文档章节

字符转换

rise-worlds
 rise-worlds
发布于 2016/06/20 13:43
字数 2856
阅读 6
收藏 0

一 C++ 中 string与wstring互转

方法一:

string WideToMutilByte(const wstring& _src)
{
int nBufSize = WideCharToMultiByte(GetACP(), 0, _src.c_str(),-1, NULL, 0, 0, FALSE);

char *szBuf = new char[nBufSize];

WideCharToMultiByte(GetACP(), 0, _src.c_str(),-1, szBuf, nBufSize, 0, FALSE);

string strRet(szBuf);

delete []szBuf;
szBuf = NULL;

return strRet;
}

wstring MutilByteToWide(const string& _src)
{
//计算字符串 string 转成 wchar_t 之后占用的内存字节数
int nBufSize = MultiByteToWideChar(GetACP(),0,_src.c_str(),-1,NULL,0);

//为 wsbuf 分配内存 BufSize 个字节
wchar_t *wsBuf = new wchar_t[nBufSize];

//转化为 unicode 的 WideString
MultiByteToWideChar(GetACP(),0,_src.c_str(),-1,wsBuf,nBufSize);

wstring wstrRet(wsBuf);

delete []wsBuf;
wsBuf = NULL;

return wstrRet;
}

转载:csdn

这篇文章里,我将给出几种C++ std::string和std::wstring相互转换的转换方法。
第一种方法:调用WideCharToMultiByte()和MultiByteToWideChar(),代码如下(关于详细的解释,可以参考《windows核心编程》):

#include <string>
#include <windows.h>
using namespace std;
//Converting a WChar string to a Ansi string
std::string WChar2Ansi(LPCWSTR pwszSrc)
{
         int nLen = WideCharToMultiByte(CP_ACP, 0, pwszSrc, -1, NULL, 0, NULL, NULL);
         if (nLen<= 0) return std::string("");
         char* pszDst = new char[nLen];
         if (NULL == pszDst) return std::string("");
         WideCharToMultiByte(CP_ACP, 0, pwszSrc, -1, pszDst, nLen, NULL, NULL);
         pszDst[nLen -1] = 0;
         std::string strTemp(pszDst);
         delete [] pszDst;
         return strTemp;
}

string ws2s(wstring& inputws)
{
        return WChar2Ansi(inputws.c_str());
}

//Converting a Ansi string to WChar string

std::wstring Ansi2WChar(LPCSTR pszSrc, int nLen)
{
    int nSize = MultiByteToWideChar(CP_ACP, 0, (LPCSTR)pszSrc, nLen, 0, 0);
    if(nSize <= 0) return NULL;
         WCHAR *pwszDst = new WCHAR[nSize+1];
    if( NULL == pwszDst) return NULL;
    MultiByteToWideChar(CP_ACP, 0,(LPCSTR)pszSrc, nLen, pwszDst, nSize);
    pwszDst[nSize] = 0;
    if( pwszDst[0] == 0xFEFF)                    // skip Oxfeff
        for(int i = 0; i < nSize; i ++)
                            pwszDst[i] = pwszDst[i+1];
    wstring wcharString(pwszDst);
         delete pwszDst;
    return wcharString;
}

std::wstring s2ws(const string& s)
{
     return Ansi2WChar(s.c_str(),s.size());
}

第二种方法:采用ATL封装_bstr_t的过渡:(注,_bstr_是Microsoft Specific的,所以下面代码可以在VS2005通过,无移植性);

#include <string>
#include <comutil.h>
using namespace std;
#pragma comment(lib, "comsuppw.lib")
string ws2s(const wstring& ws);
wstring s2ws(const string& s);
string ws2s(const wstring& ws)
{
         _bstr_t t = ws.c_str();
         char* pchar = (char*)t;
         string result = pchar;
         return result;
}

wstring s2ws(const string& s)
{
         _bstr_t t = s.c_str();
         wchar_t* pwchar = (wchar_t*)t;
         wstring result = pwchar;
         return result;
}

第三种方法:使用CRT库的mbstowcs()函数和wcstombs()函数,平台无关,需设定locale。

#include <string>
#include <locale.h>
using namespace std;
string ws2s(const wstring& ws)
{
         string curLocale = setlocale(LC_ALL, NULL);        // curLocale = "C";
         setlocale(LC_ALL, "chs");
         const wchar_t* _Source = ws.c_str();
         size_t _Dsize = 2 * ws.size() + 1;
         char *_Dest = new char[_Dsize];
         memset(_Dest,0,_Dsize);
         wcstombs(_Dest,_Source,_Dsize);
         string result = _Dest;
         delete []_Dest;
         setlocale(LC_ALL, curLocale.c_str());
         return result;
}

wstring s2ws(const string& s)
{
         setlocale(LC_ALL, "chs");
         const char* _Source = s.c_str();
         size_t _Dsize = s.size() + 1;
         wchar_t *_Dest = new wchar_t[_Dsize];
         wmemset(_Dest, 0, _Dsize);
         mbstowcs(_Dest,_Source,_Dsize);
         wstring result = _Dest;
         delete []_Dest;
         setlocale(LC_ALL, "C");
         return result;
}

二 utf8.utf16.utf32的相互转化

可以参考Unicode.org 上有ConvertUTF.c和ConvertUTF.h (下载地址:http://www.unicode.org/Public/PROGRAMS/CVTUTF/

实现文件ConvertUTF.c:(.h省)
/**//*
* Copyright 2001-2004 Unicode, Inc.
*
* Disclaimer
*
* This source code is provided as is by Unicode, Inc. No claims are
* made as to fitness for any particular purpose. No warranties of any
* kind are expressed or implied. The recipient agrees to determine
* applicability of information provided. If this file has been
* purchased on magnetic or optical media from Unicode, Inc., the
* sole remedy for any claim will be exchange of defective media
* within 90 days of receipt.
*
* Limitations on Rights to Redistribute This Code
*
* Unicode, Inc. hereby grants the right to freely use the information
* supplied in this file in the creation of products supporting the
* Unicode Standard, and to make copies of this file in any form
* for internal or external distribution as long as this notice
* remains attached.
*/

/**//* ---------------------------------------------------------------------

    Conversions between UTF32, UTF-16, and UTF-8. Source code file.
    Author: Mark E. Davis, 1994.
    Rev History: Rick McGowan, fixes & updates May 2001.
    Sept 2001: fixed const & error conditions per
    mods suggested by S. Parent & A. Lillich.
    June 2002: Tim D