windows下的多字节、utf8、unicode字符转换函数

概述

windows的C++工程一般为unicode字符集和多字节字符集，在中文目录下调用接口时经常会碰到字符转换的问题。整理了如下几个函数

• AnsiToUnicode
• UnicodeToAnsi
• UnicodeToUtf8
• Utf8ToUnicode
• AnsiToUtf8
• Utf8ToAnsi
• IsUTF8

函数实现

// 宽字符转UTF8 
std::string UnicodeToUtf8Str(const std::wstring& in)
{
	std::string s(in.length() * 3 + 1, ' ');
	size_t len = ::WideCharToMultiByte(CP_UTF8, 0, in.c_str(), in.length(), &s[0], s.length(), NULL, NULL);
	s.resize(len);
	return s;
}

// 宽字符转ansi
std::string UnicodeToAnsiStr(const std::wstring& in)
{
	std::string s(in.length() * 2 + 1, ' ');
	size_t len = ::WideCharToMultiByte(CP_ACP, 0, in.c_str(), in.length(), &s[0], s.length(), NULL, NULL);
	s.resize(len);
	return s;
}

// ansi 转宽字符 
std::wstring AnsiToUnicodeWStr(const std::string& in)
{
	std::wstring s(in.length(), _T(' '));
	size_t len = ::MultiByteToWideChar(CP_ACP, 0, in.c_str(), in.length(), &s[0], s.length());
	s.resize(len);
	return s;
}
// UTF8 转宽字符 
std::wstring Utf8ToUnicodeWStr(const std::string& in)
{
	std::wstring s(in.length(), _T(' '));
	size_t len = ::MultiByteToWideChar(CP_UTF8, 0, in.c_str(), in.length(), &s[0], s.length());
	s.resize(len);
	return s;
}

//ansi 转utf8
std::string AnsiToUtf8Str(const std::string& in)
{
	std::wstring wstr = AnsiToUnicodeWStr(in);

	return UnicodeToUtf8Str(wstr);
}

//utf8 转ansi
std::string Utf8ToAnsiStr(const std::string& in)
{
	std::wstring wstr = Utf8ToUnicodeWStr(in);

	return UnicodeToAnsiStr(wstr);
}

// 判断传入字符串是否为utf-8
bool IsUTF8(const void* pBuffer, long size)
{
	bool IsUTF8 = true;
	unsigned char* start = (unsigned char*)pBuffer;
	unsigned char* end = (unsigned char*)pBuffer + size;
	while (start < end)
	{
		if (*start < 0x80) // (10000000): 值小于0x80的为ASCII字符    
		{
			start++;
		}
		else if (*start < (0xC0)) // (11000000): 值介于0x80与0xC0之间的为无效UTF-8字符    
		{
			IsUTF8 = false;
			break;
		}
		else if (*start < (0xE0)) // (11100000): 此范围内为2字节UTF-8字符    
		{
			if (start >= end - 1)
			{
				break;
			}

			if ((start[1] & (0xC0)) != 0x80)
			{
				IsUTF8 = false;
				break;
			}

			start += 2;
		}
		else if (*start < (0xF0)) // (11110000): 此范围内为3字节UTF-8字符    
		{
			if (start >= end - 2)
			{
				break;
			}

			if ((start[1] & (0xC0)) != 0x80 || (start[2] & (0xC0)) != 0x80)
			{
				IsUTF8 = false;
				break;
			}

			start += 3;
		}
		else
		{
			IsUTF8 = false;
			break;
		}
	}

	return IsUTF8;
}