GBK转UTF_8

#define _DF1S	0x81
#define _DF1E	0xFE
#define _DS1S	0x40
#define _DS1E	0x7E
#define _DS2S	0x80
#define _DS2E	0xFE

#define IsDBCS1(c)	((BYTE)(c) >= _DF1S && (BYTE)(c) <= _DF1E)
#define IsDBCS2(c)	(((BYTE)(c) >= _DS1S && (BYTE)(c) <= _DS1E) || ((BYTE)(c) >= _DS2S && (BYTE)(c) <= _DS2E))



int GBKToUnicode(TCHAR* gbk2312, WCHAR *unicode)
{
	BYTE b, cf;
	WCHAR w, *lfn;
	int si, di;
	const TCHAR *p;

	cf=cf;
	/* Create LFN in Unicode */
	p = gbk2312; lfn = unicode; si = di = 0;
	for (;;) {
		w = p[si++];					/* Get a character */
		if (w == 0){
			lfn[di] = w;
			return di;				/* Break if end of the path name */
		}

		w &= 0xFF;
		if (IsDBCS1(w)) {				/* Check if it is a DBC 1st byte (always false on SBCS cfg) */
			b = (BYTE)p[si++];			/* Get 2nd byte */
			w = (w << 8) + b;			/* Create a DBC */
			if (!IsDBCS2(b)) return -1;	/* Reject invalid sequence */
		}
		w = ff_convert(w, 1);			/* Convert ANSI/OEM to Unicode */
		if (!w) return -1;	/* Reject invalid code */

		lfn[di++] = w;					/* Store the Unicode character */
	}
}

// 将GBK编码的字符串转换为UTF-8编码
// gbk_str: 输入的GBK字符串
// utf8_str: 输出的UTF-8字符串缓冲区
// utf8_size: utf8缓冲区大小
// 返回值: 转换后的UTF-8字符串长度，失败返回-1
int GBKToUtf8(const char *gbk_str, char *utf8_str, int utf8_size)
{
    if (!gbk_str || !utf8_str || utf8_size <= 0)
    {
        return -1;
    }

    // 临时Unicode缓冲区
    WCHAR unicode_buf[MAX_LINE_LENGTH];
    int utf8_pos = 0;

    // 先转换为Unicode
    int unicode_len = GBKToUnicode((TCHAR *)gbk_str, unicode_buf);
    if (unicode_len < 0)
    {
        return -1;
    }

    // 将Unicode转换为UTF-8
    for (int i = 0; i < unicode_len && utf8_pos < utf8_size - 3; i++)
    {
        uint32_t unicode_char = unicode_buf[i];

        if (unicode_char < 0x80)
        {
            // ASCII字符(0-127)用一个字节表示
            utf8_str[utf8_pos++] = unicode_char;
        }
        else if (unicode_char < 0x800)
        {
            // 两字节表示
            utf8_str[utf8_pos++] = 0xC0 | (unicode_char >> 6);
            utf8_str[utf8_pos++] = 0x80 | (unicode_char & 0x3F);
        }
        else
        {
            // 三字节表示
            utf8_str[utf8_pos++] = 0xE0 | (unicode_char >> 12);
            utf8_str[utf8_pos++] = 0x80 | ((unicode_char >> 6) & 0x3F);
            utf8_str[utf8_pos++] = 0x80 | (unicode_char & 0x3F);
        }
    }

    utf8_str[utf8_pos] = '\0';  // 添加字符串结束符
    return utf8_pos;
}