Reading UTF-8 char by char in C

#include <stdint.h> #include <stdio.h> #include <stdlib.h>  // https://stackoverflow.com/a/44776334 int8_t utf8_length(char c) { // 4-byte character (11110XXX) if ((c & 0b11111000) == 0b11110000) return 4; // 3-byte character (1110XXXX) if ((c & 0b11110000) == 0b11100000) return 3; // 2-byte character (110XXXXX) if ((c & 0b11100000) == 0b11000000) return 2; // 1-byte ASCII character (0XXXXXXX) if ((c & 0b10000000) == 0b00000000) return 1; // Probably a 10XXXXXXX continuation byte return -1; } void main () { const char* filepath = "example.txt"; FILE* file = fopen(filepath, "r"); if (!file) { perror(filepath); exit(1); } char c; for(;;) { c = getc(file); if (c == EOF) break; putc(c, stdout); int8_t length = utf8_length(c); while (--length) { c = getc(file); putc(c, stdout); } getchar(); } fclose (file); } 

Hello, World! 🌍🚀 Hello ¡Hola! Ça va? 你好 こんにちは 안녕하세요 ©®™✓✗ 😄😢😎🔥✨ €𐍈𒀭