随笔 - 298  文章 - 377  trackbacks - 0
<2008年12月>
30123456
78910111213
14151617181920
21222324252627
28293031123
45678910

常用链接

留言簿(34)

随笔分类

随笔档案

文章档案

相册

收藏夹

搜索

  •  

最新评论

阅读排行榜

评论排行榜

linux下:

#define         MASKBITS                0x3F
#define         MASKBYTE                0x80
#define         MASK2BYTES                0xC0
#define         MASK3BYTES                0xE0
#define         MASK4BYTES                0xF0
#define         MASK5BYTES                0xF8
#define         MASK6BYTES                0xFC

typedef unsigned short   Unicode2Bytes;
typedef unsigned int     Unicode4Bytes;


void UTF8Decode2BytesUnicode(const std::string& input, std::wstring& output)
{
    output = L"";
    BYTE b;
    Unicode2Bytes ch;
    for(size_t i=0; i < input.length();)
    {
        b = input;
        // 1110xxxx 10xxxxxx 10xxxxxx
        if((input & MASK3BYTES) == MASK3BYTES)
        {
            ch = ((Unicode2Bytes)(input & 0x0F) << 12) | (
                (Unicode2Bytes)(input[i+1] & MASKBITS) << 6)
                | (input[i+2] & MASKBITS);
            i += 3;
        }
        // 110xxxxx 10xxxxxx
        else if((input & MASK2BYTES) == MASK2BYTES)
        {
            ch = ((Unicode2Bytes)(input & 0x1F) << 6) | (input[i+1] & MASKBITS);
            i += 2;
        }
        // 0xxxxxxx
        else if(input < 0x80)
        {
            ch = input;
            i += 1;
        }

        else
        {
//            assert(false);
        }
       
        output += ch;
        //output.push_back(ch);
    }
}

void UTF8Decode2BytesAssciChar(const std::string& input, char** output)
{
    std::wstring wsStrOutput;
    if (input.empty())
        return;

    if (*output != NULL)
    {
        free(*output);
        *output = NULL;
    }
    UTF8Decode2BytesUnicode(input, wsStrOutput);
    char* pChar = (char*)malloc(wsStrOutput.length() * 2 + 1);
    memset(pChar, 0, wsStrOutput.length() * 2 + 1);
#ifdef WIN32
    WideCharToMultiByte( CP_ACP, 0, wsStrOutput.c_str(), -1,
        pChar, wsStrOutput.length() * 2 + 1, NULL, NULL );
#else
    //mbstowcs()  wcstombs()
    assert(false);
#endif
    *output = pChar;
}
//---------------------------------------
#include <iconv.h>
#include <iostream>

#define OUTLEN 255

using namespace std;

// 代码转换操作类
class CodeConverter {
private:
iconv_t cd;
public:
// 构造
CodeConverter(const char *from_charset,const char *to_charset) {
cd = iconv_open(to_charset,from_charset);
}

// 析构
~CodeConverter() {
iconv_close(cd);
}

// 转换输出
int convert(char *inbuf,int inlen,char *outbuf,int outlen) {
char **pin = &inbuf;
char **pout = &outbuf;

memset(outbuf,0,outlen);
return iconv(cd,pin,(size_t *)&inlen,pout,(size_t *)&outlen);
}
};

int main(int argc, char **argv)
{
char *in_utf8 = "姝e?ㄥ??瑁?";
char *in_gb2312 = "正在安装";
char out[OUTLEN];

// utf-8-->gb2312
CodeConverter cc = CodeConverter("utf-8","gb2312");
cc.convert(in_utf8,strlen(in_utf8),out,OUTLEN);
cout << "utf-8-->gb2312 in=" << in_utf8 << ",out=" << out << endl;

// gb2312-->utf-8
CodeConverter cc2 = CodeConverter("gb2312","utf-8");
cc2.convert(in_gb2312,strlen(in_gb2312),out,OUTLEN);
cout << "gb2312-->utf-8 in=" << in_gb2312 << ",out=" << out << endl;
}

posted on 2007-08-26 02:33 聂文龙 阅读(1166) 评论(5)  编辑 收藏 引用 所属分类: c++

FeedBack:
# re: 编码问题 2007-08-26 03:07 聂文龙
VC 实现 汉字 GBK(GB2312) 转化为 UTF8 编码
void ConvertGBKToUtf8(CString& strGBK)
{
int len=MultiByteToWideChar(CP_ACP, 0, (LPCTSTR)strGBK, -1, NULL,0);
unsigned short * wszUtf8 = new unsigned short[len+1];
memset(wszUtf8, 0, len * 2 + 2);
MultiByteToWideChar(CP_ACP, 0, (LPCTSTR)strGBK, -1, wszUtf8, len);

len = WideCharToMultiByte(CP_UTF8, 0, wszUtf8, -1, NULL, 0, NULL, NULL);
char *szUtf8=new char[len + 1];
memset(szUtf8, 0, len + 1);
WideCharToMultiByte (CP_UTF8, 0, wszUtf8, -1, szUtf8, len, NULL,NULL);

strGBK = szUtf8;
delete[] szUtf8;
delete[] wszUtf8;
}  回复  更多评论
  
# re: 编码问题 2007-08-26 03:43 聂文龙
//这是个类strCoding (strCoding.h文件)
#pragma once
#include <iostream>
#include <string>
#include <windows.h>
using namespace std;

class strCoding
{
public:
strCoding(void);
~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);

};
//这是个类strCoding (strCoding.cpp文件)
#include "StdAfx.h"

#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 | ((pchar[1] & 0xF0) >> 4));
pOut[1] = (0x80 | ((pchar[1] & 0x0F) << 2)) + ((pchar[0] & 0xC0) >> 6);
pOut[2] = (0x80 | (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) | 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;

}

//test
#include "stdafx.h"
#include "strCoding.h"

using namespace std;


int main()
{

strCoding cfm;
string keyword="大家好,欢迎你";
string Temp="";
string Output="";

//把关键字做url的utf8编码
Temp= cfm.UrlUTF8((char *)keyword.data());
cout<<Temp<<endl;

//把url的utf8编码的结果解码
Temp =cfm.UrlUTF8Decode(Temp);
cout<<Temp<<endl;

//把关键字做url的gb2312编码
Temp =cfm.UrlGB2312((char *)keyword.data());
cout<<Temp<<endl;

//把url的gb2312编码的结果解码
Temp =cfm.UrlGB2312Decode(Temp);
cout<<Temp<<endl;


//把关键字GB2312转UTF_8

cfm.GB2312ToUTF_8(Output,(char *)keyword.data(),strlen(keyword.data()));
cout<<Output<<endl;

//把GB2312转UTF_8转为中文
cfm.UTF_8ToGB2312(Temp,(char *)Output.data(),strlen(Output.data()));
cout<<Temp<<endl;


//system("pasue");
getchar();

return 0;
//
}


在VC7win32下调试通过  回复  更多评论
  
# re: 编码问题 2007-08-26 03:44 聂文龙
// ChineseCodeLib.h: interface for the CChineseCodeLib class.
//
//////////////////////////////////////////////////////////////////////
#include<string>
using namespace std;

/*
功能:汉字GB2312与UTF-8编码互转
作者:litz
Email:mycro@163.com
参考:吴康彬先生的文章《UTF-8与GB2312之间的互换》
http://www.vckbase.com/document/viewdoc/?id=1397
*/


#if !defined(__CCHINESECODELIB_H_)
#define __CCHINESECODELIB_H_

class CChineseCodeLib
{
public:
static void UTF_8ToGB2312(string& pOut,char *pText, int pLen);
static void GB2312ToUTF_8(string& pOut,char *pText, int pLen);
// Unicode 转换成UTF-8
static void UnicodeToUTF_8(char* pOut,WCHAR* pText);
// GB2312 转换成 Unicode
static void Gb2312ToUnicode(WCHAR* pOut,char *gbBuffer);
// 把Unicode 转换成 GB2312
static void UnicodeToGB2312(char* pOut,unsigned short uData);
// 把UTF-8转换成Unicode
static void UTF_8ToUnicode(WCHAR* pOut,char* pText);

CChineseCodeLib();
virtual ~CChineseCodeLib();
};

#endif // !defined(__CCHINESECODELIB_H_)











// ChineseCodeLib.cpp: implementation of the CChineseCodeLib class.
//
//////////////////////////////////////////////////////////////////////

#include "stdafx.h"
#include "ChineseCodeLib.h"

//////////////////////////////////////////////////////////////////////
// Construction/Destruction
//////////////////////////////////////////////////////////////////////

CChineseCodeLib::CChineseCodeLib()
{

}

CChineseCodeLib::~CChineseCodeLib()
{

}


void CChineseCodeLib::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 CChineseCodeLib::UnicodeToGB2312(char* pOut,unsigned short uData)
{
WideCharToMultiByte(CP_ACP,NULL,&uData,1,pOut,sizeof(WCHAR),NULL,NULL);
return;
}

void CChineseCodeLib::Gb2312ToUnicode(WCHAR* pOut,char *gbBuffer)
{
::MultiByteToWideChar(CP_ACP,MB_PRECOMPOSED,gbBuffer,2,pOut,1);
return;
}

void CChineseCodeLib::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 | ((pchar[1] & 0xF0) >> 4));
pOut[1] = (0x80 | ((pchar[1] & 0x0F) << 2)) + ((pchar[1] & 0xC0) >> 6);
pOut[2] = (0x80 | (pchar[0] & 0x3F));

return;
}

void CChineseCodeLib::GB2312ToUTF_8(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)
{
//如果是英文直接复制就可以
if( *(pText + i) >= 0)
{
rst[j++] = pText[i++];
}
else
{
WCHAR pbuffer;
Gb2312ToUnicode(&pbuffer,pText+i);

UnicodeToUTF_8(buf,&pbuffer);

unsigned short int tmp = 0;
tmp = rst[j] = buf[0];
tmp = rst[j+1] = buf[1];
tmp = rst[j+2] = buf[2];


j += 3;
i += 2;
}
}
rst[j] = '\0';

//返回结果
pOut = rst;
delete []rst;

return;
}

void CChineseCodeLib::UTF_8ToGB2312(string &pOut, char *pText, int pLen)
{
char * newBuf = new char[pLen];
char Ctemp[4];
memset(Ctemp,0,4);

int i =0;
int j = 0;

while(i < pLen)
{
if(pText[i] > 0)
{
newBuf[j++] = pText[i++];
}
else
{
WCHAR Wtemp;
UTF_8ToUnicode(&Wtemp,pText + i);

UnicodeToGB2312(Ctemp,Wtemp);

newBuf[j] = Ctemp[0];
newBuf[j + 1] = Ctemp[1];

i += 3;
j += 2;
}
}
newBuf[j] = '\0';

pOut = newBuf;
delete []newBuf;

return;
}

  回复  更多评论
  
# re: 编码问题 2007-09-07 17:13 
怎么我的不能通过编译呀  回复  更多评论
  
# re: 编码问题 2007-09-07 17:15 
我用的是带MAIN函数的那个
为什么老是说d:\oo\oo.cpp(5) : error C2143: syntax error : missing ';' before 'using' 错误呀  回复  更多评论
  

只有注册用户登录后才能发表评论。
网站导航: 博客园   IT新闻   BlogJava   知识库   博问   管理