UTF-8

来源:互联网 发布:python 10分钟 编辑:程序博客网 时间:2024/03/29 09:11

编码

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 10xxxxxx 
6字节 1111110x 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx 


#define UTF8_COMPUTE(Char, Mask, Len)        \if (Char < 128)                \{                        \Len = 1;                    \Mask = 0x7f;                \}                        \else if ((Char & 0xe0) == 0xc0)        \{                        \Len = 2;                    \Mask = 0x1f;                \}                        \else if ((Char & 0xf0) == 0xe0)        \{                        \Len = 3;                    \Mask = 0x0f;                \}                        \else if ((Char & 0xf8) == 0xf0)        \{                        \Len = 4;                    \Mask = 0x07;                \}                        \else if ((Char & 0xfc) == 0xf8)        \{                        \Len = 5;                    \Mask = 0x03;                \}                        \else if ((Char & 0xfe) == 0xfc)        \{                        \Len = 6;                    \Mask = 0x01;                \}                        \else                        \Len = -1;


0 0
原创粉丝点击