windows下C++几种编码之间的转换

前言：
1、在windows下进行编程的时候一般使用的都是unicode编码，所以我们在进行操作的时候正常情况下都会把获取的字符串转换成unicode编码在进行操作；
2、当我们根据url获取一串字符串的时候一般进行解析完都是ANSI编码，所以这种的也需要转换成unicode编码再进行操作

一、GBK -> UTF-8

void GB2312ToUTF_8(string& pOut, char *pText, int pLen)
{
	char buf[4];
	memset(buf, 0, 4);

	pOut.clear();

	int i = 0;
	while (i < pLen)
	{
		//如果是英文直接复制就可以  
		if (pText[i] >= 0)
		{
			char asciistr[2] = { 0 };
			asciistr[0] = (pText[i++]);
			pOut.append(asciistr);
		}
		else
		{
			WCHAR pbuffer;
			Gb2312ToUnicode(&pbuffer, pText + i);

			UnicodeToUTF_8(buf, &pbuffer);

			pOut.append(buf);

			i += 3;
		}
	}

	return;
}

二、UTF-8 -> GBK

void UTF_8ToGB2312(string &pOut, char *pText, int pLen)
{
	char buf[4];
	char* rst = new char[pLen + (pLen >> 2) + 2];
	memset(buf, 0, 4);
	memset(rst, 0, pLen + (pLen >> 2) + 2);

	int i = 0;
	int j = 0;

	while (i < pLen)
	{
		if (*(pText + i) >= 0)
		{

			rst[j++] = pText[i++];
		}
		else
		{
			WCHAR Wtemp;


			UTF_8ToUnicode(&Wtemp, pText + i);

			UnicodeToGB2312(buf, Wtemp);

			unsigned short int tmp = 0;
			tmp = rst[j] = buf[0];
			tmp = rst[j + 1] = buf[1];
			tmp = rst[j + 2] = buf[2];

			//newBuf[j] = Ctemp[0];  
			//newBuf[j + 1] = Ctemp[1];  

			i += 3;
			j += 3;
		}

	}
	rst[j] = '\0';
	pOut = rst;
	delete[]rst;
}

三、Unicode（wchar）-> UTF-8

1、
const char* WcharToUtf8(const wchar_t *pwStr)
{
	if (pwStr == NULL)
	{
		return NULL;
	}

	int len = WideCharToMultiByte(CP_UTF8, 0, pwStr, -1, NULL, 0, NULL, NULL);
	if (len <= 0)
	{
		return NULL;
	}
	char *pStr = new char[len];
	WideCharToMultiByte(CP_UTF8, 0, pwStr, -1, pStr, len, NULL, NULL);
	return pStr;
}

2、
void UnicodeToUTF_8(char* pOut, WCHAR* pText)
{
	// 注意 WCHAR高低字的顺序,低字节在前，高字节在后  
	char* pchar = (char *)pText;

	pOut[0] = (0xE0 | ((pchar[1] & 0xF0) >> 4));
	pOut[1] = (0x80 | ((pchar[1] & 0x0F) << 2)) + ((pchar[0] & 0xC0) >> 6);
	pOut[2] = (0x80 | (pchar[0] & 0x3F));

	return;
}

四、UTF-8 -> Unicode（wchar）

1、
const wchar_t* Utf8ToWchar(const char *pStr)
{
	if (pStr == NULL)
	{
		return NULL;
	}

	int len = MultiByteToWideChar(CP_UTF8, 0, pStr, -1, NULL, 0);
	if (len <= 0)
	{
		return NULL;
	}
	wchar_t *pwStr = new wchar_t[len];
	MultiByteToWideChar(CP_UTF8, 0, pStr, -1, pwStr, len);
	return pwStr;
}

2、
void UTF_8ToUnicode(WCHAR* pOut, char *pText)
{
	char* uchar = (char *)pOut;

	uchar[1] = ((pText[0] & 0x0F) << 4) + ((pText[1] >> 2) & 0x0F);
	uchar[0] = ((pText[1] & 0x03) << 6) + (pText[2] & 0x3F);

	return;
}

五、Ansi -> Unicode（wchar）

std::wstring Ansi2WChar(LPCSTR pszSrc, int nLen)
{

		    int nSize = MultiByteToWideChar(CP_UTF8, 0, (LPCSTR)pszSrc, nLen, 0, 0);
		     if (nSize <= 0) return NULL;
		     WCHAR *pwszDst = new WCHAR[nSize + 1];
	     if (NULL == pwszDst)
			        return NULL;
         MultiByteToWideChar(CP_UTF8, 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;
}

六、url转换成utf-8

std::string UrlDecode(const std::string& szToDecode)
{
	std::string result;
	size_t nsumlen = szToDecode.length();
	int hex = 0;
	for (size_t i = 0; i < nsumlen; ++i)
	{
		switch (szToDecode[i])
		{
		case '%':
			// 2 char after % at least
			if (i + 1 < nsumlen && i + 2 < nsumlen) {
				if (isxdigit(szToDecode[i + 1]) && isxdigit(szToDecode[i + 2]))
				{
					std::string hexStr = szToDecode.substr(i + 1, 2);
					hex = strtol(hexStr.c_str(), 0, 16);
					if (!((hex >= 48 && hex <= 57) || //0-9
						(hex >= 97 && hex <= 122) ||   //a-z
						(hex >= 65 && hex <= 90) ||    //A-Z
						//[$-_.+!*'(),]  [$&+,/:;=?@]
						hex == 0x21 || hex == 0x24 || hex == 0x26 || hex == 0x27 || hex == 0x28 || hex == 0x29
						|| hex == 0x2a || hex == 0x2b || hex == 0x2c || hex == 0x2d || hex == 0x2e || hex == 0x2f
						|| hex == 0x3A || hex == 0x3B || hex == 0x3D || hex == 0x3f || hex == 0x40 || hex == 0x5f
						))
					{
						result += char(hex);
						i += 2;
					}
					else {
						result += '%';
					}
				}
				else {
					result += '%';
				}
			}
			// if no 2 char after %
			else {
				result += szToDecode[i];
			}
			break;
		default:
			result += szToDecode[i];
			break;
		}
	}
	return result;
}