utf82u.c

utf-8和unicode的互转的c代码

#include <stdio.h>

int
utf82u(char *str, int * chPtr)
/* str is the UTF8 next character pointer */
/* chPtr is the int for the result */
{
  int byte;
  char *p;

  /* HTML4.0 entities in decimal form, e.g. &#197; */
  /*           or in hexadecimal form, e.g. &#x6C34; */
  byte = *((unsigned char *) str);
  if (byte == '&')
    {
      int i, n = 0;

      byte = *((unsigned char *) (str + 1));
      if (byte == '#')
	{
          byte = *((unsigned char *) (str + 2));
          if (byte == 'x' || byte == 'X')
            {
              for (i = 3; i < 8; i++)
                {
                  byte = *((unsigned char *) (str + i));
                  if (byte >= 'A' && byte <= 'F')
                    byte = byte - 'A' + 10;
                  else if (byte >= 'a' && byte <= 'f')
                    byte = byte - 'a' + 10;
                  else if (byte >= '0' && byte <= '9')
                    byte = byte - '0';
                  else
                    break;
                  n = (n * 16) + byte;
                }
            }
          else
            {
	      for (i = 2; i < 8; i++)
	        {
	          byte = *((unsigned char *) (str + i));
	          if (byte >= '0' && byte <= '9')
	            n = (n * 10) + (byte - '0');
	          else
		    break;
		}
	    }
	  if (byte == ';')
	    {
	      *chPtr = (int) n;
	      return ++i;
	    }
	}
      else
        {
		/*fix me*/
		*chPtr = 0;
		return 1;
        }
    }

  /*
   * Unroll 1 to 3 byte UTF-8 sequences, use loop to handle longer ones.
   */

  byte = *((unsigned char *) str);

  if (byte < 0xC0)
    {
      /*
       * Handles properly formed UTF-8 characters between
       * 0x01 and 0x7F.  Also treats \0 and naked trail
       * bytes 0x80 to 0xBF as valid characters representing
       * themselves.
       */

      *chPtr = (int) byte;
      return 1;
    }
  else if (byte < 0xE0)
    {
      if ((str[1] & 0xC0) == 0x80)
	{
	  /*
	   * Two-byte-character lead-byte followed
	   * by a trail-byte.
	   */

	  *chPtr = (int) (((byte & 0x1F) << 6) | (str[1] & 0x3F));
	  return 2;
	}
      /*
       * A two-byte-character lead-byte not followed by trail-byte
       * represents itself.
       */

      *chPtr = (int) byte;
      return 1;
    }
  else if (byte < 0xF0)
    {
      if (((str[1] & 0xC0) == 0x80) && ((str[2] & 0xC0) == 0x80))
	{
	  /*
	   * Three-byte-character lead byte followed by
	   * two trail bytes.
	   */

	  *chPtr = (int) (((byte & 0x0F) << 12)
				  | ((str[1] & 0x3F) << 6) | (str[2] & 0x3F));
	  return 3;
	}
      /*
       * A three-byte-character lead-byte not followed by
       * two trail-bytes represents itself.
       */

      *chPtr = (int) byte;
      return 1;
    }

  *chPtr = (int) byte;
  return 1;
}



int main()
{
	char str[] = {0xe8, 0x87, 0xba, 0xe7, 0x81, 0xa3, 0x00};
	char *next = str;
	int uni;
	int len;
	int i;

	for (i=0; *next; i++)
	{
		len = utf82u(next, &uni);
		next += len;
		printf("%d --0x%x\n", len, uni);

	}
}