中文字符集ARM移植

中文字符集在ARM上的移植关键点在于CodePage，从Linux源代码中找到中文CodePage表，就可以利用CodePage来进行字符转换。中文CodePage号为936。找到文件nls_cp936.cpp

关键的字符寻表算法如下：

/*Unicode转换为ASCII*/

static int uni2char(const wchar_t uni, unsigned char *out, int boundlen)

{

unsigned char *uni2charset;

unsigned char cl = uni&0xFF;

unsigned char ch = (uni>>8)&0xFF;

int n;

if (boundlen <= 0)

{

return 0;

}

uni2charset = (unsigned char*)page_uni2charset[ch];

if (uni2charset)

{

if (boundlen <= 1)

return 0;

out[0] = uni2charset[cl*2];

        out[1] = uni2charset[cl*2+1];

if (out[0] == 0x00 && out[1] == 0x00)

return 0;

        n = 2;

}

else if (ch==0 && cl)

{

out[0] = cl;

n = 1;

}

else

return 0;

return n;

}

 

/*ASCII转换为 Unicode*/

static int char2uni(const unsigned char *rawstring, int boundlen, wchar_t *uni)

{

unsigned char ch, cl;

wchar_t *charset2uni;

int n;

if (boundlen <= 0)      

return 0;

if (boundlen == 1)

       {

             *uni = rawstring[0];

        return 1;

}

 

ch = rawstring[0];

    cl = rawstring[1];

        charset2uni = (wchar_t*)page_charset2uni[ch];

if (charset2uni && cl)

{

             *uni = charset2uni[cl];

        if (*uni == 0x0000)     return 0;

        n = 2;

     }

else

{

             *uni = ch;

        n = 1;

    }

       return n;

}