UTF8與GB2312之間的轉(zhuǎn)換

夢(mèng)之永恒 2010-12-05

展開全文

　　相信一定有不少的程序開發(fā)人員時(shí)常會(huì)遇到字符編碼的問題,，而這個(gè)問題也是非常讓人頭痛的。因?yàn)檫@些都是潛在的錯(cuò)誤,，要找出這些錯(cuò)誤也得要有這方面的開發(fā)經(jīng)驗(yàn)才行,。特別是在處理xml文檔時(shí) ,，該問題的出現(xiàn)就更加的頻繁了，有一次用java寫服務(wù)器端程序,，用vc寫客戶端與之交互,。交互的協(xié)議都是用xml寫的。結(jié)果在通訊時(shí)老是發(fā)現(xiàn)數(shù)據(jù)接受不正確,。納悶,！于是用抓取網(wǎng)絡(luò)數(shù)據(jù)包工具抓取數(shù)據(jù)，后來才發(fā)現(xiàn)原來是java上xml的頭是這樣的<?xml version="1.0" encoding="UTF-8"?>,而vc上默認(rèn)的是GB2312,。所以一遇到漢字?jǐn)?shù)據(jù)就不正確了,。去網(wǎng)上找資料，這方面的文章好象特別少,，針對(duì)像這樣的問題,，下面我介紹一下我自己寫的一個(gè)轉(zhuǎn)換程序,。當(dāng)然，程序很簡單,。如果有畫蛇添足的地方,，還望各位高手一笑了之。
　　如果您對(duì)UTF-8,、Unicode,、GB2312等還是很陌生的話，請(qǐng)查看http://www./books/UTF-8-Unicode.html,，我這里就不浪費(fèi)口舌了,。下面介紹一下WinAPI的兩個(gè)函數(shù)：WideCharToMultiByte、MultiByteToWideChar,。

函數(shù)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
); //將寬字符轉(zhuǎn)換成多個(gè)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
);//將多個(gè)窄字符轉(zhuǎn)換成寬字符

需要用到的一些函數(shù)：

CString CXmlProcess::HexToBin(CString string)//將16進(jìn)制數(shù)轉(zhuǎn)換成2進(jìn)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)//將2進(jìn)制數(shù)轉(zhuǎn)換成16進(jìn)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進(jìn)制字符數(shù)據(jù)轉(zhuǎn)換成10進(jìn)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轉(zhuǎn)換成GB2312先把UTF-8轉(zhuǎn)換成Unicode.然后再把Unicode通過函數(shù)WideCharToMultiByte轉(zhuǎn)換成GB2312

WCHAR* CXmlProcess::UTF_8ToUnicode(char *ustart)  //把UTF-8轉(zhuǎn)換成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 轉(zhuǎn)換成 GB2312
{
	char *buffer ;
	buffer = new char[sizeof(WCHAR)];
	WideCharToMultiByte(CP_ACP,NULL,&uData,1,buffer,sizeof(WCHAR),NULL,NULL);
	return buffer;
}

　　GB2312轉(zhuǎn)換成UTF-8：先把GB2312通過函數(shù)MultiByteToWideChar轉(zhuǎn)換成Unicode.然后再把Unicode通過拆開Unicode后拼裝成UTF-8,。

WCHAR * CXmlProcess::Gb2312ToUnicode(char *gbBuffer)  //GB2312 轉(zhuǎn)換成　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 轉(zhuǎn)換成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：將GB2312轉(zhuǎn)換成UTF-8的調(diào)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)];//設(shè)置最大的一個(gè)緩沖區(qū)
	while(oldCharLen < revCharLen)
	{
		if( *(xmlStream + oldCharLen) >= 0)
		{
			*(newCharBuffer+newCharLen) = *(xmlStream +oldCharLen);
			newCharLen ++;
			oldCharLen ++;
		}//如果是英文直接復(fù)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;
}

　　程序都非常的簡單，由于實(shí)在太窮,。已經(jīng)吃了兩天的方便面,。所以現(xiàn)在頭昏，程序的詳細(xì)說明就不寫了,。程序員到了像我這樣的地步也真是少見,。工資低沒有辦法。哎?。,。?！

最新評(píng)論 [發(fā)表評(píng)論] [文章投稿]

查看所有評(píng)論

推薦給好友

打印

/*
字符串編碼轉(zhuǎn)換 GBK to UTF8 (ansi版)
[email protected]
*/
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 發(fā)表于 2009-11-3 19:38:00)

[ 原創(chuàng)文檔本文適合中級(jí)讀者已閱讀34485次 ]

搞笑,，這種害人害己的文章還有這么多人訪問。

作者光知道 WideCharToMultiByte 可以把 Unicode 轉(zhuǎn)成 GB2312 就不知道也可以把 Unicode 轉(zhuǎn)換為 UTF-8 嗎,？

其實(shí)這是一個(gè)很簡單的程序,，都被作者搞復(fù)雜了。

要實(shí)現(xiàn) GB2312 （其實(shí)是GBK）轉(zhuǎn)換為 UTF-8 其實(shí)很簡單,，先用 MultiByteToWideChar 把 GB2312 轉(zhuǎn)換為 Unicode,，再用 WideCharToMultiByte 把 Unicode 轉(zhuǎn)換為 UTF-8 就可以了。

UTF-8 轉(zhuǎn)換為 GB2312 是個(gè)相反的過程,，先用 MultiByteToWideChar 把 UTF-8 轉(zhuǎn)換為 Unicode,，再用 WideCharToMultiByte 把 Unicode 轉(zhuǎn)換為 GB2312 就可以了。 ( 雁過留聲發(fā)表于 2007-1-11 9:11:00)

translateCharToUTF_8的編碼不對(duì),
請(qǐng)作者檢查一下,
如: "你是我的好朋友"
轉(zhuǎn)換成了;"浣犳槸鎴戠殑濂芥i脲弸鍚?"
正確的應(yīng)是:
"浣犳槸鎴戠殑濂芥湅鍙嬪悧"
對(duì)于有的編碼還能對(duì)...
交流一下:[email protected]
( kudoo 發(fā)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，我在調(diào)試的時(shí)候發(fā)現(xiàn)：buffersize似乎已經(jīng)預(yù)先留了‘\0’的位置,，或者是不是我出錯(cuò)了
比如：“i love you,愛”GB2312是需要14個(gè)字節(jié)
UTF8是需要15個(gè)字節(jié),，返回時(shí)候就是這些了啊,，
我的地址是：[email protected]，
誰能回答以下,，感謝?。? ( robin_fox_nan 發(fā)表于 2006-3-19 20:20:00)

暈.格式?jīng)]有了
原文請(qǐng)看
http://www./viewfull.asp?id=33 ( 鬼龍之舞發(fā)表于 2005-8-25 16:13:00)

支持樓主!是因?yàn)槟阄也艑懗鰜淼?不管是在體積還是在速度,相信都比樓主的強(qiáng)一點(diǎn),如果不考慮移植性的話
感謝樓主!!

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 ( 鬼龍之舞發(fā)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 ( 鬼龍之舞發(fā)表于 2005-8-25 16:11:00)

幫忙弄以下 ( zztop5384 發(fā)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
); //將寬字符轉(zhuǎn)換成多個(gè)窄字符

這些只是函數(shù)原型,，并沒有具體實(shí)現(xiàn) ( zztop5384 發(fā)表于 2005-4-18 10:27:00)

//對(duì)不起,，少加了個(gè)擴(kuò)號(hào)
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;

}

本站是提供個(gè)人知識(shí)管理的網(wǎng)絡(luò)存儲(chǔ)空間，所有內(nèi)容均由用戶發(fā)布,，不代表本站觀點(diǎn)。請(qǐng)注意甄別內(nèi)容中的聯(lián)系方式,、誘導(dǎo)購買等信息,，謹(jǐn)防詐騙。如發(fā)現(xiàn)有害或侵權(quán)內(nèi)容,，請(qǐng)點(diǎn)擊一鍵舉報(bào),。

久久国产成人av_抖音国产毛片_a片网站免费观看_A片无码播放手机在线观看,色五月在线观看,亚洲精品m在线观看,女人自慰的免费网址,悠悠在线观看精品视频,一级日本片免费的,亚洲精品久,国产精品成人久久久久久久

UTF8與GB2312之間的轉(zhuǎn)換