http://www.oschina.net/code/snippet_179574_15065
按照如下的编码方式，对UTF8和UTF16之间进行转换
从UCS-2到UTF-8的编码方式如下：
| UCS-2编码(16进制) | UTF-8 字节流(二进制) |
| 0000 - 007F | 0xxxxxxx |
| 0080 - 07FF | 110xxxxx 10xxxxxx |
| 0800 - FFFF | 1110xxxx 10xxxxxx 10xxxxxx |
typedef
unsigned
long
UTF32;
/* at least 32 bits */
typedef
unsigned
short
UTF16;
/* at least 16 bits */
typedef
unsigned
char
UTF8;
/* typically 8 bits */
typedef
unsigned
int
INT
;
/*
UCS-2编码 UTF-8 字节流(二进制)
0000 - 007F 0xxxxxxx
0080 - 07FF 110xxxxx 10xxxxxx
0800 - FFFF 1110xxxx 10xxxxxx 10xxxxxx
*/
#define UTF8_ONE_START (0xOOO1)
#define UTF8_ONE_END (0x007F)
#define UTF8_TWO_START (0x0080)
#define UTF8_TWO_END (0x07FF)
#define UTF8_THREE_START (0x0800)
#define UTF8_THREE_END (0xFFFF)
void
UTF16ToUTF8(UTF16* pUTF16Start, UTF16* pUTF16End, UTF8* pUTF8Start, UTF8* pUTF8End)
{
UTF16* pTempUTF16 = pUTF16Start;
UTF8* pTempUTF8 = pUTF8Start;
while
(pTempUTF16 < pUTF16End)
{
if
(*pTempUTF16 <= UTF8_ONE_END
&& pTempUTF8 + 1 < pUTF8End)
{
//0000 - 007F 0xxxxxxx
*pTempUTF8++ = (UTF8)*pTempUTF16;
}
else
if
(*pTempUTF16 >= UTF8_TWO_START && *pTempUTF16 <= UTF8_TWO_END
&& pTempUTF8 + 2 < pUTF8End)
{
//0080 - 07FF 110xxxxx 10xxxxxx
*pTempUTF8++ = (*pTempUTF16 >> 6) | 0xC0;
*pTempUTF8++ = (*pTempUTF16 & 0x3F) | 0x80;
}
else
if
(*pTempUTF16 >= UTF8_THREE_START && *pTempUTF16 <= UTF8_THREE_END
&& pTempUTF8 + 3 < pUTF8End)
{
//0800 - FFFF 1110xxxx 10xxxxxx 10xxxxxx
*pTempUTF8++ = (*pTempUTF16 >> 12) | 0xE0;
*pTempUTF8++ = ((*pTempUTF16 >> 6) & 0x3F) | 0x80;
*pTempUTF8++ = (*pTempUTF16 & 0x3F) | 0x80;
}
else
{
break
;
}
pTempUTF16++;
}
*pTempUTF8 = 0;
}
void
UTF8ToUTF16(UTF8* pUTF8Start, UTF8* pUTF8End, UTF16* pUTF16Start, UTF16* pUTF16End)
{
UTF16* pTempUTF16 = pUTF16Start;
UTF8* pTempUTF8 = pUTF8Start;
while
(pTempUTF8 < pUTF8End && pTempUTF16+1 < pUTF16End)
{
if
(*pTempUTF8 >= 0xE0 && *pTempUTF8 <= 0xEF)
//是3个字节的格式
{
//0800 - FFFF 1110xxxx 10xxxxxx 10xxxxxx
*pTempUTF16 |= ((*pTempUTF8++ & 0xEF) << 12);
*pTempUTF16 |= ((*pTempUTF8++ & 0x3F) << 6);
*pTempUTF16 |= (*pTempUTF8++ & 0x3F);
}
else
if
(*pTempUTF8 >= 0xC0 && *pTempUTF8 <= 0xDF)
//是2个字节的格式
{
//0080 - 07FF 110xxxxx 10xxxxxx
*pTempUTF16 |= ((*pTempUTF8++ & 0x1F) << 6);
*pTempUTF16 |= (*pTempUTF8++ & 0x3F);
}
else
if
(*pTempUTF8 >= 0 && *pTempUTF8 <= 0x7F)
//是1个字节的格式
{
//0000 - 007F 0xxxxxxx
*pTempUTF16 = *pTempUTF8++;
}
else
{
break
;
}
pTempUTF16++;
}
*pTempUTF16 = 0;
}
int
main()
{
UTF16 utf16[256] = {L
"你a好b吗234中国~!"
};
UTF8 utf8[256];
UTF16ToUTF8(utf16, utf16+wcslen(utf16), utf8, utf8+256);
memset
(utf16, 0,
sizeof
(utf16));
UTF8ToUTF16(utf8, utf8 +
strlen
(utf8), utf16, utf16+256);
return
0;
}