Efficiently replace all accented characters in a string?

Question

For a poor man\'s implementation of near-collation-correct sorting on the client side I need a JavaScript function that does efficient single character rep

Answer 1

Based on the solution by Jason Bunting, here is what I use now.

The whole thing is for the jQuery tablesorter plug-in: For (nearly correct) sorting of non-English tables with tablesorter plugin it is necessary to make use of a custom textExtraction function.

This one:

• translates the most common accented letters to unaccented ones (the list of supported letters is easily expandable)
• changes dates in German format ('dd.mm.yyyy') to a recognized format ('yyyy-mm-dd')

Be careful to save the JavaScript file in UTF-8 encoding or it won't work.

// file encoding must be UTF-8!
function getTextExtractor()
{
  return (function() {
    var patternLetters = /[öäüÖÄÜáàâéèêúùûóòôÁÀÂÉÈÊÚÙÛÓÒÔß]/g;
    var patternDateDmy = /^(?:\D+)?(\d{1,2})\.(\d{1,2})\.(\d{2,4})$/;
    var lookupLetters = {
      "ä": "a", "ö": "o", "ü": "u",
      "Ä": "A", "Ö": "O", "Ü": "U",
      "á": "a", "à": "a", "â": "a",
      "é": "e", "è": "e", "ê": "e",
      "ú": "u", "ù": "u", "û": "u",
      "ó": "o", "ò": "o", "ô": "o",
      "Á": "A", "À": "A", "Â": "A",
      "É": "E", "È": "E", "Ê": "E",
      "Ú": "U", "Ù": "U", "Û": "U",
      "Ó": "O", "Ò": "O", "Ô": "O",
      "ß": "s"
    };
    var letterTranslator = function(match) { 
      return lookupLetters[match] || match;
    }

    return function(node) {
      var text = $.trim($(node).text());
      var date = text.match(patternDateDmy);
      if (date)
        return [date[3], date[2], date[1]].join("-");
      else
        return text.replace(patternLetters, letterTranslator);
    }
  })();
}

You can use it like this:

$("table.sortable").tablesorter({ 
  textExtraction: getTextExtractor()
});