Skip to content

Instantly share code, notes, and snippets.

@rodneyrehm

rodneyrehm/urlify.js

Last active May 8, 2024 09:36
Download ZIP

Revisions

  1. rodneyrehm revised this gist Sep 4, 2013. 1 changed file with 1 addition and 0 deletions.
    1 change: 1 addition & 0 deletions urlify.js
    View file
    Original file line number Diff line number Diff line change
    @@ -1,5 +1,6 @@
    // port of https://gist.github.com/909692
    // TODO: check char-map of https://github.com/jbroadway/urlify/blob/master/URLify.php for characters we've missed
    // TODO: check performance against http://stackoverflow.com/questions/1946040/using-javascript-to-normalize-url-rewriting-strings-entered-by-users

    var Urlifyer = function(options) {
    var _key, _code, i, _source, _sources;
  2. rodneyrehm revised this gist Sep 4, 2013. 1 changed file with 2 additions and 2 deletions.
    4 changes: 2 additions & 2 deletions urlify.js
    View file
    Original file line number Diff line number Diff line change
    @@ -79,9 +79,9 @@ Urlifyer.prototype.urlify = function(string) {
    _replacement = "i";
    } else if (_code == 0xD1 || _code == 0xF1) {
    _replacement = "n";
    } else if ((_code >= 0xD2 && _code <= 0xD8) || (_code >= 0xF2 && _code <= 0xF8)) {
    } else if ((_code >= 0xD2 && _code <= 0xD6) || (_code >= 0xF2 && _code <= 0xF6) || _code == 0xD8 || _code == 0xF8 ) {
    _replacement = "o";
    } else if ((_code >= 0xD9 && _code <= 0xDB) || (_code >= 0xF9 && _code <= 0xFB)) {
    } else if ((_code >= 0xD9 && _code <= 0xDC) || (_code >= 0xF9 && _code <= 0xFC)) {
    _replacement = "u";
    } else if (_code == 0xDD || _code == 0xFD || _code == 0xFF) {
    _replacement = "y";
  3. rodneyrehm revised this gist Aug 12, 2012. 1 changed file with 1 addition and 1 deletion.
    2 changes: 1 addition & 1 deletion urlify.js
    View file
    Original file line number Diff line number Diff line change
    @@ -1,5 +1,5 @@

    // port of https://gist.github.com/909692
    // TODO: check char-map of https://github.com/jbroadway/urlify/blob/master/URLify.php for characters we've missed

    var Urlifyer = function(options) {
    var _key, _code, i, _source, _sources;
  4. rodneyrehm created this gist May 5, 2012.
    131 changes: 131 additions & 0 deletions urlify.js
    View file
    Original file line number Diff line number Diff line change
    @@ -0,0 +1,131 @@

    // port of https://gist.github.com/909692

    var Urlifyer = function(options) {
    var _key, _code, i, _source, _sources;

    // Allow instantiation without the 'new' keyword
    if (!(this instanceof Urlifyer)) {
    return new Urlifyer(options);
    }

    if (!options) {
    options = {};
    }

    this._trim = options.trim || Urlifyer.trim;
    this._lower = options.lower || Urlifyer.lower;
    this._allow = {};
    this._replace = {};

    // allowed characters
    _sources = [Urlifyer.allow, options.allow];
    for (i=0; (_source = _sources[i]) !== undefined; i++) {
    if (!_source) {
    continue;
    }

    var index = _source.length;
    while (index--) {
    _key = _source.charCodeAt(index);
    this._allow[_key] = true;
    }
    }

    // replacements
    _sources = [Urlifyer.replace, options.replace];
    for (i=0; (_source = _sources[i]) !== undefined; i++) {
    if (!_source) {
    continue;
    }

    for (_key in _source) {
    if (Object.prototype.hasOwnProperty.call(_source, _key)) {
    console.log(_key);
    // allow passing either unicode-points or characters
    var __key = _key.match(/^[0-9]+$/) ? _key : _key.charCodeAt(0);
    this._replace[__key] = _source[_key];
    }
    }
    }

    return this;
    };
    Urlifyer.prototype.urlify = function(string) {
    var index = string.length;

    while (index--) {
    var _code = string.charCodeAt(index),
    _replacement = null;

    if ((_code >= 97 && _code <= 122) || (_code >= 65 && _code <= 90) || (_code >= 48 && _code <= 57) || _code === 95 || _code === 45) {
    // skip normalization for alphanumeric characters [a-zA-Z0-9_-]
    continue;
    } else if (this._allow && this._allow[_code]) {
    // skip normalization for allowed characters
    continue;
    } else if (this._replace[_code]) {
    // replace as defined
    _replacement = this._replace[_code];
    } else if ((_code >= 0xC0 && _code <= 0xC6) || (_code >= 0xE0 && _code <= 0xE6) || (_code >= 0x100 && _code <= 0x105)) {
    _replacement = "a";
    } else if (_code == 0xC7 || _code == 0xE7 || (_code >= 0x106 && _code <= 0x10D)) {
    _replacement = "c";
    } else if (_code == 0xD0 || (_code >= 0x10E && _code <= 0x111)) {
    _replacement = "d";
    } else if ((_code >= 0xC8 && _code <= 0xCB) || (_code >= 0xE8 && _code <= 0xEB) || (_code >= 0x112 && _code <= 0x11B)) {
    _replacement = "e";
    } else if ((_code >= 0xCC && _code <= 0xCF) || (_code >= 0xEC && _code <= 0xEF)) {
    _replacement = "i";
    } else if (_code == 0xD1 || _code == 0xF1) {
    _replacement = "n";
    } else if ((_code >= 0xD2 && _code <= 0xD8) || (_code >= 0xF2 && _code <= 0xF8)) {
    _replacement = "o";
    } else if ((_code >= 0xD9 && _code <= 0xDB) || (_code >= 0xF9 && _code <= 0xFB)) {
    _replacement = "u";
    } else if (_code == 0xDD || _code == 0xFD || _code == 0xFF) {
    _replacement = "y";
    } else {
    _replacement = "-";
    }

    string = string.slice(0, index)
    + _replacement
    + string.slice(index + 1);
    }

    if (this._trim) {
    // reduce to single dash
    string = string.replace(/-{2,}/g, '-');
    // trim dash from beginning and end
    string = string.replace(/^-|-$/g, '');
    }

    if (this._lower) {
    string = string.toLowerCase();
    }

    return string;
    };

    Urlifyer.lower = false;
    Urlifyer.trim = false;
    Urlifyer.allow = "";
    Urlifyer.replace = {
    0xE4: "ae", // ä
    0xC4: "Ae", // Ä
    0xF6: "oe", // ö
    0xD6: "Oe", // Ö
    0xFC: "ue", // ü
    0xDC: "Ue", // Ü
    0xDF: "ss", // ß
    0xE6: "ae", // æ
    0xC6: "AE" // Æ
    };



    var u = new Urlifyer({trim: true, lower: true, allow: "õ", replace: {"ñ":"#"}});
    console.log(u);
    console.log(u.urlify("häLLö w(orl)d ñõ so?"));