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./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!!!!
|
/* 字符串编码转换 GBK to UTF8 (ansi版) xmwen@126.com */ char *gbk2utf8(const char *strGBK){ int len; wchar_t *strUnicode; char *strUTF8; if (!strGBK){return NULL;} len = MultiByteToWideChar(CP_GBK, 0,strGBK, -1, NULL,0); if (len <1){return NULL;} strUnicode = (wchar_t *) malloc(sizeof(wchar_t) * len); if (!strUnicode){return NULL;} len = MultiByteToWideChar(CP_GBK, 0, strGBK, -1, strUnicode, len); if (len<1){free(strUnicode);return NULL;} len = WideCharToMultiByte(CP_UTF8, 0, strUnicode, -1, NULL, 0, NULL, NULL); if (len<1){free(strUnicode);return NULL;} strUTF8 = (char *) malloc(sizeof(char) * len); if (!strUTF8){free(strUnicode);return NULL;} len = WideCharToMultiByte (CP_UTF8, 0, strUnicode, -1, strUTF8, len, NULL,NULL); free(strUnicode); if (len<1){free(strUTF8);return NULL;} return strUTF8; }
( xmwen 发表于 2009-11-3 19:38:00)
[ 原创文档 本文适合中级读者 已阅读34485次 ]
搞笑,这种害人害己的文章还有这么多人访问。
作者光知道 WideCharToMultiByte 可以把 Unicode 转成 GB2312 就不知道也可以把 Unicode 转换为 UTF-8 吗?
其实这是一个很简单的程序,都被作者搞复杂了。
要实现 GB2312 (其实是GBK)转换为 UTF-8 其实很简单,先用 MultiByteToWideChar 把 GB2312 转换为 Unicode,再用 WideCharToMultiByte 把 Unicode 转换为 UTF-8 就可以了。
UTF-8 转换为 GB2312 是个相反的过程,先用 MultiByteToWideChar 把 UTF-8 转换为 Unicode,再用 WideCharToMultiByte 把 Unicode 转换为 GB2312 就可以了。
( 雁过留声 发表于 2007-1-11 9:11:00)
translateCharToUTF_8的编码不对, 请作者检查一下, 如: "你是我的好朋友" 转换成了;"浣犳槸鎴戠殑濂芥i脲弸鍚?" 正确的应是: "浣犳槸鎴戠殑濂芥湅鍙嬪悧" 对于有的编码还能对... 交流一下:kudoo.aos@gmail.com (
kudoo 发表于 2006-8-20 19:46:00)
shines在2005-2-6,提供了一段程序,里面有 buffersize = WideCharToMultiByte(CP_UTF8, MB_PRECOMPOSED, unicode, wide_size, NULL, 0, NULL, 0); buffer = new char[buffersize+1];
但是,我在调试的时候发现:buffersize似乎已经预先留了‘\0’的位置,或者是不是我出错了 比如:“i love you,爱”GB2312是需要14个字节 UTF8是需要15个字节,返回时候就是这些了啊, 我的地址是:robin-fox@sohu.com, 谁能回答以下,感谢!!
( robin_fox_nan 发表于 2006-3-19 20:20:00)
晕.格式没有了 原文请看 http://www./viewfull.asp?id=33 ( 鬼龙之舞 发表于
2005-8-25 16:13:00)
支持楼主!是因为你我才写出来的,不管是在体积还是在速度,相信都比楼主的强一点,如果不考虑移植性的话 感谢楼主!!
UTF8toUnicode proc uses esi edi lpszBuf_OUT,lpszUTF8_IN mov esi,lpszUTF8_IN mov edi,lpszBuf_OUT .while TRUE mov al,[esi] .if sbyte ptr al <0 mov al,[esi] and al,00001111b shl al,4 mov [edi+1],al mov al,[esi+1] and al,00111100b shr al,2 or [edi+1],al
mov al,[esi+1] and al,11b shl al,6 mov [edi+0],al mov al,[esi+2] and al,00111111b or [edi+0],al add edi,2 add esi,3 .elseif al xor ah,ah stosw inc esi .else mov WORD ptr [edi],0 .break .endif .endw ret UTF8toUnicode endp
( 鬼龙之舞 发表于 2005-8-25 16:11:00)
UnicodetoUTF8 proc uses esi edi lpBuf_OUT,lpszUTF8_IN mov esi,lpszUTF8_IN mov edi,lpBuf_OUT .while TRUE mov ax,[esi] .if ax==0 stosw .break .elseif ah==0 add esi,2 stosw .else mov al,[esi+1] shr al,4 or al,11100000b mov [edi+0],al
mov al,[esi+1] and al,00001111b shl al,2 or al,10000000b mov ah,[esi+0] shr ah,6 or al,ah mov [edi+1],al
mov al,[esi+0] and al,00111111b or al,10000000b mov [edi+2],al
add edi,3 add esi,2 .endif .endw ret UnicodetoUTF8 endp
( 鬼龙之舞 发表于 2005-8-25 16:11:00) 帮忙弄以下 ( zztop5384 发表于 2005-4-18 10:35:00)
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
这些只是函数原型,并没有具体实现
( zztop5384 发表于 2005-4-18 10:27:00)
//对不起,少加了个扩号 WCHAR* CXmlProcess::UTF_8ToUnicode(char *pText) { char uchar[2]; WCHAR *unicode;
char_one = pText[0]; char_two = pText[1]); char_three = pText[2];
uchar[1] = ((pText[0] & 0x0F) << 4) + ((pText[1] >> 2) & 0x0F); uchar[0] = ((pText[1] & 0x03) << 6) + (pText[2] & 0x3F);
unicode = (WCHAR *)uchar; return unicode;
} |
|