目录
- 一、UTF8转std:string
- 二、string_To_UTF8
- 三、wstring转string
- 四、string转wstring
- 五、unicode属性和多字节属性转换(char转wchar_t)
- 六、Unicode ansi utf8转换
一、UTF8转std:string
std::string UTF8_To_string(const std::string& str)
{
int nwLen = MultiByteToWideChar(CP_UTF8, 0, str.c_str(), -1, NULL, 0);
wchar_t* pwBuf = new wchar_t[nwLen + 1]; //一定要加1,不然会出现尾巴
memset(pwBuf, 0, nwLen * 2 + 2);
MultiByteToWideChar(CP_UTF8, 0, str.c_str(), str.length(), pwBuf, nwLen);
int nLen = WideCharToMultiByte(CP_ACP, 0, pwBuf, -1, NULL, NULL, NULL, NULL);
char* pBuf = new char[nLen + 1];
memset(pBuf, 0, nLen + 1);
WideCharToMultiByte(CP_ACP, 0, pwBuf, nwLen, pBuf, nLen, NULL, NULL);
std::string strRet = pBuf;
delete[]pBuf;
delete[]pwBuf;
pBuf = NULL;
pwBuf = NULL;
return strRet;
}
二、string_To_UTF8
std::string string_To_UTF8(const std::string& str)
{
int nwLen = ::MultiByteToWideChar(CP_ACP, 0, str.c_str(), -1, NULL, 0);
wchar_t* pwBuf = new wchar_t[nwLen + 1]; //一定要加1,不然会出现尾巴
ZeroMemory(pwBuf, nwLen * 2 + 2);
::MultiByteToWideChar(CP_ACP, 0, str.c_str(), str.length(), pwBuf, nwLen);
int nLen = ::WideCharToMultiByte(CP_UTF8, 0, pwBuf, -1, NULL, NULL, NULL, NULL);
char* pBuf = new char[nLen + 1];
ZeroMemory(pBuf, nLen + 1);
::WideCharToMultiByte(CP_UTF8, 0, pwBuf, nwLen, pBuf, nLen, NULL, NULL);
std::string strRet(pBuf);
delete[]pwBuf;
delete[]pBuf;
pwBuf = NULL;
pBuf = NULL;
return strRet;
}
三、wstring转string
std::string wstring2string(std::wstring wstr)
{
string result;
int len = WideCharToMultiByte(CP_ACP, 0, wstr.c_str(), wstr.size(), NULL, 0, NULL, NULL);
if (len <= 0)return result;
char* buffer = new char[len + 1];
if (buffer == NULL)return result;
WideCharToMultiByte(CP_ACP, 0, wstr.c_str(), wstr.size(), buffer, len, NULL, NULL);
buffer[len] = '\0';
result.append(buffer);
delete[] buffer;
return result;
}
四、string转wstring
std::wstring string2wstring(std::string str)
{
wstring result;
int len = MultiByteToWideChar(CP_ACP, 0, str.c_str(), str.size(), NULL, 0);
if (len < 0)return result;
wchar_t* buffer = new wchar_t[len + 1];
if (buffer == NULL)return result;
MultiByteToWideChar(CP_ACP, 0, str.c_str(), str.size(), buffer, len);
buffer[len] = '\0';
result.append(buffer);
delete[] buffer;
return result;
}
五、unicode属性和多字节属性转换(char转wchar_t)
// WideChar.cpp : 定义控制台应用程序的入口点。
//
#include "stdafx.h"
#include <windows.h>
#include <iostream>
#include <atlbase.h>
//#include <comutil.h>
#include <atlstr.h>
using namespace std;
//方法1:MultiByteToWideChar, WideCharToMultiByte
void Way_1()
{
//char转wchar_t
char *p1 = "abc";
wchar_t p2[20] = L"EFG";
MultiByteToWideChar(CP_ACP, 0, p1, strlen(p1) + 1, p2, sizeof(p2));
printf("%S\n", p2);
//wchar_t转char
wchar_t *p3= L"EFG";
char p4[20];
WideCharToMultiByte(CP_ACP, 0, p3, -1, p4, sizeof(p4), NULL, NULL);
printf("%s\n", p4);
}
//方法2:A2W, W2A, T2A, A2T
void Way_2()
{
//需要添加头文件 <atlbase.h>
char * p1 = "abc";
wchar_t *p2 = L"def";
TCHAR *P3 = _T("CC");
USES_CONVERSION;
wchar_t *p5 = A2W(p1);
char * p4 = T2A(P3);
}
方法3:
//void Way_3()
//{//需要添加头文件<comutil.h>,一般在MFC工程下使用
// CString str = "abc";//只能存一种
// _bstr_t bstr = "abc";//可以用非unicode
// bstr += L"efg";//可以用unicode
// char *p = bstr;
// wchar_t *p2 = bstr;
//}
int main()
{
Way_1();
//Way_2();
return 0;
}
六、Unicode ansi utf8转换
int Unicode2UTF8(const wchar_t* pUnicode, char* pUTF8Buffer, int nBufferSize)
{
if( (nBufferSize == 0) && (pUTF8Buffer != NULL) )
return 0;
int result = WideCharToMultiByte(CP_UTF8, NULL, pUnicode, -1, pUTF8Buffer, nBufferSize, NULL, NULL);
if ((result > 0) && (pUTF8Buffer != NULL))
pUTF8Buffer[result-1] = 0;
return result;
}
int UTF82Unicode(const char* pUTF8, wchar_t* pUnicodeBuffer, int nBufferSize)
{
if( (nBufferSize == 0) && (pUnicodeBuffer != NULL) )
return 0;
int result = MultiByteToWideChar(CP_UTF8, NULL, pUTF8, -1, pUnicodeBuffer, nBufferSize);
if ((result > 0) && (pUnicodeBuffer != NULL))
pUnicodeBuffer[result-1] = 0;
return result;
}
int Unicode2Ansi(const wchar_t* pUnicode, char* pAnsiBuffer, int nBufferSize)
{
if( (nBufferSize == 0) && (pAnsiBuffer != NULL) )
return 0;
int result = ::WideCharToMultiByte(CP_ACP, 0, pUnicode, -1, pAnsiBuffer, nBufferSize, NULL, NULL);
if ((result > 0) && (pAnsiBuffer != NULL))
pAnsiBuffer[result-1] = 0;
return result;
}
int Ansi2Unicode(const char* pAnsi, wchar_t* pUnicodeBuffer, int nBufferSize)
{
if( (nBufferSize == 0) && (pUnicodeBuffer != NULL) )
return 0;
int result = ::MultiByteToWideChar(CP_ACP, 0, pAnsi, -1, pUnicodeBuffer, nBufferSize);
if ((result > 0) && (pUnicodeBuffer != NULL))
pUnicodeBuffer[result-1] = 0;
return result;
}
简单实用
CString strBuf;
int nSize = Unicode2UTF8(strBuf, NULL, 0);
char* szBuf = new char[nSize];
Unicode2UTF8(strBuf, szBuf, nSize);