VC++中通过MultiByteToWideChar将string|char转换为wstring|wchar_t

女爷i 2022-08-19 01:55 121阅读 0赞

原文地址：[http://www.cnblogs.com/qq78292959/archive/2010/09/15/2077015.html][http_www.cnblogs.com_qq78292959_archive_2010_09_15_2077015.html]

#include <Windows.h>
 #include <iostream>
 using namespace std;
 
 1、string转换为wstring
 string str = _T("你好呀");
 int size = MultiByteToWideChar(CP_ACP,0,str.c_str(),-1,NULL,0);
 wchar_t *ch = new wchar_t[size+1];
 MultiByteToWideChar(CP_ACP,0,str.c_str(),-1,ch,size);
 wstring wstr = ch;
 
 2、char* 转换为wchar_t*
 char* str = _T("你好呀");
 int size = MultiByteToWideChar(CP_ACP,0,str,-1,NULL,0); 
 wchar_t *ch = new wchar_t[size+1];
 MultiByteToWideChar(CP_ACP,0,str,-1,ch,size);
 
 WideCharToMultiByte和MultiByteToWideChar函数的用法
 为了支持Unicode编码，需要多个字节与宽字节之间的相互转换
 这两个系统函数再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
 常用的代码页有CP_ACP和CP_UTF8
 使用CP_ACP代码页实现了ANSI与Unicode之间的转换
 使用CP_UTF8代码页实现了UTF-8余Unicode之间的转换
 
 1、ANSI to Unicode
 wstring ANSIToUnicode(const string &str)
 {
 	int len = str.length();
 	int unicodeLen = MultiByteToWideChar(CP_ACP,
 						0
 						str.c_str(),
 						-1,
 						NULL,
 						0);
 	wchar_t* 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 wstr;
 	wstr = (wchar_t*)pUnicode;
 	delete pUnicode;
 	return wstr;	
 }
 
 2、Unicode to ANSI
 string UnicodeToANSI(const wstring& wstr)
 {
 	char* pText;
 	int iTextLen;
 	iTextLen = WideCharToMultiByte(CP_ACP,
 					0,
 					wstr.c_str(),
 					-1,
 					NULL,
 					0,
 					NULL,
 					NULL);
 	pText = new char[iTextLen+1];
 	memset(pText,0,sizeof(char)*(iTextLen+1));
 	WideCharToMultiByte(CP_ACP,
 				0,
 				wstr.c_str(),
 				-1,
 				pText,
 				iTextLen,
 				NULL,
 				NULL);
 	string str = pText;
 	delete[] pText;
 	return str;
 } 
 
 3、Unicode to UTF-8
 string UnicodeToUTF8(const wstring& wstr)
 {
 	char *pText;
 	int iTextLen;
 	iTextLen = WideCharToMultiByte(CP_UTF8,
 	 				0,
 					wstr.c_str(),
 					-1,
 					NULL,
 					0,
 					NULL,
 					NULL);
 	pText = new char[iTextLen+1];
 	memset((void*)pText,0,sizeof(char)*(iTextLen+1));
 	WideCharToMultiByte(CP_UTF8,
 				0,
 				wstr.c_str(),
 				-1,
 				pText,
 				iTextLen,
 				NULL,
 				NULL);
 	string str = pText;
 	delete[] pText;
 	return str;
 } 
 
 4、 UTF-8 to Unicode
 wstring UTF8ToUnicode(const string& str)
 {
 	int len = str.length();
 	int unicodeLen = MultiByteToWideChar(CP_UTF8,
 	 					0,
 						str.c_str()),
 						-1,
 						NULL,
 						0 );
 	wchar_t * 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 wstr = (wchar_t *)pUnicode;
 	delete[] pUnicode;
 	return wstr;
 } 
 
 /**
 **函数输入Big5字符，返回GB简体字符
 两次转换 Big5----GB繁体----GB简体 
 **/ 
 AnsiString _fastcall Big2Gb(AnsiString sBig)
 {
 	char* pszBig5 = NULL;
 	wchar_t* wszUnicode = NULL;
 	char* pszGbt = NULL;
 	char* pszGbs = NULL;
 	AnsiString sGb;
 	int iLen = 0;
 	pszBig5 = sBig.c_str();
 	//计算转换的字符数
 	iLen = MultiByteToWideChar(950,0,pszBig5,-1,NULL,0);
 	//给wszUnicode分配内存
 	wszUnicode = new wchar_t[iLen+1];
 	//从Big5码转换成Unicode码
 	MultiByteToWideChar(950,0,pszBig5,-1,wszUnicode,iLen);
 	//计算转换的字符数
 	iLen = WideCharToMultiByte(936,0,(PWSTR)wszUnicode,-1,NULL,0,NULL,NULL);
 	//给pszGbt分配内存
 	pszGbt = new char[iLen+1];
 	//给pszGbs分配内存
 	pszGbs = new char[iLen+1];
 	//转换Unicode码到GB码繁体
 	WideCharToMultiByte(936,0,(PWSTR)wszUnicode,-1,pszGbt,iLen,NULL,NULL);
 	//GB繁体到GB简体
 	LCMapString(0x0804,LCMAP_SIMPLIFIED_CHINESE,pszGbt,-1,pszGbs,iLen);
 	sGb = pszGbs
 	delete[] wszUnicode;
 	delete[] pszGbt;
 	delete[] pszGbs;
 	return sGb; 
 
 } 
 
 /**
 **函数输入GB字符，返回Big5字符，
 **两次转换 
 **/ 
 
 AnsiString _fastcall Gb2Big(AnsiString sGb)
 {
 	char* pszGbt = NULL;
 	char* pszGbs = NULL;
 	wchar_t * wszUnicode = NULL;
 	char* pszBig5 = NULL;
 	AnsiString sBig5;
 	int iLen = 0;
 	pszGbs = sGb.c_str();
 	iLen = MultiByteToWideChar(936,0,pszGbs,-1,NULL,0);
 	pszGbt = new char[iLen*2+1];
 	LCMapString(locale,LCMAP_TRANDITIONAL_CHINESE,pszGbs,-1,pszGbt,ilen*2);
 	delete[] pszGbt; 
 	sBig5 = pszGbt;
 	return sBig5;
 }

[http_www.cnblogs.com_qq78292959_archive_2010_09_15_2077015.html]: http://www.cnblogs.com/qq78292959/archive/2010/09/15/2077015.html