Split string with delimiters in C

Question

How do I write a function to split and return an array for a string with delimiters in the C programming language?

char* str = "JAN,FEB,MAR,APR,MAY,JUN,JUL,AUG,SEP,OCT,NOV,DEC";
str_split(str,',');

Answer 1

Below is my strtok() implementation from zString library. zstring_strtok() differs from standard library's strtok() in the way it treats consecutive delimiters.

Just have a look at the code below,sure that you will get an idea about how it works (I tried to use as many comments as I could)

char *zstring_strtok(char *str, const char *delim) {
    static char *static_str=0;      /* var to store last address */
    int index=0, strlength=0;       /* integers for indexes */
    int found = 0;                  /* check if delim is found */

    /* delimiter cannot be NULL
    * if no more char left, return NULL as well
    */
    if (delim==0 || (str == 0 && static_str == 0))
        return 0;

    if (str == 0)
        str = static_str;

    /* get length of string */
    while(str[strlength])
        strlength++;

    /* find the first occurance of delim */
    for (index=0;index<strlength;index++)
        if (str[index]==delim[0]) {
            found=1;
            break;
        }

    /* if delim is not contained in str, return str */
    if (!found) {
        static_str = 0;
        return str;
    }

    /* check for consecutive delimiters
    *if first char is delim, return delim
    */
    if (str[0]==delim[0]) {
        static_str = (str + 1);
        return (char *)delim;
    }

    /* terminate the string
    * this assignmetn requires char[], so str has to
    * be char[] rather than *char
    */
    str[index] = '\0';

    /* save the rest of the string */
    if ((str + index + 1)!=0)
        static_str = (str + index + 1);
    else
        static_str = 0;

        return str;
}

Below is an example usage...

  Example Usage
      char str[] = "A,B,,,C";
      printf("1 %s\n",zstring_strtok(s,","));
      printf("2 %s\n",zstring_strtok(NULL,","));
      printf("3 %s\n",zstring_strtok(NULL,","));
      printf("4 %s\n",zstring_strtok(NULL,","));
      printf("5 %s\n",zstring_strtok(NULL,","));
      printf("6 %s\n",zstring_strtok(NULL,","));

  Example Output
      1 A
      2 B
      3 ,
      4 ,
      5 C
      6 (null)

The library can be downloaded from Github https://github.com/fnoyanisi/zString

Answer 2

For: Hassan A. El-Seoudy

Your ticket is closed so I can't respond to it ^^'. But you can try this:

'
#include <stdlib.h>
#include <stdio.h>
#include <string.h>

int     countChar(char *str)
{
  int   count;
  int   i;

  i = 0;
  count = 0;
  while (str[i] != '=') // our delimiter character
    {
      i++;
      count++;
    }

  return (count);
}

void    split(char *str)
{
  int   i;
  int   j;
  int   count;
  int   restCount;
  char  *str1;
  char  *str2;

  i = 0;
  j = 0;
  count = countChar(str) - 1; // we have our str1 lenght, -1 for the ' '
  restCount = (strlen(str) - count) -1; // we have our str2 legnht, -1 for the ' '
  str1 = malloc(sizeof(char) * count);
  str2 = malloc(sizeof(char) * restCount);

  while(i < count)
    {
      str1[i] = str[i++];
    }
  i = i + 2; // to jump directly to the first char of our str2 (no ' = ')
  while (str[i])
    {
      str2[j++] = str[i++];
    }
  printf("str1 = %s, str2 = %s\n", str1, str2);
}

int     main()
{
  char  *str = "Xo = 100k";

  split(str);

  return (0);
}'

Answer 3

Method below will do all the job (memory allocation, counting the length) for you. More information and description can be found here - Implementation of Java String.split() method to split C string

int split (const char *str, char c, char ***arr)
{
    int count = 1;
    int token_len = 1;
    int i = 0;
    char *p;
    char *t;

    p = str;
    while (*p != '\0')
    {
        if (*p == c)
            count++;
        p++;
    }

    *arr = (char**) malloc(sizeof(char*) * count);
    if (*arr == NULL)
        exit(1);

    p = str;
    while (*p != '\0')
    {
        if (*p == c)
        {
            (*arr)[i] = (char*) malloc( sizeof(char) * token_len );
            if ((*arr)[i] == NULL)
                exit(1);

            token_len = 0;
            i++;
        }
        p++;
        token_len++;
    }
    (*arr)[i] = (char*) malloc( sizeof(char) * token_len );
    if ((*arr)[i] == NULL)
        exit(1);

    i = 0;
    p = str;
    t = ((*arr)[i]);
    while (*p != '\0')
    {
        if (*p != c && *p != '\0')
        {
            *t = *p;
            t++;
        }
        else
        {
            *t = '\0';
            i++;
            t = ((*arr)[i]);
        }
        p++;
    }

    return count;
}

How to use it:

int main (int argc, char ** argv)
{
    int i;
    char *s = "Hello, this is a test module for the string splitting.";
    int c = 0;
    char **arr = NULL;

    c = split(s, ' ', &arr);

    printf("found %d tokens.\n", c);

    for (i = 0; i < c; i++)
        printf("string #%d: %s\n", i, arr[i]);

    return 0;
}

Answer 4

If you are willing to use an external library, I can't recommend bstrlib enough. It takes a little extra setup, but is easier to use in the long run.

For example, split the string below, one first creates a bstring with the bfromcstr() call. (A bstring is a wrapper around a char buffer). Next, split the string on commas, saving the result in a struct bstrList, which has fields qty and an array entry, which is an array of bstrings.

bstrlib has many other functions to operate on bstrings

Easy as pie...

#include "bstrlib.h"
#include <stdio.h>
int main() {
  int i;
  char *tmp = "Hello,World,sak";
  bstring bstr = bfromcstr(tmp);
  struct bstrList *blist = bsplit(bstr, ',');
  printf("num %d\n", blist->qty);
  for(i=0;i<blist->qty;i++) {
    printf("%d: %s\n", i, bstr2cstr(blist->entry[i], '_'));
  }

}

Answer 5

In the above example, there would be a way to return an array of null terminated strings (like you want) in place in the string. It would not make it possible to pass a literal string though, as it would have to be modified by the function:

#include <stdlib.h>
#include <stdio.h>
#include <string.h>

char** str_split( char* str, char delim, int* numSplits )
{
    char** ret;
    int retLen;
    char* c;

    if ( ( str == NULL ) ||
        ( delim == '\0' ) )
    {
        /* Either of those will cause problems */
        ret = NULL;
        retLen = -1;
    }
    else
    {
        retLen = 0;
        c = str;

        /* Pre-calculate number of elements */
        do
        {
            if ( *c == delim )
            {
                retLen++;
            }

            c++;
        } while ( *c != '\0' );

        ret = malloc( ( retLen + 1 ) * sizeof( *ret ) );
        ret[retLen] = NULL;

        c = str;
        retLen = 1;
        ret[0] = str;

        do
        {
            if ( *c == delim )
            {
                ret[retLen++] = &c[1];
                *c = '\0';
            }

            c++;
        } while ( *c != '\0' );
    }

    if ( numSplits != NULL )
    {
        *numSplits = retLen;
    }

    return ret;
}

int main( int argc, char* argv[] )
{
    const char* str = "JAN,FEB,MAR,APR,MAY,JUN,JUL,AUG,SEP,OCT,NOV,DEC";

    char* strCpy;
    char** split;
    int num;
    int i;

    strCpy = malloc( strlen( str ) * sizeof( *strCpy ) );
    strcpy( strCpy, str );

    split = str_split( strCpy, ',', &num );

    if ( split == NULL )
    {
        puts( "str_split returned NULL" );
    }
    else
    {
        printf( "%i Results: \n", num );

        for ( i = 0; i < num; i++ )
        {
            puts( split[i] );
        }
    }

    free( split );
    free( strCpy );

    return 0;
}

There is probably a neater way to do it, but you get the idea.

Answer 6

Explode & implode - initial string remains intact, dynamic memory allocation

#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <errno.h>

typedef struct
{
    uintptr_t   ptr;
    int         size;
} token_t;

int explode(char *str, int slen, const char *delimiter, token_t **tokens)
{
    int i = 0, c1 = 0, c2 = 0;

    for(i = 0; i <= slen; i++)
    {
            if(str[i] == *delimiter)
            {
                c1++;
            }
    }

    if(c1 == 0)
    {
            return -1;
    }

    *tokens = (token_t*)calloc((c1 + 1), sizeof(token_t));
    ((*tokens)[c2]).ptr = (uintptr_t)str;

    i = 0; 
    while(i <= slen)
    {
        if((str[i] == *delimiter) || (i == slen))
        {
                ((*tokens)[c2]).size = (int)((uintptr_t)&(str[i]) - (uintptr_t)(((*tokens)[c2]).ptr));
                if(i < slen)
                {
                    c2++;
                    ((*tokens)[c2]).ptr = (uintptr_t)&(str[i + 1]);
                }
        }
        i++;
    }
    return (c1 + 1);
}

char* implode(token_t *tokens, int size, const char *delimiter)
{
    int     i, len = 0;
    char    *str;

    for(i = 0; i < len; i++)
    {
        len += tokens[i].size + 1;
    }

    str = (char*)calloc(len, sizeof(char));

    len = 0;
    for(i = 0; i < size; i++)
    {
        memcpy((void*)&str[len], (void*)tokens[i].ptr, tokens[i].size);
        len += tokens[i].size;
        str[(len++)] = *delimiter;
    }

    str[len - 1] = '\0';

    return str;
}

Usage:

int main(int argc, char **argv)
{
    int         i, c;
    char        *exp = "JAN,FEB,MAR,APR,MAY,JUN,JUL,AUG,SEP,OCT,NOV,DEC";
    token_t     *tokens;
    char        *imp;

    printf("%s\n", exp);

    if((c = explode(exp, strlen(exp), ",", &tokens)) > 0)
    {
        imp = implode(tokens, c, ",");
        printf("%s\n", imp);

        for(i = 0; i < c; i++)
        {
            printf("%.*s, %d\n", tokens[i].size, (char*)tokens[i].ptr, tokens[i].size);
        }
    }

    free((void*)tokens);
    free((void*)imp);
    return 0;
}