一网打尽中文编码转换---6种编码30个方向的转换
生活随笔
收集整理的這篇文章主要介紹了
一网打尽中文编码转换---6种编码30个方向的转换
小編覺得挺不錯的,現在分享給大家,幫大家做個參考.
一網打盡中文編碼轉換——6種編碼30個方向的轉換
wchar_t*?Coder::MByteToWChar(UINT?CodePage,LPCSTR?lpcszSrcStr)?? {?? ????LPWSTR?lpcwsStrDes=NULL;?? ????int???len=MultiByteToWideChar(CodePage,0,lpcszSrcStr,-1,NULL,0);?? ????lpcwsStrDes=new?wchar_t[len+1];?? ????if(!lpcwsStrDes)?? ????????return?NULL;?? ????memset(lpcwsStrDes,0,sizeof(wchar_t)*(len+1));?? ????len=MultiByteToWideChar(CodePage,0,lpcszSrcStr,-1,lpcwsStrDes,len);?? ????if(len)?? ????????return?lpcwsStrDes;?? ????else?? ????{????? ????????delete[]?lpcwsStrDes;?? ????????return?NULL;?? ????}?? }?? ?? char*?Coder::WCharToMByte(UINT?CodePage,LPCWSTR?lpcwszSrcStr)?? {?? ????char*?lpszDesStr=NULL;?? ????int?len=WideCharToMultiByte(CodePage,0,lpcwszSrcStr,-1,NULL,0,NULL,NULL);?? ????lpszDesStr=new?char[len+1];?? ????memset(lpszDesStr,0,sizeof(char)*(len+1));?? ????if(!lpszDesStr)?? ????????return?NULL;?? ????len=WideCharToMultiByte(CodePage,0,lpcwszSrcStr,-1,lpszDesStr,len,NULL,NULL);?? ????if(len)?? ????????return?lpszDesStr;?? ????else?? ????{????? ????????delete[]?lpszDesStr;?? ????????return?NULL;?? ????}?? }???
c.LCMapString
依賴于本地機器的字符轉換函數，尤其是中文編碼在轉換時要依賴于本地機器，
直接利用上述a、b中敘述的函數會產生錯誤,例如直接從GB2312轉換到Big5，利用MultiByteToWideChar函數將GB2312轉換到Unicode字符串，然后從Unicode字符串利用函數WideCharToMultiByte轉換成Big5,將會發生錯誤，錯誤的結果如下圖所示:
因此中文編碼轉換時適當使用LCMapString函數，才能完成正確的轉換.
例如:[cpp] view plaincopyprint?//簡體中文?GB2312?轉換成?繁體中文BIG5?? char*?Coder::GB2312ToBIG5(const?char*?szGB2312Str)?? {????????? ????????LCID?lcid?=?MAKELCID(MAKELANGID(LANG_CHINESE,SUBLANG_CHINESE_SIMPLIFIED),SORT_CHINESE_PRC);?? ????????int?nLength?=?LCMapString(lcid,LCMAP_TRADITIONAL_CHINESE,szGB2312Str,-1,NULL,0);?? ????????char*?pBuffer=new?char[nLength+1];?? ????????if(!pBuffer)?? ????????????return?NULL;?? ????????LCMapString(lcid,LCMAP_TRADITIONAL_CHINESE,szGB2312Str,-1,pBuffer,nLength);?? ????????pBuffer[nLength]=0;?? ????????wchar_t*?pUnicodeBuff?=?MByteToWChar(CP_GB2312,pBuffer);?? ????????char*?pBIG5Buff?=?WCharToMByte(CP_BIG5,pUnicodeBuff);?? ????????delete[]?pBuffer;?? ????????delete[]?pUnicodeBuff;?? ????????return?pBIG5Buff;?? }??? (5)編碼實現
實現Coder類完成編碼轉換工作.
Coder類的代碼清單如下:[cpp] view plaincopyprint?//?Coder.h:?interface?for?the?Coder?class.?? //?? //?? ?? #if?!defined(AFX_ENCODING_H__2AC955FB_9F8F_4871_9B77_C6C65730507F__INCLUDED_)?? #define?AFX_ENCODING_H__2AC955FB_9F8F_4871_9B77_C6C65730507F__INCLUDED_?? ?? #if?_MSC_VER?>?1000?? #pragma?once?? #endif?//?_MSC_VER?>?1000?? //-----------------------------------------------------------------------------------------------?? //程序用途：實現GB2312、big5、GBK、Unicode、Unicode?big?endian、UTF-8六種編碼的任意裝換?????? //程序作者：湖北師范學院計算機科學與技術學院??王定橋??????????????????????????????????? //核心算法：根據不同編碼特點向其他編碼轉換?? //測試結果:在Windows7?VC6.0環境下測試通過??????????????????????????????????????????????????????? //制作時間：2012-04-24??????????????????????????????????????????????? //代碼版權:代碼公開供學習交流使用??歡迎指正錯誤??改善算法?? //-----------------------------------------------------------------------------------------------?? //Windows代碼頁?? typedef?enum?CodeType?? {?? ????CP_GB2312=936,?? ????CP_BIG5=950,?? ????CP_GBK=0?? }CodePages;?? //txt文件編碼?? typedef?enum?TextCodeType?? {????? ????GB2312=0,?? ????BIG5=1,?? ????GBK=2,?? ????UTF8=3,?? ????UNICODE=4,?? ????UNICODEBIGENDIAN=5,?? ????DefaultCodeType=-1?? }TextCode;?? class?Coder???? {?? public:?? ????Coder();?? ????virtual?~Coder();?? public:?? ????//默認一次轉換字節大小?? ????UINT??PREDEFINEDSIZE;?? ????//指定轉換時默認一次轉換字節大小?? ????void?SetDefaultConvertSize(UINT?nCount);?? ????//編碼類型轉換為字符串?? ????CString??CodeTypeToString(TextCode?tc);?? ????//文件轉到另一種文件?? ????BOOL?????FileToOtherFile(CString?filesourcepath,?CString?filesavepath,TextCode?tcTo,TextCode??tcCur=DefaultCodeType);?? ????//Unicode?和Unicode?big?endian文件之間轉換?? ????BOOL?????UnicodeEndianFileConvert(CString?filesourcepath,?CString?filesavepath,TextCode?tcTo);?? ????//多字節文件之間的轉換?? ????BOOL?????MBFileToMBFile(CString?filesourcepath,?CString?filesavepath,TextCode?tcTo,TextCode??tcCur=DefaultCodeType);?? ????//Unicode和Unicode?big?endian文件向多字節文件轉換?? ????BOOL?????UnicodeFileToMBFile(CString?filesourcepath,?CString?filesavepath,TextCode?tcTo);?? ????//多字節文件向Unicode和Unicode?big?endian文件轉換?? ????BOOL?????MBFileToUnicodeFile(CString?filesourcepath,CString?filesavepath,TextCode?tcTo,TextCode??tcCur=DefaultCodeType);?? ????//獲取文件編碼類型?? ????TextCode?GetCodeType(CString?filepath);?? ????//繁體中文BIG5?轉換成?簡體中文?GB2312?? ????char*?BIG5ToGB2312(const?char*?szBIG5Str);?? ????//簡體中文?GB2312?轉換成?繁體中文BIG5?? ????char*?GB2312ToBIG5(const?char*?szGB2312Str);?? ????//簡繁中文GBK編碼轉換成簡體中文GB2312?? ????char*?GBKToGB2312(const?char?*szGBkStr);?? ????//簡體中文GB2312編碼轉換成簡繁中文GBK?? ????char*????GB2312ToGBK(const?char?*szGB2312Str);?? ????//簡繁中文GBK轉換成繁體中文Big5?? ????char*?????GBKToBIG5(const?char?*szGBKStr);?? ????//繁體中文BIG5轉換到簡繁中文GBK?? ????char*?????BIG5ToGBK(const?char?*szBIG5Str);?? ????//寬字符串向多字節字符串轉換?? ????char*?????WCharToMByte(UINT?CodePage,LPCWSTR?lpcwszSrcStr);?? ????//多字節字符串向寬字符串轉換?? ????wchar_t*??MByteToWChar(UINT?CodePage,LPCSTR?lpcszSrcStr);?? protected:?? ????//獲取編碼類型對應的代碼頁?? ????UINT?GetCodePage(TextCode?tccur);?? ????//多字節向多字節轉換?? ????char*??MByteToMByte(UINT?CodePageCur,UINT?CodePageTo,const?char*?szSrcStr);?? ????//Unicode和Unicode?big?endian字符串之間的轉換?? ????void???UnicodeEndianConvert(LPWSTR??lpwszstr);?? ????//文件頭常量字節數組?? ????const??static???byte?UNICODEBOM[2];?? ????const??static???byte?UNICODEBEBOM[2];?? ????const??static???byte?UTF8BOM[3];?? ??};?? ?? #endif?//?!defined(AFX_ENCODING_H__2AC955FB_9F8F_4871_9B77_C6C65730507F__INCLUDED_)?? [cpp] view plaincopyprint?//?Coder.cpp:?implementation?of?the?Coder?class.?? //?? //?? ?? #include?"stdafx.h"?? #include?"Coder.h"?? #include?"Encoding.h"?? ?? #ifdef?_DEBUG?? #undef?THIS_FILE?? static?char?THIS_FILE[]=__FILE__;?? #define?new?DEBUG_NEW?? #endif?? ?? //?? //?Construction/Destruction?? //?? //初始化文件頭常量?? /*static*/?const?????byte?Coder::UNICODEBOM[2]={0xFF,0xFE};?? /*static*/?const?????byte?Coder::UNICODEBEBOM[2]={0xFE,0xFF};?? /*static*/?const?????byte?Coder::UTF8BOM[3]={0xEF,0xBB,0xBF};?? Coder::Coder()?? {?? ???PREDEFINEDSIZE=2097152;//默認一次轉換字節大小?2M字節?? }?? Coder::~Coder()?? {?? ???? }?? //繁體中文BIG5?轉換成?簡體中文?GB2312?? char*?Coder::BIG5ToGB2312(const?char*?szBIG5Str)?? {????????? ????????CString?msg;?? ????????LCID?lcid?=?MAKELCID(MAKELANGID(LANG_CHINESE,SUBLANG_CHINESE_SIMPLIFIED),SORT_CHINESE_PRC);?? ????????wchar_t*?szUnicodeBuff?=MByteToWChar(CP_BIG5,szBIG5Str);?? ????????char*?szGB2312Buff?=WCharToMByte(CP_GB2312,szUnicodeBuff);?? ????????int?nLength?=?LCMapString(lcid,LCMAP_SIMPLIFIED_CHINESE,?szGB2312Buff,-1,NULL,0);?? ????????char*?pBuffer?=?new?char[nLength?+?1];?? ????????if(!pBuffer)?? ??????????return?NULL;?? ????????memset(pBuffer,0,sizeof(char)*(nLength+1));?? ????????LCMapString(0x0804,LCMAP_SIMPLIFIED_CHINESE,szGB2312Buff,-1,pBuffer,nLength);?? ????????delete[]?szUnicodeBuff;?? ????????delete[]?szGB2312Buff;?? ????????return?pBuffer;?? }?? //?GB2312?轉?GBK?? char*?Coder::GB2312ToGBK(const?char?*szGB2312Str)?? {?? ???????int?nStrLen?=?strlen(szGB2312Str);?? ???????if(!nStrLen)?? ???????????return?NULL;?? ???????LCID?wLCID?=?MAKELCID(MAKELANGID(LANG_CHINESE,?SUBLANG_CHINESE_SIMPLIFIED),?SORT_CHINESE_PRC);?? ???????int?nReturn?=?LCMapString(wLCID,?LCMAP_TRADITIONAL_CHINESE,?szGB2312Str,?nStrLen,?NULL,?0);?? ???????if(!nReturn)?? ??????????return?NULL;?? ???????char?*pcBuf?=?new?char[nReturn?+?1];?? ???????if(!pcBuf)?? ??????????return?NULL;?? ???????memset(pcBuf,0,sizeof(char)*(nReturn?+?1));?? ???????wLCID?=?MAKELCID(MAKELANGID(LANG_CHINESE,?SUBLANG_CHINESE_SIMPLIFIED),?SORT_CHINESE_PRC);?? ???????LCMapString(wLCID,?LCMAP_TRADITIONAL_CHINESE,?szGB2312Str,?nReturn,?pcBuf,?nReturn);?? ???????return?pcBuf;?? }?? //?GBK?轉換成?GB2312?? char*?Coder::GBKToGB2312(const?char?*szGBKStr)?? {?? ????int?nStrLen?=?strlen(szGBKStr);?? ????if(!nStrLen)?? ????????return?NULL;?? ????LCID?wLCID?=?MAKELCID(MAKELANGID(LANG_CHINESE,?SUBLANG_CHINESE_SIMPLIFIED),?SORT_CHINESE_BIG5);?? ????int?nReturn?=?LCMapString(wLCID,?LCMAP_SIMPLIFIED_CHINESE,?szGBKStr,?nStrLen,?NULL,?0);?? ????if(!nReturn)?? ????????return?NULL;?? ????char?*pcBuf?=?new?char[nReturn?+?1];?? ????memset(pcBuf,0,sizeof(char)*(nReturn?+?1));?? ????wLCID?=?MAKELCID(MAKELANGID(LANG_CHINESE,?SUBLANG_CHINESE_SIMPLIFIED),?SORT_CHINESE_BIG5);?? ????LCMapString(wLCID,?LCMAP_SIMPLIFIED_CHINESE,?szGBKStr,?nReturn,?pcBuf,?nReturn);?? ????return?pcBuf;?? }?? //簡繁中文GBK轉換成繁體中文Big5?? char*???Coder::GBKToBIG5(const?char?*szGBKStr)?? {????? ????char?*pTemp=NULL;?? ????char?*pBuffer=NULL;?? ????pTemp=GBKToGB2312(szGBKStr);?? ????pBuffer=GB2312ToBIG5(pTemp);?? ????delete[]?pTemp;?? ????return?pBuffer;?? }?? //繁體中文BIG5轉換到簡繁中文GBK?? char*???Coder::BIG5ToGBK(const?char?*szBIG5Str)?? {?? ??????char?*pTemp=NULL;?? ??????char?*pBuffer=NULL;?? ??????pTemp=BIG5ToGB2312(szBIG5Str);?? ??????pBuffer=GB2312ToGBK(pTemp);?? ??????delete[]?pTemp;?? ??????return?pBuffer;?? }?? //簡體中文?GB2312?轉換成?繁體中文BIG5?? char*?Coder::GB2312ToBIG5(const?char*?szGB2312Str)?? {????????? ????????LCID?lcid?=?MAKELCID(MAKELANGID(LANG_CHINESE,SUBLANG_CHINESE_SIMPLIFIED),SORT_CHINESE_PRC);?? ????????int?nLength?=?LCMapString(lcid,LCMAP_TRADITIONAL_CHINESE,szGB2312Str,-1,NULL,0);?? ????????char*?pBuffer=new?char[nLength+1];?? ????????if(!pBuffer)?? ????????????return?NULL;?? ????????LCMapString(lcid,LCMAP_TRADITIONAL_CHINESE,szGB2312Str,-1,pBuffer,nLength);?? ????????pBuffer[nLength]=0;?? ????????wchar_t*?pUnicodeBuff?=?MByteToWChar(CP_GB2312,pBuffer);?? ????????char*?pBIG5Buff?=?WCharToMByte(CP_BIG5,pUnicodeBuff);?? ????????delete[]?pBuffer;?? ????????delete[]?pUnicodeBuff;?? ????????return?pBIG5Buff;?? }??? //獲取文件編碼類型?? //Unicode編碼文件通過讀取文件頭判別?? //中文編碼通過統計文件編碼類別來判別??判別次數最多為30次???? //中文編碼的判別存在誤差?? TextCode?Coder::GetCodeType(CString?filepath)?? {?? ????CFile?file;?? ????byte??buf[3];//unsigned?char?? ????TextCode?tctemp;?? ????if(file.Open(filepath,CFile::modeRead))?? ????{?????? ????????file.Read(buf,3);?? ????????if(buf[0]==UTF8BOM[0]?&&?buf[1]==UTF8BOM[1]?&&?buf[2]==UTF8BOM[2])?? ????????????return?UTF8;?? ????????else?? ????????if(buf[0]==UNICODEBOM[0]?&&buf[1]==UNICODEBOM[1]?)?? ????????????return?UNICODE?;?? ????????else?? ????????if(buf[0]==UNICODEBEBOM[0]?&&buf[1]==UNICODEBEBOM[1]?)?? ????????????return?UNICODEBIGENDIAN;?? ????????else?? ????????{????? ????????????int?time=30;?? ????????????while(file.Read(buf,2)?&&time?)?? ????????????{????? ????????????????if?(?(buf[0]>=176?&&?buf[0]<=247)?&&?(buf[1]>=160?&&?buf[1]<=254)?)?? ????????????????????????????tctemp=GB2312;???? ????????????????else?? ????????????????????if?(?(buf[0]>=129?&&?buf[0]<=255)?&&?(??(?buf[1]>=64?&&?buf[1]<=126)??||??(?buf[1]>=161?&&?buf[1]<=254)?)?)?? ????????????????????????????tctemp=BIG5;?? ????????????????????else?? ????????????????????????if?(?(buf[0]>=129?&&?buf[0]?<=254)?&&?(buf[1]>=64?&&?buf[1]<=254))?? ????????????????????????????tctemp=GBK;??? ????????????????time--;?? ????????????????file.Seek(100,CFile::current);//跳過一定字節??利于統計全文?? ????????????}?? ????????????return?tctemp;?? ????????}?? ????}?? ????else?? ????????return?GB2312;?? }?? //多字節文件轉換為UNICODE、UNICODE?big?endian文件?? BOOL?Coder::MBFileToUnicodeFile(CString?filesourcepath,?CString?filesavepath,TextCode?tcTo,TextCode?tcCur)?? {?? ???TextCode?curtc;?? ???CFile?filesource,filesave;;?? ???char?????*pChSrc=NULL;?? ???char?????*pChTemp=NULL;?? ???wchar_t??*pwChDes=NULL;?? ???DWORD??filelength,readlen,len;?? ???int????bufferlen,strlength;?? ???UINT?CodePage;?? ???//由于存在誤差??允許用戶自定義轉換?? ???if(tcCur!=DefaultCodeType)?? ???????curtc=tcCur;?? ???else?? ???????curtc=GetCodeType(filesourcepath);?? ???if(curtc>UTF8?||?tcTo<?UNICODE?||?curtc==tcTo)?? ???????return?FALSE;?? ???//源文件打開失敗或者源文件無內容?后者保存文件建立失敗???均返回轉換失敗?? ???if(!filesource.Open(filesourcepath,CFile::modeRead)?||?0==(filelength=filesource.GetLength()))?? ???????return?FALSE;?? ???if(?!filesave.Open(filesavepath,CFile::modeCreate|CFile::modeWrite))?? ????????return?FALSE;?? ???//預分配內存??分配失敗則轉換失敗?? ???if(filelength<PREDEFINEDSIZE)?? ???????bufferlen=filelength;?? ???else?? ???????bufferlen=PREDEFINEDSIZE;?? ???pChSrc=new?char[bufferlen+1];?? ???if(!pChSrc)?? ????????????return?FALSE;?? ???//根據當前文件類別指定轉換代碼頁?? ???switch(curtc)?? ???{?? ???case?GB2312:?? ???????CodePage=CP_GB2312;?? ???????break;?? ???case?GBK:?? ???????CodePage=CP_GB2312;//特殊處理?? ???????break;?? ???case?BIG5:?? ???????CodePage=CP_BIG5;?? ???????break;?? ???case?UTF8:?? ???????CodePage=CP_UTF8;?? ???????break;?? ???default:?? ???????break;?? ????}?? ???//UTF8文件跳過文件?? ???if(UTF8==curtc)?? ???????filesource.Seek(3*sizeof(byte),CFile::begin);?? ???//寫入文件頭?? ???if(UNICODEBIGENDIAN==tcTo)?? ???????filesave.Write(&UNICODEBEBOM,2*sizeof(byte));?? ???else?? ???????filesave.Write(&UNICODEBOM,2*sizeof(byte));?? ???//讀取文件??分段轉換知道結束?? ???while(filelength>0)?? ???{?? ???????memset(pChSrc,0,?sizeof(char)*(bufferlen+1));?? ???????if(filelength>PREDEFINEDSIZE)?? ???????????len=PREDEFINEDSIZE;?? ???????else?? ???????????len=filelength;?? ???????readlen=filesource.Read(pChSrc,len);?? ???????if(!readlen)?? ????????????break;?? ???????//GBK轉換為GB2312處理?? ???????if(GBK==curtc)?? ???????{????? ???????????pChTemp=pChSrc;?? ???????????pChSrc=GBKToGB2312(pChSrc);?? ???????}?? ???????pwChDes=MByteToWChar(CodePage,pChSrc);?? ???????if(pwChDes)?? ???????{?? ???????????if(UNICODEBIGENDIAN==tcTo)?? ???????????????UnicodeEndianConvert(pwChDes);?? ???????????strlength=wcslen(pwChDes)*2;//這里注意寫入文件的長度?? ???????????filesave.Write(pwChDes,strlength);?? ???????????filesave.Flush();?? ???????????filelength-=readlen;?? ???????}?? ???????else?? ???????????break;?? ???}?? ???delete[]?pChSrc;?? ???delete[]?pChTemp;?? ???delete[]?pwChDes;?? ???return?TRUE;?? }?? //?? wchar_t*?Coder::MByteToWChar(UINT?CodePage,LPCSTR?lpcszSrcStr)?? {?? ????LPWSTR?lpcwsStrDes=NULL;?? ????int???len=MultiByteToWideChar(CodePage,0,lpcszSrcStr,-1,NULL,0);?? ????lpcwsStrDes=new?wchar_t[len+1];?? ????if(!lpcwsStrDes)?? ????????return?NULL;?? ????memset(lpcwsStrDes,0,sizeof(wchar_t)*(len+1));?? ????len=MultiByteToWideChar(CodePage,0,lpcszSrcStr,-1,lpcwsStrDes,len);?? ????if(len)?? ????????return?lpcwsStrDes;?? ????else?? ????{????? ????????delete[]?lpcwsStrDes;?? ????????return?NULL;?? ????}?? }?? ?? char*?Coder::WCharToMByte(UINT?CodePage,LPCWSTR?lpcwszSrcStr)?? {?? ????char*?lpszDesStr=NULL;?? ????int?len=WideCharToMultiByte(CodePage,0,lpcwszSrcStr,-1,NULL,0,NULL,NULL);?? ????lpszDesStr=new?char[len+1];?? ????memset(lpszDesStr,0,sizeof(char)*(len+1));?? ????if(!lpszDesStr)?? ????????return?NULL;?? ????len=WideCharToMultiByte(CodePage,0,lpcwszSrcStr,-1,lpszDesStr,len,NULL,NULL);?? ????if(len)?? ????????return?lpszDesStr;?? ????else?? ????{????? ????????delete[]?lpszDesStr;?? ????????return?NULL;?? ????}?? }??? //Unicode?和Unicode?big?endian之間字節序的轉換?? void?Coder::UnicodeEndianConvert(LPWSTR?lpwszstr)?? {?????? ?????wchar_t??wchtemp[2];???? ?????long?????index;??? ?????int?len=wcslen(lpwszstr);?? ?????if(!len)?? ?????????return;?? ???//交換高低字節?直到遇到結束符?? ???index=0;?? ???while(?index<len)?? ???{?? ???????wchtemp[0]=lpwszstr[index];?? ???????wchtemp[1]=lpwszstr[index+1];?? ????????? ???????unsigned?char?high,?low;?? ???????high?=?(wchtemp[0]?&?0xFF00)?>>8;?? ???????low??=?wchtemp[0]?&?0x00FF;?? ???????wchtemp[0]?=?(?low?<<8)?|?high;?? ???????high?=?(wchtemp[1]?&?0xFF00)?>>8;?? ???????low??=?wchtemp[1]?&?0x00FF;?? ???????wchtemp[1]?=?(?low?<<8)?|?high;?? ????????? ???????lpwszstr[index]=wchtemp[0];?? ???????lpwszstr[index+1]=wchtemp[1];?? ???????index+=2;?? ???}?? }?? //Unicode和Unicode?big?endian文件向多字節文件轉換?? BOOL?Coder::UnicodeFileToMBFile(CString?filesourcepath,?CString?filesavepath,TextCode?tcTo)?? {????? ????TextCode?curtc;?? ????CFile?filesource,filesave;;?? ????char????*pChDes=NULL;?? ????char????*pChTemp=NULL;?? ????wchar_t?*pwChSrc=NULL;?? ????DWORD??filelength,readlen,len;?? ????int????bufferlen,strlength;?? ????UINT?CodePage;?? ????curtc=GetCodeType(filesourcepath);?? ????//文件轉換類型錯誤?則轉換失敗?? ????if(curtc<=UTF8?||??tcTo>UTF8?||?curtc==tcTo)?? ????????return?FALSE;?? ????//源文件打開失敗或者源文件無內容?后者保存文件建立失敗???均轉換失敗?? ????if(!filesource.Open(filesourcepath,CFile::modeRead)?||?0==(filelength=filesource.GetLength()))?? ????????return?FALSE;?? ????if(?!filesave.Open(filesavepath,CFile::modeCreate|CFile::modeWrite))?? ????????return?FALSE;?? ????//預分配內存??分配失敗則轉換失敗?? ????if(filelength<PREDEFINEDSIZE)?? ????????bufferlen=filelength;?? ????else?? ????????bufferlen=PREDEFINEDSIZE;?? ????pwChSrc=new?wchar_t[(bufferlen/2)+1];?? ????if(!pwChSrc)?? ????????return?FALSE;?? ????//預先決定代碼頁?? ????switch(tcTo)?? ????{????? ????case?GB2312:?? ????????CodePage=CP_GB2312;?? ????????break;?? ????case?GBK:?? ????????CodePage=CP_GB2312;//特殊處理?? ????????break;?? ????case?BIG5:??? ????????CodePage=CP_GB2312;//特殊處理?? ????????break;?? ????case?UTF8:?? ????????CodePage=CP_UTF8;?? ????????break;?? ????default:?? ????????break;?? ????????}?? ????filesource.Seek(sizeof(wchar_t),CFile::begin);?? ????while(filelength>0)?? ????{?? ????????memset(pwChSrc,0,sizeof(wchar_t)*((bufferlen/2)+1));?? ????????if(filelength>PREDEFINEDSIZE)?? ????????????len=PREDEFINEDSIZE;?? ????????else?? ????????????len=filelength;?? ????????readlen=filesource.Read(pwChSrc,len);?? ????????if(!readlen)?? ????????????break;?? ????????if(UNICODEBIGENDIAN==curtc)?? ????????????UnicodeEndianConvert(pwChSrc);?? ????????pChDes=WCharToMByte(CodePage,pwChSrc);?? ????????//GBK無法直接轉換??BIG5直接轉換會產生錯誤??二者均先轉到GB2312然后再轉到目的類型?? ????????if(GBK==tcTo)?? ????????{?? ????????????pChTemp=pChDes;?? ????????????pChDes=GB2312ToGBK(pChDes);?? ????????}?? ????????if(BIG5==tcTo)?? ????????{?? ????????????pChTemp=pChDes;?? ????????????pChDes=GB2312ToBIG5(pChDes);?? ????????}?? ????????if(pChDes)?? ????????{????? ????????????strlength=strlen(pChDes);?? ????????????filesave.Write(pChDes,strlength);?? ????????????filesave.Flush();?? ????????????filelength-=readlen;?? ????????}?? ????????else?? ????????????break;?? ????}?? ????delete[]?pChDes;?? ????delete[]?pChTemp;?? ????delete[]?pwChSrc;?? ????return?TRUE;?? }?? //多字節文件轉為多字節文件?? //多字節轉為多字節時，一般先轉為UNICODE類型，再轉換到指定目的類型，實行兩次轉換?? BOOL?Coder::MBFileToMBFile(CString?filesourcepath,?CString?filesavepath,TextCode?tcTo,TextCode??tcCur)?? {?? ????BOOL?bret=FALSE;?? ????TextCode?curtc;?? ????CFile?filesource,filesave;?? ????char????*pChDes=NULL;?? ????char????*pChSrc=NULL;?? ????DWORD??filelength,readlen,len;?? ????int????bufferlen,strlength;?? ????UINT???CodePageCur,CodePageTo;?? ????//由于存在誤差??允許用戶自定義轉換?? ????if(DefaultCodeType!=tcCur)?? ?????????curtc=tcCur;?? ????else?? ????????curtc=GetCodeType(filesourcepath);?? ????//轉換類型錯誤??則返回轉換失敗?? ????if(curtc>UTF8?||?tcTo>UTF8?||?curtc==tcTo)?? ????????return?FALSE;?? ????//源文件打開失敗或者源文件無內容?后者保存文件建立失敗???均返回轉換失敗?? ????if(!filesource.Open(filesourcepath,CFile::modeRead)?||?0==(filelength=filesource.GetLength()))?? ????????return?FALSE;?? ????if(?!filesave.Open(filesavepath,CFile::modeCreate|CFile::modeWrite))?? ????????return?FALSE;?? ????//預分配內存??分配失敗則轉換失敗?? ????if(filelength<PREDEFINEDSIZE)?? ????????bufferlen=filelength;?? ????else?? ????????bufferlen=PREDEFINEDSIZE;?? ????pChSrc=new?char[bufferlen+1];?? ????if(!pChSrc)?? ????????????return?FALSE;?? ????if(UTF8==curtc)?? ????????filesource.Seek(3*sizeof(byte),CFile::begin);?? ????CodePageCur=GetCodePage(curtc);?? ????CodePageTo=GetCodePage(tcTo);?? ????while(filelength>0)?? ????{????? ????????memset(pChSrc,0,sizeof(char)*(bufferlen+1));?? ????????if(filelength>PREDEFINEDSIZE)?? ????????????len=PREDEFINEDSIZE;?? ????????else?? ????????????len=filelength;?? ????????readlen=filesource.Read(pChSrc,len);?? ????????if(!readlen)?? ????????????break;?? ????????pChDes=MByteToMByte(CodePageCur,CodePageTo,pChSrc);?? ????????if(pChDes)?? ????????{????? ????????????strlength=strlen(pChDes);?? ????????????filesave.Write(pChDes,strlength);?? ????????????filelength-=readlen;?? ????????}?? ????????else?? ????????????break;?? ????}?? ????delete[]?pChSrc;?? ????delete[]?pChDes;?? ????return?TRUE;?? }?? //Unicode?和Unicode?big?endian文件之間轉換?? BOOL?Coder::UnicodeEndianFileConvert(CString?filesourcepath,?CString?filesavepath,TextCode?tcTo)?? {?? ????TextCode?curtc=GetCodeType(filesourcepath);?? ????if(curtc!=UNICODE?&&?curtc!=UNICODEBIGENDIAN)?? ????????return?FALSE;?? ????if(curtc==tcTo)?? ????????return?FALSE;?? ????CFile?filesource,filesave;;?? ????wchar_t?*pwChDes;?? ????DWORD?length;?? ????if(!filesource.Open(filesourcepath,CFile::modeRead)?||?!filesave.Open(filesavepath,CFile::modeCreate|CFile::modeWrite))?? ????????return?FALSE;?? ????length=filesource.GetLength();?? ????if(!length)?? ????????return?FALSE;?? ????pwChDes=new?wchar_t[(length/2)+1];?? ????if(!pwChDes)?? ????????return?FALSE;?? ????memset(pwChDes,0,sizeof(wchar_t)*((length/2)+1));?? ????filesource.Read(pwChDes,length);?? ????UnicodeEndianConvert(pwChDes);?? ????length=wcslen(pwChDes)*2;?? ????if(UNICODE==tcTo)?? ????????filesave.Write(&UNICODEBOM,2*sizeof(byte));?? ????else?? ????????filesave.Write(&UNICODEBEBOM,2*sizeof(byte));?? ????filesave.Write(pwChDes,length);?? ????filesave.Flush();?? ????delete[]?pwChDes;?? ????return?TRUE;?? }?? //文件轉到另一種文件?? //6種格式文件兩兩轉換??共計30種轉換?? BOOL?Coder::FileToOtherFile(CString?filesourcepath,?CString?filesavepath,?TextCode?tcTo,TextCode??tcCur)?? {????? ????TextCode?curtc;?? ????BOOL?bret=FALSE;?? ????if(DefaultCodeType!=tcCur)?? ????????curtc=tcCur;?? ????else?? ????????curtc=GetCodeType(filesourcepath);?? ????if(curtc==tcTo)?? ????????return?FALSE;?? ????//UNICODE和UNICODE?big?endian文件之間轉換?共2種?? ????if(curtc>=UNICODE&&?tcTo>=UNICODE)?? ????????????bret=UnicodeEndianFileConvert(filesourcepath,filesavepath,tcTo);?? ????else?? ????????//多字節文件向?UNICODE和UNICODE?big?endian文件之間轉換?共8種?? ????????if(curtc<UNICODE?&&?tcTo>=UNICODE)?? ????????????bret=MBFileToUnicodeFile(filesourcepath,filesavepath,tcTo,curtc);?? ????else?? ????????//UNICODE和UNICODE?big?endian文件向多字節文件轉換?共8種?? ????????if(curtc>=UNICODE?&&?tcTo<UNICODE)?? ????????????bret=UnicodeFileToMBFile(filesourcepath,filesavepath,tcTo);?? ????else?? ????????//多字節文件之間轉換?共12種?? ????????if(curtc<UNICODE?&&?tcTo<UNICODE)?? ????????????bret=MBFileToMBFile(filesourcepath,filesavepath,tcTo,curtc);?? ????return?bret;?? }?? //編碼類型轉換為字符串?? CString?Coder::CodeTypeToString(TextCode?tc)?? {?? ??????CString?strtype;?? ??????switch(tc)?? ??????{?? ??????case?GB2312:?? ???????????strtype=_T("GB2312");?? ???????????break;?? ??????case?BIG5:?? ??????????strtype=_T("Big5");?? ???????????break;?? ??????case?GBK:?? ??????????strtype=_T("GBK");?? ???????????break;?? ??????case?UTF8:?? ??????????strtype=_T("UTF-8");?? ???????????break;?? ??????case?UNICODE:?? ??????????strtype=_T("Unicode");?? ???????????break;?? ??????case?UNICODEBIGENDIAN:?? ??????????strtype=_T("Unicode?big?endian");?? ???????????break;?? ??????}?? ??????return?strtype;?? }?? //多字節向多字節轉換?? char*?Coder::MByteToMByte(UINT?CodePageCur,?UINT?CodePageTo,?const?char*?szSrcStr)?? {?? ????char????*pchDes=NULL;?? ????char????*pchTemp=NULL;?? ????wchar_t?*pwchtemp=NULL;?? ????//三種中文編碼之間轉換?? ????if(CodePageCur!=CP_UTF8??&&?CodePageTo!=CP_UTF8)?? ????{?? ????????switch(CodePageCur)?? ????????{?? ????????????case?CP_GB2312:?? ????????????????{?? ????????????????????if(CP_BIG5==CodePageTo)??? ???????????????????????pchDes=GB2312ToBIG5(szSrcStr);?? ????????????????????else?? ???????????????????????pchDes=GB2312ToGBK(szSrcStr);?? ????????????????????break;?? ????????????????}?? ????????????case?CP_BIG5:?? ????????????????{????? ????????????????????if(CP_GB2312==CodePageTo)?? ????????????????????????pchDes=BIG5ToGB2312(szSrcStr);?? ????????????????????else?? ????????????????????????pchDes=BIG5ToGBK(szSrcStr);?? ????????????????????break;?? ????????????????}?? ????????????case?CP_GBK:?? ????????????????{????? ????????????????????if(CP_GB2312==CodePageTo)?? ????????????????????????pchDes=GBKToGB2312(szSrcStr);?? ????????????????????else?? ????????????????????????pchDes=GBKToBIG5(szSrcStr);?? ????????????????????break;?? ????????????????}?? ????????}?? ????}?? ????else?? ????{????//從UTF-8轉到其他多字節??直接轉到GB2312?其他形式用GB2312做中間形式?? ?????????if(CP_UTF8==CodePageCur)?? ?????????{???? ????????????pwchtemp=MByteToWChar(CodePageCur,szSrcStr);?? ????????????if(CP_GB2312==CodePageTo)?? ????????????{?? ????????????????pchDes=WCharToMByte(CP_GB2312,pwchtemp);?? ????????????}?? ????????????else?? ????????????{?????? ????????????????pchTemp=WCharToMByte(CP_GB2312,pwchtemp);?? ?????????????????if(CP_GBK==CodePageTo)?? ????????????????????pchDes=GB2312ToGBK(pchTemp);?? ?????????????????else?? ????????????????????pchDes=GB2312ToBIG5(pchTemp);?? ????????????}?? ?????????}?? ?????????//從其他多字節轉到UTF-8?? ?????????else??? ?????????{?????? ??????????????if(CP_GBK==CodePageCur)?? ??????????????{????? ?? ??????????????????pchTemp=GBKToGB2312(szSrcStr);?? ??????????????????pwchtemp=MByteToWChar(CP_GB2312,pchTemp);?? ??????????????}?? ??????????????else?? ????????????????pwchtemp=MByteToWChar(CodePageCur,szSrcStr);?? ??????????????pchDes=WCharToMByte(CodePageTo,pwchtemp);?? ?????????}?? ????}?? ????delete[]?pchTemp;?? ????delete[]?pwchtemp;?? ????return?pchDes;?? }?? //獲取編碼類型對應的代碼頁?? UINT?Coder::GetCodePage(TextCode?tccur)?? {?? ??????UINT?CodePage;?? ??????switch(tccur)?? ??????{?? ??????case?GB2312:?? ??????????CodePage=CP_GB2312;?? ??????????break;?? ??????case?BIG5:?? ??????????CodePage=CP_BIG5;?? ??????????break;?? ??????case?GBK:?? ??????????CodePage=CP_GBK;?? ??????????break;?? ??????case?UTF8:?? ??????????CodePage=CP_UTF8;?? ??????????break;?? ??????case?UNICODEBIGENDIAN:?? ??????case?UNICODE:?? ???????????break;?? ????}?? ??????return?CodePage;?? }?? //指定轉換時默認一次轉換字節大小?? void?Coder::SetDefaultConvertSize(UINT?nCount)?? {?????? ?????if(nCount!=0)?? ????????PREDEFINEDSIZE=nCount;?? }?? 3.運行效果
在win7 VC 6.0下測試六種編碼的轉換測試通過，30個方向的轉換如下圖所示:
測試程序運行效果如下圖所示:
GB2312轉換到GBK編碼效果如下圖所示:
UTF-8轉換到Big5編碼的效果如下圖所示:
1.問題提出
??? 在學編程序時，曾經有人問過“你可以編一個記事本程序嗎?”當時很不屑一顧，但是隨著學習MFC的深入，了解到記事本程序也并非易事，難點就是四種編碼之間的轉換。
對于編碼，這是一個令初學者頭疼的問題，特別是對于編碼的轉換，更是難以捉摸。筆者為了完成畢業設計中的一個編碼轉換模塊，研究了中文編碼和常見的字符集后，決定解決"記事本"程序的編碼問題，更進一步完成GB2312、Big5、GBK、Unicode 、Unicode big endian、UTF-8共6種編碼之間的任意轉換。
2.問題解決?????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????
(1)編碼基礎知識
a.了解編碼和字符集
這部分內容，我不在贅述，可參見CSDN Ancky的專欄中《各種字符集和編碼詳解》
博客地址:http://blog.csdn.net/ancky/article/details/2034809
b.單字節、雙字節、多字節
這部分內容，可參見我先前翻譯的博文《C++字符串完全指南--第一部分:win32?字符編碼》
博客地址:http://blog.csdn.net/ziyuanxiazai123/article/details/7482360
c.區域和代碼頁
這部分內容，可參見博客 ? ?? http://hi.baidu.com/tzpwater/blog/item/bd4abb0b60bff1db3ac7636a.html
d.中文編碼GB2312、GBK、Big5，這部分內容請參見CSDN? lengshine 博客中《GB2312、GBK、Big5漢字編碼
》，博客地址:http://blog.csdn.net/lengshine/article/details/5470545
e.Windows程序的字符編碼
這部分內容，可參見博客http://blog.sina.com.cn/s/blog_4e3197f20100a6z2.html 中《Windows程序的字符編碼》
(2)編碼總結
a.六種編碼的特點
六種編碼的特點如下圖所示:
b.編碼存儲差別
ANSI(在簡體中文中默認為GB2312)、Unicode、Unicode big endian 、UTF-8存儲存在差別。
以中文"你好"二字為例，他們存貯格式如下圖所示:
c.GB2312、Big5、GBK編碼的區別
三者中漢字均采用二個字節表示，但是字節表示的值范圍有所不同，如下圖所示:
(3)編碼轉換方式
6種編碼互相轉換，由排列組合知識知道共有30個方向的轉換.筆者采用的轉換方法,
多字節文件與Unicode文件轉換如下圖所示:
多字節文件之間轉換如下圖所示:
(4)編碼轉換使用的三個函數
a.MultiByteToWideChar
該函數完成多字節字符串向Unicode寬字符串的轉換.
函數原型為:
int MultiByteToWideChar(UINT CodePage,???????? // 代碼頁DWORD dwFlags,???????? // 轉換標志LPCSTR lpMultiByteStr, // 待轉換的字符串int cbMultiByte,?????? // 待轉換字符串的字節數目LPWSTR lpWideCharStr,? // 轉換后寬字符串的存儲空間int cchWideChar??????? // 轉換后寬字符串的存儲空間大小? 以寬字符大小為單位 ); b.WideCharToMultiByte 該函數完成Unicode寬字符串到多字節字符串的轉換，使用方法具體參見MSDN。 以上兩個函數可以完成大部分的字符串轉換，可以將其封裝成多字節和寬字節之間的轉換函數:[cpp] view plaincopyprint?GB2312轉換到GBK編碼效果如下圖所示:
UTF-8轉換到Big5編碼的效果如下圖所示:
本文代碼及轉碼程序下載 ：http://download.csdn.net/user/ziyuanxiazai123
4.尚未解決的問題?????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????
(1)LCMapString函數的理解還不完全熟悉，其中參數偏多，理解需要一定基礎知識。
(2)為什么記事本程序的轉碼后存在些亂碼,亂碼是正確的嗎?因為我的程序使用了中間過渡形式，因此沒有任何亂碼。
(3)是否有更簡單和清晰的方式實現編碼轉換，待進一步研究。總結
以上是生活随笔為你收集整理的一网打尽中文编码转换---6种编码30个方向的转换的全部內容，希望文章能夠幫你解決所遇到的問題。
- 上一篇： 使用XmlTextWriter生成XML
- 下一篇： datatable数据类型方法