer 6

Another one, with one line doing the real job:

#include <stdio.h>

int main()
{
   const char *target = "   haha   ";
   char buf[256];
   sscanf(target, "%s", buf); // Trimming on both sides occurs here
   printf("<%s>\n", buf);
}