求二个函数,unicodeToUTF8与UTF8toUnicode

a8323418 2009-10-12 04:42:26
rt
...全文
1559 26 打赏 收藏 转发到动态 举报
写回复
用AI写文章
26 条回复
切换为时间正序
请发表友善的回复…
发表回复
  • 打赏
  • 举报
回复
void Decode_Utf8_Unicode_To_Unicode(char ** m_pbuff,uint32 *char_len)
{
char* pBuffer = NULL;
if(*m_pbuff==NULL)
return ;
pBuffer = MALLOC(sizeof(AECHAR)*((*char_len)+32)); //多加点内存,用来放版本号,最多放32个字符的版本号
if(pBuffer==NULL)
return ;
if ( ( unsigned char )**m_pbuff == 0xff && ( unsigned char )*(*m_pbuff+1) == 0xfe )//是Unicode
{
WSTRCPY((AECHAR *)pBuffer,(AECHAR *)(*m_pbuff+2));
}
else if(( unsigned char )**m_pbuff == 0xef && ( unsigned char )*(*m_pbuff+1) == 0xbb&& ( unsigned char )*(*m_pbuff+2) == 0xbf) //utf8内容进行解码,偏移3字节
{
UTF8TOWSTR((byte *)(*m_pbuff+3),(*char_len)-3,(AECHAR *)pBuffer,sizeof(AECHAR)*(*char_len));
}
else //未知编码格式内容不处理
{
FREEIF(pBuffer);
return;
}
*char_len=2*WSTRLEN((AECHAR *)pBuffer);
FREEIF(*m_pbuff);
*m_pbuff=pBuffer;
}
jiayucunyan 2009-10-13
  • 打赏
  • 举报
回复
http://www.gnu.org/software/libiconv/
用iconv吧
使用起来很方便

以前用这个做过unicode转gb
  • 打赏
  • 举报
回复
MultiByteToWideChar给用的话就ok。
nadoo 2009-10-13
  • 打赏
  • 举报
回复
实际项目中使用的话,还是建议用iconv
nadoo 2009-10-13
  • 打赏
  • 举报
回复
C语言版(自己优化):


/************************************************************************/
/* Author: NadOo (nadoo@21cn.com)
Reference:
http://blog.csdn.net/lovekatherine/archive/2007/08/30/1765903.aspx
Testing Tool:
http://www.hanzify.org/?Go=Show::List&ID=9627
*/
/************************************************************************/
#include <stdio.h>
#include <string.h>
#include <malloc.h>
#include <memory.h>

#ifdef WIN32
#define uint8_t unsigned __int8
#define uint16_t unsigned __int16
#define uint32_t unsigned __int32
#define uint64_t unsigned __int64

#define int8_t __int8
#define int16_t __int16
#define int32_t __int32
#endif

int unicode_to_utf8(uint16_t *in, int insize, uint8_t **out)
{
int i = 0;
int outsize = 0;
int charscount = 0;
uint8_t *result = NULL;
uint8_t *tmp = NULL;

charscount = insize / sizeof(uint16_t);
result = (uint8_t *)malloc(charscount * 3 + 1);
memset(result, 0, charscount * 3 + 1);
tmp = result;

for (i = 0; i < charscount; i++)
{
uint16_t unicode = in[i];

if (unicode >= 0x0000 && unicode <= 0x007f)
{
*tmp = (uint8_t)unicode;
tmp += 1;
outsize += 1;
}
else if (unicode >= 0x0080 && unicode <= 0x07ff)
{
*tmp = 0xc0 | (unicode >> 6);
tmp += 1;
*tmp = 0x80 | (unicode & (0xff >> 2));
tmp += 1;
outsize += 2;
}
else if (unicode >= 0x0800 && unicode <= 0xffff)
{
*tmp = 0xe0 | (unicode >> 12);
tmp += 1;
*tmp = 0x80 | (unicode >> 6 & 0x00ff);
tmp += 1;
*tmp = 0x80 | (unicode & (0xff >> 2));
tmp += 1;
outsize += 3;
}

}

*tmp = '\0';
*out = result;
return 0;
}

int utf8_to_unicode(uint8_t *in, uint16_t **out, int *outsize)
{
uint8_t *p = in;
uint16_t *result = NULL;
int resultsize = 0;
uint8_t *tmp = NULL;

result = (uint16_t *)malloc(strlen(in) * 2 + 2); /* should be enough */
memset(result, 0, strlen(in) * 2 + 2);
tmp = (uint8_t *)result;

while(*p)
{
if (*p >= 0x00 && *p <= 0x7f)
{
*tmp = *p;
tmp++;
*tmp = '\0';
resultsize += 2;
}
else if ((*p & (0xff << 5))== 0xc0)
{
uint16_t t = 0;
uint8_t t1 = 0;
uint8_t t2 = 0;

t1 = *p & (0xff >> 3);
p++;
t2 = *p & (0xff >> 2);

*tmp = t2 | ((t1 & (0xff >> 6)) << 6);//t1 >> 2;
tmp++;

*tmp = t1 >> 2;//t2 | ((t1 & (0xff >> 6)) << 6);
tmp++;

resultsize += 2;
}
else if ((*p & (0xff << 4))== 0xe0)
{
uint16_t t = 0;
uint8_t t1 = 0;
uint8_t t2 = 0;
uint8_t t3 = 0;

t1 = *p & (0xff >> 3);
p++;
t2 = *p & (0xff >> 2);
p++;
t3 = *p & (0xff >> 2);

//Little Endian
*tmp = ((t2 & (0xff >> 6)) << 6) | t3;//(t1 << 4) | (t2 >> 2);
tmp++;

*tmp = (t1 << 4) | (t2 >> 2);//((t2 & (0xff >> 6)) << 6) | t3;
tmp++;
resultsize += 2;
}

p++;
}

*tmp = '\0';
tmp++;
*tmp = '\0';
resultsize += 2;

*out = result;
*outsize = resultsize;
return 0;
}

void dump_utf8(uint8_t *utf8)
{
uint8_t *p = utf8;

while(*p)
{
printf("%02X", *p);
p++;
}
putchar('\n');
}

void dump_unicode(uint16_t *utf16, int size)
{
uint8_t *p = (uint8_t *)utf16;
int i = 0;

for (i = 0; i < size; i++)
{
printf("%02X", *p);
p++;
}
putchar('\n');
}

int main()
{
uint16_t unicode[] = L"中文";
uint8_t *utf8 = NULL;

int unisize = 0;
uint16_t *uni = NULL;

printf("original unicode: \n");
dump_unicode(unicode, sizeof(unicode));

printf("converted to utf8: \n");
unicode_to_utf8(unicode, sizeof(unicode), &utf8);
dump_utf8(utf8);

printf("converted to unicode: \n");
utf8_to_unicode(utf8, &uni, &unisize);
dump_unicode(uni, unisize);

return 0;
}



输出结果:
original unicode:
4E2D6587
converted to utf8:
E2B58EE89DA5
converted to unicode:
4E2D65870000

测试写的,应该有不少Bug。
a8323418 2009-10-12
  • 打赏
  • 举报
回复
来一个c语言写的
2009-10-12
  • 打赏
  • 举报
回复
曾经写过一个 C++ 的,未经过优化,未经过充分测试,慎用……仅供参考……
http://blog.csdn.net/hpsmouse/archive/2009/09/23/4586044.aspx


个人觉得 12 楼写得已经很好了。
a8323418 2009-10-12
  • 打赏
  • 举报
回复
lcc编译器
whg01 2009-10-12
  • 打赏
  • 举报
回复
char* UnicodeToUtf8( WCHAR* wszUtf8)
{
int 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);
return szUtf8;
}
WCHAR* ConvertUtf8ToGBK( char* szUtf8 )
{
int len=MultiByteToWideChar(CP_UTF8,0, szUtf8 ,-1, NULL,0);
WCHAR* wszUCD=new WCHAR[len+1];
memset(wszUCD,0, len*2+2);
MultiByteToWideChar(CP_UTF8,0, szUtf8,-1, wszUCD, len);
return wszUCD;
}
在VS2008里编译通过。要#include <Shlwapi.h>
whg01 2009-10-12
  • 打赏
  • 举报
回复
你是什么平台?
a8323418 2009-10-12
  • 打赏
  • 举报
回复
大家都不会?
a8323418 2009-10-12
  • 打赏
  • 举报
回复
[Quote=引用 14 楼 whg01 的回复:]
前两天刚解答过类似的问题。
直接调用MultiByteToWideChar和WideCharToMultiByte 即可。

char* UnicodeToUtf8( WCHAR*  wszUtf8)
{
    int len= WideCharToMultiByte(CP_UTF8,0, wszUtf8,-1, NULL,0, NULL, NULL);
    char* szUtf8=newchar[len+1];
    memset(szUtf8,0, len+1);
    WideCharToMultiByte (CP_UTF8,0, wszUtf8,-1, szUtf8, len, NULL,NULL);
    return szUtf8;
}
WCHAR* ConvertUtf8ToGBK( char* szUtf8 )
{
    int len=MultiByteToWideChar(CP_UTF8,0, (LPCTSTR)szUtf8 ,-1, NULL,0);
    WCHAR* wszUCD=new WCHAR[len+1];
    memset(wszUCD,0, len*2+2);
    MultiByteToWideChar(CP_UTF8,0, (LPCTSTR)strUtf8,-1, wszUCD, len);
    return wszUCD;
}

[/Quote]

MultiByteToWideChar
编译器不过
whg01 2009-10-12
  • 打赏
  • 举报
回复
前两天刚解答过类似的问题。
直接调用MultiByteToWideChar和WideCharToMultiByte 即可。

char* UnicodeToUtf8( WCHAR* wszUtf8)
{
int len= WideCharToMultiByte(CP_UTF8,0, wszUtf8,-1, NULL,0, NULL, NULL);
char* szUtf8=newchar[len+1];
memset(szUtf8,0, len+1);
WideCharToMultiByte (CP_UTF8,0, wszUtf8,-1, szUtf8, len, NULL,NULL);
return szUtf8;
}
WCHAR* ConvertUtf8ToGBK( char* szUtf8 )
{
int len=MultiByteToWideChar(CP_UTF8,0, (LPCTSTR)szUtf8 ,-1, NULL,0);
WCHAR* wszUCD=new WCHAR[len+1];
memset(wszUCD,0, len*2+2);
MultiByteToWideChar(CP_UTF8,0, (LPCTSTR)strUtf8,-1, wszUCD, len);
return wszUCD;
}
zpf82118 2009-10-12
  • 打赏
  • 举报
回复
人家已经给你函数了
你改一下不就行了吗?
thy38 2009-10-12
  • 打赏
  • 举报
回复
#include <string>
using namespace std;

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

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

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

void CChineseCode::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 CChineseCode::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;
}
a8323418 2009-10-12
  • 打赏
  • 举报
回复
[Quote=引用 10 楼 akirya 的回复:]
引用 9 楼 a8323418 的回复:
引用 5 楼 lihan6415151528 的回复:
void CChineseCode::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 CChineseCode::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;
}


#include   "stdio.h"

wchar_t* UTF_8ToUnicode(char* UTF_8)
{

}
char* UnicodeToUTF_8(wchar_t* Unicode)
{

}
int main(int argc,char* argv[])
{
return  0;
}
能不能把UTF_8ToUnicode和UnicodeToUTF_8 不全



这个函数声明有问题,
[/Quote]

请指点
  • 打赏
  • 举报
回复
[Quote=引用 9 楼 a8323418 的回复:]
引用 5 楼 lihan6415151528 的回复:
void CChineseCode::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 CChineseCode::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;
}




#include  "stdio.h"

wchar_t* UTF_8ToUnicode(char* UTF_8)
{

}
char* UnicodeToUTF_8(wchar_t* Unicode)
{

}
int main(int argc,char* argv[])
{
return  0;
}
能不能把UTF_8ToUnicode和UnicodeToUTF_8 不全


[/Quote]
这个函数声明有问题,
a8323418 2009-10-12
  • 打赏
  • 举报
回复
[Quote=引用 5 楼 lihan6415151528 的回复:]
void CChineseCode::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 CChineseCode::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;
}

[/Quote]



#include "stdio.h"

wchar_t* UTF_8ToUnicode(char* UTF_8)
{

}
char* UnicodeToUTF_8(wchar_t* Unicode)
{

}
int main(int argc,char* argv[])
{
return 0;
}
能不能把UTF_8ToUnicode和UnicodeToUTF_8 不全

lihan6415151528 2009-10-12
  • 打赏
  • 举报
回复
UTF-8: 3字节一个字符
UNICODE: 2字节一个字符
GB2312: 1字节一个字符
加载更多回复(6)

69,337

社区成员

发帖
与我相关
我的任务
社区描述
C语言相关问题讨论
社区管理员
  • C语言
  • 花神庙码农
  • 架构师李肯
加入社区
  • 近7日
  • 近30日
  • 至今
社区公告
暂无公告

试试用AI创作助手写篇文章吧