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

// 0XXXXXXX (1)
// 110XXXXX (2)
// 1110XXXX (3)
// 11110XXX (4)

// 10XXXXXX  (continuing byte)



// 11010111 10101111 11101101 10111100 10001011 01001101 00000000
//                                                       ^                                                                                                                                                                 
size_t utf8_strlen(char *string) {
    size_t num_code_points = 0;
    for (char *code_point = string; *code_point != '\0';) {
        if ((*code_point & 0xF8) == 0xF0) {
            // 4-byte head byte
            code_point += 4;
        } else if ((*code_point & 0xF0) == 0xE0) {
            // 3-byte head byte
            code_point += 3;
        } else if ((*code_point & 0xE0) == 0xC0) {
            // 2-byte head byte
            code_point += 2;
        } else if ((*code_point & 0xC0) == 0x80) {
            // INVALID STRING
            // tail byte - should not be here
            // as we should be moving from head byte to head byte
            fprintf(stderr, "Invalid UTF-8 string: \"%s\"\n", string);
            fprintf(stderr, "Found a tail byte when head byte was expected\n");
            assert(0);
        } else if ((*code_point & 0x80) == 0x00) {
            // ASCII
            code_point += 1;
        } else {
            // INVALID STRING
            // this is not a valid UTF-8 byte
            fprintf(stderr, "Invalid UTF-8 string: \"%s\"\n", string);
            fprintf(stderr, "Head byte indicates invalid length\n");
            assert(0);
        }
        num_code_points++;
    }

    return num_code_points;
}

int main(void) {
    char *s = "😊";
    printf("Strlen of %s is %ld...hmm...\n", s, strlen(s));
    printf("Correct strlen of %s is %ld...yay!\n", s, utf8_strlen(s));
    return 0;
}