Simple converter from utf-8 unicode character to its corresponding decimal value

utf-8ToInt.c

int getDecimalOfUtf8(char * utfPointer){
      int outPut = utfPointer[0];                             //sets the final output number to the value of the first byte of the utf-8 code
      int numStarting1 = 0;                                   //tracks number of 0's at beggining of character to see if utf-8
      while ((utfPointer[0] << numStarting1 & 0x80) ? 1 : 0)  //shifts bits of first byte of utfPointer and checks if the MSB is 1 or 0
      {
          numStarting1++;                                     //increments numStarting1
      }
  
      //At this point numStarting1 could be returned to know the length in bytes of the unicode character
  
      if(numStarting1 != 0){                                  //If there are no starting 1s then it is a regular ascii character
          int mask = 32;                                      //Create a mask to keep only the bits needed from the first byte of the utf-8 code
          for(int i = 0; i < numStarting1-2; i++){            //For each additional 1 at the beggining of the first byte of the utf code less bits are needed and the mask needs to be smaller
            mask /= 2;
          }
          mask -= 1;                                          //The final masked value needs to have one subtracted so there are 1's in the right places for the mask (ie 32 = 100000 and 31 = 11111)
          outPut = utfPointer[0] & mask;                      //Mask the value in input to keep only the bits important for the utf-8 code
          for (int x = 1; x < numStarting1; x++)              //The number of 0s at the begging of the first byte of the utf-8 code tell us how many additional bytes we need for the full code
          {
              outPut = outPut << 6;                           //We shift the output value by 6 as the first two bits of each additional byte are for indexing
              outPut = outPut | (utfPointer[x] & 0x3F);       //The shifted value is then bitwise ored with last 6 bits of the next bytes in the pointer
          }
      }
      return outPut;                                          //Once all of the additional bytes have been used up the final value is returned as output
}