（C/C++）UTF8字符串中字的切分

UTF-8 采用变长度字节来表示字符，理论上最多可以到 6 个字节长度。UTF-8 编码兼容了 ASC II(0-127)， 也就是说 UTF-8 对于 ASC II 字符的编码是和 ASC II 一样的。对于超过一个字节长度的字符，才用以下编码规范： 
左边第一个字节1的个数表示这个字符编码字节的位数，例如两位字节字符编码样式为为：110xxxxx 10xxxxxx； 三位字节字符的编码样式为：1110xxxx 10xxxxxx 10xxxxxx.；以此类推，六位字节字符的编码样式为：1111110x 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx。 xxx 的值由字符编码的二进制表示的位填入。 
1字节：0xxxxxxx 
2字节：110xxxxx 10xxxxxx 
3字节：1110xxxx 10xxxxxx 10xxxxxx 
4字节：11110xxx 10xxxxxx 10xxxxxx 10xxxxxx 
5字节：111110xx 10xxxxxx 10xxxxxx 10xxxxxx

///
# include <string.h>
# include <vector>

///
using namespace std;

///
void fnReadCharactersUTF8( const char* pszSentence, vector<string>& vec )
{
    int iLen;
    iLen = strlen( pszSentence );
 
   const char*   p;
 
     p = pszSentence;
 
     unsigned char * q;
 
     char    szCharacter[101];
     int     iChar;
 
     int     iNumChars;
     iNumChars = 0;
 
     vec.clear();
 
     string  strCharacter;
 
     while ( p != NULL && strlen( p ) > 0 )
     {
         q = ( unsigned char * ) p;
         if ( q[0] < 0x80 )
         {
             //p[ 0 ] must be an ASCII character
             iChar = 0;
             szCharacter[iChar++] = p[0];
             p++;
             q = ( unsigned char * ) p;
             while ( p != NULL && q[0] < 0x80 )
             {
                 szCharacter[iChar++] = p[0];
                 p++;
                 q = ( unsigned char * ) p;
             }
             szCharacter[iChar] = '\0';
 
             vec.push_back( string( szCharacter ) );
 
             iNumChars++;
         }
         else if ( q[0] < 0xC0 )
         {
             //invalid char between 0x80 and 0xC0
             p++;
         }
         else if ( q[0] < 0xE0 )
         {
             //two chars
             szCharacter[0] = p[0];
             szCharacter[1] = p[1];
             szCharacter[2] = '\0';
             p = p + 2;
 
             strCharacter = string( szCharacter );
             vec.push_back( strCharacter );
 
             iNumChars++;
         }
         else if ( q[0] < 0xF0 )
         {
             //three chars
             szCharacter[0] = p[0];
             szCharacter[1] = p[1];
             szCharacter[2] = p[2];
             szCharacter[3] = '\0';
             p = p + 3;
 
             strCharacter = string( szCharacter );
             vec.push_back( strCharacter );
 
             //printf( "%s ", strCharacter.c_str( ) );
 
             iNumChars++;
         }
         else if ( q[0] < 0xF8 )
         {
             //four chars
             p += 4;
         }
         else if ( q[0] < 0xFC )
         {
             //five chars
             p += 5;
         }
         else if ( q[0] < 0xFE )
         {
             //6 chars
             p += 5;
         }
         else
         {
             //>=0xFE
             p++;
         }
     }
 }
 
 // FILE END ///