- /*!
- * \def PUT_UTF8(val, tmp, PUT_BYTE)
- * converts a 32-bit unicode character to its UTF-8 encoded form (up to 4 bytes long).
- * \param val is an input only argument and should be of type uint32_t. It holds
- * a ucs4 encoded unicode character that is to be converted to UTF-8. If
- * val is given as a function it's executed only once.
- * \param tmp is a temporary variable and should be of type uint8_t. It
- * represents an intermediate value during conversion that is to be
- * outputted by PUT_BYTE.
- * \param PUT_BYTE writes the converted UTF-8 bytes to any proper destination.
- * It could be a function or a statement, and uses tmp as the input byte.
- * For example, PUT_BYTE could be "*output++ = tmp;" PUT_BYTE will be
- * executed up to 4 times for values in the valid UTF-8 range and up to
- * 7 times in the general case, depending on the length of the converted
- * unicode character.
- */
- #define PUT_UTF8(val, tmp, PUT_BYTE)\
- {\
- int bytes, shift;\
- uint32_t in = val;\
- if (in < 0x80) {\
- tmp = in;\
- PUT_BYTE\
- } else {\
- bytes = (av_log2(in) + 4) / 5;\
- shift = (bytes - 1) * 6;\
- tmp = (256 - (256 >> bytes)) | (in >> shift);\
- PUT_BYTE\
- while (shift >= 6) {\
- shift -= 6;\
- tmp = 0x80 | ((in >> shift) & 0x3f);\
- PUT_BYTE\
- }\
- }\
- }
复制代码
- static inline int av_log2(unsigned int v)
- {
- int n;
- n = 0;
- if (v & 0xffff0000) {
- v >>= 16;
- n += 16;
- }
- if (v & 0xff00) {
- v >>= 8;
- n += 8;
- }
- n += ff_log2_tab[v];
- return n;
- }
复制代码- const uint8_t ff_log2_tab[256]={
- 0,0,1,1,2,2,2,2,3,3,3,3,3,3,3,3,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,
- 5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,
- 6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,
- 6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,
- 7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,
- 7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,
- 7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,
- 7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7
- };
复制代码
这里就是get_ucs2str()所使用的所有的宏和函数等,没有发现它给结尾加'\0'。原来的字符串也是有'\0'的。
我用编译后的程序连接mms:地址时,就是通过调用asf_read_head() (in readhead.c file)将数据按照结构的要求进行读取,如果title,author等所有的内容都存在的时候,则能和mplayer在控制台中显示的一样,如果有些串的内容不存在,就会出现乱码,或者输出信息类型不全问题。
通过分分析HEX分析文件,对于空和一般的字符用的长度不同 |