统计UTF-8编码方式字符串中的符号个数

方法1：转载自： http://blog.csdn.net/chrisniu1984/article/details/7359908

int utf8_wchar_count(char *buffer, int len)
{
	#define UTF8_ASCII(byte) ( ((unsigned char)(byte)>=0x00)&&((unsigned char)(byte)<=0x7F) )  
	#define UTF8_FIRST(byte) ( ((unsigned char)(byte)>=0xC0)&&((unsigned char)(byte)<=0xFD) )  
	#define UTF8_OTHER(byte) ( ((unsigned char)(byte)>=0x80)&&((unsigned char)(byte)<=0xBF) )  

	char *p = 0;  
	long count = 0;  

	if (!buffer || len <= 0) 
	{  
		return 0;  
	}  

	for(p=buffer; p<buffer+len; p++) 
	{  
		if (UTF8_ASCII(*p) || (UTF8_FIRST(*p))) 
		{  
			count++;  
		}  
	}  

	return count;  
}

方法2：转载自：http://www.tuicool.com/articles/v67jay

int get_utf8_count(const std::string &input)
{
	int length = 0;
	for (size_t i = 0, len = 0; i != input.length(); i += len) 
	{
		unsigned char byte = input[i];

		if (byte >= 0xFC)		
			len = 6;  
		else if (byte >= 0xF8)
			len = 5;
		else if (byte >= 0xF0)
			len = 4;
		else if (byte >= 0xE0)
			len = 3;
		else if (byte >= 0xC0)
			len = 2;
		else
			len = 1;

		length ++;
	}   
	return length;
}