Function AR_SUBSTRING

src/arithmetic/string_funcs/string_funcs.c:151–211

returns a substring of the original string, beginning with a 0-based index start and length.

// returns a substring of the original string, beginning with a 0-based index start and length.
SIValue AR_SUBSTRING(SIValue *argv, int argc, void *private_data) {
	/*
	    argv[0] - original string
	    argv[1] - start position
	    argv[2] - length
	    If length is omitted, the function returns the substring starting at the position given by start and extending to the end of original.
	    If either start or length is null or a negative integer, an error is raised.
	    If start is 0, the substring will start at the beginning of original.
	    If length is 0, the empty string will be returned.
	*/
	if(SIValue_IsNull(argv[0])) return SI_NullVal();

	int64_t length;
	const char   *original     = argv[0].stringval;
	const int64_t original_len = strlen(original);
	const int64_t start        = argv[1].longval;

	/* Make sure start doesn't overreach. */
	if(start < 0) {
		ErrorCtx_SetError("start must be a non-negative integer");
		return SI_NullVal();
	}

	if(start >= original_len) {
		return SI_ConstStringVal("");
	}

	const int64_t suffix_len = original_len - start;
	if(argc == 2) {
		length = suffix_len;
	} else {
		length = argv[2].longval;
		if(length < 0) {
			ErrorCtx_SetError("length must be a non-negative integer");
			return SI_ConstStringVal("");
		}

		/* Make sure length does not overreach. */
		length = MIN(length, suffix_len);
	}

	utf8proc_int32_t c;
	// find the start position to copy from
	const char *start_p = original;
	for (int i = 0; i < start; i++) {
		start_p += utf8proc_iterate((const utf8proc_uint8_t *)start_p, -1, &c);
	}

	// find the end position
	const char *end_p = start_p;
	for (int i = 0; i < length; i++) {
		end_p += utf8proc_iterate((const utf8proc_uint8_t *)end_p, -1, &c);
	}

	int len = end_p - start_p;
	char *substring = rm_malloc((len + 1) * sizeof(char));
	strncpy(substring, start_p, len);
	substring[len] = '\0';