utf8编码检测非法字符

名字只能限定为中文,英语字母,数字.编码为utf8.

static bool _illegal_char(char c)
{
    if( (c >= 48 && c <=57) //数字
        || (c >= 65 && c <= 90)  //大写字母
        || (c >= 97 && c <= 122)) //小写字母
        return false;
    return true;
}

static bool has_illegal_char(unsigned char* str, int len)
{
    int i = -1, k = 1;
    while(i < len)
    {
        i += k;
        if(str[i] == '\0')
            break;

        if(str[i] < 0x80) // ascii 0-127位字符
        {
            if (_illegal_char(str[i]))
                return true;
            k = 1; // 0-127位占一字节
        }
        else if(str[i] < 0xE0)
        {
            if(str[i] < 0xC4) //ascii 128-255位字符
                if (_illegal_char(str[i]))
                    return true; 
            k = 2;
        }
        else if(str[i] < 0xF0)
            k = 3;
        else
            k = 4;
    }
    return false;
}

以下排除只限定中文为0x4e00-0x9fa5.强暴的做法.改就改吧.

static bool has_illegal_char(unsigned char* str, int len)
{
	int i = -1, k = 1;
	while(i < len)
	{
		i += k;
		if(str[i] == '\0')
			break;

		if(str[i] < 0x80) // ascii 0-127位字符
		{
			if (_illegal_char(str[i]))
				return true;
			k = 1; // 0-127位占一字节
		}
		else if(str[i] < 0xE0)
		{
			return true;
			k = 2;
		}
		else if(str[i] < 0xF0)
		{
			if(str[i] < 0xE4)//查表去
				return true;
			k = 3;
		}
		else
		{
			//unsigned short a = (str[i] | 0x7);
			//unsigned short b = (str[i+1] | 0x3F);
			//unsigned short c = (str[i+2] | 0x3F);
			//unsigned short d = (str[i+3] | 0x3F);
			if(str[i] > 0xF0 || str[i+1] > 0x89)//要改就改吧
				return true;
			if(str[i+1] == 0x89) {
				if(str[i+2] > 0xBE)
					return true;
				if(str[i+2] == 0xBE) {
					if(str[i+3] > 0xA5)
						return true;
				}
			}
			k = 4;
		}
	}
	return false;
}

　　

 

这篇文章:

http://www.ruanyifeng.com/blog/2007/10/ascii_unicode_and_utf-8.html

讲解utf8编码比较清楚.