常用工具函数记录--字符串转换

c/c++日常工作开发中没有什么比字符串操作、文件操作用的更多了，这里记录一下工程里经常用到的字符串操作的一些代码片段，方便后面需要的朋友摘取使用：

1. 对std::string 首尾进行空格删除操作：

std::string StringStrim(_In_ std::string& strIn)
{
	if (!strIn.empty())
	{
		strIn.erase(0, strIn.find_first_not_of(" "));
		strIn.erase(strIn.find_last_not_of(" ") + 1);
	}
	return std::move(strIn);
}

2. 按照给定的特征对std::string 进行分割，并返回std::vector存储的分割后的内容：

std::vector<std::string> vStringSplit(_In_ const std::string& s, _In_ const std::string& delim)
{
	std::vector<std::string> elems;
	size_t pos = 0;
	size_t len = s.length();
	size_t delim_len = delim.length();
	if (delim_len == 0)
		return elems;
	while (pos < len)
	{
		int find_pos = s.find(delim, pos);
		if (find_pos < 0)
		{
			elems.push_back(s.substr(pos, len - pos));
			break;
		}
		std::string sss(s.substr(pos, find_pos - pos));
		if (sss.length() > 0 && sss != " ")
		{
			elems.push_back(sss);
		}

		pos = find_pos + delim_len;
	}
	return std::move(elems);
}

3. 对字符串进行URL格式编码或者反编码：

//需要使用的工具函数
unsigned char ToHex(unsigned char x)
{
	return  x > 9 ? x + 55 : x + 48;
}

unsigned char FromHex(unsigned char x)
{
	unsigned char y;
	if (x >= 'A' && x <= 'Z') y = x - 'A' + 10;
	else if (x >= 'a' && x <= 'z') y = x - 'a' + 10;
	else if (x >= '0' && x <= '9') y = x - '0';

	return y;
}

static inline bool is_unambiguous(char c) {
	return IS_ALPHANUM(c) ||
		c == '-' ||
		c == '_' ||
		c == '.' ||
		c == '/' ||
		c == '~';
}

static inline unsigned char hex2i(char hex) {
	return hex <= '9' ? hex - '0' :
		hex <= 'F' ? hex - 'A' + 10 : hex - 'a' + 10;
}

//对std::string 进行URL编码
std::string url_escape(_In_ const char* istr)
{
	std::string ostr;
	const char* p = istr;
	char szHex[4] = { 0 };
	while (*p != '\0') {
		if (is_unambiguous(*p)) {
			ostr += *p;
		}
		else {
			sprintf_s(szHex,4, "%%%02X", *p);
			ostr += szHex;
		}
		++p;
	}
	return std::move(ostr);
}

//对URL类型字符串进行反编码
std::string url_unescape(_In_ const char* istr)
{
	std::string ostr;
	const char* p = istr;
	while (*p != '\0') {
		if (*p == '%' &&
			IS_HEX(p[1]) &&
			IS_HEX(p[2])) {
			ostr += ((hex2i(p[1]) << 4) | hex2i(p[2]));
			p += 3;
		}
		else {
			ostr += *p;
			++p;
		}
	}
	return std::move(ostr);;
}

4. UNICODE/ANSI相关的转换

#define MAX_STRING_LENGTH 1024*1024
//代码里使用了std::make_shared，注意编译时的c++标准需要切换到17及其以上

bool Ansi_To_Unicode(_In_ const std::string& strIn, _Out_ std::wstring& strOut)
{
	bool bCov = false;
	size_t  len = strIn.length();
	if (len && len<= MAX_STRING_LENGTH)
	{
		int unicodeLen = MultiByteToWideChar(CP_ACP,
			0,
			strIn.c_str(),
			-1,
			NULL,
			0);

		auto pUnicode = std::make_shared<wchar_t[]>(unicodeLen + 1);
		if(pUnicode)
		{
			MultiByteToWideChar(CP_ACP,
				0,
				strIn.c_str(),
				-1,
				(LPWSTR)pUnicode.get(),
				unicodeLen);

			strOut = pUnicode.get();
			bCov = true;
		}
		else
		{
			//内存申请失败，大小为 unicodeLen
		}
	}
	else
	{
		//字符串长度为0，或者长度大于1M
	}
	
	return bCov;
}

bool Unicode_To_Ansi(const std::wstring& strIn, std::string& strOut)
{
	bool bCov = false;
	int iLen = strIn.length() * 2;
	if (iLen && iLen <= MAX_STRING_LENGTH)
	{
		auto pBuf = std::make_shared<char[]>(iLen + 1);
		size_t iRet = WideCharToMultiByte(CP_ACP, 0, strIn.c_str(), -1, pBuf.get(), iLen, NULL, NULL);
		if (iRet > 0)
		{
			strOut = pBuf.get();
			bCov = true;
		}
		else
		{
			//字符串转换失败
		}
	}
	else
	{
		//字符串长度为0，或者长度大于1M
	}

	return bCov;
}


bool string_To_UTF8(_In_ const std::string& str, _Out_ std::string& strOut)
{
	bool bSuc = false;
	int nwLen = ::MultiByteToWideChar(CP_ACP, 0, str.c_str(), -1, NULL, 0);
	if (nwLen && nwLen<= MAX_STRING_LENGTH)
	{
		auto pwBuf = std::make_shared<wchar_t[]>(nwLen + 1); 

		::MultiByteToWideChar(CP_ACP, 0, str.c_str(), str.length(), (LPWSTR)pwBuf.get(), nwLen);

		int nLen = ::WideCharToMultiByte(CP_UTF8, 0, pwBuf.get(), -1, NULL, NULL, NULL, NULL);
		if(nLen)
		{
			auto pBuf = std::make_shared<char[]>(nLen + 1);

			::WideCharToMultiByte(CP_UTF8, 0, pwBuf.get(), nwLen, (LPSTR)pBuf.get(), nLen, NULL, NULL);

			strOut = (char*)pBuf.get();
			bSuc = true;
		}
		else
		{
			//内存申请失败
		}

	}
	else
	{
		//字符串长度为0，或者长度大于1M
	}


	return bSuc;
}

 bool UTF8_To_ANSI(_In_ std::string& strUtf8In,_Out_ std::string& strOut)
{
	 bool bSuc = false;
	int nLen = MultiByteToWideChar(CP_UTF8, NULL, strUtf8In.c_str(), -1, NULL, NULL);
	if (nLen && nLen <= MAX_STRING_LENGTH)
	{
		auto wszBuffer = std::make_shared<wchar_t[]>(nLen + 1);
		
		nLen = MultiByteToWideChar(CP_UTF8, NULL, strUtf8In.c_str(), -1, wszBuffer.get(), nLen);
		if (nLen)
		{
			wszBuffer[nLen] = 0;

			nLen = WideCharToMultiByte(936, NULL, wszBuffer.get(), -1, NULL, NULL, NULL, NULL);
			if (nLen)
			{
				auto szBuffer = std::make_shared<char[]>(nLen + 1);
				nLen = WideCharToMultiByte(936, NULL, wszBuffer.get(), -1, (LPSTR)szBuffer.get(), nLen, NULL, NULL);
				szBuffer[nLen] = 0;

				strOut = (char*) szBuffer.get();
				bSuc = true;

			}
			else
			{
				//内存申请失败
			}

		}
		else
		{
			//内存申请失败
		}
	}
	else
	{
		//字符串长度为0，或者长度大于1M
	}

	return bSuc;
}

5. GUID子串创建

//注意需要包含这个库
#pragma comment(lib,"rpcrt4.lib")

std::string MakeGuid()
{
	std::string strGuid;
	GUID guid;
	if (S_OK == ::UuidCreate(&guid)) 
	{
		char cguid[128] = { 0 };
		sprintf_s(cguid,128,"%08X-%04X-%04x-%02X%02X-%02X%02X%02X%02X%02X%02X",
			guid.Data1, guid.Data2, guid.Data3,
			guid.Data4[0], guid.Data4[1], guid.Data4[2], guid.Data4[3],
			guid.Data4[4], guid.Data4[5], guid.Data4[6], guid.Data4[7]);
		strGuid = cguid;
	}
	return strGuid;
}