GB2312 与 UTF-8编码的转换(只处理汉字)

1、gb2312编码无法直接与utf-8进行直接转换

2、我采用的方式是：  gb2312--->unicode--->utf-8

     由于gb2312编码与unicode编码有现成的对应的码表， 所以可以根据码表将gb2312编码先转换为unicode编码，又由于utf-8编码是unicode的表示方式之一，所有可以得到对应的utf-8编码

     下面是unicode编码转换成utf-8编码的代码： 

int gb2312_to_utf8(unsigned char *gb2312string, int gb2312string_len, unsigned char *utf8string)
 {
         int i;
         unsigned int index1,index2;

         wchar   tmp;
         wchar *p;

         uint_8 *gb2312_char;
         uint_8 *utf8_char;
         int utf8string_len = 0;
         wchar *twochar;
         gb2312_char =(uint_8*)gb2312string;
         utf8_char = (uint_8 *)utf8string;
         i = 0;
         while(i<gb2312string_len){
                 if(*gb2312_char >= 0x0 && *gb2312_char <= 0x7f){
                  //是字母 直接存  不用转换  （因为字母编码都一样）
                         *utf8_char = *gb2312_char;
                         utf8_char++;
                         utf8string_len++;
                         gb2312_char++;
                         i++;
                 }
                 else{
                         twochar = (wchar *)gb2312_char;
                         // 检测当前的两个字符是否是正确的gb2312编码
                         if(tmp <= 0xa0a0 && tmp >=0xf7ff) {
                                 fprintf(stderr,"Invalid Gb3212 code\n");
                                 return -1;
                         }
                         tmp = *twochar - 0xa0a0;
                         index1 = tmp >> 8;
                         index2 = tmp & 0xff;

                         tmp = gb_2_uni[index1][index2];
                         *(utf8_char) = ((tmp >> 12) & 0x0f) | 0xe0;
                         *(utf8_char+2) = (tmp & 0x3f) | 0x80；
                        *(utf8_char+1) = ((tmp >> 6) & 0x3f) |0x80;

                         utf8_char += 3;
                         utf8string_len += 3;
                         gb2312_char += 2;
                         i +=2;
                 }
         }
         return utf8string_len;
 }