为什么Unicode中文字符转换UTF-8 结果是乱码
请问，各位熟悉编码方式的，为什么在转换UTF8编码之后，结果出现乱码，不知道哪里出错了
wchar_t pUnicode[]=L"中国";
char* pTransText;
pTransText=UnicodeToUTF_8(pUnicode);
CString strTest=pTransText;
MessageBox(strTest);
char* UnicodeToUTF_8(wchar_t* pText)
{
int u8Len = WideCharToMultiByte(CP_UTF8,NULL,pText,-1,NULL,0,NULL,NULL);
char* pOut = new char[u8Len + 1];
memset(pOut,0,u8Len + 1);
WideCharToMultiByte(CP_UTF8,NULL,pText,-1,pOut,u8Len,NULL,NULL);
return pOut;
}
class strCoding
{
public:
strCoding(void);
virtual ~strCoding(void);
void UTF_8ToGB2312(string &pOut, char *pText, int pLen);//utf_8转为gb2312
void GB2312ToUTF_8(string& pOut,char *pText, int pLen); //gb2312 转utf_8
string UrlGB2312(char * str); //urlgb2312编码
string UrlUTF8(char * str); //urlutf8 编码
string UrlUTF8Decode(string str); //urlutf8解码
string UrlGB2312Decode(string str); //urlgb2312解码
private:
void Gb2312ToUnicode(WCHAR* pOut,char *gbBuffer);
void UTF_8ToUnicode(WCHAR* pOut,char *pText);
void UnicodeToUTF_8(char* pOut,WCHAR* pText);
void UnicodeToGB2312(char* pOut,WCHAR uData);
char CharToInt(char ch);
char StrToBin(char *str);
};
#include "strCoding.h"
strCoding::strCoding(void)
{
}
strCoding::~strCoding(void)
{
}
void strCoding::Gb2312ToUnicode(WCHAR* pOut,char *gbBuffer)
{
::MultiByteToWideChar(CP_ACP,MB_PRECOMPOSED,gbBuffer,2,pOut,1);
return;
}
void strCoding::UTF_8ToUnicode(WCHAR* pOut,char *pText)
{
char* uchar = (char *)pOut;
uchar[1] = ((pText[0] & 0x0F) << 4) + ((pText[1] >> 2) & 0x0F);
uchar[0] = ((pText[1] & 0x03) << 6) + (pText[2] & 0x3F);
return;
}
void strCoding::UnicodeToUTF_8(char* pOut,WCHAR* pText)
{
// 注意 WCHAR高低字的顺序,低字节在前，高字节在后
char* pchar = (char *)pText;
pOut[0] = (0xE0
[解决办法]
((pchar[1] & 0xF0) >> 4));
pOut[1] = (0x80
[解决办法]
((pchar[1] & 0x0F) << 2)) + ((pchar[0] & 0xC0) >> 6);
pOut[2] = (0x80
[解决办法]
(pchar[0] & 0x3F));
return;
}
void strCoding::UnicodeToGB2312(char* pOut,WCHAR uData)
{
WideCharToMultiByte(CP_ACP,NULL,&uData,1,pOut,sizeof(WCHAR),NULL,NULL);
return;
}
//做为解Url使用
char strCoding:: CharToInt(char ch){
if(ch>='0' && ch<='9')return (char)(ch-'0');
if(ch>='a' && ch<='f')return (char)(ch-'a'+10);
if(ch>='A' && ch<='F')return (char)(ch-'A'+10);
return -1;
}
char strCoding::StrToBin(char *str){
char tempWord[2];
char chn;
tempWord[0] = CharToInt(str[0]); //make the B to 11 -- 00001011
tempWord[1] = CharToInt(str[1]); //make the 0 to 0 -- 00000000
chn = (tempWord[0] << 4)
[解决办法]
tempWord[1]; //to change the BO to 10110000
return chn;
}
//UTF_8 转gb2312
void strCoding::UTF_8ToGB2312(string &pOut, char *pText, int pLen)
{
char buf[4];
char* rst = new char[pLen + (pLen >> 2) + 2];
memset(buf,0,4);
memset(rst,0,pLen + (pLen >> 2) + 2);
int i =0;
int j = 0;
while(i < pLen)
{
if(*(pText + i) >= 0)
{
rst[j++] = pText[i++];
}
else
{
WCHAR Wtemp;
UTF_8ToUnicode(&Wtemp,pText + i);
UnicodeToGB2312(buf,Wtemp);
unsigned short int tmp = 0;
tmp = rst[j] = buf[0];
tmp = rst[j+1] = buf[1];
tmp = rst[j+2] = buf[2];
//newBuf[j] = Ctemp[0];
//newBuf[j + 1] = Ctemp[1];
i += 3;
j += 2;
}
}
rst[j]='\0';
pOut = rst;
delete []rst;
}
//GB2312 转为 UTF-8
void strCoding::GB2312ToUTF_8(string& pOut,char *pText, int pLen)
{
char buf[4];
memset(buf,0,4);
//pOut.clear();
int i = 0;
while(i < pLen)
{
//如果是英文直接复制就可以
if( pText[i] >= 0)
{
char asciistr[2]={0};
asciistr[0] = (pText[i++]);
pOut.append(asciistr);
}
else
{
WCHAR pbuffer;
Gb2312ToUnicode(&pbuffer,pText+i);
UnicodeToUTF_8(buf,&pbuffer);
pOut.append(buf);
i += 2;
}
}
return;
}
//把str编码为网页中的 GB2312 url encode ,英文不变，汉字双字节 如%3D%AE%88
string strCoding::UrlGB2312(char * str)
{
string dd;
size_t len = strlen(str);
for (size_t i=0;i<len;i++)
{
if(isalnum((BYTE)str[i]))
{
char tempbuff[2];
sprintf(tempbuff,"%c",str[i]);
dd.append(tempbuff);
}
else if (isspace((BYTE)str[i]))
{
dd.append("+");
}
else
{
char tempbuff[4];
sprintf(tempbuff,"%%%X%X",((BYTE*)str)[i] >>4,((BYTE*)str)[i] %16);
dd.append(tempbuff);
}
}
return dd;
}
//把str编码为网页中的 UTF-8 url encode ,英文不变，汉字三字节 如%3D%AE%88
string strCoding::UrlUTF8(char * str)
{
string tt;
string dd;
GB2312ToUTF_8(tt,str,(int)strlen(str));
size_t len=tt.length();
for (size_t i=0;i<len;i++)
{
if(isalnum((BYTE)tt.at(i)))
{
char tempbuff[2]={0};
sprintf(tempbuff,"%c",(BYTE)tt.at(i));
dd.append(tempbuff);
}
else if (isspace((BYTE)tt.at(i)))
{
dd.append("+");
}
else
{
char tempbuff[4];
sprintf(tempbuff,"%%%X%X",((BYTE)tt.at(i)) >>4,((BYTE)tt.at(i)) %16);
dd.append(tempbuff);
}
}
return dd;
}
//把url GB2312解码
string strCoding::UrlGB2312Decode(string str)
{
string output="";
char tmp[2];
int i=0,idx=0/*,ndx*/,len=str.length();
while(i<len){
if(str[i]=='%'){
tmp[0]=str[i+1];
tmp[1]=str[i+2];
output += StrToBin(tmp);
i=i+3;
}
else if(str[i]=='+'){
output+=' ';
i++;
}
else{
output+=str[i];
i++;
}
}
return output;
}
//把url utf8解码
string strCoding::UrlUTF8Decode(string str)
{
string output="";
string temp =UrlGB2312Decode(str);//
UTF_8ToGB2312(output,(char *)temp.data(),strlen(temp.data()));
return output;
}
strCoding myStrCoding;
string strNameEncode = myStrCoding.UrlUTF8(m_strUserName.GetBuffer(m_strUserName.GetLength()));
Private Declare Function MultiByteToWideChar Lib "kernel32" (ByVal CodePage As Long, ByVal dwFlags As Long, ByRef lpMultiByteStr As Any, ByVal cchMultiByte As Long, ByVal lpWideCharStr As Long, ByVal cchWideChar As Long) As Long
Private Declare Function WideCharToMultiByte Lib "kernel32" (ByVal CodePage As Long, ByVal dwFlags As Long, ByVal lpWideCharStr As Long, ByVal cchWideChar As Long, ByRef lpMultiByteStr As Any, ByVal cchMultiByte As Long, ByVal lpDefaultChar As Long, ByVal lpUsedDefaultChar As Long) As Long
'常用的代码页：
const cpUTF8 =65001
const cpGB2312 = 936
const cpGB18030=54936
const cpUTF7 =65000
Function MultiByteToUTF16(UTF8() As Byte, CodePage As Long) As String
Dim bufSize As Long
bufSize = MultiByteToWideChar(CodePage, 0&, UTF8(0), UBound(UTF8) + 1, 0, 0)
MultiByteToUTF16 = Space(bufSize)
MultiByteToWideChar CodePage, 0&, UTF8(0), UBound(UTF8) + 1, StrPtr(MultiByteToUTF16), bufSize
End Function
Function UTF16ToMultiByte(UTF16 As String, CodePage As Long) As Byte()
Dim bufSize As Long
Dim arr() As Byte
bufSize = WideCharToMultiByte(CodePage, 0&, StrPtr(UTF16), Len(UTF16), 0, 0, 0, 0)
ReDim arr(bufSize - 1)
WideCharToMultiByte CodePage, 0&, StrPtr(UTF16), Len(UTF16), arr(0), bufSize, 0, 0
UTF16ToMultiByte = arr
End Function
Private Sub Command1_Click()
MsgBox MultiByteToUTF16(UTF16ToMultiByte("ab中,c", cpUTF8), cpUTF8)
End Sub
