UTF8、UTF16 之间的转换

原文：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

1. [代码][C/C++]代码    跳至 [1] [全屏预览]

?

1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107

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; }