判断文件编码类型

主要是根据文件的前面几个字节进行判断，这里对UTF32等没做判断

#include <iostream>
#include <fstream>
using namespace std;

enum
{
	CODE_TYPE_UNICODE_LE,
	CODE_TYPE_UNICODE_BE,
	CODE_TYPE_UTF8,
	CODE_TYPE_NEED_VERIFY,
};

int DetectCodeType(char *pFilePath)
{
	int codeType = 0;

	char buffer[16] = {0};
	ifstream ifs;

	ifs.open(pFilePath, ifstream::in);
	if(ifs.good())
	{
		// 读取前面三个字节即可
		ifs.read(buffer, 3);
		if (memcmp("\xFE\xFF", buffer, 2) == 0)
		{
			codeType = CODE_TYPE_UNICODE_BE;
		}
		else if (memcmp("\xFF\xFE", buffer, 2) == 0)
		{
			codeType = CODE_TYPE_UNICODE_LE;
		}
		else if (memcmp("\xEF\xBB", buffer, 2) == 0)
		{
			codeType = CODE_TYPE_UTF8;
		}
		else
		{
			codeType = CODE_TYPE_NEED_VERIFY;
		}
	}

	ifs.close();

	return codeType;
}

char* TestMemMove(char *src, char *dst, int count)
{
	char *ret = dst;
	if (src == NULL || dst == NULL)
	{
		return NULL;
	}
	if (dst <= src || dst >= (src + count))
	{
		while (count--)
		{
			*dst++ = *src++;
		}
	}
	else // 内存重叠
	{
		dst += count - 1;
		src += count - 1;
		while (count--)
		{
			*dst-- = *src--;
		}
	}

	return ret;
}

int _tmain(int argc, _TCHAR* argv[])
{
	char fileName[][64] = 
	{
		"E:\\Temp\\TestUnicodeBE.txt",
		"E:\\Temp\\TestUnicodeLE.txt",
		"E:\\Temp\\TestUTF8.txt",
		"E:\\Temp\\TestANSI.txt"
	};

	int count = sizeof(fileName) / 64;

	for (int i = 0; i < count; i++)
	{
		int codeType = DetectCodeType(fileName[i]);
		switch (codeType)
		{
		case CODE_TYPE_UNICODE_LE:
			{
				cout << "This is a Unicode LE file" << endl;
			}
			break;
		case CODE_TYPE_UNICODE_BE:
			{
				cout << "This is a Unicode BE file" << endl;
			}
			break;
		case CODE_TYPE_UTF8:
			{
				cout << "This is a UTF8 file" << endl;
			}
			break;
		case CODE_TYPE_NEED_VERIFY:
			{
				cout << "This file type need verify" << endl;
			}
			break;
		}
	}
	
	return 0;
}