转：UTF-8与GB2312之间的互换

╰+哭是因爲堅強的太久メ 2021-12-15 15:59 266阅读 0赞

UTF-8与GB2312之间的互换

作者：吴康彬  
　　相信一定有不少的程序开发人员时常会遇到字符编码的问题，而这个问题也是非常让人头痛的。因为这些都是潜在的错误，要找出这些错误也得要有这方面的开发经验才行。特别是在处理xml文档时 ，该问题的出现就更加的频繁了，有一次用java写服务器端程序，用vc写客户端与之交互。交互的协议都是用xml写的。结果在通讯时老是发现数据接受不正确。纳闷！于是用抓取网络数据包工具抓取数据，后来才发现原来是java上xml的头是这样的<?xml version="1.0" encoding="UTF-8"?>,而vc上默认的是GB2312。所以一遇到汉字数据就不正确了。去网上找资料，这方面的文章好象特别少，针对像这样的问题，下面我介绍一下我自己写的一个转换程序。当然，程序很简单。如果有画蛇添足的地方，还望各位高手一笑了之。  
　　如果您对UTF-8、Unicode、GB2312等还是很陌生的话，请查看[http://www.linuxforum.net/books/UTF-8-Unicode.html][http_www.linuxforum.net_books_UTF-8-Unicode.html]，我这里就不浪费口舌了。下面介绍一下WinAPI的两个函数：WideCharToMultiByte、MultiByteToWideChar。

函数原型：

int WideCharToMultiByte(  
UINT CodePage, // code page  
DWORD dwFlags, // performance and mapping flags  
LPCWSTR lpWideCharStr, // wide-character string  
int cchWideChar, // number of chars in string  
LPSTR lpMultiByteStr, // buffer for new string  
int cbMultiByte, // size of buffer  
LPCSTR lpDefaultChar, // default for unmappable chars  
LPBOOL lpUsedDefaultChar // set when default char used  
); //将宽字符转换成多个窄字符

int MultiByteToWideChar(  
UINT CodePage, // code page  
DWORD dwFlags, // character-type options  
LPCSTR lpMultiByteStr, // string to map  
int cbMultiByte, // number of bytes in string  
LPWSTR lpWideCharStr, // wide-character buffer  
int cchWideChar // size of buffer  
);//将多个窄字符转换成宽字符 需要用到的一些函数：  
CString CXmlProcess::HexToBin(CString string)//将16进制数转换成2进制  
\{  
if( string == "0") return "0000";  
if( string == "1") return "0001";  
if( string == "2") return "0010";  
if( string == "3") return "0011";  
if( string == "4") return "0100";  
if( string == "5") return "0101";  
if( string == "6") return "0110";  
if( string == "7") return "0111";  
if( string == "8") return "1000";  
if( string == "9") return "1001";  
if( string == "a") return "1010";  
if( string == "b") return "1011";  
if( string == "c") return "1100";  
if( string == "d") return "1101";  
if( string == "e") return "1110";  
if( string == "f") return "1111";  
return "";  
\}

CString CXmlProcess::BinToHex(CString BinString)//将2进制数转换成16进制  
\{  
if( BinString == "0000") return "0";  
if( BinString == "0001") return "1";  
if( BinString == "0010") return "2";  
if( BinString == "0011") return "3";  
if( BinString == "0100") return "4";  
if( BinString == "0101") return "5";  
if( BinString == "0110") return "6";  
if( BinString == "0111") return "7";  
if( BinString == "1000") return "8";  
if( BinString == "1001") return "9";  
if( BinString == "1010") return "a";  
if( BinString == "1011") return "b";  
if( BinString == "1100") return "c";  
if( BinString == "1101") return "d";  
if( BinString == "1110") return "e";  
if( BinString == "1111") return "f";  
return "";  
\}

int CXmlProcess::BinToInt(CString string)//2进制字符数据转换成10进制整型  
\{  
int len =0;  
int tempInt = 0;  
int strInt = 0;  
for(int i =0 ;i < string.GetLength() ;i ++)  
\{  
tempInt = 1;  
strInt = (int)string.GetAt(i)-48;  
for(int k =0 ;k < 7-i ; k++)  
\{  
tempInt = 2\*tempInt;  
\}  
len += tempInt\*strInt;  
\}  
return len;  
\} UTF-8转换成GB2312先把UTF-8转换成Unicode.然后再把Unicode通过函数WideCharToMultiByte转换成GB2312  
WCHAR\* CXmlProcess::UTF\_8ToUnicode(char \*ustart) //把UTF-8转换成Unicode  
\{  
char char\_one;  
char char\_two;  
char char\_three;  
int Hchar;  
int Lchar;  
char uchar\[2\];  
WCHAR \*unicode;  
CString string\_one;  
CString string\_two;  
CString string\_three;  
CString combiString;  
char\_one = \*ustart;  
char\_two = \*(ustart+1);  
char\_three = \*(ustart+2);  
string\_one.Format("%x",char\_one);  
string\_two.Format("%x",char\_two);  
string\_three.Format("%x",char\_three);  
string\_three = string\_three.Right(2);  
string\_two = string\_two.Right(2);  
string\_one = string\_one.Right(2);  
string\_three = HexToBin(string\_three.Left(1))+HexToBin(string\_three.Right(1));  
string\_two = HexToBin(string\_two.Left(1))+HexToBin(string\_two.Right(1));  
string\_one = HexToBin(string\_one.Left(1))+HexToBin(string\_one.Right(1));  
combiString = string\_one +string\_two +string\_three;  
combiString = combiString.Right(20);  
combiString.Delete(4,2);  
combiString.Delete(10,2);  
Hchar = BinToInt(combiString.Left(8));  
Lchar = BinToInt(combiString.Right(8));  
uchar\[1\] = (char)Hchar;  
uchar\[0\] = (char)Lchar;  
unicode = (WCHAR \*)uchar;  
return unicode;  
\}

char \* CXmlProcess::UnicodeToGB2312(unsigned short uData) //把Unicode 转换成 GB2312  
\{  
char \*buffer ;  
buffer = new char\[sizeof(WCHAR)\];  
WideCharToMultiByte(CP\_ACP,NULL,&uData,1,buffer,sizeof(WCHAR),NULL,NULL);  
return buffer;  
\} 　　GB2312转换成UTF-8：先把GB2312通过函数MultiByteToWideChar转换成Unicode.然后再把Unicode通过拆开Unicode后拼装成UTF-8。

WCHAR \* CXmlProcess::Gb2312ToUnicode(char \*gbBuffer) //GB2312 转换成　Unicode  
\{  
WCHAR \*uniChar;  
uniChar = new WCHAR\[1\];  
::MultiByteToWideChar(CP\_ACP,MB\_PRECOMPOSED,gbBuffer,2,uniChar,1);  
return uniChar;  
\}  
char \* CXmlProcess::UnicodeToUTF\_8(WCHAR \*UniChar) // Unicode 转换成UTF-8  
\{  
char \*buffer;  
CString strOne;  
CString strTwo;  
CString strThree;  
CString strFour;  
CString strAnd;  
buffer = new char\[3\];  
int hInt,lInt;  
hInt = (int)((\*UniChar)/256);  
lInt = (\*UniChar)%256;  
CString string ;  
string.Format("%x",hInt);  
strTwo = HexToBin(string.Right(1));  
string = string.Left(string.GetLength() - 1);  
strOne = HexToBin(string.Right(1));  
string.Format("%x",lInt);  
strFour = HexToBin(string.Right(1));  
string = string.Left(string.GetLength() -1);  
strThree = HexToBin(string.Right(1));  
strAnd = strOne +strTwo + strThree + strFour;  
strAnd.Insert(0,"1110");  
strAnd.Insert(8,"10");  
strAnd.Insert(16,"10");  
strOne = strAnd.Left(8);  
strAnd = strAnd.Right(16);  
strTwo = strAnd.Left(8);  
strThree = strAnd.Right(8);  
\*buffer = (char)BinToInt(strOne);  
buffer\[1\] = (char)BinToInt(strTwo);  
buffer\[2\] = (char)BinToInt(strThree);  
return buffer;  
\} 例子：将GB2312转换成UTF-8的调用：  
char \* CXmlProcess::translateCharToUTF\_8(char \*xmlStream, int len)  
\{  
int newCharLen =0 ;  
int oldCharLen = 0;  
int revCharLen = len;  
char\* newCharBuffer;  
char\* finalCharBuffer;  
char \*buffer ;  
CString string;  
buffer = new char\[sizeof(WCHAR)\];  
newCharBuffer = new char\[int(1.5\*revCharLen)\];//设置最大的一个缓冲区  
while(oldCharLen < revCharLen)  
\{  
if( \*(xmlStream + oldCharLen) >= 0)  
\{  
\*(newCharBuffer+newCharLen) = \*(xmlStream +oldCharLen);  
newCharLen ++;  
oldCharLen ++;  
\}//如果是英文直接复制就可以  
else  
\{  
WCHAR \*pbuffer = this->Gb2312ToUnicode(xmlStream+oldCharLen);  
buffer = this->UnicodeToUTF\_8(pbuffer);  
\*(newCharBuffer+newCharLen) = \*buffer;  
\*(newCharBuffer +newCharLen +1) = \*(buffer + 1);  
\*(newCharBuffer +newCharLen +2) = \*(buffer + 2);  
newCharLen += 3;  
oldCharLen += 2;  
\}  
\}  
newCharBuffer\[newCharLen\] = ''\\0'';  
CString string1 ;  
string1.Format("%s",newCharBuffer);  
finalCharBuffer = new char\[newCharLen+1\];  
memcpy(finalCharBuffer,newCharBuffer,newCharLen+1);  
return finalCharBuffer;  
\}  
程序都非常的简单，由于实在太穷。已经吃了两天的方便面。所以现在头昏，程序的详细说明就不写了。程序员到了像我这样的地步也真是少见。工资低没有办法。哎！！！！

本文来自CSDN博客，转载请标明出处：[http://blog.csdn.net/andylin02/archive/2010/01/22/5224962.aspx][http_blog.csdn.net_andylin02_archive_2010_01_22_5224962.aspx]

转载于:https://www.cnblogs.com/cumtb3S/archive/2010/06/14/1758381.html

[http_www.linuxforum.net_books_UTF-8-Unicode.html]: http://www.linuxforum.net/books/UTF-8-Unicode.html
[http_blog.csdn.net_andylin02_archive_2010_01_22_5224962.aspx]: http://blog.csdn.net/andylin02/archive/2010/01/22/5224962.aspx