Unicode and URI encoding, decoding and escaping in JavaScript

Question

If you look at this table here, it has a list of escape sequences for Unicode characters that don't actually work for me.

For example for "%96", which should be a –, I get an error when trying decode:

decodeURIComponent("%96");
URIError: URI malformed

If I attempt to encode "–" I actually get:

encodeURIComponent("–");
"%E2%80%93"

I searched through the internet and I saw this page, which mentions using escape and unescape with decodeURIComponent and encodeURIComponent respectively. This doesn't seem to help because %96 doesn't show up as "–" no matter what I try and this of course wouldn't work:

decodeURIComponent(escape("%96));
"%96"

Not very helpful.

How can I get "%96" to be a "–" with JavaScript (without hardcoding a map for every single possible unicode character I may run into)?

Answer 1

See this question, specifically this answer:

there is a special “%uNNNN” format for encoding Unicode UTF-16 code points, instead of encoding UTF-8 bytes

I suspect "–" is one of those characters since 0x96 in the Ascii table is û

Answer 2

Posting as a community wiki entry as it's from "Building Scalable Websites" by Carl Henderson. The book says it's OK to reproduce significant portions of the examples though. You may be able to create a special case for "-" with it.

function escape_utf8(data) {
        if (data == '' || data == null){
               return '';
        }
       data = data.toString();
       var buffer = '';
       for(var i=0; i<data.length; i++){
               var c = data.charCodeAt(i);
               var bs = new Array();
              if (c > 0x10000){
                       // 4 bytes
                       bs[0] = 0xF0 | ((c & 0x1C0000) >>> 18);
                       bs[1] = 0x80 | ((c & 0x3F000) >>> 12);
                       bs[2] = 0x80 | ((c & 0xFC0) >>> 6);
                   bs[3] = 0x80 | (c & 0x3F);
               }else if (c > 0x800){
                        // 3 bytes
                        bs[0] = 0xE0 | ((c & 0xF000) >>> 12);
                        bs[1] = 0x80 | ((c & 0xFC0) >>> 6);
                       bs[2] = 0x80 | (c & 0x3F);
             }else if (c > 0x80){
                      // 2 bytes
                       bs[0] = 0xC0 | ((c & 0x7C0) >>> 6);
                      bs[1] = 0x80 | (c & 0x3F);
               }else{
                       // 1 byte
                    bs[0] = c;
              }
             for(var j=0; j<bs.length; j++){
                      var b = bs[j];
                       var hex = nibble_to_hex((b & 0xF0) >>> 4) 
                      + nibble_to_hex(b &0x0F);buffer += '%'+hex;
              }
    }
    return buffer;
}
function nibble_to_hex(nibble){
        var chars = '0123456789ABCDEF';
        return chars.charAt(nibble);
}