Unicode，UTF8，GB2312，UCS2，GBK之間的轉換
阿新 • • 發佈：2019-02-09
void UCS2toUTF8(unsigned short *ucs2, int count, char *utf8)
{
unsigned short unicode;
unsigned char bytes[4] = {0};
int nbytes = 0;
int i = 0, j = 0;
int len=0;
if((ucs2 != NULL) && (utf8 != NULL))
{
if(count == 0)
{
len = 0;
}
else
{
for (i=0; i<count; i++)
{
unicode = ucs2[i];
if (unicode < 0x80)
{
nbytes = 1;
bytes[0] = unicode;
}
else if (unicode < 0x800)
{
nbytes = 2;
bytes[1] = (unicode & 0x3f) | 0x80;
bytes[0] = ((unicode << 2) & 0x1f00 | 0xc000) >> 8;
}
else
{
nbytes = 3;
bytes[2] = (unicode & 0x3f) | 0x80;
bytes[1] = ((unicode << 2) & 0x3f00 | 0x8000) >> 8;
bytes[0] = ((unicode << 4) & 0x0f0000 | 0xe00000) >> 16;
}
for (j=0; j<nbytes; j++)
{
utf8[len] = bytes[j];
len++;
}
}
}
utf8[len] = '/0';
}
}
{
unsigned short unicode;
unsigned char bytes[4] = {0};
int nbytes = 0;
int i = 0, j = 0;
int len=0;
if((ucs2 != NULL) && (utf8 != NULL))
{
if(count == 0)
{
len = 0;
}
else
{
for (i=0; i<count; i++)
{
unicode = ucs2[i];
if (unicode < 0x80)
{
nbytes = 1;
bytes[0] = unicode;
}
else if (unicode < 0x800)
{
nbytes = 2;
bytes[1] = (unicode & 0x3f) | 0x80;
bytes[0] = ((unicode << 2) & 0x1f00 | 0xc000) >> 8;
}
else
{
nbytes = 3;
bytes[2] = (unicode & 0x3f) | 0x80;
bytes[1] = ((unicode << 2) & 0x3f00 | 0x8000) >> 8;
bytes[0] = ((unicode << 4) & 0x0f0000 | 0xe00000) >> 16;
}
for (j=0; j<nbytes; j++)
{
utf8[len] = bytes[j];
len++;
}
}
}
utf8[len] = '/0';
}
}