c++ 判断gbk或者utf-8编码，然后互转

1：windows版和linux版

#include <iostream>
#include <string>
#include <string.h>
#include <stdlib.h>

using namespace std;

int preNUm(unsigned char byte) {
	unsigned char mask = 0x80;
	int num = 0;
	for (int i = 0; i < 8; i++) {
		if ((byte & mask) == mask) {
			mask = mask >> 1;
			num++;
		}
		else {
			break;
		}
	}
	return num;
}

bool isUtf8(unsigned char* data, int len) {
	int num = 0;
	int i = 0;
	while (i < len) {
		if ((data[i] & 0x80) == 0x00) {
			// 0XXX_XXXX
			i++;
			continue;
		}
		else if ((num = preNUm(data[i])) > 2) {
			// 110X_XXXX 10XX_XXXX
			// 1110_XXXX 10XX_XXXX 10XX_XXXX
			// 1111_0XXX 10XX_XXXX 10XX_XXXX 10XX_XXXX
			// 1111_10XX 10XX_XXXX 10XX_XXXX 10XX_XXXX 10XX_XXXX
			// 1111_110X 10XX_XXXX 10XX_XXXX 10XX_XXXX 10XX_XXXX 10XX_XXXX
			// preNUm() 返回首个字节8个bits中首�?0bit前面1bit的个数，该数量也是该字符所使用的字节数        
			i++;
			for (int j = 0; j < num - 1; j++) {
				//判断后面num - 1 个字节是不是都是10开
				if ((data[i] & 0xc0) != 0x80) {
					return false;
				}
				i++;
			}
		}
		else {
			//其他情况说明不是utf-8
			return false;
		}
	}
	return true;
}

bool isGBK(unsigned char* data, int len) {
	int i = 0;
	while (i < len) {
		if (data[i] <= 0x7f) {
			//编码小于等于127,只有一个字节的编码，兼容ASCII
			i++;
			continue;
		}
		else {
			//大于127的使用双字节编码
			if (data[i] >= 0x81 &&
				data[i] <= 0xfe &&
				data[i + 1] >= 0x40 &&
				data[i + 1] <= 0xfe &&
				data[i + 1] != 0xf7) {
				i += 2;
				continue;
			}
			else {
				return false;
			}
		}
	}
	return true;
}

typedef enum {
	GBK,
	UTF8,
	UNKOWN
} CODING;
//需要说明的是，isGBK()是通过双字节是否落在gbk的编码范围内实现的，
//而utf-8编码格式的每个字节都是落在gbk的编码范围内�?
//所以只有先调用isUtf8()先判断不是utf-8编码，再调用isGBK()才有意义
CODING GetCoding(unsigned char* data, int len) {
	CODING coding;
	if (isUtf8(data, len) == true) {
		coding = UTF8;
	}
	else if (isGBK(data, len) == true) {
		coding = GBK;
	}
	else {
		coding = UNKOWN;
	}
	return coding;
}



#ifdef _WIN32
#include <windows.h>

string GbkToUtf8(const char *src_str)
{
	int len = MultiByteToWideChar(CP_ACP, 0, src_str, -1, NULL, 0);
	wchar_t* wstr = new wchar_t[len + 1];
	memset(wstr, 0, len + 1);
	MultiByteToWideChar(CP_ACP, 0, src_str, -1, wstr, len);
	len = WideCharToMultiByte(CP_UTF8, 0, wstr, -1, NULL, 0, NULL, NULL);
	char* str = new char[len + 1];
	memset(str, 0, len + 1);
	WideCharToMultiByte(CP_UTF8, 0, wstr, -1, str, len, NULL, NULL);
	string strTemp = str;
	if (wstr) delete[] wstr;
	if (str) delete[] str;
	return strTemp;
}

string Utf8ToGbk(const char *src_str)
{
	int len = MultiByteToWideChar(CP_UTF8, 0, src_str, -1, NULL, 0);
	wchar_t* wszGBK = new wchar_t[len + 1];
	memset(wszGBK, 0, len * 2 + 2);
	MultiByteToWideChar(CP_UTF8, 0, src_str, -1, wszGBK, len);
	len = WideCharToMultiByte(CP_ACP, 0, wszGBK, -1, NULL, 0, NULL, NULL);
	char* szGBK = new char[len + 1];
	memset(szGBK, 0, len + 1);
	WideCharToMultiByte(CP_ACP, 0, wszGBK, -1, szGBK, len, NULL, NULL);
	string strTemp(szGBK);
	if (wszGBK) delete[] wszGBK;
	if (szGBK) delete[] szGBK;
	return strTemp;
}
#else
#include <iconv.h>

int GbkToUtf8(char *str_str, size_t src_len, char *dst_str, size_t dst_len)
{
	iconv_t cd;
	char **pin = &str_str;
	char **pout = &dst_str;

	cd = iconv_open("utf8", "gbk");
	if (cd == 0)
		return -1;
	memset(dst_str, 0, dst_len);
	if (iconv(cd, pin, &src_len, pout, &dst_len) == -1)
		return -1;
	iconv_close(cd);
	*pout = '\0';

	return 0;
}

int Utf8ToGbk(char *src_str, size_t src_len, char *dst_str, size_t dst_len)
{
	iconv_t cd;
	char **pin = &src_str;
	char **pout = &dst_str;

	cd = iconv_open("gbk", "utf8");
	if (cd == 0)
		return -1;
	memset(dst_str, 0, dst_len);
	if (iconv(cd, pin, &src_len, pout, &dst_len) == -1)
		return -1;
	iconv_close(cd);
	*pout = '\0';

	return 0;
}


#endif



int main(void)
{
	char *src_str = "hello,你好撒大沙发,这里是科大讯飞啊撒旦飞洒发大师傅撒犯得上发生";
	cout << "origin string: " << src_str << endl;
	cout << "GetCoding: " << GetCoding((unsigned char*)src_str, strlen(src_str)) << endl;
#ifdef _WIN32
	string dst_str = Utf8ToGbk(src_str);
	cout << "utf8 to gbk: " << dst_str << endl;

	string str_utf8 = GbkToUtf8(dst_str.c_str());
	cout << "gbk to utf: " << str_utf8 << endl;
#else
	// unix default is utf8
	char dst_gbk[1024] = { 0 };
	Utf8ToGbk(src_str, strlen(src_str), dst_gbk, sizeof(dst_gbk));
	cout << "utf8 to gbk: " << dst_gbk << endl;

	char dst_utf8[1024] = { 0 };
	GbkToUtf8(dst_gbk, strlen(dst_gbk), dst_utf8, sizeof(dst_utf8));
	cout << "gbk to utf8: " << dst_utf8 << endl;
#endif
	system("pause");
	return 0;
}

2：c++11 版windows和linux

#include <iostream>
#include <string>
#include <string.h>
#include <stdlib.h>
#include <locale>
#include <codecvt>

using namespace std;

int preNUm(unsigned char byte) {
	unsigned char mask = 0x80;
	int num = 0;
	for (int i = 0; i < 8; i++) {
		if ((byte & mask) == mask) {
			mask = mask >> 1;
			num++;
		}
		else {
			break;
		}
	}
	return num;
}

bool isUtf8(unsigned char* data, int len) {
	int num = 0;
	int i = 0;
	while (i < len) {
		if ((data[i] & 0x80) == 0x00) {
			// 0XXX_XXXX
			i++;
			continue;
		}
		else if ((num = preNUm(data[i])) > 2) {
			// 110X_XXXX 10XX_XXXX
			// 1110_XXXX 10XX_XXXX 10XX_XXXX
			// 1111_0XXX 10XX_XXXX 10XX_XXXX 10XX_XXXX
			// 1111_10XX 10XX_XXXX 10XX_XXXX 10XX_XXXX 10XX_XXXX
			// 1111_110X 10XX_XXXX 10XX_XXXX 10XX_XXXX 10XX_XXXX 10XX_XXXX
			// preNUm() 返回首个字节8个bits中首�?0bit前面1bit的个数，该数量也是该字符所使用的字节数        
			i++;
			for (int j = 0; j < num - 1; j++) {
				//判断后面num - 1 个字节是不是都是10开
				if ((data[i] & 0xc0) != 0x80) {
					return false;
				}
				i++;
			}
		}
		else {
			//其他情况说明不是utf-8
			return false;
		}
	}
	return true;
}

bool isGBK(unsigned char* data, int len) {
	int i = 0;
	while (i < len) {
		if (data[i] <= 0x7f) {
			//编码小于等于127,只有一个字节的编码，兼容ASCII
			i++;
			continue;
		}
		else {
			//大于127的使用双字节编码
			if (data[i] >= 0x81 &&
				data[i] <= 0xfe &&
				data[i + 1] >= 0x40 &&
				data[i + 1] <= 0xfe &&
				data[i + 1] != 0xf7) {
				i += 2;
				continue;
			}
			else {
				return false;
			}
		}
	}
	return true;
}

typedef enum {
	GBK,
	UTF8,
	UNKOWN
} CODING;
//需要说明的是，isGBK()是通过双字节是否落在gbk的编码范围内实现的，
//而utf-8编码格式的每个字节都是落在gbk的编码范围内�?
//所以只有先调用isUtf8()先判断不是utf-8编码，再调用isGBK()才有意义
CODING GetCoding(unsigned char* data, int len) {
	CODING coding;
	if (isUtf8(data, len) == true) {
		coding = UTF8;
	}
	else if (isGBK(data, len) == true) {
		coding = GBK;
	}
	else {
		coding = UNKOWN;
	}
	return coding;
}


string GbkToUtf8(const std::string& str)
{
#ifdef _WIN32
	//GBK locale name in windows
	const char* GBK_LOCALE_NAME = ".936";
#else
	//GBK locale name in linux
	const char* GBK_LOCALE_NAME = "zh_CN.GBK";
#endif
	std::wstring_convert<std::codecvt_byname<wchar_t, char, mbstate_t>> convert(new std::codecvt_byname<wchar_t, char, mbstate_t>(GBK_LOCALE_NAME));
	std::wstring tmp_wstr = convert.from_bytes(str);

	std::wstring_convert<std::codecvt_utf8_utf16<wchar_t>> cv2;
	return cv2.to_bytes(tmp_wstr);
}

string Utf8ToGbk(const std::string& str)
{
	std::wstring_convert<std::codecvt_utf8<wchar_t> > conv;
	std::wstring tmp_wstr = conv.from_bytes(str);
#ifdef _WIN32
	//GBK locale name in windows
	const char* GBK_LOCALE_NAME = ".936";
#else
	//GBK locale name in linux
	const char* GBK_LOCALE_NAME = "zh_CN.GBK";
#endif
	std::wstring_convert<std::codecvt_byname<wchar_t, char, mbstate_t>> convert(new std::codecvt_byname<wchar_t, char, mbstate_t>(GBK_LOCALE_NAME));
	return convert.to_bytes(tmp_wstr);
}



int main(void)
{
	std::string src_str = "hello,你好撒大沙发,这里是科大讯飞啊撒旦飞洒发大师傅撒犯得上发生";
	cout << "origin string: " << src_str << endl;
	cout << "GetCoding: " << GetCoding((unsigned char*)src_str.c_str(), src_str.length()) << endl;
#ifdef _WIN32
	string dst_str = Utf8ToGbk(src_str);
	cout << "utf8 to gbk: " << dst_str << endl;

	string str_utf8 = GbkToUtf8(dst_str.c_str());
	cout << "gbk to utf: " << str_utf8 << endl;

	system("pause");
	return 0;
}