Convert cp1252 to unicode in javascript

Question

I need to convert cp125*2* text to unicode utf in javascript function.

Function to convert CP125*1* to utf I already find.

Please help me if you have this functionality, thanks!

Answer 1

If ISO-8859-1 is close enough, there is a special shortcut to convert ISO-8859-1-bytes-in-code-units to Unicode characters, due to the simple byte=code-point mapping:

var chars= decodeURIComponent(escape(bytes));

For any other encoding there is no built-in functionality; you would have to include your own lookup tables. For example:

var encodings= {
    // Windows code page 1252 Western European
    //
    cp1252: '\x00\x01\x02\x03\x04\x05\x06\x07\x08\t\n\x0b\x0c\r\x0e\x0f\x10\x11\x12\x13\x14\x15\x16\x17\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f !"#$%&\'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\x7f\u20ac\ufffd\u201a\u0192\u201e\u2026\u2020\u2021\u02c6\u2030\u0160\u2039\u0152\ufffd\u017d\ufffd\ufffd\u2018\u2019\u201c\u201d\u2022\u2013\u2014\u02dc\u2122\u0161\u203a\u0153\ufffd\u017e\u0178\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7\xa8\xa9\xaa\xab\xac\xad\xae\xaf\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7\xe8\xe9\xea\xeb\xec\xed\xee\xef\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff',

    // Windows code page 1251 Cyrillic
    //
    cp1251: '\x00\x01\x02\x03\x04\x05\x06\x07\x08\t\n\x0b\x0c\r\x0e\x0f\x10\x11\x12\x13\x14\x15\x16\x17\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f !"#$%&\'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\x7f\u0402\u0403\u201a\u0453\u201e\u2026\u2020\u2021\u20ac\u2030\u0409\u2039\u040a\u040c\u040b\u040f\u0452\u2018\u2019\u201c\u201d\u2022\u2013\u2014\ufffd\u2122\u0459\u203a\u045a\u045c\u045b\u045f\xa0\u040e\u045e\u0408\xa4\u0490\xa6\xa7\u0401\xa9\u0404\xab\xac\xad\xae\u0407\xb0\xb1\u0406\u0456\u0491\xb5\xb6\xb7\u0451\u2116\u0454\xbb\u0458\u0405\u0455\u0457\u0410\u0411\u0412\u0413\u0414\u0415\u0416\u0417\u0418\u0419\u041a\u041b\u041c\u041d\u041e\u041f\u0420\u0421\u0422\u0423\u0424\u0425\u0426\u0427\u0428\u0429\u042a\u042b\u042c\u042d\u042e\u042f\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044a\u044b\u044c\u044d\u044e\u044f'
};

function decodeBytes(bytes, encoding) {
    var enc= encodings[encoding];
    var n= bytes.length;
    var chars= new Array(n);
    for (var i= 0; i<n; i++)
        chars[i]= enc.charAt(bytes.charCodeAt(i));
    return chars.join('');
}

alert(decodeBytes('\xc7\xe4\xf0\xe0\xe2\xf1\xf2\xe2\xf3\xe9 \xec\xe8\xf0', 'cp1251'));
// '\u0417\u0434\u0440\u0430\u0432\u0441\u0442\u0432\u0443\u0439 \u043c\u0438\u0440'
// Здравствуй мир

ETA:

So, I get the raw page html just after it loaded (in my firefox addon), run the javascript function that parse this page by regexp.

Yeah, don't do that. You can't parse HTML with regex.

Why not let Firefox take care of parsing the page for its given charset?

ETA(2):

'koi8-r': '\x00\x01\x02\x03\x04\x05\x06\x07\x08\t\n\x0b\x0c\r\x0e\x0f\x10\x11\x12\x13\x14\x15\x16\x17\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f !"#$%&\'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\x7f\u2500\u2502\u250c\u2510\u2514\u2518\u251c\u2524\u252c\u2534\u253c\u2580\u2584\u2588\u258c\u2590\u2591\u2592\u2593\u2320\u25a0\u2219\u221a\u2248\u2264\u2265\xa0\u2321\xb0\xb2\xb7\xf7\u2550\u2551\u2552\u0451\u2553\u2554\u2555\u2556\u2557\u2558\u2559\u255a\u255b\u255c\u255d\u255e\u255f\u2560\u2561\u0401\u2562\u2563\u2564\u2565\u2566\u2567\u2568\u2569\u256a\u256b\u256c\xa9\u044e\u0430\u0431\u0446\u0434\u0435\u0444\u0433\u0445\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u044f\u0440\u0441\u0442\u0443\u0436\u0432\u044c\u044b\u0437\u0448\u044d\u0449\u0447\u044a\u042e\u0410\u0411\u0426\u0414\u0415\u0424\u0413\u0425\u0418\u0419\u041a\u041b\u041c\u041d\u041e\u041f\u042f\u0420\u0421\u0422\u0423\u0416\u0412\u042c\u042b\u0417\u0428\u042d\u0429\u0427\u042a'

(You can grab the mappings for single-byte encodings out of Python, saying something like:)

>>> ''.join(map(chr, range(256))).decode('koi8-r', 'replace')

I don't know how you're going about reading the input stream, but you shouldn't normally need to be doing this kind of encoding unmangling manually.