1、如何创建unicode 项目
选择“Project->Setting”菜单
(1)选 Win32 Unicode Debug :
切换到“c/C++ ” Tab页 从下拉列表框中选择 “Preprocessor” ,去掉_MBCS,添加UNICODE,_UNICODE(注意逗号隔开) ,如果是MFC程序,还要在
link中,Category选output,将Entry-Point Symbol设为wWinMainCRTStartup
2、unicode码格式存放的16进制数据显示成可见的字符
例子: 如何在电脑上显示出 0x6211 0x4eec ?
代码:
//我们: 我们 0x6211 0x4eec
TCHAR MyWchar[128];
//WCHAR MyWchar[128];
memset(MyWchar, 0, sizeof(MyWchar));
MyWchar[0] = 0x6211;
MyWchar[1] = 0x4eec;
MyWchar[2] = 25105;
MyWchar[3] = 20204;
int a = ((6*16 + 2)*16 + 1)*16 + 1;
MessageBox(MyWchar);
3、Ascii码格式存放的16进制数据显示成可见的字符
同2,
具体代码:
// ab: 87,98
char str[20] = {97,98,0};
MessageBox(str);
转换函数:
/**
*把unicode形式的字节数据转成字符格式的字串
例如:"62114eec"-> "我们"
*/
TCHAR* UnicoidByteData2Char(char* pByteIn,int nLenInByte, TCHAR* pCharOut)
{
if(nLenInByte <= 0 || pByteIn == NULL || pCharOut == NULL)
{
MessageBox(_T("UnicoidByteData2Char: 传入解析参数错误!"));
return NULL;
}
char temp[5] = {0};
int intValue = 0;
TCHAR* pOut = pCharOut;
for(int i=0; i<nLenInByte/2; i++)
{
memset(temp, 0, sizeof(temp));
temp[0] = pByteIn[4*i];
temp[1] = pByteIn[4*i + 1];
temp[2] = pByteIn[4*i + 2];
temp[3] = pByteIn[4*i + 3];
intValue = 0;
for(int j=0; j<4; j++)
{
if(temp[j]>='a' && temp[j] <='f')
{
intValue = intValue*16 + (temp[j] - 'a') + 10;
}
else if(temp[0]>='A' && temp[j] <='F')
{
intValue = intValue*16 + (temp[j] - 'A') + 10;
}
else if(temp[0]>='0' && temp[j] <='9')
{
intValue = intValue*16 + (temp[j] - '0');
}
else
{
MessageBox(_T("UnicoidByteData2Char:STK 数据有误"));
return NULL;
}
}
//swprintf(&pOut[i],_T("%d"), intValue);
pOut[i] = intValue;
}
return pOut;
}
/**
*把ascii形式的字节数据转成字符格式的字串
例如:"61623031323334" -> "ab01234"
*/
char* AsciiByteData2Char(char* pByteIn,int nLenInByte, char* pCharOut)
{
if(nLenInByte <= 0 || pByteIn == NULL || pCharOut == NULL)
{
MessageBox(_T("AsciiByteData2Char: 传入解析参数错误!"));
return NULL;
}
char temp[3] = {0};
int intValue = 0;
char* pOut = pCharOut;
for(int i=0; i<nLenInByte; i++)
{
memset(temp, 0, sizeof(temp));
temp[0] = pByteIn[2*i];
temp[1] = pByteIn[2*i + 1];
//十位数
if(temp[0]>='a' && temp[0] <='f')
{
intValue = 16*(temp[0] - 'a');
}
else if(temp[0]>='A' && temp[0] <='F')
{
intValue = 16*(temp[0] - 'A');
}
else if(temp[0]>='0' && temp[0] <='9')
{
intValue = 16*(temp[0] - '0');
}
else
{
MessageBox(_T("AsciiByteData2Char:STK 数据有误"));
return NULL;
}
//个位数
if(temp[1]>='a' && temp[1] <='f')
{
intValue += (temp[1] - 'a') + 10;
}
else if(temp[1]>='A' && temp[1] <='F')
{
intValue += (temp[1] - 'A') + 10;
}
else if(temp[1]>='0' && temp[1] <='9')
{
intValue += (temp[1] - '0');
}
else
{
MessageBox(_T("STK 数据有误"));
return NULL;
}
sprintf(&pOut[i],"%c", intValue);
}
return pOut;
}
/**
*把ascii形式的字串转换成unicode字串
*/
int Ascii2Unicode(char *pchIn, CString *pstrOut)
{
int nLen;
WCHAR *ptch;
if(pchIn == NULL)
{
return 0;
}
//WideCharToMultiByte(); //unicode 2 ascii
//MultiByteToWideChar(); //ascii 2 unicode
nLen = MultiByteToWideChar(CP_ACP, 0, pchIn, -1, NULL, 0);
ptch = new WCHAR[nLen];
MultiByteToWideChar(CP_ACP, 0, pchIn, -1, ptch, nLen);
pstrOut->Format(_T("%s"), ptch);
delete [] ptch;
return nLen;
}
输入参数1 @buf ascii码字符串
输入参数2 @len 字符串buf的长度
返回对应的hex进制的值
4、例如: 输入"23abcfe"字符串, 输出的hex值为: 0x23abcfe
UINT ascii2hex(char *buf, int len)
{
int i = 0;
int j = 0;
unsigned int ret = 0;
char p[2] = {0};
int tmp = 1;
for(i = 0; i<len; i++)
{
memcpy(p,&buf[i],1);
switch (p[0]){
case 'a':
tmp = 1;
for(j=0;j<len-1-i;j++)
tmp *= 16;
ret += 10*tmp;
break;
case 'b':
tmp = 1;
for(j=0;j<len-1-i;j++)
tmp *= 16;
ret += 11*tmp;
break;
case 'c':
tmp = 1;
for(j=0;j<len-1-i;j++)
tmp *= 16;
ret += 12*tmp;
break;
case 'd':
tmp = 1;
for(j=0;j<len-1-i;j++)
tmp *= 16;
ret += 13*tmp;
break;
case 'e':
tmp = 1;
for(j=0;j<len-1-i;j++)
tmp *= 16;
ret += 14*tmp;
break;
case 'f':
tmp = 1;
for(j=0;j<len-1-i;j++)
tmp *= 16;
ret += 15*tmp;
break;
default:
tmp = 1;
for(j=0;j<len-1-i;j++)
tmp *= 16;
ret += atoi(p)*tmp;
break;
}
}
return ret;
}
/*
*
* 把ascii形式的字串转换成16进制数
* 例如:"ab01234" -> "61623031323334"
*/
char* CStkTreeDlg::AscToHex(char* pInData, char* pOutData)
{
char* pIn = pInData;
char* pOut = pOutData;
int hexValue = 0;
for(int i=0; i<strlen(pIn); i++)
{
hexValue = pIn[i];
sprintf(pOut + 2*i, "%0x", hexValue);
}
return pOut;
}
/*
*
* 把CString形式的字串转换成16进制数
5、* 例如:"我们0123"->"62114eec0030003100320033"
*/
char* CStkTreeDlg::CStringToHexByteStr(CString strIn, char* pOutHexStr)
{
int len = strIn.GetLength();
if((pOutHexStr == NULL) || (len <= 0))
{
return NULL;
}
uint16* text = NULL;
text = (uint16 *)new uint16[len + 1];
if(text == NULL)
{
return NULL;
}
char * pOut = pOutHexStr;
//取得内存内容
uint16* ptext = strIn.GetBuffer(len);
wcscpy(text, ptext);
//转成16进制数
int index = 0;
for(int i=0; i<len; i++)
{
if(text[i] > 0xff)
{
sprintf(pOut+index, "%0x", text[i]);
index += 4;
}
else
{
sprintf(pOut+index, "%s", "00");
index += 2;
sprintf(pOut+index, "%0x", text[i]);
index += 2;
}
}
delete [] text;
return pOut;
}
/*
*
6* 把unicode形式的字串转换成ascii字串
*//Cstring 转 char
*/
char* CStkTreeDlg::CStringToChar(CString szItem, char* pOutChars)
{
int len = WideCharToMultiByte(CP_ACP,0,szItem,szItem.GetLength(),NULL,0,NULL,NULL);
char * pOutStr = pOutChars;
if(pOutStr == NULL)
{
return NULL;
}
WideCharToMultiByte(CP_ACP,0,szItem,szItem.GetLength(),pOutStr,len,NULL,NULL);
pOutStr[len] = '\0';
return pOutStr;
}
7* 把unicode形式的字串转换成ascii字串
************************************************************************/
/* 输入efbbbf字符串, 输出"efbbbf" 取得utf-8文件的前三个字符,用于比较文件类型 */
/************************************************************************/
char* CStkTreeDlg::Adr2Char(char *pIn, char *pOut)
{
int value1 = *(pIn+0) & 0xff;
int value2 = *(pIn+1) & 0xff;
int value3 = *(pIn+2) & 0xff;
char ch1[3] = {0};
char ch2[3] = {0};
char ch3[3] = {0};
sprintf(ch1, "%X", value1);
sprintf(ch2, "%X", value2);
sprintf(ch3, "%X", value3);
sprintf(pOut,"%s%s%s", ch1, ch2, ch3);
return pOut;
}
8* 判断文件类型
/************************************************************************/
/* get file type : EF BB BF UTF-8 1
FF FE UNICODE 2
FE FF UNICODE BIG EDIAN 3
ELSE ASCII 0
*
/************************************************************************/
int CStkTreeDlg::GetFileType()
{
char fileBegin[4];
memset(fileBegin, 0, sizeof(fileBegin));
m_File.Read(fileBegin, 3);
char strType[7];
memset(strType, 0, sizeof(strType));
Adr2Char(fileBegin, strType);
if((memcmp(strType, "efbbbf", 6) == 0) || (memcmp(strType, "EFBBBF", 6) == 0)){
m_fileType = 1; //utf-8
}else if((memcmp(strType, "fffe", 4) == 0) || (memcmp(strType, "FFFE", 4) == 0)){
m_fileType = 2; //UNICODE
}else if((memcmp(strType, "feff", 4) == 0) || (memcmp(strType, "FEFF", 4) == 0)){
m_fileType = 3; //UNICODE BIG EDIAN
}else{
m_fileType = 0; //ASCII
}
return m_fileType;
}
// 根据语言取得配置文件中的字符串
CString LoadMutiLanString(CString szID)
{
CString szValue;
DWORD dwSize = 1000;
TCHAR szStylesPath[_MAX_PATH];
CString strStylesPath;
VERIFY(::GetModuleFileName(AfxGetApp()->m_hInstance, szStylesPath, _MAX_PATH));
strStylesPath = szStylesPath;
int nIndex = strStylesPath.ReverseFind(_T('\\'));
if (nIndex > 0)
{
strStylesPath = strStylesPath.Left(nIndex);
}
else
{
strStylesPath.Empty();
}
strStylesPath += _T("\\Lang\\");
switch (theApp.m_sSettingOnPc.sSystem.nLang)
{
case LANG_TYPE_ENG_USA:
{
GetPrivateProfileString(_T("String"),szID,_T("Not found"),
szValue.GetBuffer(dwSize),dwSize, strStylesPath + _T("English.ini"));
}
break;
case LANG_TYPE_CH_SIMP:
{
GetPrivateProfileString(_T("String"),szID,_T("Not found"),
szValue.GetBuffer(dwSize),dwSize,strStylesPath + _T("SimpleChinese.ini"));
}
break;
default:
break;
}
szValue.ReleaseBuffer();
szValue.Replace(_T("\\n"),_T("\n"));
return szValue;
}
WideCharToMultiByte和MultiByteToWideChar函数的用法
转自:http://www.cnblogs.com/gakusei/articles/1585211.html
为了支持Unicode编码,需要多字节与宽字节之间的相互转换。这两个系统函数在使用时需要指定代码页,在实际应用过程中遇到乱码问题,然后重新阅读《Windows核心编程》,总结出正确的用法。
WideCharToMultiByte的代码页用来标记与新转换的字符串相关的代码页。
MultiByteToWideChar的代码页用来标记与一个多字节字符串相关的代码页。
常用的代码页由CP_ACP和CP_UTF8两个。
使用CP_ACP代码页就实现了ANSI与Unicode之间的转换。
使用CP_UTF8代码页就实现了UTF-8与Unicode之间的转换。
下面是代码实现:
1. ANSI to Unicode
wstring ANSIToUnicode( const string& str )
{
int len = 0;
len = str.length();
int unicodeLen = ::MultiByteToWideChar( CP_ACP,
0,
str.c_str(),
-1,
NULL,
0 );
wchar_t * pUnicode;
pUnicode = new wchar_t[unicodeLen+1];
memset(pUnicode,0,(unicodeLen+1)*sizeof(wchar_t));
::MultiByteToWideChar( CP_ACP,
0,
str.c_str(),
-1,
(LPWSTR)pUnicode,
unicodeLen );
wstring rt;
rt = ( wchar_t* )pUnicode;
delete pUnicode;
return rt;
}
2. Unicode to ANSI
string UnicodeToANSI( const wstring& str )
{
char* pElementText;
int iTextLen;
// wide char to multi char
iTextLen = WideCharToMultiByte( CP_ACP,
0,
str.c_str(),
-1,
NULL,
0,
NULL,
NULL );
pElementText = new char[iTextLen + 1];
memset( ( void* )pElementText, 0, sizeof( char ) * ( iTextLen + 1 ) );
::WideCharToMultiByte( CP_ACP,
0,
str.c_str(),
-1,
pElementText,
iTextLen,
NULL,
NULL );
string strText;
strText = pElementText;
delete[] pElementText;
return strText;
}
3. UTF-8 to Unicode
wstring UTF8ToUnicode( const string& str )
{
int len = 0;
len = str.length();
int unicodeLen = ::MultiByteToWideChar( CP_UTF8,
0,
str.c_str(),
-1,
NULL,
0 );
wchar_t * pUnicode;
pUnicode = new wchar_t[unicodeLen+1];
memset(pUnicode,0,(unicodeLen+1)*sizeof(wchar_t));
::MultiByteToWideChar( CP_UTF8,
0,
str.c_str(),
-1,
(LPWSTR)pUnicode,
unicodeLen );
wstring rt;
rt = ( wchar_t* )pUnicode;
delete pUnicode;
return rt;
}
4. Unicode to UTF-8
string UnicodeToUTF8( const wstring& str )
{
char* pElementText;
int iTextLen;
// wide char to multi char
iTextLen = WideCharToMultiByte( CP_UTF8,
0,
str.c_str(),
-1,
NULL,
0,
NULL,
NULL );
pElementText = new char[iTextLen + 1];
memset( ( void* )pElementText, 0, sizeof( char ) * ( iTextLen + 1 ) );
::WideCharToMultiByte( CP_UTF8,
0,
str.c_str(),
-1,
pElementText,
iTextLen,
NULL,
NULL );
string strText;
strText = pElementText;
delete[] pElementText;
return strText;
}