分类： C/C++
2008-08-07 17:42:11
UCS-4范围（16进制） UTF-8 系列（二进制） 0000 0000<->0000 007F 0xxxxxxx 0000 0080<->0000 07FF 110xxxxx 10xxxxxx 0000 0800<->0000 FFFF 1110xxxx 10xxxxxx 10xxxxxx 0001 0000<->001F FFFF 11110xxx 10xxxxxx 10xxxxxx 10xxxxxx 0020 0000<->03FF FFFF 111110xx 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx 0400 0000<->7FFF FFFF 1111110x 10xxxxxx ... 10xxxxxx
typedef usigned short WCHAR
// 输出的UTF8编码至多是3个字节。
int UnicodeToUTF8(WCHAR ucs2, unsigned char *buffer)
{
memset(buffer, 0, 4);
if ((0x0000 <= ucs2) && (ucs2 <= 0x007f)) // one char of UTF8
{
buffer[0] = (char)ucs2;
return 1;
}
if ((0x0080 <= ucs2) && (ucs2 <= 0x07ff)) // two char of UTF8
{
buffer[1] = 0x80 | char(ucs2 & 0x003f);
buffer[0] = 0xc0 | char((ucs2 >> 6) & 0x001f);
return 2;
}
if ((0x0800 <= ucs2) && (ucs2 <= 0xffff)) // three char of UTF8
{
buffer[2] = 0x80 | char(ucs2 & 0x003f);
buffer[1] = 0x80 | char((ucs2 >> 6) & 0x003f);
buffer[0] = 0xe0 | char((ucs2 >> 12) & 0x001f);
return 3;
}
return 0;
}
WCHAR UTF8ToUnicode(unsigned char *buffer)
{
WCHAR temp = 0;
if (buffer[0] < 0x80) // one char of UTF8
{
temp = buffer[0];
}
if ((0xc0 <= buffer[0]) && (buffer[0] < 0xe0)) // two char of UTF8
{
temp = buffer[0] & 0x1f;
temp = temp << 6;
temp = temp | (buffer[1] & 0x3f);
}
if ((0xe0 <= buffer[0]) && (buffer[0] < 0xf0)) // three char of UTF8
{
temp = buffer[0] & 0x0f;
temp = temp << 6;
temp = temp | (buffer[1] & 0x3f);
temp = temp << 6;
temp = temp | (buffer[2] & 0x3f);
}
if ((0x80 <= buffer[0]) && (buffer[0] < 0xc0)) // not the first byte of UTF8 character
return 0xfeff; // 0xfeff will never appear in usual
return temp; // more than 3-bytes return 0
}
typedef unsigned char byte // 64 characters for base64 coding byte base64Chars[] = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789 /"; // 8 characters are safe just as base64 characters for MAIL gates byte safeChars[] = "''(),-.:?"; // 4 characters all means space byte spaceChars[] = " \t\n\r";
// mask value defined for indentify the type of a byte
#define BASE64 0x01
#define SAFE 0x02
#define SPACE 0x04
byte byteType[256]; // hash table used for find the type of a byte
bool firstTime = true; // the first time to use the lib, wait for init the table
// 注：为了解码base64编码部分的字符，需要一个哈希表，对一个base64字符都可以直接得到0-64之间的一个数：
byte base64Value[128];
这两个哈希表在使用前要初始化：
void initUTF7Tables()
{
byte *s;
if(!firstTime)
return;
// not necessary, but should do it to be robust
memset(byteType, 0, 256);
memset(base64Value, 0, 128);
for(s=base64Chars; *s!=''\0''; s )
{
byteType[*s] |= BASE64;
base64Value[*s] = s - base64Chars; // the offset, it is a 6bits value,0-64
}
for(s=safeChars; *s!=''\0''; s )
byteType[*s] |= SAFE;
for(s=spaceChars; *s!=''\0''; s )
byteType[*s] |= SPACE;
firstTime = false;
}
UTF-7编码转换时候，是与当前字符是与状态有关的，也就是说：// the state of current character #define IN_ASCII 0 #define IN_BASE64 1 #define AFTER_PLUS 2在使用规则2进行编码时候，需要使用base64的方法，也就需要2个全局的辅助变量：
int state; // state in which we are working int nbits; // number of bits in the bit buffer unsigned long bitBuffer; // used for base64 coding把一个Unicode字符转化为一个UTF-7序列：返回写到缓冲区里的字节数目，函数影响了state，nbits，bitBuffer三个全局变量。这里先实现了一个简单的辅助函数，功能是把一个Unicode字符转变后写到提供的缓冲区中，返回写入的字节个数。在开始编码Unicode字符数组中第一个字符的时候，state，nbits，bitBuffer三个全局变量需要被初始化：
state = IN_ASCII;
nbits = 0;
bitBuffer = 0;
int UnicodeToUTF7(WCHAR ucs2, byte *buffer)
{
byte *head = buffer;
int index;
// is an ASCII and is a byte in char set defined
if (((ucs2 & 0xff80) == 0)) && (byteType[(byte)u2] & (BASE64|SAFE|SPACE)))
{
byte temp = (byte)ucs2;
if (state == IN_BASE64) // should switch out from base64 coding here
{
if (nbits > 0) // if some bits in buffer, then output them
{
index = (bitBuffer << (6 - nbits)) & 0x3f;
*s = base64[index];
}
if ((byteType[temp] & BASE64) || (temp == ''-''))
*s = ''-'';
state = IN_ASCII;
}
*s = temp;
if (temp == '' '')
*s = ''-'';
}
else
{
if (state == IN_ASCII)
{
*s = '' '';
state = IN_BASE64; // begins base64 coding here
nbits = 0;
bitBuffer = 0;
}
bitBuffer <<= 16;
bitBuffer |= ucs2;
nbits = 16;
while(nbits >= 6)
{
nbits -= 6;
index = (bitBuffer >> nbits) & 0x3f; // output the high 6 bits
*s = base64[index];
}
}
return (s - head);
}
state = IN_ASCII;
nbits = 0;
bitBuffer = 0;
#define RET0 0xfeff
WCHAR UTF7ToUnicode(byte c)
{
if(state == IN_ASCII)
{
if (c == '' '')
{
state = AFTER_PLUS;
return RET0;
}
else
return (WCHAR)c;
}
if (state == AFTER_PLUS)
{
if (c == ''-'')
{
return (WCHAR)'' '';
}
else
{
state = IN_BASE64;
nbits = 0;
bitBuffer = 0; // it is not necessary
// don''t return yet, continue to the IN_BASE64 mode
}
}
// state == Base64
if (byteType[c] & BASE64)
{
bitBuffer <<= 6;
bitBuffer |= base64Value[c];
nbits = 6;
if (nbits >= 16)
{
nbits -= 16;
return (WCHAR)((bitBuffer >> nbits) & 0x0000ffff);
}
return RET0;
}
// encount a byte which is not in base64 character set, switch out of base64 coding
state = IN_ASCII;
if (c != ''-'')
{
return (WCHAR)c;
}
return RET0;
}
说明：对于一个UTF-7序列，可以通过连续输入字节并调用上面的函数，判断返回值，得到一个Unicode字符数组。
int StringEncode::UnicodeToGB2312(char **dest, const WCHAR *src)
{
char* buffer;
int size = ::WideCharToMultiByte(CP_ACP, 0, src, -1, NULL, 0, NULL, NULL);
// null termidated wchar''s buffer
buffer = new char[size];
int ret = ::WideCharToMultiByte(CP_ACP, NULL, src, -1, buffer, size 1, NULL, NULL);
if (*dest != 0)
delete *dest;
*dest = buffer;
return ret;
}
int StringEncode::Gb2312ToUnicode(WCHAR **dest, const char *src)
{
int length = strlen(src); // null terminated buffer
WCHAR *buffer = new WCHAR[length 1]; // WCHAR means unsinged short, 2 bytes
// provide enough buffer size for Unicodes
int ret = ::MultiByteToWideChar(CP_ACP, MB_PRECOMPOSED, src, length, buffer, length);
buffer[ret] = 0;
if (*dest != 0)
delete *dest;
*dest = buffer;
return ret;
}
CString CTestUrlDlg::UrlToString(CString url)
{
CString str = "";
int n = url.GetLength();
url.MakeLower();
BYTE a, b1, b2;
for (int i=0; i= ''0'') && (c <= ''9''))
d = c - ''0'';
else if ((c >= ''a'') && (c <= ''f''))
{
d = c - ''a'' 10;
}
else if ((c >= ''A'') && (c <= ''F''))
{
d = c - ''A'' 10;
}
else
d = 0;
return d;
}
static void UnicodeToGB2312(const WCHAR unicode, char* buffer)
{
// int size = ::WideCharToMultiByte(CP_ACP, 0, unicode, -1, NULL, 0, NULL, NULL);
int ret = ::WideCharToMultiByte(CP_ACP, NULL, &unicode, -1, buffer, 3, NULL, NULL);
}
CString CTestUrlDlg::Uft8ToGB(CString url)
{
CString str = "";
char buffer[3];
WCHAR unicode;
unsigned char * p = (unsigned char *)(LPCTSTR)url;
int n = url.GetLength();
int t = 0;
while (t < n)
{
unicode = UTF8ToUnicode(p, t);
UnicodeToGB2312(unicode, buffer);
buffer[2] = 0;
str = buffer;
}
return str;
}
CString str = "/MFC鑻辨枃鎵嬪唽.chm"; CString ret = UrlToString(str); ret = Uft8ToGB(ret); // MFC英文手册.chm