这个方法是用windows的字符集转换的，跟sybase
的unicode码表可能在某些符号上有差别，对于大部分字符来说，尤其是
汉字，应该不会有问题的，如果要求比较高的话，可以买sybase的
unicode开发包，:P
[code]
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <locale.h>
#include <ctype.h>
#include <mbstring.h>
size_t mbstoutf8(unsigned char* utf, unsigned char* mbs)
{
size_t mbl = 0;
size_t wcneed = mbstowcs(NULL, mbs, mbl);
wchar_t* wc = NULL;
size_t u8need = 0;
wchar_t* wp = NULL;
mbl = _mbslen(mbs);
wcneed = mbstowcs(NULL, mbs, mbl);
wc= calloc(wcneed + 1, sizeof(wchar_t));
if (!wc)
return -1;
if (mbstowcs(wc, mbs, mbl) < mbl)
return -1;
wc[mbl] = L‘\0‘;
wp = wc;
if (!utf)
{
while (*wp)
{
if ((*wp & 0x7f) == *wp)
u8need += 1;
else if ((*wp & 0x7ff) == *wp)
u8need += 2;
else
u8need +=3;
*wp++;
}
}
else
{
while (*wp)
{
if ((*wp & 0x7f) == *wp)
{
*utf++ = *wp & 0x7f;
u8need += 1;
}
else if ((*wp & 0x7ff) == *wp)
{
*utf++ = 0xc0 | (*wp >> 6);
*utf++ = 0x80 | (*wp & 0x3f);
u8need += 2;
}
else
{
*utf++ = 0xe0 | (*wp >> 12);
*utf++ = 0x80 | ((*wp >> 6) & 0x3f);
*utf++ = 0x80 | (*wp & 0x3f);
u8need += 3;
}
*wp++;
}
*utf = 0;
}
free(wc);
return u8need;
}
int main(void)
{
char mbs[81];
size_t sz = 0;
setlocale(LC_CTYPE, ".936");
for (; ; )
{
fgets(mbs, 80, stdin);
mbs[strlen(mbs) - 1] = ‘\0‘;
if (!*mbs)
break;
sz = mbstoutf8(NULL, mbs);
if (sz != -1)
{
char* u = malloc(sz + 1);
if (u)
{
mbstoutf8(u, mbs);
puts(u);
free(u);
}
}
}
return 0;
}
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <locale.h>
#include <ctype.h>
#include <mbstring.h>
#include <wchar.h>
size_t utf8tombs(unsigned char* mbs, wchar_t* utf)
{
size_t wcl = 0;
size_t mbneed = wcstombs(NULL, utf, wcl);
char* mc = NULL;
size_t gbneed = 0;
char* mp = NULL;
wcl = wcslen(utf);
gbneed = wcstombs(NULL, utf, wcl);
mc= calloc(gbneed + 1, sizeof(unsigned char));
if (!mc)
return -1;
if (wcstombs(mc, utf, wcl) < wcl)
return -1;
mc[wcl] = ‘\0‘;
mp = mc;
if (!mbs)
{
while (*mp)
{
if ((*mp & 0x80) == *mp)
gbneed += 1;
else if ((*mp & 0x800) == *mp)
gbneed += 2;
else
gbneed +=3;
*mp++;
}
}
else
{
while (*mp)
{
if ((*mp & 0x80) == *mp)
{
*mbs++ = *mp & 0x80;
gbneed += 1;
}
else if ((*mp & 0x800) == *mp)
{
*mbs++ = 0x3f | (*mp << 6);
*mbs++ = 0x7f | (*mp & 0xc0);
gbneed += 2;
}
else
{
*mbs++ = 0x1f | (*mp << 12);
*mbs++ = 0x7f | ((*mp << 6) & 0xc0);
*mbs++ = 0x7f | (*mp & 0xc0);
gbneed += 3;
}
*mp++;
}
*mbs = 0;
}
free(mc);
return gbneed;
}
int main(void)
{
char utf[81];
size_t sz = 0;
setlocale(LC_CTYPE, ".936");
for (; ; )
{
fgets(utf, 80, stdin);
utf[strlen(utf) - 1] = ‘\0‘;
if (!*utf)
break;
sz = utf8tombs(NULL, utf);
if (sz != -1)
{
char* u = malloc(sz + 1);
if (u)
{
utf8tombs(u, utf);
puts(u);
free(u);
}
}
}
return 0;
} [/code]
UTF8转换为GB编码gb2312转换为utf-8,布布扣,bubuko.com
原文地址：http://www.cnblogs.com/pengkunfan/p/3794663.html
