Conversion between Unicode, UTF8, GB2312, UCS2, and GBK

Conversion between Unicode, UTF8, GB2312, UCS2, and GBK

Conversion of several encoding formats. Not many are used at ordinary times. However, we often encounter text message protocols. During this time, I made an SMS platform interface and summarized a few, which is not very complete.

 

//////////////////////////////////////// //////////////////////////////////////

// Format Chinese characters to % HH
Int URLEncode (LPCTSTR pInBuf, LPTSTR szOut)
{
LPBYTE pInTmp, pOutTmp;
PInTmp = (LPBYTE) pInBuf;
POutTmp = (LPBYTE) szOut;
While (* pInTmp ){
If (isalnum (* pInTmp )){
* POutTmp ++ = * pInTmp;
} Else {

If (isspace (* pInTmp )){
* POutTmp ++ = '+ ';
} Else {
* POutTmp ++ = '% ';
* POutTmp ++ = toHex (* pInTmp> 4 );
* POutTmp ++ = toHex (* pInTmp & 0xF );
}
}
PInTmp ++;
}
* POutTmp = '/0 ';
Return (int) (pOutTmp-(LPBYTE) szOut );
}

 

 

//////////////////////////////////////// ///////////////////////////

// Unicode Character converted to UTF-8 Encoding
LPCTSTR UnicodeToUTF8Char (LPTSTR pOut, WCHAR wcText)
{
// Pay attention to the order of WCHAR high and low characters. The lower byte is in the front and the higher byte is in the back
LPTSTR pchar = (LPTSTR) & wcText;
POut [0] = (0xE0 | (pchar [1] & 0xF0)> 4 ));
POut [1] = (0x80 | (pchar [1] & 0x0F) <2) + (pchar [0] & 0xC0)> 6 );
POut [2] = (0x80 | (pchar [0] & 0x3F ));
POut [3] = '/0 ';
Return pOut;
}

 

 

 

// Convert GB2312 string to UTF-8 Encoding
LPCTSTR GB2312ToUTF8 (LPTSTR pUTF8Out, LPCTSTR pGB2312Input, int GB2312Len)
{
CHAR buf [4];
LPCTSTR lpReturn, pGB2312Cursor, pGB2312InputEnd;
WCHAR wcBuffer;
 
LpReturn = (LPCTSTR) pUTF8Out;
PGB2312Cursor = (LPTSTR) pGB2312Input;
PGB2312InputEnd = pGB2312Cursor + GB2312Len;
 
While (pGB2312Cursor <pGB2312InputEnd ){
// You can copy the data directly if anⅱ is used.
If (* pGB2312Cursor> 0 ){
* PUTF8Out ++ = * pGB2312Cursor ++;
} Else {
: MultiByteToWideChar (CP_ACP, MB_PRECOMPOSED, pGB2312Cursor, 2, & wcBuffer, 1 );
Memcpy (pUTF8Out, UnicodeToUTF8Char (buf, wcBuffer), 3 );
PGB2312Cursor + = 2;
PUTF8Out + = 3;
}
}
* PUTF8Out = '/0 ';
Return lpReturn;
}

 

 

 

 

Int UTF8ToGB (const char * str, char * out)
{
WCHAR * strSrc;
TCHAR * szRes;
Int len;
 
// Obtain the size of the Temporary Variable
Int I = MultiByteToWideChar (CP_UTF8, 0, str,-1, NULL, 0 );
StrSrc = new WCHAR [I + 1];
MultiByteToWideChar (CP_UTF8, 0, str,-1, strSrc, I );
 
// Obtain the size of the Temporary Variable
I = WideCharToMultiByte (CP_ACP, 0, strSrc,-1, NULL, 0, NULL, NULL );
SzRes = new TCHAR [I + 1];
WideCharToMultiByte (CP_ACP, 0, strSrc,-1, szRes, I, NULL, NULL );
 
Len = (I + 1) * sizeof (CHAR );
Memcpy (out, szRes, len );
Out [len + 1] = '/0 ';
 
Delete [] strSrc;
Delete [] szRes;
 
Return len;
}

 

 

 

// Convert the GB2312 string to GB2312 webpage Encoding
LPCTSTR GB2312ToWebGB2312 (LPTSTR pWebGB2312Out, LPCTSTR pGB2312Input, int GB2312Len)
{
 
LPCTSTR lpReturn, pGB2312Cursor, pGB2312InputEnd;
WCHAR wcBuffer;
 
LpReturn = (LPCTSTR) pWebGB2312Out;
PGB2312Cursor = (LPTSTR) pGB2312Input;
PGB2312InputEnd = pGB2312Cursor + GB2312Len;
 
While (pGB2312Cursor <pGB2312InputEnd ){
// You can copy the data directly if anⅱ is used.
If (* pGB2312Cursor> 0 ){
* PWebGB2312Out ++ = * pGB2312Cursor ++;
} Else {
: MultiByteToWideChar (CP_ACP, MB_PRECOMPOSED, pGB2312Cursor, 2, & wcBuffer, 1 );
PWebGB2312Out + = sprintf (pWebGB2312Out, "& # % d;", wcBuffer );
PGB2312Cursor + = 2;
}
}
* PWebGB2312Out = '/0 ';
Return lpReturn;
}

 

 

 

Void UCS2toUTF8 (unsigned short * ucs2, int count, char * utf8)
{
Unsigned short unicode;
Unsigned char bytes [4] = {0 };
Int nbytes = 0;
Int I = 0, j = 0;
Int len = 0;
 
If (ucs2! = NULL) & (utf8! = NULL ))
{
If (count = 0)
{
Len = 0;
}
Else
{
For (I = 0; I <count; I ++)
{
Unicode = ucs2 [I];

If (unicode <0x80)
{
Nbytes = 1;
Bytes [0] = unicode;
}
Else if (unicode <0x800)
{
Nbytes = 2;
Bytes [1] = (unicode & 0x3f) | 0x80;
Bytes [0] = (unicode <2) & 0x1f00 | 0xc000)> 8;
}
Else
{
Nbytes = 3;
Bytes [2] = (unicode & 0x3f) | 0x80;
Bytes [1] = (unicode <2) & 0x3f00 | 0x8000)> 8;
Bytes [0] = (unicode <4) & 0x0f0000 | 0xe00000)> 16;
}

For (j = 0; j <nbytes; j ++)
{
Utf8 [len] = bytes [j];
Len ++;
}
}
}

Utf8 [len] = '/0 ';
}
}

 

 

//////////////////////////////////////// ///////////////////////////

// UCS2 converts UTF8

//////////////////////////////////////// ///////////////////////////

//////////////////////////////////////// ///////////////////////////

// Convert UTF8 to GB

//////////////////////////////////////// ///////////////////////////