过滤网页中的全角半角字母的程序

// 把双字节汉字转化为十六进制字符串
int chinese_to_hex(char *word ,char *hex)
{
	 char temp_char[17];
	 memset( temp_char, 0, 17 );
	 
   sprintf( temp_char, "%X%X", word[ 0 ], word[ 1 ] );
   sprintf( hex, "%c%c%c%c", temp_char[6], temp_char[7], temp_char[14], temp_char[15] );
   
   return 0;
}

// 分割字符为字单元
int get_single_word( char *sz_text, char**word_list , long int &word_count )
{
	char temp[3];
	int dcount=0;
	char hex[4];

  memset( hex, 0, 4 );
	memset(temp ,0 ,sizeof( temp ) );
	                                                                       
  long int i, nLen = strlen( sz_text ); 
  word_count = 0;                                                                               
  for(i = 0; i < nLen; i++)                                                                                             
  {                                                                                                                
    if((int)sz_text[i] >= 0 && (int)sz_text[i] <= 127) //半角[ 英文字母 ]
    {  
    	 if( ( (int)sz_text[i] >= 48 && (int)sz_text[i]  <= 57  )  ||
    	 	   ( (int)sz_text[i] >=65  && (int)sz_text[i]  <= 90  )  ||
    	 	   ( (int)sz_text[i] >= 97 && (int)sz_text[i]  <= 122 )  ||  
    	 	     (int)sz_text[i] ==46  || (int)sz_text[i]  == 32  ) 
    	 {
    	    temp[0] = sz_text[i];
    	    dcount = 0;
    	    if((int)sz_text[i] ==46  || (int)sz_text[i]  == 32)
    	    {
    	     	 dcount++;
    	    }
    	 }else
    	 {
    	 	 if( dcount == 0 )
    	 	 {
    	 	   temp[0] = ',';
    	 	   dcount++;
    	 	 }
    	 }
    }                                                                                       
    else //全角字符[ 中文是2个字节 ] 
    {                           
      temp[ 0 ] = sz_text[i]; temp[ 1 ] = sz_text[ i + 1 ];         
      chinese_to_hex( temp, hex );
      
      if( ( strtol( hex, NULL, 16 ) >= 0XA1A0 && strtol( hex, NULL, 16 ) <=0XA3AF ) || 
      	  ( strtol( hex, NULL, 16 ) >= 0XA3BA && strtol( hex, NULL, 16 ) <=0XA3C0 ) ||
      	  ( strtol( hex, NULL, 16 ) >= 0XA3DB && strtol( hex, NULL, 16 ) <=0XA3E0 ) ||
      	  ( strtol( hex, NULL, 16 ) >= 0XA3FB && strtol( hex, NULL, 16 ) <=0XA3FF ) ||
      	  ( strtol( hex, NULL, 16 ) >= 0XA4A0 && strtol( hex, NULL, 16 ) <=0XA996 )  )
      {
      	 memset( temp, 0, 3);
      	 if( dcount == 0 )
    	 	 {
      	   temp[ 0 ]=',';
      	   dcount++;
      	 }
      }else
      {
      	dcount=0;
      }
      i++;  
    }
    sprintf( word_list[ word_count ], "%s", temp );
    word_count++;
    memset( temp , 0, sizeof( temp ) );  
    memset( hex, 0, 4 );                                                                                                     
  }
  return 0;
}

// 文本杂志过滤
int filter_chars_text( char *in_put_text , char *out_put_text )
{
	 char *word_list[ BLOCKS_WORD_LEN ];
   long int word_count = 0; 
   char sin_temp[ BLOCKS_WORD_LEN ];
   int sin_count=0;
   
   memset( out_put_text, 0, sizeof( out_put_text ) );
   memset( sin_temp, 0, sizeof( sin_temp ) );
   
   for(int i=0; i<BLOCKS_WORD_LEN; i++)
   {
      word_list[i] =new char[3];
      memset( word_list[i], 0, 3 );
   }   
   get_single_word( in_put_text, word_list, word_count );
   
   for( int i = 0; i < BLOCKS_WORD_LEN; i++ )
   {
   	  if( i < word_count )
   	  {
   	  	if( (int)(word_list[i][0]) >= 0 && (int)(word_list[i][0]) <= 127)
   	  	{
   	  	    sin_temp[sin_count] =  word_list[ i ][0];
   	  	    sin_count++;
   	  	}else
   	  	{
   	  	  if( strlen( sin_temp ) >0 && sin_temp!=NULL )	
   	  	  {
   	  	  	 if(sin_count < 9)
   	  	  	 {
   	  		      strcat( out_put_text, sin_temp );
   	  		      strcat( out_put_text, word_list[ i ] );
   	  		      
   	  		   }else
   	  		   {
   	  		   	  strcat( out_put_text, word_list[ i ] );
   	  		   }
   	  		}else
   	  		{
   	  			 strcat( out_put_text, word_list[ i ] );
   	  		}
   	  		
   	  		sin_count=0;
   	  		memset( sin_temp, 0, BLOCKS_WORD_LEN );
   	  	}
   	  }
      delete word_list[ i ];
   }
   return 0;
}