VC中怎么实现将unicode转换为汉字，再写入某个txt文件中？

[flywke]

比如：有一个unicode字符串“%CC%EC%D1%C4%BA%CE%B4%A6%CE%DE%B7%BC%B2%DD”，
想把它转换成汉字形式写入某个TXT文件，应该怎么实现啊？谢谢各位大侠！

[gamedragon]

1.这不是UNICODE字符串，就是个转义的序列而已
2.看样子这串字符就是GB编码，就是{0xCC, 0xEC, 0xD1, ...}，把这个字符串写到文件里就行了。

[hzy694358]

你这是urlencode吧，

[newasoft]

//urlcode.h
#ifndef __CODES_CONVERT_H__
#define __CODES_CONVERT_H_
#include <errno.h>
#include <string.h>
#include <stdio.h>
#include <ctype.h>

int urlencode(char *ib, int il, char *ob);
int urldecode(char *ib, int il, char *ob);
char * str_replace(const char * s, const char * f, const char * r);
#endif

//urlcode.c

#include "urlcode.h"

extern int errno;

char urls[] = "0123456789ABCDEF";

int geturlspos(char ch)
{
int i;

for(i=0; i<strlen(urls); i++)
{
if (urls[i] == ch)
return i;
}

return 0;
}

/* normal to url */
/* ascii no deal, ' ' to '+', others to %XY, X is high, Y is lower */
int urlencode(char *ib, int il, char *ob)
{
int i=0;
int j=0;

for(i=0; i<il; i++, j++)
{
if (!isascii(ib[i]))
{
ob[j++] = '%';
ob[j++] = urls[(ib[i] >> 4) & 0x0f];
ob[j] = urls[ib[i] & 0x0f];
}
else
{
ob[j] = ib[i];
}
}

ob[j] = '\0';

return j;
}

/* url to normal */
/* ascii no deal, '+' to ' ', others to normal, %XY->X is high, Y is lower */
int urldecode(char *ib, int il, char *ob)
{
int i=0;
int j=0;

for(i=0; i<il; i++)
{
if (ib[i] == '%')
{
ob[j] = ((geturlspos(ib[i+1]) << 4) & 0xf0) | (geturlspos(ib[i+2]) & 0x0f);
i += 2;
}
else
{
ob[j] = ib[i];
}

j++;
}

return j;
}
//函数: str_replace
//功能: 将字符串s中所有f的内容替换成r的内容
//返回: 新字符串的地址(使用free释放), 失败返回0。
char * str_replace(const char * s, const char * f, const char * r)
{
int inum = 1;
int if_len, ir_len;
char * ps;
char * pt;
char * pn;
char * pp;

if(s==0 || f==0 || r==0) return 0;
if(s[0]==0 || f[0]==0) return 0;

if_len = strlen(f);
ir_len = strlen(r);

for(ps=(char *)s;;)
{
pt = strstr(ps, f);
if(pt == 0)
{
inum += strlen(ps);
break;
}
inum += (pt - ps) + ir_len;
ps = pt + if_len;
}

pn = pp = malloc(inum);
if(pn == 0) return 0;
pn[inum-1] = 0;

for(ps=(char *)s;;)
{
pt = strstr(ps, f);
if(pt == 0)
{
memcpy(pp, ps, strlen(ps));
break;
}

memcpy(pp, ps, pt - ps);
pp += pt - ps;
memcpy(pp, r, ir_len);
pp += ir_len;
ps = pt + if_len;
}

return pn;
}

[newasoft]

//chinesecode.h
#pragma once
#include "atlstr.h"
#include "string"
using namespace std;

void UTF_8ToUnicode(wchar_t* pOut,char *pText); // 把UTF-8转换成Unicode
void UnicodeToUTF_8(char* pOut,wchar_t* pText); //Unicode 转换成UTF-8
void UnicodeToGB2312(char* pOut,wchar_t uData); // 把Unicode 转换成 GB2312
void Gb2312ToUnicode(wchar_t* pOut,char *gbBuffer);// GB2312 转换成　Unicode
void GB2312ToUTF_8(string& pOut,char *pText, int pLen);//GB2312 转为 UTF-8
void UTF_8ToGB2312(char* pOut, char *pText, int pLen);//UTF-8 转为 GB2312

CString URLDecode(CString sIn);
CString URLEncode(CString sIn);


//chinesecode.cpp
#include ".\chinesecode.h"

void UTF_8ToUnicode(wchar_t* 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 UnicodeToUTF_8(char* pOut,wchar_t* 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 UnicodeToGB2312(char* pOut,wchar_t uData)
{
WideCharToMultiByte(CP_ACP,NULL,&uData,1,pOut,sizeof(wchar_t),NULL,NULL);
return;
}

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

void GB2312ToUTF_8(string& pOut,char *pText, int pLen)
{
char buf[4];
int nLength = pLen* 3;
char* rst = new char[nLength];

memset(buf,0,4);
memset(rst,0,nLength);

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_t 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 UTF_8ToGB2312(char* newBuf, char *pText, int 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';
return;
}

inline BYTE toHex(const BYTE &x)
{
return x > 9 ? x + 55: x + 48;
}
inline BYTE toByte(const BYTE &x)
{
return x > 57? x - 55: x - 48;
}
CString URLDecode(CString sIn)
{
CString sOut;
const int nLen = sIn.GetLength() + 1;
register LPBYTE pOutTmp = NULL;
LPBYTE pOutBuf = NULL;
register LPBYTE pInTmp = NULL;
LPBYTE pInBuf =(LPBYTE)sIn.GetBuffer(nLen);
//alloc out buffer
pOutBuf = (LPBYTE)sOut.GetBuffer(nLen);

if(pOutBuf)
{
pInTmp = pInBuf;
pOutTmp = pOutBuf;
// do encoding
while (*pInTmp)
{
if('%'==*pInTmp)
{
pInTmp++;
*pOutTmp++ = (toByte(*pInTmp)%16<<4) + toByte(*(pInTmp+1))%16;//高4位+低4位
pInTmp++;
}
else if('+'==*pInTmp)
*pOutTmp++ = ' ';
else
*pOutTmp++ = *pInTmp;
pInTmp++;
}
*pOutTmp = '\0';
sOut.ReleaseBuffer();
}
sIn.ReleaseBuffer();

return sOut;
}
CString URLEncode(CString sIn)
{
CString sOut;
const int nLen = sIn.GetLength() + 1;
register LPBYTE pOutTmp = NULL;
LPBYTE pOutBuf = NULL;
register LPBYTE pInTmp = NULL;
LPBYTE pInBuf =(LPBYTE)sIn.GetBuffer(nLen);
//alloc out buffer
pOutBuf = (LPBYTE)sOut.GetBuffer(nLen*3);

if(pOutBuf)
{
pInTmp = pInBuf;
pOutTmp = pOutBuf;
// do encoding
while (*pInTmp)
{
if(isalnum(*pInTmp) || '-'==*pInTmp || '_'==*pInTmp || '.'==*pInTmp)
*pOutTmp++ = *pInTmp;
else if(isspace(*pInTmp))
*pOutTmp++ = '+';
else
{
*pOutTmp++ = '%';
*pOutTmp++ = toHex(*pInTmp>>4);//高4位
*pOutTmp++ = toHex(*pInTmp%16);//低4位
}
pInTmp++;
}
*pOutTmp = '\0';
sOut.ReleaseBuffer();
}
sIn.ReleaseBuffer();

return sOut;
}

[klkvc386]

Mark.............

[hzy694358]

mark

[flywke]

谢谢各位，我这串字符是网页上，直接用Get或Post方法发出HTTP请求。该请求生成的URL中包含汉字。
如：http://www.baidu.com/s?wd=%B4%BA%BD%DA ,应该是GB2312字符集。
这串字符想转换为汉字形式写入TXT文件，可以按gamedragon所说，直接把{0xb4, 0xba, 0xda, ...}，写文件吗？代码应该怎么写啊？

[向立天]

您好
我是本版版主
此帖已多日无人关注
请您及时结帖
如您认为问题没有解决可按无满意结帖处理
另外本版设置了疑难问题汇总帖
并已在版面置顶
相关规定其帖子中有说明
您可以根据规定提交您帖子的链接
如您目前不想结帖只需回帖说明
我们会删除此结帖通知

见此回复三日内无回应
我们将强制结帖
相关规定详见界面界面版关于版主结帖工作的具体办法