I'm a beginner in C and I just created the split () function of Python in that language.
The only missing part is to pass the delimiters as a parameter, instead of using only spaces / tabs. But it would be quite easy by modifying isDelimiter and it is not important.
For those who have not used split (), here is an example:
>>> "test test2 ? .. stack overflow ".split()
('test', 'test2', '?', '..', 'stack', 'overflow')
I have sufficiently documented it to not need a lot of explanations, but if something is not clear, thank you for letting me know. All comments and suggestions are welcome, also for the design itself 🙂
#include
#define TRUE 1
#define FALSE 0
#define DEFAULT_BUFSIZE 512
static inline int isDelimiter(char s) {
return s == ' ' || s == 't';
}
// Splits a string with elements delimited by spaces or tabs into an array
// of strings. It works very similarly to Python's split() function.
int parser(char *source, char ***destination) {
// The auxiliar variable `aux` will save the array contents, rather than
// using *destination. Its elements length is initially DEFAULT_BUFSIZE
// so that realloc() doesn't have to be called everytime a character
// is copied. The memory used by each element will be reduced to the
// minimum possible afterwards.
// The most efficient solution would actually be having two buffer
// variables: one for the element size and another for the array itself.
// But currently this isn't neccessary.
size_t bufsize = DEFAULT_BUFSIZE;
char **aux = malloc(sizeof(char *));
// The source string is iterated and its contents are copied to the aux
// array, so we need 3 counters:
// * `len` is the array length
// * `iArr` is the array's current element index.
// * `iStr` is the source array's index.
size_t len = 1;
int iStr = 0;
int iArr = 0;
// If there's more than 1 delimiter in a row, a new element shouldn't be
// created. This is why `newEl` has to be created. It acts as a boolean
// that indicates when a new element should start.
int newEl = TRUE;
// The first element of the array is created. The rest will be allocated
// inside the loop.
aux(0) = malloc(bufsize * sizeof(char));
while (source(iStr) != ' ') {
if (isDelimiter(source(iStr)) && !newEl) {
// The used memory is reduced to what's actually being used.
aux(len-1) = realloc(aux(len-1), (iArr+1) * sizeof(char));
// The current element ends.
aux(len-1)(iArr) = ' ';
iArr = 0;
++len;
// Don't come back here until a character other than a delimiter
// is found.
newEl = TRUE;
// The new element is allocated.
aux = realloc(aux, len * sizeof(char *));
aux(len-1) = malloc(bufsize * sizeof(char));
} else if (!isDelimiter(source(iStr))) {
// The source character is copied to the destination.
aux(len-1)(iArr) = source(iStr);
++iArr;
// From now on, a new element can be started.
newEl = FALSE;
// The buffer is enlargened if neccessary.
if (iArr >= bufsize) {
bufsize += DEFAULT_BUFSIZE;
aux(len-1) = realloc(aux(len-1), bufsize * sizeof(char *));
}
}
++iStr;
}
// The last element's size has to be reduced outside of the loop, and a
// ' ' is added to finish it. If newEl is true, it means the last element
// is filled with delimiters and it shouldn't be included in the array.
if (newEl) {
--len;
aux(len) = NULL;
} else {
aux(len-1) = realloc(aux(len-1), (iArr+1) * sizeof(char));
aux(len-1)(iArr) = ' ';
// Finally, the last element is NULL.
aux(len) = NULL;
}
// Saving the destination variable and returning its length.
*destination = aux;
return len;
}
I've also made a small test file:
#include // fgets()...
#include // strlen()
#include // size_t, atoi...
#include "parser.h"
#define MAX 1024
int main() {
char str(MAX);
printf("Introduce numbers delimited by spaces or tabs: ");
fgets(str, MAX, stdin);
// Removing the 'n' from fgets()
str(strlen(str)-1) = ' ';
char **nums;
size_t len = parser(str, &nums);
if (len == 0) {
fprintf(stderr, "No input.n");
exit(1);
}
int sum = 0;
for (int i = 0; i < len; ++i)
sum += atoi(nums(i));
printf("Sum: %dn", sum);
free(nums);
return 0;
}
In addition, here is a GodBolt code snippet: https://godbolt.org/z/rGtvN9
