[C/C++]_[初級]_[替換過濾utf8字符串裡無效字符]

場景:

1. 分析數據時,獲取到的數據是字符串,但是有可能不是正確的完整的utf8字符串,打印出來或輸出到文件時表現出來的就是顯示亂碼.

這時候就需要過濾掉非法字符使utf8字符串能正確顯示, 比如把非法字符替換為#

代碼:

1. 這個函數的特性是1個個字符判斷, 適合任意長度,任意構造的 utf8 (無效)字符串.

bool IREUtil::FilterUtf8(unsigned char * string,int length)
{
	if(!string)
	{
		return false;
	}
		
	unsigned char * bytes = string;
	unsigned char * end = bytes+length;

	
	//10xxxxxx 應該出現個數
	int count_s = 0;
	//10xxxxxx 剩余個數
	int minus_s = 0;
	while(bytes != end)
	{
		if(bytes[0] > 0xF7)
		{
			if(minus_s)
			{
				int m = count_s-minus_s+1;
				memset((void*)(bytes-m),'#',m);
			}
			minus_s = 0;
			count_s = 0;

			bytes[0] = '#';
			bytes+=1;
			continue;
		}

		if(bytes[0] <= 0x7F)
		{
			if(minus_s)
			{
				int m = count_s-minus_s+1;
				memset((void*)(bytes-m),'#',m);
			}
			minus_s = 0;
			count_s = 0;

			//過濾掉不可見字符	
			if((bytes[0] == 0x09 || bytes[0] == 0x0A || bytes[0] == 0x0D ||
				(0x20 <= bytes[0] && bytes[0] <= 0x7E))) 
			{
				;
			}else
			{
				bytes[0] = '#';
			}

			bytes+=1;
			continue;
		}

		if((bytes[0] & 0xF8) == 0xF0)
		{
			// 1111 0XXX
			if(minus_s)
			{
				int m = count_s-minus_s+1;
				memset((void*)(bytes-m),'#',m);
			}
			count_s = 3;
			minus_s = 3;
			bytes+=1;
			continue;
		}

		if((bytes[0] & 0xF0) == 0xE0)
		{
			// 1110 XXXX
			if(minus_s)
			{
				int m = count_s-minus_s+1;
				memset((void*)(bytes-m),'#',m);
			}
			count_s = 2;
			minus_s = 2;
			bytes+=1;
			continue;
		}

		if((bytes[0] & 0xE0) == 0xC0)
		{
			// 110X XXXX
			if(minus_s)
			{
				int m = count_s-minus_s+1;
				memset((void*)(bytes-m),'#',m);
			}
			count_s = 1;
			minus_s = 1;
			bytes+=1;
			continue;
		}
		if((bytes[0] & 0xC0) == 0x80)
		{
			// 10XX XXXX
			if(minus_s)
			{
				--minus_s;
			}else
			{
				bytes[0] = '#';
			}
			bytes+=1;
			continue;
		}
		
		if(minus_s)
		{
			int m = count_s-minus_s+1;
			memset((void*)(bytes-m),'#',m);
		}else
		{
			bytes[0] = '#';
		}
		minus_s = 0;
		count_s = 0;
		bytes+=1;
		continue;
	}

	if(minus_s)
	{
		int m = count_s-minus_s+1;
		memset((void*)(bytes-m),'#',m);
	}
	return true;
}

原文地址沒留下:

bool IREUtil::is_utf8(const unsigned char * string,int length)
{
	if(!string)
	{
		return false;
	}
		
	const unsigned char * bytes = (const unsigned char *)string;
	const unsigned char * end = bytes+length;
	while(bytes != end)
	{
		if( (// ASCII
			// use bytes[0] <= 0x7F to allow ASCII control characters
			bytes[0] == 0x09 ||
			bytes[0] == 0x0A ||
			bytes[0] == 0x0D ||
			(0x20 <= bytes[0] && bytes[0] <= 0x7E)
			)
			) {
				bytes += 1;
				continue;
		}

		if( (// non-overlong 2-byte
			(0xC2 <= bytes[0] && bytes[0] <= 0xDF) &&
			(0x80 <= bytes[1] && bytes[1] <= 0xBF)
			)
			) {
				bytes += 2;
				continue;
		}

		if( (// excluding overlongs
			bytes[0] == 0xE0 &&
			(0xA0 <= bytes[1] && bytes[1] <= 0xBF) &&
			(0x80 <= bytes[2] && bytes[2] <= 0xBF)
			) ||
			(// straight 3-byte
			((0xE1 <= bytes[0] && bytes[0] <= 0xEC) ||
			bytes[0] == 0xEE ||
			bytes[0] == 0xEF) &&
			(0x80 <= bytes[1] && bytes[1] <= 0xBF) &&
			(0x80 <= bytes[2] && bytes[2] <= 0xBF)
			) ||
			(// excluding surrogates
			bytes[0] == 0xED &&
			(0x80 <= bytes[1] && bytes[1] <= 0x9F) &&
			(0x80 <= bytes[2] && bytes[2] <= 0xBF)
			)
			) {
				bytes += 3;
				continue;
		}

		if( (// planes 1-3
			bytes[0] == 0xF0 &&
			(0x90 <= bytes[1] && bytes[1] <= 0xBF) &&
			(0x80 <= bytes[2] && bytes[2] <= 0xBF) &&
			(0x80 <= bytes[3] && bytes[3] <= 0xBF)
			) ||
			(// planes 4-15
			(0xF1 <= bytes[0] && bytes[0] <= 0xF3) &&
			(0x80 <= bytes[1] && bytes[1] <= 0xBF) &&
			(0x80 <= bytes[2] && bytes[2] <= 0xBF) &&
			(0x80 <= bytes[3] && bytes[3] <= 0xBF)
			) ||
			(// plane 16
			bytes[0] == 0xF4 &&
			(0x80 <= bytes[1] && bytes[1] <= 0x8F) &&
			(0x80 <= bytes[2] && bytes[2] <= 0xBF) &&
			(0x80 <= bytes[3] && bytes[3] <= 0xBF)
			)
			) {
				bytes += 4;
				continue;
		}

		return false;
	}

	return true;
}

歡迎指正!