Suggestion for #1602, urlify.js blocks out non-English chars [was urlify.js blocks out...]

[Bill de hÓra]

Malcolm Tredinnick wrote:

> Personally, I was kind of hoping whoever wrote
> the patch might think this sort of thing through and give us a concrete
> target to throw ideas at. :-)

Hi Malcolm,

Here we go:

[[[urlify.js:

     var LATIN_MAP =
     {
        'À':'A',
        'Á':'A',
        'à':'a',
        'á':'a',
'©':'c'
     } ;
     var LATIN_SYMBOLS_MAP =
     {
     }
     var GREEK_MAP =
     {
     }
     var TURKISH_MAP =
     {
     }
     var RUSSIAN_MAP =
     {
     }

var ALL_DOWNCODE_MAPS=new Array()
ALL_DOWNCODE_MAPS[0]=LATIN_MAP
ALL_DOWNCODE_MAPS[1]=LATIN_SYMBOLS_MAP
ALL_DOWNCODE_MAPS[2]=GREEK_MAP
ALL_DOWNCODE_MAPS[3]=TURKISH_MAP
ALL_DOWNCODE_MAPS[4]=RUSSIAN_MAP

var Downcoder = new Object() ;

Downcoder.Initialize = function()
{
     if (Downcoder.map) // already made
         return ;
     Downcoder.map ={}
     Downcoder.chars = '' ;
     for(var i in ALL_DOWNCODE_MAPS)
     {
         var lookup = ALL_DOWNCODE_MAPS[i]
         for (var c in lookup)
         {
             Downcoder.map[c] = lookup[c] ;
             Downcoder.chars += c ;
         }
      }
     Downcoder.regex = new RegExp('[' + Downcoder.chars + ']|[^' + 
Downcoder.chars + ']+','g') ;
}

downcode= function( slug )
{
     Downcoder.Initialize() ;
     var downcoded =""
     var pieces = str.match(Downcoder.regex);
     if(pieces)
     {
        for (var i = 0 ; i < pieces.length ; i++)
        {
             if (pieces[i].length == 1)
             {
                var mapped = Downcoder.map[pieces[i]] ;
                if (mapped != null)
                {
                     downcoded+=mapped;
                     continue ;
                }
             }
             else
             {
                 downcoded+=pieces[i];
               }
         }
     }  
     else
     {
         downcoded = slug;
     }
     return downcoded;
}

function URLify(s, num_chars) {
     s = downcode(s);
     removelist = ["a", "an", "as", "at", "before", "but", "by", "for", 
"from",
                   "is", "in", "into", "like", "of", "off", "on", 
"onto", "per",
                   "since", "than", "the", "this", "that", "to", "up", 
"via",
                   "with"];
     r = new RegExp('\\b(' + removelist.join('|') + ')\\b', 'gi');
     s = s.replace(r, '');
     // if downcode fails, the char will be stripped here
     s = s.replace(/[^-A-Z0-9\s]/gi, '');
     s = s.replace(/^\s+|\s+$/g, ''); // trim leading/trailing spaces
     s = s.replace(/[-\s]+/g, '-');   // convert spaces to hyphens
     s = s.toLowerCase();             // convert to lowercase
     return s.substring(0, num_chars);// trim to first num_chars chars
     return s.substring(0, num_chars);// trim to first num_chars chars
}
]]]


I need to test this properly and fill in the mappings, but the gist of
the approach should be clear. When that's done, unless someone has an 
objection, I'll file a patch against

   http://code.djangoproject.com/ticket/1602
   (also 2282)
.

cheers
Bill

--~--~---------~--~----~------------~-------~--~----~
You received this message because you are subscribed to the Google Groups 
"Django developers" group.
To post to this group, send email to django-developers@googlegroups.com
To unsubscribe from this group, send email to [EMAIL PROTECTED]
For more options, visit this group at 
http://groups.google.com/group/django-developers
-~----------~----~----~----~------~----~------~--~---