Function utf8makevalid

3rd/utf8/include/utf8.h:1102–1165

}

int utf8makevalid(utf8_int8_t *str, const utf8_int32_t replacement) {
  utf8_int8_t *read = str;
  utf8_int8_t *write = read;
  const utf8_int8_t r = (utf8_int8_t)replacement;
  utf8_int32_t codepoint = 0;

  if (replacement > 0x7f) {
    return -1;
  }

  while ('\0' != *read) {
    if (0xf0 == (0xf8 & *read)) {
      // ensure each of the 3 following bytes in this 4-byte
      // utf8 codepoint began with 0b10xxxxxx
      if ((0x80 != (0xc0 & read[1])) || (0x80 != (0xc0 & read[2])) ||
          (0x80 != (0xc0 & read[3]))) {
        *write++ = r;
        read++;
        continue;
      }

      // 4-byte utf8 code point (began with 0b11110xxx)
      read = utf8codepoint(read, &codepoint);
      write = utf8catcodepoint(write, codepoint, 4);
    } else if (0xe0 == (0xf0 & *read)) {
      // ensure each of the 2 following bytes in this 3-byte
      // utf8 codepoint began with 0b10xxxxxx
      if ((0x80 != (0xc0 & read[1])) || (0x80 != (0xc0 & read[2]))) {
        *write++ = r;
        read++;
        continue;
      }

      // 3-byte utf8 code point (began with 0b1110xxxx)
      read = utf8codepoint(read, &codepoint);
      write = utf8catcodepoint(write, codepoint, 3);
    } else if (0xc0 == (0xe0 & *read)) {
      // ensure the 1 following byte in this 2-byte
      // utf8 codepoint began with 0b10xxxxxx
      if (0x80 != (0xc0 & read[1])) {
        *write++ = r;
        read++;
        continue;
      }

      // 2-byte utf8 code point (began with 0b110xxxxx)
      read = utf8codepoint(read, &codepoint);
      write = utf8catcodepoint(write, codepoint, 2);
    } else if (0x00 == (0x80 & *read)) {
      // 1-byte ascii (began with 0b0xxxxxxx)
      read = utf8codepoint(read, &codepoint);
      write = utf8catcodepoint(write, codepoint, 1);
    } else {
      // if we got here then we've got a dangling continuation (0b10xxxxxx)
      *write++ = r;
      read++;
      continue;
    }